The Science and Information (SAI) Organization
  • Home
  • About Us
  • Journals
  • Conferences
  • Contact Us

Publication Links

  • IJACSA
  • Author Guidelines
  • Publication Policies
  • Metadata Harvesting (OAI2)
  • Digital Archiving Policy
  • Promote your Publication

IJACSA

  • About the Journal
  • Call for Papers
  • Author Guidelines
  • Fees/ APC
  • Submit your Paper
  • Current Issue
  • Archives
  • Indexing
  • Editors
  • Reviewers
  • Apply as a Reviewer

IJARAI

  • About the Journal
  • Archives
  • Indexing & Archiving

Special Issues

  • Home
  • Archives
  • Proposals
  • Guest Editors

Future of Information and Communication Conference (FICC)

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact

Computing Conference

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact

Intelligent Systems Conference (IntelliSys)

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact

Future Technologies Conference (FTC)

  • Home
  • Call for Papers
  • Submit your Paper/Poster
  • Register
  • Venue
  • Contact
  • Home
  • Call for Papers
  • Guidelines
  • Fees
  • Submit your Paper
  • Current Issue
  • Archives
  • Indexing
  • Editors
  • Reviewers
  • Subscribe

IJACSA Volume 13 Issue 5

Copyright Statement: This is an open access publication licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.

View Full Issue

Paper 1: Implementation of Data Mining on a Secure Cloud Computing over a Web API using Supervised Machine Learning Algorithm

Abstract: Ever since the era of internet had ushered in cloud computing, there had been increase in the demand for the unlimited data available through cloud computing for data analysis, pattern recognition and technology advancement. With this also bring the problem of scalability, efficiency and security threat. This research paper focuses on how data can be dynamically mine in real time for pattern detection in a secure cloud computing environment using combination of decision tree algorithm and Random Forest over a restful Application Programming Interface (API). We are able to successfully Implement data mining on cloud computing bypassing or avoiding direct interaction with data warehouse and without any terminal involve by using combination of IBM Cloud storage facility, Amazing Web Service, Application Programming Interface and Window service along with a decision tree and Random Forest algorithm for our classifier. We were able to successfully bypass direct connection with the data warehouse and cloud terminal with 94% accuracy in our model.

Author 1: Tosin Ige
Author 2: Sikiru Adewale

Keywords: Cloud computing; data warehouse; data mining; window service; Web API; machine learning algorithm; secure cloud computing

Download PDF

Paper 2: AI Powered Anti-Cyber Bullying System using Machine Learning Algorithm of Multinomial Naïve Bayes and Optimized Linear Support Vector Machine

Abstract: “Unless and until our society recognizes cyber bullying for what it is, the suffering of thousands of silent victims will continue.” ~ Anna Maria Chavez. There had been series of research on cyber bullying which are unable to provide reliable solution to cyber bullying. In this research work, we were able to provide a permanent solution to this by developing a model capable of detecting and intercepting bullying incoming and outgoing messages with 92% accuracy. We also developed a chatbot automation messaging system to test our model leading to the development of Artificial Intelligence powered anti-cyber bullying system using machine learning algorithm of Multinomial Naïve Bayes (MNB) and optimized linear Support Vector Machine (SVM). Our model is able to detect and intercept bullying outgoing and incoming bullying messages and take immediate action.

Author 1: Tosin Ige
Author 2: Sikiru Adewale

Keywords: Cyberbullying; anti cyberbullying; machine learning; NLP; social media; multinomial Naïve Bayes; support vector machine

Download PDF

Paper 3: Replica Scheduling Strategy for Streaming Data Mining

Abstract: In a distributed storage and computing framework, traditional streaming data mining techniques are inefficient when processing massive amounts of data. In this paper, we take the copy in cloud storage as an allocatable resource for scheduling and propose a RepRM strategy to improve the efficiency of data mining and analysis. The key idea of this work is to take the data copy as the resource to be allocated, and use the backward inference method of dynamic programming to solve the data copy ratio, the optimal number of copies is obtained. Experiments and observations have proved that compared with the traditional scheduling method of Hadoop, after adopting the RepRM strategy scheduling, the memory resources of the homogeneous cluster are saved by about 40-50% during parallel mining of streaming data, and the throughput rate is increased by 20% to 30%.

Author 1: Shufan Li
Author 2: Siyuan Yu
Author 3: Fang Xiao

Keywords: Streaming data mining; dynamic programming; replica scheduling strategy; cloud computing

Download PDF

Paper 4: Use of Neural Networks in the Adaptive Testing System

Abstract: The paper examines the issues of the use of adaptive testing systems in terms of their incorporation in artificial neural network modules designed to solve the problem of choosing the next question, thereby forming an individual testing trajectory. The study presents an analysis of data affecting the quality of problem-solving, proposes a general modular structure of a system, and describes the main data flows at the input of an artificial neural network. The solution proposed for the problem of choosing the difficulty of the question is to use feedforward neural networks. Different architectures and parameters of training artificial neural networks (weight update mechanisms, loss functions, the number of training epochs, batch sizes) are compared. As an alternative, the option of using recurrent long-short term memory networks is considered.

Author 1: Ekaterina Vitalevna Chumakova
Author 2: Tatiana Alexandrovna Chernova
Author 3: Yulia Aleksandrovna Belyaeva
Author 4: Dmitry Gennadievich Korneev
Author 5: Mikhail Samuilovich Gasparian

Keywords: Adaptive testing system; artificial neural network; machine learning

Download PDF

Paper 5: Development of Ontology-based Domain Knowledge Model for IT Domain in e-Tutor Systems

Abstract: Ontology as a technology has been studied in many areas and is being used in several fields. A number of studies have utilized ontology to manage problems such as interoperability in teaching materials, modeling and enriching education resources, and personalizing learning content recommendations in the educational context. A possible reason for the lack of success may be that simply posting lecture notes on the internet does not provide enough learning and training. However, this situation can improve by using education software like an e-tutoring system. The e-tutor system has built-in modules to track students' performance and personalize learning according to an adaptation of students' learning styles, knowledge levels, and proper teaching techniques in e-learning systems. e-Tutor is an excellent area in the context of electronic instruction since it provides adequate aid for learners and becomes increasingly important for individual and collaborative learning. Thus, there has been significant interest in adopting e-tutoring to facilitate learning processes and enhance learners' performance. This paper represents a domain knowledge model for an e-tutoring system that enables knowledge to be stored in such a way separated from the domain of interest and assists in storing transfer and prerequisite knowledge relationships. This innovative technique is helpful for the students in improving their learning progress. This paper introduced a domain knowledge model for an e-tutor system to support the way of teaching and learning process. The model implementation is developed in Python and Owlready2. Two types of ontologies are provided: general concepts of the domain knowledge ontology and specific domain knowledge ontology. This solution represents the knowledge to be learned, delivers input to the expert model, and eventually provides specific feedback, selects problems, generates guidance, and supports the student model.

Author 1: Ghanim Hussein Ali Ahmed
Author 2: Jawad Alshboul
Author 3: Laszlo Kovacs

Keywords: e-learning; knowledge model; domain model; e-tutor system; SPARQL

Download PDF

Paper 6: The Design of Home Fire Monitoring System based on NB-IoT

Abstract: In the field of home fire monitoring, the currently relatively mature monitoring solutions include GPRS/GSM com-munication and Zigbee communication. The main disadvantage of GPRS wireless communication is high power consumption, and the disadvantage of Zigbee technology is that it needs to be combined with other communication technologies to realize remote monitoring. In addition, the above technical solutions all require self-built local or remote monitoring servers to save mon-itoring data. In view of the above problems, this system designs a home fire monitoring system based on NB-IoT technology and cloud platform. The system uses a single-chip STM32F103C8T6 as the core controller and contains a sensor data acquisition module and a narrowband IoT communication module. The data fusion of multi-sensor data is performed by BP neural network algorithm.On the basis of remote transmission, the system solves the problems of high power consumption, high cost and insufficient signal coverage of terminal hardware. The system can collect indoor environmental parameters and fire information in real time, and upload them to the cloud platform for storage. If abnormal data is detected, an early warning message will be issued. The feasibility of the system is verified, and the verification results show that the system works normally and the output is accurate, which meets the design requirements and can be widely used.

Author 1: Jun Wang
Author 2: Ting Ke
Author 3: Mengjie Hou
Author 4: Gangyu Hu

Keywords: NB-IoT; cloud platform; fire monitoring system; STM32F103C8T6; sensor; BP neural network

Download PDF

Paper 7: The Effect of Natural Language Processing on the Analysis of Unstructured Text: A Systematic Review

Abstract: The analysis of the unstructured text has become a challenge for the community dedicated to natural language processing (NLP) and Machine Learning (ML). This paper aims to describe the potential of the most used NLP techniques and ML algorithms to address various problems afflicting our society. Several original articles were reviewed and published in SCOPUS during 2021. The applied approach was retrospective, transversal and descriptive. The data collected were entered into the SPSS statistical software v25 and among the findings, it was determined that the most used NLP technique was the Term frequency - Inverse document frequency (TF-IDF), while the most used supervised learning algorithm was the Support Vector Machines (SVM). Likewise, the predominant deep learning algorithm was Long Short-Term Memory (LSTM). This research aims to support experts and those starting in research to identify the most used algorithms of NLP and ML.

Author 1: Walter Luis Roldan-Baluis
Author 2: Noel Alcas Zapata
Author 3: Maria Soledad Manaccasa Vasquez

Keywords: Artificial intelligence; natural language processing; machine learning; unstructured text analysis

Download PDF

Paper 8: Hybrid Fault Diagnosis Method based on Wavelet Packet Energy Spectrum and SSA-SVM

Abstract: As one of the important components of mechanical equipment, rolling bearing has been widely used, and its motion state affects the safety and performance of equipment. To enhance the fault feature information in the bearing signal and improve the classification accuracy of support vector machine, a hybrid fault diagnosis method based on wavelet packet energy spectrum and SSA-SVM is proposed. Firstly, the wavelet packet decomposition is used to decompose vibration signals to generate frequency band energy spectrum, and the bearing characteristic information is constructed from the energy spectrum to extract and enhance the bearing fault characteristic information. Secondly, the penalty and kernel parameters are optimized globally by sparrow search algorithm to improve the classification accuracy of support vector machine, and then construct the WPES-SSA-SVM model. Finally, the proposed model is used to diagnose and analyze the measured signals. Compared with BP, ELM and SVM, the effectiveness and superiority of the proposed method are verified.

Author 1: Jinglei Qu
Author 2: Bingxin Ma
Author 3: Xiaojie Ma
Author 4: Mengmeng Wang

Keywords: Wavelet packet energy spectrum; sparrow search optimization; support vector machine; rolling bearing

Download PDF

Paper 9: Multi-instance Finger Vein-based Authentication with Secured Templates

Abstract: The illegitimate access to biometric templates is one of the major issues to be handled for authentication systems. In this work, we propose to use two instances of finger vein images which inherits the advantages of a robust multi-modal biometric authentication system without needing different sensors. Two local texture feature extraction methods are experimented on standard finger-vein datasets. Fused discriminating features with reduced dimension lowers down the system computational cost. A cancelable template protection scheme as Gaussian Random Projection based Index-of-Max is then applied for embedding privacy and security to the templates. Foremost template protection properties like revocability, non-invertibility and unlinkability are observed to be significantly obeyed by the proposed system with considerable authentication performance. Recognition performance of the proposed methods are compared with some previously executed finger vein systems and observed to be less complex and overperforming on the combined basis of authentication and template protection. Thus, the proposed system utilizes multiple evidence and provides a balanced performance with respect to authentication, template protection and computational cost.

Author 1: Swati K. Choudhary
Author 2: Ameya K. Naik

Keywords: Finger vein; multi-instance; authentication; cancelable; template protection

Download PDF

Paper 10: SHD-IoV: Secure Handover Decision in IoV

Abstract: Internet of Vehicle (IoV) is the smartest thing being connected over the Internet. With continuously increasing urban population and swiftly growing of cities, causes moving vehicles with various speeds. These high speeds may increase the handover delay (HoD), accordingly causing an insecure connection due to the handover interruption. For instance, some of the network protocols try to overcome the problem without considering transport layer supports. This article proposes a dynamic HO algorithm with a cross-layer architecture called Secure Handover Decision (SHD) in IoV to assist the protocol layers aware of consecutive HOs of the vehicle. The results show that vehicle communication in IoV is more secure and lossless by reducing HoD in both sides of vehicle and network during fast movement.

Author 1: Hala E. I. Jubara

Keywords: Internet of Vehicle (IoV); HO; L2; Stream Control Transmission Protocol (SCTP); Secure Handover Decision (SHD); security

Download PDF

Paper 11: The Impact of Security and Payment Method On Consumers’ Perception of Marketplace in Saudi Arabia

Abstract: Digital transformation has been accelerated in recent years, and COVID-19 has resulted in a rise in overall internet spending. Businesses must take measures in order to ensure that customers have a safe and enjoyable online purchasing experience. In this paper, customers’ security perceptions regarding the most popular e-commerce applications in Saudi Arabia are explored. Surveys were distributed online via Google Form to 200 participants in total as part of a cross-sectional research design using quantitative methodology. The main findings were related to confirming eight main hypotheses of the research that were related to testing if some factors were important to forming perceived trust by customers. Five factors (trust, security, reputation, benefits, and convenience) were found to have a positive effect, and the remaining three were not (familiarity, size, and usefulness). Finally, this study recommends various actions for practitioners and policymakers to take in order to improve customer perceptions of payment methods and security in Saudi Arabia.

Author 1: Mdawi Alqahtani
Author 2: Marwan Ali Albahar

Keywords: Payment security; digital strategy; digital transformation; user security

Download PDF

Paper 12: Individual Risk Classification of Crime Groups using Ensemble Classifier Method

Abstract: The most significant challenge for humanity worldwide to crime, especially terrorist attacks, should be considered. Determining the priority scale for anticipating individual terrorist groups is not easy and will significantly affect work activities and subsequent decision-making measures. Priority scale determination decisions should be made carefully so team members cannot choose the desired priority target. Determining the exact priority scale for a target can be influenced by several factors, such as desire factors and ability factors, using Dataset Intelligence. This research aims to find out the ability of each target and pattern to be carried out. Based on this problem, the study used the K-Nearest Neighbor (KNN), Naïve Bayes (NB), Decision Tree (DT), and Ensemble Bagging methods. Each of these algorithms has its characteristics; This classification technique can group priority targets according to their similarities, abilities, and desires. The value of each method used can be used as a reference to determine the correct group information for officers to determine the next steps. The study obtained a maximum accuracy of 70.25% using the Ensemble Bagging-Backward Elimination-K-Nearest Neighbor (KNN) classification method using 20 features. The results showed tests conducted and final analysis and conclusions based on accuracy and recall performance. The precision performance revealed that the Ensemble Bagged KNN, more precisely than KNN, Naïve Bayes, Decision Tree, and Bagging Naïve Bayes and Bagging Decision Tree. The KNN Bagging ensemble model can add accuracy, map individuals, and detect who should be intensely monitored based on predictive results.

Author 1: Ardhito P. Anggana
Author 2: Amalia Zahra

Keywords: Priority scale; data mining; classification; ensemble classifier method

Download PDF

Paper 13: Evaluating the Effectiveness and Usability of AR-based OSH Application: HazHunt

Abstract: This study investigates the effectiveness and usability level of an augmented reality (AR) application called HazHunt to improve occupational safety and health (OSH) training. Previous research shows that AR has been growing in popularity as an innovative tool to enhance hazard identification courses. HazHunt, a marker-based AR app, was first developed using Vuforia software with OSH experts' guidance. Then, two online sessions of hazard identification course were conducted, where the experimental group's (EG) training was enhanced with the implementation of HazHunt. Analysis shows that the EG scores better (mean = 13.82, s = 3.38, n = 22) than the CG (mean = 13.41, s = 2.15, n = 22) in the post-quiz, but this difference is statistically non-significant, with t (21) = 0.48 and one-tail p = 0.32. Reduced Instructional Motivation Survey (RIMMS) shows that EG participants obtained higher confidence levels among the Attention, relevance, confidence, satisfaction (ARCS) factors in learning motivation. The System Usability Scale (SUS) score of HazHunt recorded the maximum count of 'Good' rating (mean = 78.41, n = 8). It is concluded that HazHunt has positive impacts on enhancing OSH training in terms of effectiveness and motivational impact. HazHunt also scored a high SUS score among the EG.

Author 1: Ahmad A. Kamal
Author 2: Syahrul N. Junaini
Author 3: Abdul H. Hashim

Keywords: OSH training; computer-aided training; online learning; marker-based AR; AR-based application; SUS score

Download PDF

Paper 14: Efficacy of the Image Augmentation Method using CNN Transfer Learning in Identification of Timber Defect

Abstract: This paper discusses the efficacy of the data augmentation method deployed in many Convolutional Neural Network (CNN) algorithms for determining timber defect in four timber species from Malaysia. A sequence of morphological transformation, involving x-reflection and rotation, was executed in the timber defect augmentation dataset for aiding CNN model training and generating the finest CNN models which offer the best classification performance in determining timber defect. For further assessing the CNN algorithms’ classification performance, several deep learning hyperparameters were tried on the Merbau timber species by utilising epoch as well as learning rate. A comparison of the classification performance was then done between other timber classes, namely KSK, Meranti, and Rubberwood. According to the results, the ResNet50 algorithm, which has its basis in the transfer learning methodology, outclasses other CNN algorithms (ShuffleNet, AlexNet, MobileNetV2, NASNetMobile, and GoogLeNet) with the best classification accuracy of 94.59% using the data augmentation method. Furthermore, the outcomes indicate that utilising an augmentation methodology not just addresses the issue of a limited dataset but also enhances CNN classification output by 5.78% with the support of T-test that demonstrates a significant difference across all CNN algorithms except for Alexnet. Our study on hyperparameter optimisation by utilising learning rate as well as epoch is sufficient to infer that a greater number of epoch and learning rate does not deliver superior precision in CNN classification. The experimental findings suggest that the proposed methods improved CNN algorithms classification performance in identification of timber defect while tackling the imbalanced and limited dataset challenges.

Author 1: Teo Hong Chun
Author 2: Ummi Rabaah Hashim
Author 3: Sabrina Ahmad
Author 4: Lizawati Salahuddin
Author 5: Ngo Hea Choon
Author 6: Kasturi Kanchymalay

Keywords: Convolutional neural network; deep learning; defect identification; image augmentation; transfer learning

Download PDF

Paper 15: Security Analysis on an Improved Anonymous Authentication Protocol for Wearable Health Monitoring Systems

Abstract: The wearable health monitoring system (WHMS) plays a significant role in medical experts collecting and using patient medical data. The WHMS is becoming more popular than in the past through mobile devices due to meaningful progress in wireless sensor networks. However, because the data about health used by the WHMS is related to privacy, it has to be protected from malicious access when wirelessly transmitted. Jiang et al. proposed a two-factor suitable for WHMSs using a fuzzy verifier. However, Jiaqing Mo et al. revealed that the protocol proposed by Jiang et al. had various security vulnerabilities and proposed an authentication protocol with improved security and guaranteed anonymity for WHMSs. In this paper, we analyse the authentication protocol proposed by Jiaqing Mo et al. and determine problems with the offline identification, password guessing attacks, operation process bit mismatch, no perfect forward secrecy, no mutual authentication and insider attacks.

Author 1: Gayeong Eom
Author 2: Haewon Byeon
Author 3: Younsung Choi

Keywords: Authentication protocol; health status; physiological data; security analysis; WHMS

Download PDF

Paper 16: A Review on Bio-inspired Optimization Method for Supervised Feature Selection

Abstract: Feature selection is a technique that is commonly used to prepare particular significant features or produce understandable data for improving the task of classification. Bio-inspired optimization algorithms have been successfully used to perform feature selection techniques. The exploration and exploitation mechanism that is based on the inspiration of living things to find a food source and the biological evolution in nature. Nevertheless, irrelevant, noisy, and redundant features persist from the situation of fall into local optima in case of high dimensionality. Thus, this review is conducted to shed some light on techniques that have been used to overcome the problem. The taxonomy of bio-inspired algorithms is presented, along with its performances and limitations, followed by the techniques used in supervised feature selection in term of data perspectives and applications. This review paper has also included the analysis of supervised feature selection on large dataset which showed that recent studies focus on metaheuristic methods because of their promising results. In addition, a discussion of some open issues is presented for further research.

Author 1: Montha Petwan
Author 2: Ku Ruhana Ku-Mahamud

Keywords: Bio-inspired optimization; swarm intelligence; evolutionary algorithm; machine learning

Download PDF

Paper 17: Implementation of a Data Protection Model dubbed Harricent_RSECC

Abstract: Every organization subsists on data, which is a quintessential resource. Quite a number of studies have been carried out relative to procedures that can be deployed to enhance data protection. However, available literature indicates most authors have focused on either encryption or encoding schemes to provide data security. The ability to integrate these techniques and leverage on their strengths to achieve a robust data protection is the pivot of this study. As a result, a data protection model, dubbed Harricent_RSECC has been designed and implemented to achieve the study’s objective through the utilization of Elliptic Curve Cryptography (ECC) and Reed Solomon (RS) codes. The model consists of five components, namely: message identification, generator module, data encoding, data encryption and data signature. The result is the generation of the Reed Solomon codewords; cipher texts; and generated hash values which are utilized to detect and correct corrupt data; obfuscates data; and sign data respectively, during transmission or storage. The contribution of this paper is the ability to combine encoding and encryption schemes to enhance data protection to ensure confidentiality, authenticity, integrity, and non-repudiation.

Author 1: Frimpong Twum
Author 2: Vincent Amankona
Author 3: Yaw Marfo Missah
Author 4: Ussiph Najim
Author 5: Michael Opoku

Keywords: Elliptic curve cryptography; encoding; encryption; Reed Solomon; security

Download PDF

Paper 18: Goal Question Metric as an Interdisciplinary Tool for Assessing Mobile Learning Application

Abstract: Assessing the mobile learning application among interdisciplinary researchers is a non-trivial task. Mandarin Learning App is a Mandarin 3D game tailor-made for students who choose PBC1033 Mandarin Language Level 1 as an elective course. It is an interdisciplinary project which it involves researchers from software engineering, computational science/mathematics and the Faculty of Language studies. In the project, the software engineer focuses on producing a quality application mostly through usability studies; the language teacher focuses on students’ study performance upon using the Mandarin Learning App and the mathematician focuses on finding the statistical data dependency of collected data through the various statistical packages. Hence, we are facing issues like how to reach a consensus in working on assessing the Mandarin 3D games? How to enable the discussion among the researchers; how to consolidate the results so that we can understand? We introduce Goal Question Metric to tackle these issues. In this paper, we demonstrate how Goal Question Metric is used to form a holistic view of assessing requirements on mobile applications and guide the discussion and reach consensus in analyzing the results of the evaluation. The contribution of this paper is to introduce Goal Question Metric as an interdisciplinary tool while assessing the mobile learning application. With Goal Question Metric, we demonstrate how it can structure the assessment from a different viewpoint in a comprehensive and systematic manner; 1) better structure of the experiments, 2) able to reach consensus among researchers from different disciplines, 3) able to analyze the dependencies among various experiments and 4) able to find hidden results.

Author 1: Sim Yee Wai
Author 2: Cheah WaiShiang
Author 3: Piau Phang
Author 4: Kai-Chee Lam
Author 5: Eaqerzilla Phang
Author 6: Nurfauza binti Jali

Keywords: Goal question metric; mobile application; evaluation; communication; interdisciplinary

Download PDF

Paper 19: Spatial Feature Fusion for Biomedical Image Classification based on Ensemble Deep CNN and Transfer Learning

Abstract: Biomedical imaging is a rapidly evolving field that covers different types of imaging techniques which are used for diagnostic and therapeutic purposes. It plays a vital role in diagnosis and treating health conditions of human body. Classification of different imaging modalities plays a vital role in terms of providing better care and treatment options to the patients. Advancements in technology open up the new doors for medical professionals and this involves deep learning methods for automatic image classification. Convolutional neural network (CNN) is a special class of deep learning that is applied to visual imagery. In this paper, a novel spatial feature fusion based deep CNN is proposed for classification of microscopic peripheral blood cell images. In this work, multiple transfer learning features are extracted through four pre-trained CNN architectures namely VGG19, ResNet50, MobileNetV2 and DenseNet169. These features are fused into a generalized feature space that increases the classification accuracy. The dataset considered for the experiment contains 17902 microscopic images that are categorized into 8 distinct classes. The result shows that the proposed CNN model with fusion of multiple transfer learning features outperforms the individual pre-trained CNN model. The proposed model achieved 96.10% accuracy, 96.55% F1-score, 96.40% Precision and 96.70% Recall values.

Author 1: Sanskruti Patel
Author 2: Rachana Patel
Author 3: Nilay Ganatra
Author 4: Atul Patel

Keywords: Biomedical images; convolutional neural network; ensemble deep learning; feature fusion

Download PDF

Paper 20: Effectivity Score of Simulation Tools towards Modelling Design in Internet-of-Things

Abstract: Simulation tools play an integral and significant role in studying the applicability and effectiveness of different algorithms for solving real-world problems cost-effectively. In the case of Internet-of-Things, the issues associated with real-world implementation are exponentially multi-fold. Although various simulators have facilitated the evolution of schemes to address the problems in IoT applications in the last few years, their applicability in the real world is highly questionable. Hence, this paper discusses the potential features of existing simulations (both commercial and research-based) and investigates features of different assessment environment tools to understand their current state. The paper further contributes toward a distinct research pattern. The core contribution of this manuscript is to review standard practices of using simulation tool along with different test environments. The paper also contributes towards exploring various prospects of unaddressed problems associated with a usage of existing simulation environment/tool for investigating the challenging and practical environment of an IoT ecosystem. The learning outcome of this study will assist the reader to make a decision towards adopting precise simulation tool for their work as well as it also highlights the need to perform more number of customization towards including the features that is found in research gap.

Author 1: Gauri Sameer Rapate
Author 2: N C Naveen

Keywords: Internet-of-things; real-world; application; simulation model; environment

Download PDF

Paper 21: Analysis and Prediction of COVID-19 by using Recurrent LSTM Neural Network Model in Machine Learning

Abstract: As we all know that corona virus is announced as pandemic in the world by WHO. It is spreaded all over the world with few days of time. To control this spreading, every citizen maintains social distance and self preventive measures are the best strategies. As of now many researchers and scientists are continuing their research in finding out the exact vaccine. The machine learning model finds that the corona virus disease behaves in exponential manner. To abolish the consequence of this pandemic, an efficient step should be taken to analyze this disease. In this paper, a recurrent neural network model is chosen to predict the number of active cases in a particular state. To do this prediction of active cases, we need database. The database of COVID-19 is downloaded from KAGGLE website and is analyzed by applying recurrent LSTM neural network with univariant features to predict for the number of active cases of patients suffering from corona virus. The downloaded database is divided into training and testing the chosen neural network model. The model is trained with the training data set and tested with testing dataset to predict the number of active cases in a particular state here we have concentrated on Andhra Pradesh state.

Author 1: N. P. Dharani
Author 2: Polaiah Bojja

Keywords: COVID-19; corona virus; KAGGLE; LSTM neural network; machine learning

Download PDF

Paper 22: A Proposed Fraud Detection Model based on e-Payments Attributes a Case Study in Egyptian e-Payment Gateway

Abstract: As per Payfort's 2017 report, titled State of payments in the Arab world; Egypt had a 22% yearly increase in the overall volume of internet payments in 2016, which was assessed at $6.2 billion. e-Payments are the major point of life nowadays in Egypt and the whole world; with tens of e-payments companies in Egypt and more than 5 million transactions done every day and 60 billion EGP volume of payments in 2018. Online and mobile fraud was estimated at $10.7 billion in 2015, as per Juniper Research, and is expected to reach $25.6 billion by the end of the decade. As the whole e-payments business is affected by fraud, e-payments firms and their consumers lose a lot of money. On the other hand, one of the most powerful techniques that could be used for fraud predictive is data mining techniques such as the decision tree. This paper introduces a prediction model for managing the risk of fraud in the Egyptian e-payment market that helps to reduce the loss of money. This model is developed using a real dataset from one of Egypt's top e-payment gateways based on the e-payment transaction attributes importance like transaction time, transaction amount, transaction limit, and transaction customer No. repetition limit. The importance of these attributes was determined using IBM SPSS modeler's decision tree and its predictors' importance. The model significantly assisted in the reduction of fraud cases by a very high rate, with an accuracy of 88.45% and a precision of 93.5% resulting in a savings of 101970.52 EGP out of 131297.83 EGP.

Author 1: Mohamed Hassan Nasr
Author 2: Mohamed Hassan Farrag
Author 3: Mona Mohamed Nasr

Keywords: Data mining; decision tree; e-payments; fraud detection; e-payment gateways; e-commerce

Download PDF

Paper 23: Improved ISODATA Clustering Method with Parameter Estimation based on Genetic Algorithm

Abstract: Improved ISODATA clustering method with merge and split parameters as well as initial cluster center determination with GA: Genetic Algorithm is proposed. Although ISODATA method is well-known clustering method, there is a problem that the iteration and clustering result is strongly depending on the initial parameters, especially the threshold for merge and split. Furthermore, it shows a relatively poor clustering performance in the case that the probability density function of data in concern cannot be expressed with convex function. To overcome this situation, GA is introduced for the determination of initial cluster center as well as the threshold of merge and split between constructing clusters. Through experiments with simulated data, the well-known the University of California, Irvine: UCI repository data for clustering performance evaluations and ASTER/VNIR: Advanced Spaceborne Thermal Emission and Reflection Radiometer / Visible and Near Infrared Radiometer onboard Terra satellite of imagery data, the proposed method is confirmed to be superior to the conventional ISODATA method.

Author 1: Kohei Arai

Keywords: ISODATA clustering; nonlinear merge and split; concaveness of probability density function: PDF; remote sensing satellite imagery data; clustering; genetic algorithm: GA; nonlinear optimization

Download PDF

Paper 24: A Pre-trained Neural Network to Predict Alzheimer’s Disease at an Early Stage

Abstract: Alzheimer’s disease (AD), which is a neuro associated disease, has become a common for past few years. In this competitive world, individual has to perform lot of multi tasking to prove their efficiency, in this process the neurons in the brain gets affected after a while i.e., “Alzheimer’s Disease”. Existing models to identify the disease at early stage has taken the individuals speech as input then they are converted into textual transcripts. These transcripts are analyzed using neural network approached by integrating them with NLP techniques. These techniques failed in designing the model which can process the long conversation text at faster rate and few models are unable to recognize the replacement of the unknown words during the translation process. The proposed system addresses these issues by converting the speech obtained into image format and then the output “Mel-spectrum” is passed as input to pre-trained VGG-16. This process has greatly reduced the pre-processing step and improved the efficiency of the system with less kernel size architecture. The speech to image translation mechanism has improved accuracy when compared to speech to text translators.

Author 1: Ragavamsi Davuluri
Author 2: Ragupathy Rengaswamy

Keywords: Mel-spectrum; VGG-16; ADAM optimizer; softmax; flatten layers; ReLU

Download PDF

Paper 25: A k-interpolation Model Clustering Algorithm based on Kriging Method

Abstract: In this work, a k-interpolation model clustering algorithm is proposed based on Kriging method, aim to partition data according to the relationship between the response of interest and input variables. Kriging method is used to describe the relationship between the response of interest and input variables. For each datum, the estimation errors of the interpolation models of the clusters are used to decide its assignment. An optimization strategy is proposed to obtain the final clustering results. The key factors of the proposed algorithm on its performance are studied through the synthetic and real-world datasets. The results show that the proposed algorithm is able to cluster the data according to the response of interest and input variables, and provides competitive clustering performance compared with the other clustering algorithms.

Author 1: Guoyan Chen
Author 2: Yaping Qian

Keywords: Data clustering; Kriging method; k-means algorithm; interpolation model

Download PDF

Paper 26: A Food Waste Mobile Gamified Application Design Model using UX Agile Approach in Malaysia

Abstract: Food waste is a significant worldwide issue in landfill management. Due to improper implementation, technology applications related to food waste collection and its management system are still lacking in practice. The available applications have yet to address the issue of food waste management. Constructing an interactive mobile application is necessary for managing food waste collection for the decomposition process using Black Soldier Fly (BSF) treatment. Furthermore, as the mobile application requires participation from various user backgrounds, maintaining user involvement has become a priority. Gamification has emerged as one of the approaches that might favourably affect individual engagement behaviour. A comprehensive game element design is required where it focuses on how gamification can influence user engagement. This study aims to model the food waste gamified mobile application design to benefit Malaysia's decomposition ecosystem. It includes gamification, management features, and data visualization for reporting and will involve users from households, businesses, and the BSF farm. This paper presents the modelling process of a new mobile application design for this concept of study. The UX agile approach was used in gathering and designing the application requirements as it allows for active participation from all stakeholders. The result shows that the experts agree on the application design. This research will indirectly benefit the BSF industry in Malaysia, and it will have a significant impact on gamification, user experience, and food waste management in the direction of a sustainable environment.

Author 1: Nooralisa Mohd Tuah
Author 2: Siti Khadijah Abd. Ghani
Author 3: Suryani Darham
Author 4: Suaini Sura

Keywords: Avatar; food waste disposal; mobile apps; gamification; data visualization; black soldier fly

Download PDF

Paper 27: Entanglement Quantification and Classification: A Systematic Literature Review

Abstract: Quantum entanglement is one of the essences of quantum mechanics and quantum information theory. It is a physical phenomenon in which entangled particles remain correlated with each other regardless of the distance between them. Quantum entanglement plays a significant role in areas such as quantum computing, quantum cryptography, and quantum teleportation. Quantifying entanglement is important for determining the depth of the entanglement level and has an impact on quantum information tasks performance. Entanglement classification is critical in quantum information theory for determining the class of states in a quantum system. The entanglement classification of two qubits as separable or entangled has been established. The classification of multiqubit entanglement is more challenging, especially in higher-qubit systems. The goal of this study is to identify different established measurements for entanglement quantification and entanglement classification methods through a systematic literature review. Indexed articles between 2017 and 2021 were selected as secondary resources from several sources based on specific keywords. This study presents a conceptual framework of entanglement quantification and classification based on previous studies.

Author 1: Amirul Asyraf Zhahir
Author 2: Siti Munirah Mohd
Author 3: Mohd Ilias M Shuhud
Author 4: Bahari Idrus
Author 5: Hishamuddin Zainuddin
Author 6: Nurhidaya Mohamad Jan
Author 7: Mohamed Ridza Wahiddin

Keywords: Entanglement quantification; quantum entanglement; entanglement classification; quantum measurement

Download PDF

Paper 28: Effective Cross Synthesized Methodology for Movie Recommendation with Emotion Analysis through Ranking Score

Abstract: Providing accurate movie recommendations to a user with limited computing capability is a challenging task. A hybrid system offers a good trade-off between the accuracy and computations needed for such recommendations. Collaborative Filtering and Content-Based Filtering are two of the most widely employed methods of computing such recommendations. In this work, a high-efficient hybrid recommendation algorithm is proposed, which deeds users’ contour attributes to screen them into various groups and recommends movie to a user based on rating given by other similar users. Compared to traditional clustering-based CF recommendation schemes, our technique can effectively decrease the time complexity, whereas attaining remarkable recommendation output. This approach mitigates the shortcomings of the individual methods, while maintaining the advantages. This allows the system to be highly reactive to new viewer inputs without sacrificing on the quality of the recommendations themselves. Building on other hybrids of a similar kind, our proposed system aims to reduce the complexity and features needed for calculation while maintaining good accuracy and further enhanced by utilizing Sentiment Analysis to rank the movies and take user reviews into consideration, which traditional hybrids do not take into account. Then analysis was performed on the data set and the results show that the proposed recommendation system outperforms other traditional approaches.

Author 1: R Lavanya
Author 2: B Bharathi

Keywords: Recommendation systems; collaborative filtering; styling; content based filtering; implicit feedback; hybrid recommendation; sentiment analysis; singular value decomposition

Download PDF

Paper 29: Supervisory Control and Data Acquisition System for Machines used for Thermal Processing of Materials

Abstract: A supervisory control and data acquisition (SCADA) system has been developed for three machines used for the thermal processing of materials: a hot wire cutter, an induction heater and a welding test stand. The cutter uses a transformer with adjustable voltage between 20 V and 32 V, and current of 8 A, measuring the temperature of the wire with thermal expansion. The heater uses a 24 V, 15 A source, and a type K thermocouple embedded in the sample in order to measure temperature. In welding, a temperature control system was implemented for the sample using type K thermocouple and a cooling fan using a 12 V and 20 A source. The SCADA system consists of a PLC and a PC with a graphical interface which serves to select the process to be worked on as it displays the thermal history of the monitored object. The supervisory system uses a PC with a 32-bit Windows 7 operating system and an OPC software package running on the academic LabVIEW platform. It was designed to use a single human-machine interface for different thermal processes. This paper describes the important components of the system, including its architecture, software development and performance testing.

Author 1: Diego Patino
Author 2: Wilson Tafur Preciado
Author 3: Albert Miyer Suarez Castrillon
Author 4: Sir-Alexci Suarez Castrillon

Keywords: Automatic control of thermal processes; programmable logic controllers; monitoring and supervision in automatic control systems; machine components; Sensors and virtual instruments for control

Download PDF

Paper 30: Modeling Wireless Mesh Networks for Load Management

Abstract: Developing a simulation model for multi-hop multi-gateway wireless mesh networks (WMNs) is a challenging task. In this paper, a multi-hop multi-gateway WMN simulation model is developed in a step-by-step approach. This paper presents a MATLAB Simulink-based simulation model of Wireless Mesh Network (WMN) designed for easy optimization of layer 2. The proposed model is of special utility for the simulation of scheduling of GateWay (GW) and packet within a multi-hop multi gateway wireless network. The simulation model provides the flexibility of controlling the flow of packets through the networks. Load management among the GWs of WMN is performed in a distributed manner wherein the nodes based on their local knowledge of neighborhood beacons optimize their path to a GW. This paper presents a centralized Load Management Scheme (LMS). The LMS is based on the formation of Gateway Service Sets (GSS). The GSS is formed on basis of equal load distribution among the GWs. The proposed LMS is then analyzed for throughput improvement by leveraging the MATLAB Simulink model developed in the paper. A throughput improvement of almost 600% and a 40% reduction in packet loss was observed through simulations thus indicating the efficacy of the proposed LMS. The uniqueness of the simulation model presented in this paper are its scalability and flexibility in terms of network topology parameters.

Author 1: Soma Pandey
Author 2: Govind R. Kadambi

Keywords: MATLAB; Simulink; multi-hop; wireless mesh network (WMN); gateway; simulation model; load management

Download PDF

Paper 31: A Model for Classification and Diagnosis of Skin Disease using Machine Learning and Image Processing Techniques

Abstract: Skin diseases are a global health problem that is difficult to diagnose sometimes due to the disease’s complexity, and the time-consuming effort. In addition to the fact that skin diseases affect human health, it also affects the psycho-social life if not diagnosed and controlled early. The enhancement of images processing techniques and machine learning leads to an effective and fast diagnosis that help detect the skin disease early. This paper presents a model that takes an image of the skin affected by a disease and diagnose acne, cherry angioma, melanoma, and psoriasis. The proposed model is composed of five steps, i.e., image acquisition, preprocessing, segmentation, feature extraction, and classification. In addition to using the machine learning algorithms for evaluating the model, i.e., Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (K-NN) classifiers, and achieved 90.7%, 84.2%, and 67.1%, respectively. Also, the SVM classifier result of the proposed model was compared with other papers, and mostly the proposed model’s result is better. In contrast, one paper achieved an accuracy of 100%.

Author 1: Shaden Abdulaziz AlDera
Author 2: Mohamed Tahar Ben Othman

Keywords: Skin disease; image processing; classification; machine learning; diagnosis; SVM; RF; K-NN; acne; cherry angioma; melanoma; psoriasis

Download PDF

Paper 32: A Hybrid Material Generation Algorithm with Probabilistic Neural Networks for Solving Classification Problems

Abstract: Classification is based on machine learning, in which each element in a set of data is classified into one of a predetermined set of groups. In data mining, an artificial neural network (ANN) is the most significant methodology because of the exact results obtained through this algorithm and applied in solving many classification problems. ANN consists of a group of types of feed-forward networks, feed-back network, RFB networks, and the probabilistic neural networks (PNN). For classification issues, the PNN is frequently utilized. The primary goals of this research are to fine-tune the weights of neural networks to enhance the classification accuracy. To accomplish this goal, the Material Generation Algorithm (MGA) was investigated with PNN in a hybrid model. Newly, the hybridization of algorithms is ubiquitous and it has led to the development of unique procedures that outperform those that use a single algorithm. Several distinct classification tasks are used to test the efficiency of the suggested (MGA-PNN) approach. The MGA algorithm's efficiency is evaluated using the PNN training outcomes generated, and its outcomes are compared to that of other optimization strategies. By 11 benchmark datasets, the suggested algorithm's performance in terms of classification accuracy is evaluated. The outcomes display that the MGA outperforms the biogeography based optimization, firefly method in terms of classification accuracy.

Author 1: Mohammad Wedyan
Author 2: Omar Alshaweesh
Author 3: Enas Ramadan
Author 4: Ryan Alturki
Author 5: Foziah Gazzawe
Author 6: Mohammed J. Alghamdi

Keywords: Artificial neural network (ANN); material generation algorithm (MGA); classification; probabilistic neural networks (PNN)

Download PDF

Paper 33: IoT based Portable Weather Station for Irrigation Management using Real-Time Parameters

Abstract: Rainfall in India is very unpredictable and is characterised by monsoon gaps. Rainfall prediction is very crucial for irrigation management to enhance farm productivity.. This article presents a portable rainfall prediction device which can be carried to fields. In the field by sensing the current atmospheric parameters like temperature, humidity, atmospheric pressure along with the current status of the sky to know the types of clouds present and gives the chances of rainfall. It is a novel approach in terms of portability of the device and it will give the prediction based on current information at a particular location by combining the predictions from the model of image processing of the clouds using deep learning and the currently sensed weather parameters are processed using machine learning without using WIFI or internet connection by providing Edge analytics where the data processing, rainfall prediction, and decision making is carried out locally on the device without any backend servers or cloud platform which will be very useful for the people like farmers who don’t have accessibility to internet in villages. The farmers can decide before every irrigation schedule, based on the prediction to what extent the crops can be irrigated. If chances of rain are very low 90% irrigation can be carried out, If chances of rain are predicted as low to medium then 40 to 60% irrigation can be done and if the prediction says medium to heavy rainfall then no irrigation is recommended.

Author 1: Geeta Ambildhuke
Author 2: Barnali Gupta Banik

Keywords: Deep learning; edge analytics; internet of things; machine learning; irrigation management; precision agriculture; rainfall prediction

Download PDF

Paper 34: E-Evaluation based on CSE-UCLA Model Refers to Glickman Pattern for Evaluating the Leadership Training Program

Abstract: This study aimed to describe the implementation of the level III leadership training program at the human resource development agency. The evaluation process used the CSE-UCLA model that was divided into: (1) components of system assessment, (2) program planning, (3) program implementation, (4) program improvement, and (5) program certification. This study involved 100 participants from the human resource development agency as institutional leaders, heads of divisions and heads of sub-sectors, lecturers/Widyaiswara, implementers/committees, superiors of alumni/mentors, and leadership training participants. Data was collected through questionnaires, interviews, observation, and documentation. The data were analyzed by quantitative descriptive analysis and verified by the Glickman quadrant, while the weaknesses found in the evaluation used qualitative descriptive analysis. The results showed that the level of effectiveness in terms of system assessment component included good criteria with a percentage of 82.4%, program planning component included good criteria (86.4%), program implementation component included good criteria (82.8%), and program improvement component included good criteria (83.2%). Lastly, the program certification component included good criteria (83%). The implementation of this Leadership Training Program is a strategy in developing SCA competencies, both managerial competencies, technical competencies, and socio-cultural competencies, to create a world-class bureaucracy in 2025 through independent learning and learning through coaching and mentoring.

Author 1: Ketut Rusmulyani
Author 2: I Made Yudana
Author 3: I Nyoman Natajaya
Author 4: Dewa Gede Hendra Divayana

Keywords: E-evaluation; leadership training; evaluation of educational programs; CSE-UCLA; human resource development agency

Download PDF

Paper 35: Rule-based Text Extraction for Multimodal Knowledge Graph

Abstract: Textual information is widely integrated in visual tasks such as object/scene detection and image annotation. However, the textual information is not fully exploited, overlooking the wide background knowledge available for Web images. This work proposes a multimodal knowledge graph (KG) to represent the knowledge extracted from unstructured Web image surrounding text and to integrate the relationship between image and text entities. Existing multimodal KG works have mainly focused on advanced visual processes for extracting entities and relations from images, and only employed standard text processing techniques such as tokenization, stop word removal, and part-of-speech (POS) tagging to capture nouns only or basic subject-verb-object from text in the semantic enrichment process. Adversely, neglecting other rich information in the text. Thus, the proposed approach attempts to address this as an automatic relation extraction (RE) problem to extract all possible triples from the text information from simple to complex sentences, in constructing the multimodal KG which eventually can be used as a training seed for visual tasks. A linguistic analysis is performed on a set of Web news articles consisting of news images and their related text. The dependency relations and POS information obtained are used to formulate a set of domain-agnostic entity-relation extraction rules. A triple extractor incorporating these rules, is developed to extract the triples from a news articles dataset and construct the proposed MKG. The Precision and Recall metrics are used to evaluate the extractor’s performance. The evaluation results show that the proposed approach can extract entities and relations in the dataset with the precision score of 0.90 and recall score of 0.60. While the results are promising, the extraction rules can still be improved to capture all the knowledge.

Author 1: Idza Aisara Norabid
Author 2: Fariza Fauzi

Keywords: Relation extraction; knowledge graph; multimodal knowledge graph; dependency relations; object/scene detection

Download PDF

Paper 36: Soil Color as a Measurement for Estimation of Fertility using Deep Learning Techniques

Abstract: Soil Behavior helps the farmer predict performance for growing crops, nutrient movement, and determine soil limitations. The traditional methods for soil classification in the laboratory require time and human resources and are expensive. This analysis examines the possibility of image recognition by artificial intelligence, with a machine learning technique called deep learning, to develop the cases that use artificial intelligence. This study performed deep learning with a model using a neural network. Neural Networks has used to evaluate relationships between the parameters of the three-dimensional coordinates resulting in soil classification and parameters. So Artificial Neural Networks (ANN) can be an effective tool for soil classification. This paper focused on AI techniques used to predict the soil type, advice the crop to yield, and discuss the transformed learning and benefits.

Author 1: N Lakshmi Kalyani
Author 2: Kolla Bhanu Prakash

Keywords: Artificial neural networks; deep learning; soil classification; soil nutrients; data augmentation; transform learning

Download PDF

Paper 37: A Survey on Genomic Dataset for Predicting the DNA Abnormalities Using Ml

Abstract: Genomic data is used in bioinformatics for collecting, storing and processing the genomes of living things. In order to process the genetic information, machine learning algorithms plays a vital role in building a computational model by using the statistical theory. This paper helps the researchers, who are doing research with the DNA dataset by applying the machine learning logics. Feature scaling machine learning techniques helps in predicting the sequence of genome for extrachromosomal amplification and predicting the tumor intensity in the human gene. Identification of unconventional chromosome in the DNA sequence minimizes the structural risk. In this paper, researchers can get clear insight on classification, sequence prediction, fuzzy relationship and SNP on genome dataset. The performance of various existing models is measured using the performance metrics and the accuracy.

Author 1: Siripuri Divya
Author 2: Y. Bhavani
Author 3: Thota Mahesh Kumar

Keywords: Genomic data; deoxyribonucleic acid (DNA); machine learning algorithms; single nucleotide polymorphism (SNPs)

Download PDF

Paper 38: An Architecture of Domain Independent and Extensible Intelligent Tutoring System based on Concept Dependencies and Subject Paths

Abstract: Intelligent Tutoring Systems (ITS) seek to provide personalized tutoring to learners, but are often domain specific, and lack extensibility. When featuring extensibility and domain independence, it is a challenge to provide appropriate level of personalization for every learner. In this paper, an architecture of a system that features domain-independence and extensibility with personalization and automatic course improvements without requiring persistent subject expert intervention has been proposed. The proposed architecture utilizes the notion of concept dependencies and the ability to sequence inter-dependent concepts intelligently into subject paths that enable automated tutoring as well as effective course customization per learner. It features a separate interface for subject experts through which they do not require ITS building knowledge to fulfil their appropriately assigned tasks assisted intelligently by the system, and an API based interface layer that supports today’s mobile requirements for better engagement.

Author 1: Sanjay Singh
Author 2: Vikram Singh

Keywords: Personalized tutoring; intelligent tutoring system; adaptive learning

Download PDF

Paper 39: Secure Routing Protocol for Low Power and Lossy Networks Against Rank Attack: A Systematic Review

Abstract: The Internet of Things (IoT) is witnessing massive widespread along in almost all aspects of life. IoT is defined as a network of interconnected devices applied in various environments including smart cities, transportation, health, industries, military, and agriculture. Its main purpose is to simplify the exchange and collect data from and to deployment environments. Due to their small size and cost-effectiveness, Wireless Sensor Networks (WSN) form one of the core technologies deployed in IoT. Yet, things interconnected with each other and exchanging data are prone to different kinds of security attacks. As a result, it is possible to compromise data while transmitted from source to destination through nodes. Routing Protocol for Low Power and Lossy Networks (RPL) offers only slight protection against routing attacks, but having a network with limited energy sources, processors, and memory, besides being deployed in unattended nature and hostile environment requires more scalable security measures. This paper focuses on investigating the problem of security provisioning in RPL. As such, a Systematic Literature Review (SLR) of security mechanisms proposed for RPL will be discussed. An extensive search was conducted on various online databases, then findings were filtered by reviewing abstracts, introduction, and conclusion. Finally, a summary of recent research work is presented. This work is important to highlight various aspects of securing RPL and get an initial insight for studying them.

Author 1: Laila Al-Qaisi
Author 2: Suhaidi Hassan
Author 3: Nur Haryani Binti Zakaria

Keywords: Wireless sensor networks; internet of things (IoT); routing security; RPL; objective function

Download PDF

Paper 40: Validation of Evacuation Assessment Algorithm in Finding the Best Indoor Evacuation Model

Abstract: This paper proposed an indoor evacuation assessment algorithm. Indoor evacuation wayfinding to the nearest exit becomes more difficult due to the intricacy of the inside layout and the involvement of numerous people. Thus, evacuation models were developed by researchers to assist evacuees in safely exiting a building. Unfortunately, building owners are unsure which evacuation model is best for their high-rise buildings. Therefore, we proposed an assessment algorithm to help the owners assess the best evacuation model. This research uses floor plan levels 13 and 14 of Yayasan Melaka’s, an office building, to simulate the evacuation. Ten simulation studies for each level are created. The proposed assessment algorithm focuses on three Microscopic evacuation models; agent-based, cellular automata, and social force. Hence, three simulation software were used to represent the mentioned evacuation model: Pathfinder, PedGo, and AnyLogic. K-Mean is then used to cluster the simulation time results. Elbow, Silhouette and V-measure techniques were applied to produce accurate results of the K-Mean. We compiled and analyzed the results from ten simulation studies for each level. The validation was done by comparing the final results. It shows that 70% of the lowest time taken is from Pathfinder, 30% from PedGo, and 0% from AnyLogic. Based on the result, it is proven that the proposed assessment algorithm can provide the best indoor evacuation model followed the attributes set for the building.

Author 1: Amir Haikal Abdul Halim
Author 2: Khyrina Airin Fariza Abu Samah

Keywords: Assessment algorithm; evacuation model; indoor evacuation; k-mean; validation

Download PDF

Paper 41: Effective Prediction of Software Defects using Random-tree Entropy based Feature Selection Framework

Abstract: Software systems have grown in size and complexity. These characteristics increase the difficulty of preventing software errors. As a result, forecasting the frequency of software module failures is critical to a developer’s efficiency. Many methods for defect detection and correcting problems exist. Hence, Machine Learning (ML) classification performance has to be greatly improved. Thus, in this study, a novel approach is proposed for predicting the number of software defects based on relevant variables using ML. First, feature entropy on each raw features is performed and then identifying the un-pruned random feature. Then is selected the relevant feature through the identical existence among the entropy and un-pruned feature. And finally, the software defect dataset of National Aeronautics and Space Administration (NASA) PC-1 is sent to an ML-based model to estimate the number of faults. Initial PC-1 dataset comprises 37 raw features from this only 8 critical characteristics are utilized to enhance the ML model. A random tree feature selection strategy is shown to be accurate and potentially outperform existing methods in the experimental results. The proposed method considerably outperformed the performance of current ML models by obtaining the accuracy of 97.76% in Random Forest (RF) model.

Author 1: Abdulaziz Alhumam

Keywords: Software defect prediction; machine learning; classification; feature entropy

Download PDF

Paper 42: Parameter Optimization of Nonlinear Piezoelectric Energy Harvesting System for IoT Applications

Abstract: The vibrational energy harvesting has been essentially applied to power up low-power electronics, microsystems, and wireless sensors especially in the areas of Internet of Things (IoT) devices. This paper investigates the prospect of incorporating nonlinearity in a unimorph piezoelectric cantilever beam with a tip magnet placed under a harmonic base excitation in IoT enabled environment. An empirical and theoretical analysis on the impact of various parameters such as spacing distance between magnets, presence of magnetic tip mass and positioning of vibrational source on the frequency response output was performed. It was observed that the largest spectrum of frequency can be produced when at the lowest resonant frequency of the cantilever. The positioning of vibrational source deeply impacts the hysteresis region and frequency range in realizing broadband energy harvesting. The inclusiveness of vibration source on both the cantilever beam as well as the external magnets impacts the energy harvester in terms of frequency range and the minimal distance for bistable condition.

Author 1: Li Wah Thong
Author 2: Swee Leong Kok
Author 3: Roszaidi Ramlan

Keywords: Energy harvesting; nonlinear dynamics; piezoelectric; vibration; broadband frequency

Download PDF

Paper 43: Smart Blended Learning Framework based on Artificial Intelligence using MobileNet Single Shot Detector and Centroid Tracking Algorithm

Abstract: The Covid-19 pandemic has affected all aspects of human life and has even forced humans to shift their life habits, including in the world of education. The learning model must shift from the traditional face-to-face pattern to a modern face-to-face pattern or an asynchronous pattern with information technology-based applications. Blended learning is one of the appropriate solutions to adjust the limited face-to-face learning conditions. Blended learning can be done, for example, by scheduling learning by dividing the number of participants by 50% and entering on a scheduled basis. However, the problem is that the time and effort used are less efficient. Blended learning can also be done by conducting learning simultaneously with 50% of students in class and the remaining 50% through conferences. This concept will streamline the time and effort used. However, the problem is that there is a gap in the learning experience between students in class and students who do learning via conference. This innovative blended learning system framework is proposed to overcome these problems. The system built seeks to present an online learning experience atmosphere so that it is expected to be able to resemble an offline learning atmosphere. We created a system using camera technology and object detection that will track the movement of the teacher so that the teacher can move freely in the room without having to be stuck in front of the computer holding the conference. The algorithms used are MobileNet Single Shot Detector and Centroid Tracking. This research produces an accurate model for detecting teacher movement at a distance of 2, 4, and 6 meters with a camera installation height of 1.5 and 3 meters.

Author 1: Abdul Wahid
Author 2: Muhammad Fajar B
Author 3: Jumadi M. Parenreng
Author 4: Seny Luhriyani
Author 5: Puput Dani Prasetyo Adi

Keywords: Smart blended learning; mobilenet; single shot detector; convolutional neural network; centroid tracking

Download PDF

Paper 44: Smart Agriculture Monitoring System using Clean Energy

Abstract: Internet of Things (IoT) technology makes all areas of human life more comfortable. The development of farms through the use of IoT positively influences agricultural production not only by strengthening it, but also by making it more profitable and reducing the cost of production. The goal of this paper is to offer a new IoT-based smart agriculture system that helps farmers get real-time data such as (temperature, humidity, soil moisture) for effective environmental monitoring that will allow them to increase overall yield and product quality. The farm monitoring system proposed in this paper is based on the ESP32 microcontroller with a set of sensors. This new model produces a real-time data feed that can be viewed online via a mobile app. The proposed new system uses solar energy with battery as an energy source.

Author 1: Karim ABOUELMEHDI
Author 2: Kamal ELHATTAB
Author 3: Abdelmajid EL MOUTAOUAKKIL

Keywords: IoT; smart agriculture; new model; solar panel; esp32; mobile app

Download PDF

Paper 45: RENTAKA: A Novel Machine Learning Framework for Crypto-Ransomware Pre-encryption Detection

Abstract: Crypto ransomware is malware that locks its victim’s file for ransom using an encryption algorithm. Its popularity has risen at an alarming rate among the cyber community due to several successful worldwide attacks. The encryption employed had caused irreversible damage to the victim’s digital files, even when the victim chose to pay the ransom. As a result, cybercriminals have found ransomware a lucrative and profitable cyber-extortion approach. The increasing computing power, memory, cryptography, and digital currency advancement have caused ransomware attacks. It spreads through phishing emails, encrypting sensitive data, and causing harm to the designated client. Most research in ransomware detection focuses on detecting during the encryption and post-attack phase. However, the damage done by crypto-ransomware is almost impossible to reverse, and there is a need for an early detection mechanism. For early detection of crypto-ransomware, behavior-based detection techniques are the most effective. This work describes RENTAKA, a framework based on machine learning for the early detection of crypto-ransomware. The features extracted are based on the phases of the ransomware lifecycle. This experiment included five widely used machine learning classifiers: Naïve Bayes, kNN, Support Vector Machines, Random Forest, and J48. This study proposed a pre-encryption detection framework for crypto-ransomware using a machine learning approach. Based on our experiments, support vector machines (SVM) performed with the best accuracy and TPR, 97.05% and 0.995, respectively.

Author 1: Wira Z. A. Zakaria
Author 2: Mohd Faizal Abdollah
Author 3: Othman Mohd
Author 4: S. M. Warusia Mohamed S. M. M Yassin
Author 5: Aswami Ariffin

Keywords: Ransomware; crypto-ransomware; ransomware early detection; pre-encryption; pre-attack; ransomware lifecycle

Download PDF

Paper 46: Non-contact Facial based Vital Sign Estimation using Convolutional Neural Network Approach

Abstract: A rapid heart rate may indicate early diagnosis of heart disease, which could result in abrupt mortality if a heart attack occurs while exercising. A fatal incident is usually precipitated by a heart attack while strenuously exercising. This paper proposed invasive health monitoring through remote photoplethysmography (rPPG) analysis captured by RGB video camera to measure a wide range of biological data. A non-contact facial-based vital signs prediction can facilitate checking pulse rate and respiration rate regularly. Several studies have been conducted on evaluating rPPG signals under a variety of static conditions and little head movement, including different skin tones, angles of the camera, and distance from the camera. A study of heart rate (HR) and breathing rate (BR) data from facial videos for fitness applications were presented in this paper. Most studies still do not have a way to measure vital sign estimation especially for physical activity application from facial videos. The face detector was applied based on three regions of interest on facial landmarks for vital sign estimation. Then, the rPPG method with convolutional neural network (CNN) is presented to construct a spatio-temporal mapping of essential characteristics and estimate the vital sign from a sequence of facial images of people after doing various types of exercises. This will allow people to keep track of their health while exercising and creating a tailored training program based on their physiological preferences. The absolute error (AE) between the estimated HR and the reference HR from all experiments is 2.16 ± 2.2 beats/min. While the AE for the estimated BR from the references BR are 1.53 ± 2.3 beats/min.

Author 1: Nor Surayahani Suriani
Author 2: Nur Syahida Shahdan
Author 3: Nan Md. Sahar
Author 4: Nik Shahidah Afifi Md. Taujuddin

Keywords: rPPG; remote heart rate estimation; respiration rate; fitness

Download PDF

Paper 47: A Survey on MCT vs. DCT: Who is the Winner in COVID-19

Abstract: Coronavirus disease (COVID-19) is a contagious disease appeared in late 2019 and caused by a virus called SARS-CoV-2. It is a pandemic spreading across the whole world and impacts millions of people and sadly causes death. There are two main Contact Tracing Methods (CTMs) to limit and slow down any chance of transmission of it: Manual Contact Tracing (MCT) and Digital Contact Tracing (DCT). The MCT abides by the guide to World Health Organization's guidance (WHO) on COVID-19 in terms of properly applying social distancing, wearing masks, washing hands, using sanitizers, etc. while the DCT abides by the digital contact tracing applications developed by several countries. This survey is mainly focused on these CTMs and the recent proposed solutions in this field, in order to highlight their drawbacks that negatively impact on both of satisfaction and feasibility in using them. The findings in the survey will be beneficial to understand the effectiveness of CTMs and current proposed solutions, in order to develop a comprehensive smart tracking system able to cooperatively contribute with both of MCT and DCT in extremely detecting, preventing, and slowing down the spread of COVID-19 or even any other similar pandemics in the future.

Author 1: Omar Khattab

Keywords: COVID-19; coronavirus disease; manual contact tracing; digital contact tracing

Download PDF

Paper 48: Social Customer Relationship Management as a Communication Tool for Academic Communities in Higher Education Institutions through Social Media

Abstract: The interaction between academic community members in universities is fundamental in facilitating the learning management process and workflow, thereby necessitating a communication tool system that is unrestricted by time and place. Social customer relationship management as a communication tool through social media is also essential. Therefore, this research employed a mixed-method exploratory design to evaluate 2421 subjects determined based on a proportional random sampling technique from the academic community of universities in four cities in Indonesia. The data collection method used an online interview questionnaire, and the coding techniques, namely open, axial, and selective coding, as well as the value stream analysis, were used. This research found that Social Customer Relationship Management (SCRM) can be a communication tool between the academic communities in higher education. This tool can be exploited by utilizing effective social media platforms, namely Instagram, Facebook, WhatsApp, and YouTube, integrated and connected as a center for information retrieval.

Author 1: Ali Ibrahim
Author 2: Ermatita
Author 3: Saparudin

Keywords: Social customer relationship management; communication tools; social media; academic client and communities

Download PDF

Paper 49: Application of the Clahe Method Contrast Enhancement of X-Ray Images

Abstract: Due to the nonlinearity of the luminance function produced by many medical recording devices, the quality of medical images deteriorates, which creates problems in the visual research work of physicians. X-rays can be taken as an example. This article examines methods of improving the contrast of graphic images methods of improving the quality of X-ray images. The research was carried out in several stages. Attempts were made to increase the contrast of several dozen X-ray images to select the best image brightness using brightness conversion methods in the MATLAB system. Contrast enhancement was observed during the experiments, resulting in the selection of a brightness range corresponding to the visual contrast enhancement. The selection of variables γ for the selected brightness range of the image was performed. The possibilities of the image histogram equalization method were considered. To obtain the best result before performing gamma correction the method of X-ray image histogram equalization is suggested. An enhancement version of this algorithm is presented because of the comparison. Application of the adaptive histogram equalization algorithm with contrast limitation provides a visual effect of improving the contrast of X-ray images. The NIQE and BRISQUE evaluation functions, which do not use reference images, are used to objectively quantify the conversion results.

Author 1: Omarova G. S
Author 2: Starovoitov V. V
Author 3: Aitkozha Zh. Zh
Author 4: Bekbolatov S
Author 5: Ostayeva A. B
Author 6: Nuridinov O

Keywords: Digital X-ray image; image quality assessment; image enhancement; contrast enhancement; luminance transformation; adaptive image histogram equalization

Download PDF

Paper 50: Efficient Segment-based Image Ciphering using Discretized Chaotic Standard Map with ECB, OFB and CBC

Abstract: This paper presents a block-based ciphering scheme that employs the 2D discretized chaotic Standard map (CSM) in three different operation modes. The employed operation modes include the electronic codebook (ECB), the output feedback (OFB) and the cipher block chaining (CBC) modes. In the presented 2D discretized CSM with the OFB and CBC, the initiation vector (IV) is employed as the primary secret key. The presented 2D discretized CSM with the CBC has two merits. The first merit is the ability of the presented 2D discretized CSM with the ECB, OFB and CBC to encipher images of any dimensions in a comparatively short time. The second merit is the high level of security of the presented 2D discretized CSM with the OFB and CBC through the integration of both diffusion and confusion operations. Different security key metrics like histogram deviation, irregular, and coefficient of correlation, are examined to assess the functionality of the presented 2D discretized CSM with the OFB and CBC. The resistance to noise, uniformity of histogram, and encryption speed are also investigated. The suggested 2D discretized CSM with the OFB and CBC is compared with the 2D discretized CSM in ECB. The achieved outcomes demonstrate that the proposed 2D discretized CSM with the OFB and CBC has a high security than in ECB from cryptographic viewpoint. Also, achieved outcomes demonstrate that the proposed 2D discretized CSM has better noise immunity in OFB compared with ECB and OFB.

Author 1: Mohammed A. AlZain

Keywords: Cryptography; 2D discretized CSM; ECB; OFB; CBC

Download PDF

Paper 51: Flower Pollination Algorithm for Feature Selection in Tweets Sentiment Analysis

Abstract: Text-based social media platforms have developed into important components for communication between customers and businesses. Users can easily state their thoughts and evaluations about products or services on social media. Machine learning algorithms have been hailed as one of the most efficient approaches for sentiment analysis in recent years. However, as the number of online reviews increases, the dimensionality of text data increases significantly. Due to the dimensionality issue, the performance of machine learning methods has been degraded. However, traditional feature selection methods select attributes based on their popularity, which typically does not improve classification performance. This work presents a population-based metaheuristic for feature selection algorithms named Flower Pollination Algorithms (FPA) because of their propensity to accept less optimum solutions and avoid getting caught in local optimum solutions. The study analyses tweets from Kaggle first with the usual Term Frequency-Inverse Document Frequency statistical weighting filter and then with the FPA. Four baseline classifiers are used to train the features: Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN). The results demonstrate that the FPA outperforms alternative feature subset selection algorithms. For the FPA, an average improvement in accuracy of 2.7% is seen. The SVM achieves a better accuracy of 98.99%.

Author 1: Muhammad Iqbal Abu Latiffi
Author 2: Mohd Ridzwan Yaakub
Author 3: Ibrahim Said Ahmad

Keywords: Sentiment analysis; metaheuristic algorithm; flower pollination algorithm; machine learning; feature selection

Download PDF

Paper 52: Re-CRUD Code Automation Framework Evaluation using DESMET Feature Analysis

Abstract: A unified view of web application design and development is crucial for dealing with complexity. However, the literature proposes many denominations, depending on the development methodology, frameworks or tools. This multitude of Create, Read, Update and Delete (CRUD) approaches does not allow a holistic view of the web application. Besides, in a web application, the search for good practice in design, features and essential functions is still a relevant issue. A subset of essential CRUD operations is to provide code automation for web application rapid prototyping. Re-CRUD articulates the records management features into CRUD operation. This study aims to provide insight into the effectiveness and efficiency of Re-CRUD in web application development and to compare it with other web application frameworks' CRUD output. The qualitative feature analysis is used based on the evaluation guideline proposed in DESMET and reviewed by experts for validation. A document management system is developed and used as a case study for Re-CRUD evaluation. The feature analysis comprises Re-CRUD and four other web application frameworks CRUD, namely, CakePHP, Laravel, Symfony and FuelPHP. According to the review, Re-CRUD satisfies its expectations by providing more useful features and delivering higher code automation in the web application development process. Compared to the other existing CRUD generator, Re-CRUD has integrated records management features that are useful in providing support in managing born-digital data and also contributes to effectiveness and efficiency in web application development.

Author 1: Asyraf Wahi Anuar
Author 2: Nazri Kama
Author 3: Azri Azmi
Author 4: Hazlifah Mohd Rusli
Author 5: Yazriwati Yahya

Keywords: Re-CRUD; web application; DESMET feature analysis; electronic records features

Download PDF

Paper 53: A Novel Readability Complexity Score for Gujarati Idiomatic Text

Abstract: Gujarati language is used for conversation by more than 55 million people worldwide and it is more than 1000 years old language. It is the chief language of the Indian state of Gujarat. There are many dialects of Gujarati like Standard Gujarati, Amdawadi Gujarati, Kathiawadi Gujarati, Kutchi Gujarati etc. The Gujarati language is very rich in morphology like other Indo-Aryan languages like Hindi. Many readability tests are available in the English language, but no readability complexity test is available for the Gujarati idiomatic text. The Complexity score is the sub concept of the readability test. In order to define complexity level of Gujarati text, complexity score of Gujarati text is calculated. We deployed a novel readability complexity score calculation method in which we considered the number of letters of each word, the number of diacritics of each word, Gujarati idiomatic text of n-gram where n=1 to 9, Gujarati idiomatic text of m-meaning idioms where m=1 to 7. The complexity score is calculated as the sum of word complexity score, diacritics complexity score, n-gram complexity score of Gujarati idioms and m-meaning complexity score of Gujarati idioms. We emphasized Gujarati idiomatic text for the calculation of complexity score as idioms make the text more complex to understand. This is an innovative and first of its kind work in the research community of Gujarati language. The results are hopeful enough to employ the suggested complexity score method for developing a readability test method for natural language processing tasks for the Gujarati language.

Author 1: Jatin C. Modh
Author 2: Jatinderkumar R. Saini
Author 3: Ketan Kotecha

Keywords: Complexity; Gujarati; idiomatic text; natural language processing (NLP); readability

Download PDF

Paper 54: Importance of Memory Management Layer in Big Data Architecture

Abstract: The generation of daily massive amounts of heterogeneous data from a variety of sources presents a challenge in terms of storage and analysis capabilities and brings new problems into high-performance computing clusters. To better utilize this huge and heterogeneous data, the continuous development of advanced Big Data platforms and Big Data analytic techniques are required. One of the significant issues with in-memory Big Data processing platforms, such as Apache Spark, is the user’s responsibility to decide whether the intermediate data should be cached or not. In addition, the data may be kept in several storage systems and physically scattered over different racks, regions, and clouds. Data need to be close to the computation nodes and hence data locality issue is a challenge. In this paper, using a distinct memory management layer between the data processing layer and the data storage layer, which automatically caches data without the need for any interaction from the applications’ developers, is evaluated. K-means, PageRank and WordCount workloads from the HiBench benchmark beside a real case to predict the price of Real Estate that is implemented using Gradient Boosting Regression Tree model, are used to evaluate this framework. Experiments show that the memory management layer outperforms the Apache Spark in reducing the execution time.

Author 1: Maha Dessokey
Author 2: Sherif M. Saif
Author 3: Hesham Eldeeb
Author 4: Sameh Salem
Author 5: Elsayed Saad

Keywords: Apache Spark; Big Data; data analytics algorithms; memory management

Download PDF

Paper 55: Structural Equation Modelling for Validating Disruptive Factors in Livestock Supply Chain

Abstract: The purpose of this paper is to deploy a structural equation modeling approach through the Partial Small Square technique to validate the disruptions factors that affect livestock supply chain performance. The disruption prediction factors were obtained from the analysis of literature studies and data from the Department of Veterinary Services (DSV) and expert evaluation. Factors considered in the study model are Livestock Process, Finance, Breeders, Quality, Facilities, Technology, Demand, Supply, Information Communication, Sales, Transportation, Government Involvement, Disaster and Syariah Compliance. The results of the study found that the factors of Livestock Process, Finance, Breeders, Livestock Quality, Technology, Supply, Sales, Transportation, Government Involvement and Syariah Compliance were accepted as disruptions in the livestock supply chain. The findings of this study will assist farmers and livestock stakeholders to take necessary measures to minimise the disruption and further the government's goal of enlivening small and medium livestock enterprises in Malaysia.

Author 1: Nur Amlya Abd Majid
Author 2: Noraidah Sahari
Author 3: Nur Fazidah Elias
Author 4: Hazura Mohamed
Author 5: Latifah Abd Latib
Author 6: Khairul Firdaus Ne’matullah

Keywords: Supply chain management; disruption; livestock; structural equation modelling

Download PDF

Paper 56: IoT Enabled Smart Parking System for Improvising the Prediction Availability of the Parking Space

Abstract: Smart cities are a result of persistent technological advancements aimed at improving the quality of life for their residents. IoT-enabled smart parking is one of the foundations of smart transportation which seeks to be versatile, long-lasting, and integrated into a Smart City. One of the studies shows that the drivers who are searching for free parking space can cause congestion problems up to 30%. There is a possibility to reduce air pollution and fluidity noise traffic by combining Internet of Things (IoT) sensors positioned in different parking areas with a mobile application and help the drivers to search for free places in different areas of the city and also provide guidance toward the parking space. In this paper, we show and explain a unique Data Mining-based Ensemble technique for anticipating parking lot occupancy to reduce parking search time and improve car flow in congested locations, with a favorable overall impact on traffic in urban centers. In this paper multi scanning, IoT Enabled smart parking model is proposed along with ensemble classifier that improvises the predictive availability of the free parking space. The predictors' parameters were additionally optimized using a Bootstrap and bagging algorithm. The proposed method was tested an IoT dataset containing a number of sensor recordings. The tests conducted on the data set resulted in an average mean absolute error of 0.07% using the Bagging Regression method (BRM).

Author 1: Anchal Dahiya
Author 2: Pooja Mittal

Keywords: IoT; Data mining; sensors; ensemble; decision tree; bagging technique; boosting technique

Download PDF

Paper 57: An Optimized Kernel MSVM Machine Learning-based Model for Churn Analysis

Abstract: Customer churn is considered as a significant issue in any industry due to various services, clients, and commodities. A massive amount of data is being created from e-commerce services and tools. Analytical data and machine learning-based approaches have been implemented and utilized for CA (churn analysis) to design a plan, i.e., required to comprehend the rationale for the CC (Customer Churn) and to generate a profitable and actual customer holding program. The analytics and machine learning approaches mainly focus on customer profiling, CC classification, and detection of features that affect churn. However, there are no specific techniques which can be used to determine how often a prospective customer is inclined to cover all the expenses whether they are churned or not. In this paper, an Optimized Kernel MSVM classification model is proposed to predict and classify churn. In the proposed work, MSVM algorithm has been used for classification. The kernel PCA and ALO optimizer method has been used for Feature extraction and selection. The proposed model Optimized Kernel MSVM has been implemented on Tele-communication sector customer churn database to demonstrate the proposed model's generalization ability. The Optimized Kernel MSVM model has achieved an accuracy of 91.05%, AUC 85% being maximum and reduced the RMSE score to 2.838. The implementation shows that both churn detection and classification may be examined at the same time while maintaining the highest overall accuracy and AUC.

Author 1: Pankaj Hooda
Author 2: Pooja Mittal

Keywords: CA (Churn Analysis); CC (Customer Churn); OKMSVM (Optimized Kernel-MultiClass Support Vector Machine) Model; KPCA (Kernel Principle Component Analysis); A.L.O. (Ant Lion Optimization) method

Download PDF

Paper 58: Study on Feature Engineering and Ensemble Learning for Student Academic Performance Prediction

Abstract: Student academic performance prediction is one of the important works in the teaching management, which can realize accurate management, scientific teaching and personalized learning by mining important features affecting the academic performance and accurately predicting academic. Due to the subjectivity of feature extraction and the randomness of hyperparameters, the accuracy of academic performance prediction needs to be improved. Therefore, in order to improve the accuracy of prediction, an academic prediction method based on Feature Engineering and ensemble learning is proposed, which makes full use of the advantages of random forest in feature extraction and the ability of XGBoost in prediction. Firstly, the feature importance is calculated and ranked by using the random forest method, and the optimal feature subset combined with the forward search strategy. Secondly, the optimal feature subset is input into the XGBoost model for prediction. The sparrow search algorithm is used to optimize the XGBoost hyperparameters to further improve the accuracy of academic prediction. Finally, the performance of the proposed method is verified through the experiments of the public data set. The experimental results show that the academic prediction method designed is better than the single learner prediction method and other integrated learning prediction methods. The accuracy result jumps to 82.4%. It has good prediction performance and can provide support for teachers to teach according to students’ aptitude.

Author 1: Du Xiaoming
Author 2: Chen Ying
Author 3: Zhang Xiaofang
Author 4: Guo Yu

Keywords: Academic performance prediction; feature engineering; ensemble learning; random forest; XGBoost

Download PDF

Paper 59: Development of Hausa Acoustic Model for Speech Recognition

Abstract: Acoustic modeling is essential for enhancing the accuracy of voice recognition software. To build an automatic speech system and application for any language, building an acoustic model is essential. In this regard, this research is concerned with the development of the Hausa acoustic model for automatic speech recognition. The goal of this work is to design and develop an acoustic model for the Hausa language. This is done by creating a word-level phonemes dataset from the Hausa speech corpus database. Then implement a deep learning algorithm for acoustic modeling. The model was built using Convolutional Neural Network that achieved 83% accuracy. The developed model can be used as a foundation for the development and testing of the Hausa speech recognition system.

Author 1: Umar Adam Ibrahim
Author 2: Moussa Mahamat Boukar
Author 3: Muhammad Aliyu Suleiman

Keywords: Acoustic model; Hausa Phonemes; word level; CNN

Download PDF

Paper 60: New Method for 4D Reconstruction of Medical Images

Abstract: This paper proposes a new optimized method that is fast in rendering for 4D reconstruction from 2D medical images of human anatomy permitting their real–time refined visualization. This method uses the 3D reconstruction algorithm based on contour matching of medical image sequences and on the tessellation of recent GPU. In our framework, the construction of the low-resolution mesh that is based on contour extraction allows to create a 3D mesh without any ambiguity and exactly matches the real shape of the human anatomy. Such preliminary result is of great interest, since it permits to lead to other valuable realizations such as reducing the computation burden of basic meshes and displacement vectors. Moreover, one can achieve a very low storage memory, as well as one can ease the fast real-time 4D visualization with a high desired resolution. Hence, it is then straight forward that this study can contribute to easing the diagnosis and detection in real-time of human organs in motion damage and deterioration. Especially, 4D visualization technology that is still under development is highly important and needed for assessing some dangerously evaluative diseases, as in the case of lung diseases.

Author 1: Lamyae MIARA
Author 2: Said BENOMAR ELMDEGHRI
Author 3: Mohammed Oucamah CHERKAOUI MALKI

Keywords: 2D medical image; 4D reconstruction; contour matching; recent GPU; 3D mesh

Download PDF

Paper 61: An Adaptive Approach for Preserving Privacy in Context Aware Applications for Smartphones in Cloud Computing Platform

Abstract: With the widespread use of mobile phones and smartphone applications, protecting one’s privacy has become a major concern. Because active defensive strategies and temporal connections between situations relevant to users are not taken into account, present privacy preservation systems for cell phones are often ineffective. This work defines secrecy maintenance issues similar to optimizing tasks, thereby verifying their accuracy and optimization capabilities through a hypothetical study. Many optimal issues arise while preserving one’s privacy and these optimal issues are to be addressed as linear programming issues. By addressing linear programming issues, an effective context-aware privacy-preserving algorithm (CAPP) was created that uses an active defence strategy to determine how to release a user’s current context to enhance the quality of service (QoS) regarding context-aware applications while maintaining secrecy. CAPP outperforms other standard methodologies in lengthy simulations of actual data. Additionally, the minimax learning algorithm (MLA) optimizes the policy users and improves the satisfaction threshold of the context-aware applications. Moreover, a cloud-based approach is introduced in the work to protect the user’s privacy from third parties. The obtained performance measures are compared with existing approaches in terms of privacy policy breaches, context sensitivity, satisfaction threshold, adversary power, and convergence speed for online and offline attacks.

Author 1: H. Manoj T. Gadiyar
Author 2: Thyagaraju G. S
Author 3: R. H. Goudar

Keywords: Context-aware; privacy; active defence; privacy protection and mobile phones

Download PDF

Paper 62: Digital Learning Tools for Security Inductions in Mining Interns: A PLS-SEM Analysis

Abstract: New pedagogical tools have been introduced in educational contexts in recent years. They have been shown to impact learning compared to conventional education strategies positively. Before implementing new learning tools, a study of technological acceptance is needed for its application to succeed. For this reason, the objective of this research was to measure the intention and acceptance of the use of new digital learning tools, such as mobile applications, holograms, interactive platforms, and virtual or augmented reality, through the Technology Acceptance Model 3 (TAM3) in safety on-board training inductions in a mining company. This measurement was based on the analysis of a survey carried out in Google Forms based on the Likert scale; the results were processed using the partial least squares technique in structural equation models (PLS-SEM), processed through SmartPLS 3. As a result, we got positive correlations between the instrument's variables and acceptance by the participants studied. The findings indicate that it is essential to consider the participants' opinions a priori to implementing new digital education tools for managerial decision-making. It was considering highlighting the teaching about safety in mining companies since this allows contributing to engineering education and protecting the most precious resource of any company, the human being.

Author 1: Jose Julian Rodriguez-Delgado
Author 2: Patricia Lopez-Casaperalta
Author 3: Mario Gustavo Berrios-Espezua
Author 4: Alejandro Marcelo Acosta-Quelopana
Author 5: Jose Sulla-Torres

Keywords: Technology acceptance model 3; PLS-SEM; SmartPLS; mining company; safety; safety inductions; safety talk; learning; education; teaching; technology; learning tools

Download PDF

Paper 63: Enhanced Symbol Recognition based on Advanced Data Augmentation for Engineering Diagrams

Abstract: Symbol recognition has generated research interest for image analytics of engineering diagrams. Techniques including structural, syntactic, statistical, Convolution Neural Network (CNN) were studied to identify gaps of research. Despite popularity, CNN requires huge learning dataset, which often involves costly procurement. To address this, combination between CycleGAN and CNN is proposed. CycleGAN generates more learning dataset synthetically, thus yielding opportunity to improve accuracy of symbol recognition. In the domain of for engineering symbols, standard CNN model is developed and used in experimental testing. Different ratios of training dataset were tested in multiple experiments using Piping and Instrument Diagram (P&IDs) drawings. Result of highest accuracy for symbol recognition is up to 92.85% against baseline and other method. The results determined that gradual reduction of training samples, the effectiveness of recognition accuracy performance after using proposed method was remained substantially stable.

Author 1: Ong Kai Bin
Author 2: Yew Kwang Hooi
Author 3: Said Jadid Abdul Kadir
Author 4: Haruhiro Fujita
Author 5: Luqman Hakim Rosli

Keywords: Symbol recognition; symbol spotting; engineering drawing; convolution neural network (CNN); CycleGAN; piping and instrument diagram (P&ID)

Download PDF

Paper 64: A Graph-oriented Framework for Online Analytical Processing

Abstract: OLAP (Online Analytical Processing) is a tried-and-tested technology and a core concept in Business Intelligence. With data flowing from different and countless sources, exploring data in order to deliver actionable insights has become a daunting task with current OLAP tools despite the cycle of improvement that has gone through it. In the last decade, with the emergence of the big data phenomenon, NoSQL databases are seeing a spike in popularity and become more used in industry and academia as their value in handling a huge and varied amount of data become increasingly evident. Graph oriented database is one of the four chief types of NoSQL oriented databases that represent a promising technology candidate for big data analytics. In this paper we bring forward our contribution to graph-oriented analytical processing, which is twofold. First, we provide a novel approach for modeling a graph-oriented data warehouse. Second, we propose a data cube materialization through the precomputation of aggregated nodes. We present how typical OLAP queries can be performed against data warehouses stored in NoSQL graph-oriented database management systems. An implementation is conducted on a fictional data warehouse using Neo4j and the Cypher declarative language. The same dataset is stored in a relational data warehouse in order to compare storage space and query performance. Thus, the obtained results shows that graph OLAP implementation outperform clearly the relational alternative in term of query response time.

Author 1: Abdelhak KHALIL
Author 2: Mustapha BELAISSAOUI

Keywords: Graph OLAP; data warehousing; graph databases; NoSQL; data cube; decision support system

Download PDF

Paper 65: Sentiment Analysis to Explore User Perception of Teleworking in Saudi Arabia

Abstract: Due to the emergence of the COVID-19 pandemic in 2019, many public and private organizations from different sectors in Saudi Arabia were forced to enforce teleworking as the main work arrangement. This paper seeks to understand the experience and attitude of the public toward remote work by analyzing Twitter data from March 2020 to July 2021 by using "Mazajak" the online Arabic analyzer. A corpus of 39,523 tweets with hashtags mentioning the teleworking program in Saudi Arabia was obtained. The results indicate that neutrality was the most prevalent sentiment with 58.21%, followed by positive sentiment with 30.67%. Thematic analysis was used to identify themes in the tweets with positive and negative sentiment. Flexibility, teamwork, teleworking preference, and learning were the major themes related to positive sentiment, while themes related to negative sentiment were private sector, companies, and fake.

Author 1: Malak Nazal Alotaibi
Author 2: Zahyah H. Alharbi

Keywords: Mazajak; sentiment analysis; thematic analysis; telework; remote work

Download PDF

Paper 66: Framework for Development of 3D Temple Objects based on Photogrammetry Method

Abstract: Indonesia has a lot of cultural buildings that need to capture as digital objects for other purposes, especially for digital preservation. One of the methods of making 3D objects is using the photogrammetry method. The photogrammetry method makes 3D objects using many photos captured by the camera that will be integrated into the software and processed into 3D objects. In this research, the framework for modeling 3D objects of the cultural building is proposed based on the photogrammetry approach. This framework includes data capture, modeling and processing, and calibration. This framework was tested while making the 3D object of the Candi Badut temple and reported that the 3D model has significantly had similarities with the real object. The framework is useful for standard guidelines for making 3D modeling of historical relics efficiently.

Author 1: Herman Tolle
Author 2: Ratih Kartika Dewi
Author 3: Komang Candra Brata
Author 4: Benyamin Perdamean

Keywords: Photogrammetry; historical relic; 3D objects; digital preservation; virtual reality

Download PDF

Paper 67: Dual-fast Greedy Heuristic Algorithm for Green ICT

Abstract: The Internet power consumption represents 3.6% to 6.2% of the annual worldwide power consumption and is continually expanding. The awareness of this problem has increased, hence, a few strategies are being put into place to decrease the power consumption of the Information Communication Technology (ICT) sectors, in general. Backbone networks are the main part of the Internet power consumption because their line cards expend a lot of energy, also their links are commonly bundled and provide larger capacity than needed. Therefore, bundled links are partially shut down during times of low demand to reduce power consumption. Literature introduces a few heuristic algorithms that are run periodically to shut down bundled links partially. This paper proposes a Dual-Fast Greedy Heuristic algorithm (DGH), which significantly speeds up the power savings. DGH is examined on the topology and traffic of the Abilene backbone. The experimental results show that DGH provides competitive power savings with minimum execution time.

Author 1: Inas Abuqaddom

Keywords: Abilene backbone; backbone network; bundled link; capacity; Internet power consumption; power savings

Download PDF

Paper 68: Parallel Improved Genetic Algorithm for the Quadratic Assignment Problem

Abstract: Quadratic Assignment Problem is one of the most common combinatorial optimization problems that represents many real-life problems. Many techniques are applied to solve Quadratic Assignment Problem, these include exact, heuristic, and metaheuristic methods. A Genetic Algorithm is a powerful heuristic approach used to find optimal solutions or near-to-optimal for Quadratic Assignment problems. In this paper, we developed a Genetic Algorithm with a new crossover operator with new technology closer to that found in nature without a crossover point and a new suggested intelligent mutation operator, then we developed a Parallel Genetic Algorithm using the same crossover and mutation. The sequential Genetic Algorithm will be implemented in the Central Processing Unit (CPU), and the Parallel Genetic Algorithm will be implemented in the Graphical Processing Unit (GPU). This paper presents two comparisons, first calculates elapsed time for crossover, mutation, and selection in both CPU and GPU, then compares the results. This comparison clearly shows the enhancement degree of computation time in the parallel environment, which is around half the time executed in the sequential environment. The second comparison, iterates these operators into several generations, using twenty benchmark instances reported in Quadratic Assignment Problem Library with sizes from (12-70), population size equal to 600, the number of generations equal to 2000, and the maximum number of parallel threads will be 600. Proposed crossover and mutation give the optimal solutions with ten benchmarks with problem sizes from 12 to 32 in both Sequential Genetic Algorithm and Parallel Genetic Algorithm, the next ten benchmarks give solutions closed to the optimal solution with a small error rate.

Author 1: Huda Alfaifi
Author 2: Yassine Daadaa

Keywords: Component; Quadratic Assignment Problem (QAP); Genetic Algorithm (GA); Parallel Genetic Algorithm (PGA); Sequential Genetic Algorithm (SGA); Central Processing Unit (CPU); Compute Unified Device Architecture (CUDA); Quadratic Assignment Problem Library (QAPLIB); Best Known Solution (BKS); Average Percent Deviation (APD)

Download PDF

Paper 69: Modeling for Car Quality Complaint Classification based on Machine Learning

Abstract: Cars play an important role in many aspects of people's social life, and the effective handling of car quality complaints is of great significance to the proper running of cars and the reputation maintenance of car brands; effective classification of car quality complaint texts is the basis of the efficient handling of corresponding quality complaints, while relying on manual classification has disadvantages such as heavy workload, experience dependence, and error proneness; machine learning methods have been quite widely used in the automatic classification modeling for different types of natural language texts. It is of great practical significance to construct the automatic classification model of car quality complaints based on machine learning. Based on the characteristics of car quality complaint texts, this study vectorized the texts after word segmentation, performed feature selection and dimension reduction based on correlation analysis, and combined the progressive model training method and support vector machine to construct the classification model; in model reliability analysis, it was evaluated based on the effect of data amount on the modeling and the effect of text length on the prediction probability distribution. The results show that based on the method in this study, effective automatic classification model of car quality complaint texts could be constructed.

Author 1: Chen Xiao Yu
Author 2: Hou Xia
Author 3: Zhang Xiao Min
Author 4: Song Ying

Keywords: Car; quality complaint; natural language text; classification modeling; machine learning

Download PDF

Paper 70: Identifying Influential Nodes with Centrality Indices Combinations using Symbolic Regressions

Abstract: Numerous strategies for determining the most influential nodes in a connected network have been developed. The use of centrality indices in a network allows the identification of the most important nodes in the network. Specific indices, on the other hand, cannot search for a network's entire meaning because they are only interested in a single attribute. Researchers frequently overlook an index's characteristics in favour of focusing on its application. The purpose of this research is to integrate selected centrality indices classified by their various properties. A symbolic regression approach was used to find meaningful mathematical expressions for this combination of indices. When the efficacy of the combined indices is compared to other methods, the combined indices react similarly and outperform the previous method. Using this adaptive technique, network researchers can now identify the most influential network nodes.

Author 1: Mohd Fariduddin Mukhtar
Author 2: Zuraida Abal Abas
Author 3: Amir Hamzah Abdul Rasib
Author 4: Siti Haryanti Hairol Anuar
Author 5: Nurul Hafizah Mohd Zaki
Author 6: Ahmad Fadzli Nizam Abdul Rahman
Author 7: Zaheera Zainal Abidin
Author 8: Abdul Samad Shibghatullah

Keywords: Centrality indices; combination; symbolic regressions; influential nodes

Download PDF

Paper 71: Improving Computational Thinking in Nursing Students through Learning Computer Programming

Abstract: Computational thinking is a fundamental skill for problem-solving, it uses computational concepts and other types of thinking such as algorithmic. The experience of improving computational thinking in nursing students using block-based programming environments such as Code.org, Lightbot, and the Python textual programming language is described. The results obtained are analyzed by applying a pre-and post-test of computational thinking to the students. The methodological design is quasi-experimental since it did not work with a control group. The study group was made up of 30 students from the Professional School of Nursing of the National University of San Agustin de Arequipa. The results show that teaching programming allows the understanding of computational concepts and improves computational thinking. It is concluded that block-based programming environments and the Python language facilitate the development of algorithmic thinking and computational thinking.

Author 1: Leticia Laura-Ochoa
Author 2: Norka Bedregal-Alpaca
Author 3: Elizabeth Vidal

Keywords: Computational thinking; computational thinking assessment; computational thinking test; programming; programming environments

Download PDF

Paper 72: Improving Social Engineering Awareness, Training and Education (SEATE) using a Behavioral Change Model

Abstract: Social Engineering (SE) Awareness, Training, and Education (SEATE) is one of the recommended defenses against SE attacks among users of Information Systems. However, many of these SEATE programs fails to achieve the desired impact leading to exposures. This study sought to explore SEATE programs to identify gaps/challenges and propose relevant content, Delivery Methods, and a novel behavioral change Model to improve SEATE programs among users. An explorative Literature Search was conducted on the relevant SEATE Content, Delivery methods and the challenges of SEATE Programs. Consequently, the relevant and critical content and delivery methods were proposed. The challenges that impede the efficient and effective conduct of SEATE Programs were established. A behavioral change Model known as Social Engineering Awareness, Transition, Adaptation and Consolidation (ATAC) based on Stable-Quasi-Stationary Equilibrium theory was proposed. The model was validated using Expert Opinions. Five (5) expert in cybersecurity were recruited to appraise the model based on five metrics; fit for purpose, novelty, ease of use and structure. The results show that, challenges still exist in the conduct of SEATE programs. To improve SEATE programs requires relevant and innovative content, and delivery method (Hybrid Approach). Validation of the proposed behavioral change model showed an average score at 73.6% and performance metrics at 92%. As the menace of SE attacks rages on and exploiting the user, the need for SEATE programs remains imperative. A well-developed and relevant content, delivery methods and a clear understanding of the challenges is required to improve SEATE. Following the model developed, and the repeated use of it will lead to improving user resistance and or immunity to SE attacks and by extension improve security culture among users.

Author 1: Azaabi Cletus
Author 2: Benjamin Weyory
Author 3: Alex Opoku

Keywords: Social engineering; user training; user awareness; user education; ATAC model

Download PDF

Paper 73: Evaluating Learning Management System based on PACMAD Usability Model: Brighten Mobile Application

Abstract: During the pre-COVID-19 pandemic, mobile learning is just an optional or a supplementary module in learning process. However, when the pandemic hit the world in the middle of 2020, a large number of students were forced to move from traditional learning process to online learning. This has become a critical issue especially for new online learners. Usability of a mobile learning application is important in ensuring that learners are able to learn efficiently and effectively with ease. This study evaluates the usability of the Brighten mobile application; a Moodle-based Learning Management System (LMS) which is currently used by all Universiti Tenaga Nasional’s students. The evaluation is based on People at the Center of Mobile Application Development (PACMAD). The results indicate that Brighten mobile application is acceptable in terms of usability’s effectiveness, efficiency, learnability, memorability and error-tolerance. Learners’ satisfaction level shows a “marginally acceptable” result based on the SUS Adjective Rating Scale and the result for cognitive load shows that the highest cognitive load was in terms of the performance factor.

Author 1: Masyura Ahmad Faudzi
Author 2: Zaihisma Che Cob
Author 3: Ridha Omar
Author 4: Sharul Azim Sharudin

Keywords: Mobile learning; usability; PACMAD; learning management system; Moodle

Download PDF

Paper 74: Voice Biometrics for Indonesian Language Users using Algorithm of Deep Learning CNN Residual and Hybrid of DWT-MFCC Extraction Features

Abstract: This research develops a Voice Biometrics model for the Indonesian language users by using deep learning algorithm of CNN Residual and Hybrid of DWT-MFCC Feature Extraction. The voice dataset of Indonesian speakers were created with a duration of 5, 10, 15, 20, and 25 minutes. The testing phase of speaker recognition and speech recognition were carried out by comparing the model of CNN Residual with CNN Standard. In the phase of speaker recognition, CNN Residual model has obtained the best results with the highest precision percentage of 99.91% and the highest accuracy of 99.47% at 25 minutes voice samples, compared to the CNN Standard obtaining precision of 96.83% and accuracy of 99.00%. In the phase of speech recognition, CNN Residual model has reached the best performance at 100% accuracy during 20 trials, while CNN Standard only gave 95% accuracy. CNN Residual Model provides a better performance for its accuracy and precision, but it is slightly slower than the CNN Standard, with a time difference of 0.03 – 1.28 seconds.

Author 1: Haris Isyanto
Author 2: Ajib Setyo Arifin
Author 3: Muhammad Suryanegara

Keywords: Voice biometric; deep learning; CNN; DWT-MFCC; security

Download PDF

Paper 75: Hybrid Deformable Convolutional with Recurrent Neural Network for Optimal Traffic Congestion Prediction: A Fuzzy Logic Congestion Index System

Abstract: In the field of Intelligent Transportation Systems (ITs), traffic congestion is considered as an important problem. Traffic blockage usually affects the quality of time, travel time, economy of the country, and transportability of people. The information of traffic congestion is collected and analyzed in ITs, and the methods to prevent the traffic congestion are predicted. However, the tackling of huge data is still challenging. The rapid increase in vehicle usage and road construction has resulted in traffic congestion. Various studies are undergone in ITs to recognize the traffic management system by adopting few resources. Real time-based traffic services are implemented to prevent the traffic congestion in existing areas. These services provide high expense accuracy. This paper plans to develop a new technique to predict the traffic congestion using improved deep learning approaches. At first, the benchmark dataset is gathered and the pre-processing of data is performed with removing the bad data, organizing the raw data, and filling the null values. The optimized weighted features are selected from the pre-processed data by adopting a new meta-heuristic Hybrid Jaya Harris Hawk Optimization (HJHHO) algorithm. The prediction of congestion parameters such as speed reduction rate, very low speed rate, and volume to capacity ratio of vehicles are performed by the proposed Improved Deformable Convolutional Recurrent Network (IDCRN) prediction model. These predicted measures are subjected to fuzzy interference system for congestion index computation. From the experimental analysis, it has proved that the proposed method has reduced the error rate while comparing with other deep learning and machine learning approaches.

Author 1: Sara Berrouk
Author 2: Abdelaziz El Fazziki
Author 3: Mohammed Sadgal

Keywords: Optimal traffic congestion prediction; deformable convolutional network; recurrent neural network; Hybrid Jaya Harris Hawk Optimization Algorithm; congestion index computation; fuzzy interference system

Download PDF

Paper 76: Impact of the Pandemic on the Development and Regulation of Electronic Commerce in Russia

Abstract: The article deals with topical issues of legal support for the development of electronic commerce in the Russian Federation. The analysis of the main categories of e-commerce has been carried out, the content of which is standardized in domestic regulatory legal acts, the following is among them: elements of the purchase and sale process, the concept of types of trading activities, electronic signature, digital assets, digital currency, smart contracts, digital transactions, etc.). The categories have been defined, the concept of which is absent in the normative legal acts of Russia: the concept of digital goods, e-commerce infrastructure, e-commerce services, delivery channels in online stores, the concept of a courier/courier service, the concept of smart applications, the definition of varieties of online stores, etc. The problem of research is defined: insufficiently effective legal support of economic activity in electronic commerce. An imperfect system of planning strategies for the development of trade organizations in the online environment has been revealed. The conclusions have been formed that the process of digitalization and the consequences of the pandemic have a significant impact on the dynamics of legal support for the development of electronic commerce, but its level is currently not high enough and requires improvement (by making additions to several regulatory legal acts, such as the Law on Trade, the Strategy for the Development of Electronic Commerce in Russia, etc.). The study used system, situational, complex methods, graphical, block grouping, methods of comparative analysis of normative legal acts, and synthesis of conclusions and proposals.

Author 1: Svetlana Panasenko
Author 2: Maisa Seifullaeva
Author 3: Ibragim Ramazanov
Author 4: Elena Mayorova
Author 5: Alexander Nikishin
Author 6: A. M. Vovk

Keywords: Legal support; strategy; development; electronic commerce; Russian federation; digitalization; informatization; online stores; delivery channels; digital product

Download PDF

Paper 77: Application for a Waste Management via the QR-Code System

Abstract: This research aims in developing an application for the waste management via the QR code system: 1) to study the quality of the application and 2) to study the satisfaction of users of the application by using the system development life cycle (SDLC) principle. There were 388 people of sample groups in this research which consisted of community leaders, village health volunteers, youth and the general public of Ban Yang Sub-district, Mueang Buriram District, and Buriram Province. The research instruments were the application for a waste management via the QR code system, Application Quality Assessment Form, and the application satisfaction questionnaire. The statistics used in the data analysis were mean and standard deviation. The results of the research revealed that there were three main functions of the application for a waste management via the QR code system as follows: 1) The quality assessment of the application in all aspects at a high level (Mean = 4.41, S.D.=0.10). 2) Study of satisfaction of the application users in all aspects at a high level (Mean = 4.42, S.D. = 0.45). 3) The application of waste management application via the QR code system allowed group members in the community to reduce the process of managing household waste more conveniently and create a positive attitude in using waste to elevate through the work of the group members in the community.

Author 1: Pichit Wandee
Author 2: Zakon Bussabong
Author 3: Seksit Duangkum

Keywords: Application; QR–Code system; waste management; SDLC; community information

Download PDF

Paper 78: Empirical Study of a Spatial Analysis for Prone Road Traffic Accident Classification based on MCDM Method

Abstract: Spatial analysis techniques are widely used as an effective approach for prone road traffic accident classification. This paper will present the results of empirical behavioral testing on the spatial analysis for prone road traffic accident classification using the Multicriteria Decision Making (MCDM) method. The performance of MCDM is compared on arterial and collector road types processed with multicriteria parameters. MCDM was chosen because it can be used as a decision making based on an alternative selection with many criteria. Empirical tests of the MCDM method used include Weighted Sum Model (WSM), Weighted Product (WP), Simple Additive Weighting (SAW), Weighted Product Model (WPM), Multi-Attribute Utility Theory (MAUT), Technique for Others Reference by Similarity to Ideal Solution (TOPSIS), and Analytical Hierarchy Process (AHP). The multicriteria parameter weight values are based on expert judgment and the Fuzzy-AHP method (EJ-AHP), which comprises volume-to-capacity ratio (VCR), international roughness index (IRI), vehicle type, horizontal alignment, vertical alignment, design speed, and shoulder. Then, the performance of the models was compared to determine the value of accuracy, precision, recall, and F1-score as decision-making on the prone road traffic accident classification using Multicriteria Evaluation Techniques (MCE). The empirical test results on arterial roads show that the SAW and TOPSIS methods have the same performance and are superior to other methods, with an accuracy value of 63%. However, the results on the collector road type show that the accuracy value of the AHP method outperforms other methods with an accuracy value of 70%.

Author 1: Anik Vega Vitianingsih
Author 2: Zahriah Othman
Author 3: Safiza Suhana Kamal Baharin
Author 4: Aji Suraji

Keywords: Spatial Analysis; GIS; prone road traffic accident; MCDM Model; WSM; WP; SAW; WPM; MAUT; TOPSIS; AHP

Download PDF

Paper 79: Application of the Fuzzy Delphi Method to Identify and Prioritize the Social-Health Family Disintegration Indicators in Yemen

Abstract: Constantly increasing political events and socially related changes have led governments worldwide to adopt strategies to reduce their negative effects on the cohesion of societies, which requires developing assessment frameworks that include realistic, measurable, and useful indicators for analyzing the family disintegration causes, taking into consideration the circumstances surrounding the countries and the development trends that they adopt. Therefore, this study aims to identify and prioritize indicators of a decision-making support framework for evaluation, ranking, and structural comparison of the family disintegration causes resulting from the child marriage phenomenon in Yemen. To achieve this, the Fuzzy Delphi Method was applied. Firstly, a set of related literature and theories were analyzed to extract the expected framework's suitable initial indicators. Then, with the participation of twenty-four local experts, the extracted factors were revised, and the most suitable factors were selected. As a result, one social factor out of nine social-health factors was excluded due to its inappropriateness, and a framework of eight indicators was built. Also, with a rating average of 0.727, it was consistently agreed that the indicator "Increasing divorce rates in marital cases that do not take place according to the common desire of the spouses" is the most important indicator. Also, with high consistent evaluation averages (0.652–0.658), all three health indicators were ranked in the second and third places, while the other four social indicators were ranked in the last three positions (fourth–sixth). Finally, the real applications of the proposed framework were recommended.

Author 1: Abed Saif Ahmed Alghawli
Author 2: Abdualmajed A. Al-khulaidi
Author 3: Adel A. Nasser
Author 4: Nesmah A. AL-Khulaidi
Author 5: Faisal A. Abass

Keywords: Family disintegration; child marriage; early marriage; Fuzzy Delphi Method; multi-criteria decision making; Yemen

Download PDF

Paper 80: A Penetration Testing on Malaysia Popular e-Wallets and m-Banking Apps

Abstract: e-Wallets and m-banking apps became more and more popular in the developed world, approaching a point of tipping. This can be due to the global use of big and small merchants of paying equipment and the ubiquity of e-wallet and m-banking apps adoption. Many consumers are using e-wallets and m-banking apps that can be an effective cybercrime option. e-Wallets and m-banking apps allow financial transactions via smartphones that give cybercriminals a lucrative opportunity. Mobile technology has become increasingly mainstream and continually strengthening, with the focus on mobile apps protection and forensic analysis developing. In this paper, the security aspect of five popular e-wallets in Malaysia were analyzed. This paper also provides a security analysis of another five leading m-banking apps. The security analysis is based on a security principle that is recommended by Open Web Application Security (OWASP) under Mobile Security Testing Guide (MSTG) and Mobile Security Threats (MST). The static analysis has been done by using three mobile application-testing tools. This study included a variation of vulnerability scanning, code review and, most significantly, penetration testing. Each app complied with the security requirement, but their security features and characteristics, such as encryption, security protocols, and app services, are different to each other. This study was carried out using a DELL computer with Intel Core i7 CPU, 3.40 GHz CPU, 6 GB RAM. Finally, the results revealed the secure e-wallet and m-banking apps among the selected apps.

Author 1: Md Arif Hassan
Author 2: Zarina Shukur
Author 3: Masnizah Mohd

Keywords: Electronic payments; e-wallet; m-banking; android; static analysis; security analysis

Download PDF

Paper 81: Demand Forecasting Model using Deep Learning Methods for Supply Chain Management 4.0

Abstract: In the context of Supply Chain Management 4.0, costumers’ demand forecasting has a crucial role within an industry in order to maintain the balance between the demand and supply, thus improve the decision making. Throughout the Supply Chain (SC), a large amount of data is generated. Artificial Intelligence (AI) can consume this data in order to allow each actor in the SC to gain in performance but also to better know and understand the customer. This study is carried out in order to improve the performance of the demand forecasting system of the SC based on Deep Learning methods, including Auto-Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) using historical transaction record of a company. The experimental results enable to select the most efficient method that could provide better accuracy than the tested methods.

Author 1: Loubna Terrada
Author 2: Mohamed El Khaili
Author 3: Hassan Ouajji

Keywords: Supply chain management 4.0; demand forecasting; decision making; artificial intelligence; deep learning; Auto-Regressive Integrated Moving Average (ARIMA); Long Short-Term Memory (LSTM)

Download PDF

Paper 82: Improved Deep Learning Performance for Real-Time Traffic Sign Detection and Recognition Applicable to Intelligent Transportation Systems

Abstract: In this paper, we improve the performance of Deep Learning (DL) by creating a robust and efficient Convolutional Neural Network (CNN) model. This CNN model will be subjected to detecting and recognizing traffic signs in real-time. We apply several techniques; the first is pre-processing, which includes conversion of color space RGB, then equalization and normalization histogram of the image dataset according to Computer Vision (CV) tools. The second is devoted to Artificial Intelligence (AI), which needs the right choice of a neural layer such convolution layer, or dropout layer, with powerful optimizer as Adam and activation functions such as ReLU and SoftMax. Also, we use the technique of augmentation dataset which characterizes by the function of batch size for each epoch. The results obtained is very satisfactory, the prediction at the average is equal to 98%, which encourages this approach to the integration in Intelligent Transportation Systems (ITS) in the automotive sector.

Author 1: Anass BARODI
Author 2: Abderrahim Bajit
Author 3: Abdelkarim ZEMMOURI
Author 4: Mohammed Benbrahim
Author 5: Ahmed Tamtaoui

Keywords: Deep learning; convolutional neural network; computer vision; artificial intelligence; traffic sign detection; traffic sign recognition; intelligent transportation systems

Download PDF

Paper 83: Research on Students' Course Selection Preference based on Collaborative Filtering Algorithm

Abstract: Due to the events caused by the COVID-19 pandemic, the education industry is no longer limited to offline, and online classroom education is widely used. The rapid development of online education provides users with more abundant educational course resources and flexible learning methods. Various online education platforms are also constantly improving their service models to give users a better learning experience. However, at present, there are few personalized information recommendation services in student course selection. Students receive the same course selection information and cannot be "tailored" according to their specific preferences. This paper focuses on the integration of collaborative filtering technology into a college course selection system to construct a rating matrix based on students' ratings of the courses they take through correlation between courses and correlation between students. Based on the collaborative filtering algorithm, a predictive rating matrix is generated to produce a recommendation list to achieve intelligent recommendation of suitable courses for students. The experimental results show that, based on the traditional collaborative filtering recommendation technique, the improved collaborative filtering algorithm based on both item and user weighting is used to achieve course recommendation with higher recommendation accuracy. The application of the improved collaborative filtering technique in the course selection recommendation system of colleges and universities is very good at recommending courses for students intelligently, and the recommended courses for students have good rationality and accuracy, and achieve more intelligent course selection for students, which has great practicality and practical significance.

Author 1: Mustafa Man
Author 2: Jianhui Xu
Author 3: Ily Amalina Ahmad Sabri
Author 4: Jiaxin Li

Keywords: Collaborative filtering; course selection system; recommendation; scoring matrix; weighting

Download PDF

Paper 84: Intelligent Interfaces for Assisting Blind People using Object Recognition Methods

Abstract: Object recognition method is a computer vision technique for identifying objects in images. The main purpose of this system build is to put an end to blindness by constructing automated hardware with Raspberry Pi that enables a visually impaired person to detect objects or persons in front of them instantly, and inform what is in front of them through audio. Raspberry Pi receives data from a camera then processes it. In addition, the blind will listen to a voice narration via an audio receiver. This paper’s key objective is to provide the blind with cost-effective smart assistance to explore and sense the world independently. The second objective is to provide a convenient portable device allows users to recognise objects without touch, having the system determine the object in front of them. The camera module attached in Raspberry Pi will capture image and the processor will then process it. Subsequently, the processed image sends data to the audio receiver narrating the detected object(s). This system will be very useful for a blind person to explore the world by listening to the voice narration. The generated voice narration after processing the image will help the blind to visualise objects in front of them.

Author 1: Jamil Abedalrahim Jamil Alsayaydeh
Author 2: Irianto
Author 3: Maslan Zainon
Author 4: Hasvinii Baskaran
Author 5: Safarudin Gazali Herawan

Keywords: Object recognition method; computer vision; blind people; image processing; Raspberry Pi; Pi camera; smart assistance; portable device; voice narration; visualise

Download PDF

Paper 85: Application of Random Forest Regression with Hyper-parameters Tuning to Estimate Reference Evapotranspiration

Abstract: Estimation of reference evapotranspiration (ETo) is a complex and non-linear problem that is used for the quantification of crop water requirements. In this study, random forest regression based models are developed to predict the ETo of Bhopal city, Madhya Pradesh, India. The meteorological data is collected from IMD, Pune for the periods of the years 2015-16. Based on the correlation among meteorological variables with observed ETo, four different random forest regression models are created. Moreover, the effects of three important hyper-parameters of random forest, such as the number of trees in the forest, depth of the tree, and the number of samples at a leaf node are evaluated to estimate ETo using the proposed models. These hyper-parameters are applied in three different ways to the models such as one hyper-parameter parameter at a time, and combination of hyper-parameters using grid search, and random search approaches. In this study, the result indicates that a random forest regression based model with maximal meteorological input variables exhibits great predictive power in small execution time than minimal input variables. This study also reveals that the model that optimises the hyper-parameters using a grid search approach shows equal predictive power but takes much execution time whereas random search based optimization exhibits the same level of predictive capability in less computation time. Stakeholders can utilize random forest regression models with sufficient meteorological data to estimate crop water requirements, and enhance the food production.

Author 1: Satendra Kumar Jain
Author 2: Anil Kumar Gupta

Keywords: Reference evapotranspiration; random forest regression; hyper-parameters; grid search; random search optimization

Download PDF

Paper 86: Abnormal Event Detection using Additive Summarization Model for Intelligent Transportation Systems

Abstract: Video surveillance is used for capturing the abnormal events on roadsides that are caused due to improper driving, accidents, and hindrances resulting in transportation lags and life-critical issues. It is essential to highlight the accident keyframes in videos to achieve intelligent video surveillance. Video summarization plays a vital role in summarizing the keyframe for an abnormal event from the stacked video surveillance input. The observed video is converted into frames and analyzed for providing an accurate summarization for accident analysis forecast and guiding the users in avoiding such events. The main issues in summarization arise from the inconsistency between the spatiotemporal redundancies and the classification of sequence verification in video surveillance. This article introduces an Additive Event Summarization Method (AESM) for projecting classified events through a gated recurrent unit learning paradigm. In this process, the gates are assigned for unclassified and active frames for sequence verification. Based on the sequence, the abnormality is classified and summarized with higher accuracy than the state of art techniques. This proposed method relies on heterogeneous features for classifying events with better structural indices. The proposed method’s performance is analyzed using the metrics accuracy, false rate, analysis time, SSIM, and F1-Score.

Author 1: G. Balamurugan
Author 2: J. Jayabharathy

Keywords: Event detection; gated recurrent unit; summarization; intelligent transportation system

Download PDF

Paper 87: Relational Deep Learning Detection with Multi-Sequence Representation for Insider Threats

Abstract: Insider threats are typically more challenging to be detected since security protocols struggle to recognize the anomaly behavior of privileged users in the network. Intuitively, an insider threat detection model depends on analyzing the audit data, representing trusted users’ activity streams, on recognizing malicious behaviors. However, the audit data is high dimensional data in that it presents n dependent streams of activities where it establishes a complex feature extraction. In this context, the dependent streams represent user activities where each activity is represented by an ordered set of real variables that pertain to a specific occurrence, such as log-in records. As a result, multiple actions can be represented simultaneously, with one or more values being recorded at each timestamp. Moreover, the relations between dependent streams are typically neglected while detecting the anomaly behavior. Ideally, relation learning is commonly considered to recognize occurrence patterns in streaming data. Thus, the latent relations are thought to have insight for the accurate detection of anomaly behavior concerning insider threats. This study introduces a novel model to detect insider threats by representing audit data as multivariate time series to explicitly learn the existing inter-relations between activity streams using a Recurrent Neural Network (RNN). The model considers learning the latent relationships to effectively extract features for modeling the behavior profile where anomaly behavior can be detected accurately. The evaluation, using the CERT dataset has shown that the proposed model outperforms the comparator approaches to insider threats detection with AUC of 0.99.

Author 1: Abdullah Alshehri

Keywords: Insider threats; machine learning; recurrent neural network; user behavior analytic

Download PDF

Paper 88: An Improved Label Initialization based Label Propagation Method for Detecting Graph Clusters in Complex Networks

Abstract: Community structure is one of the fundamental characteristics of complex networks. Detection of community structure can provide insight into the structural and functional or-ganization that helps to understand various dynamical processes such as epidemics and information spreading. Label propagation algorithm (LPA) is a well-known method for community struc-ture identification due to linear time complexity. However, the communities extracted by the LPA is unstable since it produces different combinations of communities at each run on the same network. In this paper, a novel label initialization method for label propagation algorithm (ILI-LPA) is proposed to detect stable and accurate community structures. The proposed ILI-LPA focuses on more accurate label initialization rather than assigning unique labels thereby reduce the effect of randomness in LPA. The experiments on several real-world and synthetic networks show that the ILI-LPA improves the quality and stability of communities compared to existing algorithms. The results also demonstrate that appropriate label initialization can significantly improve the performance of label propagation algorithms, and the stability has been improved up to 50-78% relative to the standard LPA.

Author 1: Jyothimon Chandran
Author 2: V Madhu Viswanatham

Keywords: Social networks; community detection; graph clus-tering; edge clustering coefficient; label initialization; triangle count

Download PDF

Paper 89: Natural Language Processing for the Analysis Sentiment using a LSTM Model

Abstract: Over the past decade, social networks have revo-lutionised the communication between organisations and their customers, and the data provided by customers on social net-work platforms is having an increasingly important impact on how organisations collect and analyse this data to make better decisions. We have prepared a new dataset that will allow the scientific community to estimate and evaluate new models using nearly the same conditions. Moreover, this dataset represents a recent and interesting sample for the proposed machine learning models to correctly identify the topics or points on which the company should focus to improve customer satisfaction and better meet their needs. Therefore, we have proposed a recurrent neural network (RNN) with Long short-term memory (LSTM) that we will run in the cloud to predict sentiment analysis. The objective is also to define systems capable of extracting subjective information from natural language texts, such as feelings and opinions, with the aim of creating structured knowledge that can be used by a decision support system or a decision maker for better customer management. The proposed neural network has been trained on the proposed dataset which contains 50 000 customer observations. The performance of the proposed architecture is very important as the success rate is 96%.

Author 1: Achraf BERRAJAA

Keywords: Artificial intelligence; NLP; RNN; LSTM; customer relationship management

Download PDF

Paper 90: Alarm System using Image Processing to Prevent a Patient with Nasogastric Tube Feeding from Removing Tube

Abstract: A removal nasogastric (NG) tube of a patient is a critical problem especially the patients resist swallowing. To solve this problem, the conventional approach using a personal caretaker is a time-consuming and intense focus on the patient’s hands. However, visual technology can decrease the intense focus of a personal caretaker by using image processing to evaluate the patient’s gesture and warn the personal caretaker when the patient acts in a risky pose. This work illustrates the feasible solution to prevent a patient with nasogastric tube feeding on removing tube by applied the face detection using Haar and Fiducial markers which consist of color marker and ArUco marker. An image processing can evaluate the patient’s gesture and warn the personal caretaker when the subject acts the risky pose. A Raspberry Pi 3 Model B and a Camera module with Python and Open CV package are applied to detect and evaluate the warning gestures with 648 measurements. Six detection methods to evaluate and warn when the patient on bed tries to remove a nasal feeding tube were performed and the results were analyzed. The results show that the detection method using ArUco marker is found to be a good candidate for the alarm system preventing nasogastric (NG) tube removal of a patient.

Author 1: Amonrat Prasitsupparote
Author 2: Pakorn Pasitsuparoad

Keywords: NG tube; image processing; fiducial markers; face detection; Aruco

Download PDF

Paper 91: Multileveled ALPR using Block-Binary-Pixel-Sum Descriptor and Linear SVC

Abstract: Automatic license plate recognition (ALPR) is es-sential component of security and surveillance. ALPR mainly aims to detect and prevent the crime and fraud activities; it also plays an important role in traffic monitoring. An algorithm is proposed for recognizing license plate candidates. The proposed work aimed to recognize the license plate of a car. Proposed work is designed in multilevel for more accurate License Plate (LP) recognition, At level 1 algorithm produced 93.5% accuracy and in level 3 algorithm gives 96% accuracy. For training and testing purpose, LP images were used from Medialab cars dataset, kaggle car dataset and goggle map images. These images in the dataset is formulated at various angles and illumination. Proposed algorithm for LP recognition is done by using the Block Binary Pixel descriptors (BBPS) and Linear Support Vector Classification (SVC). Proposed algorithm is novel and produces higher accuracy in minimal processing time of an average 0.42 milliseconds with 96% accuracy when compared with state-of-the art methods.

Author 1: B. Lavanya
Author 2: G. Lalitha

Keywords: BBPS – Block Binary Pixel Sum; ALPR - Automatic License Plate Recognition; ROI - Region of Interest; SVC - Support Vector Classification; LP - License Plate

Download PDF

Paper 92: Genetic Algorithms Applied to the Searching of the Optimal Path in Image-based Robotic Navigation Environments

Abstract: This paper describes an optimal-path finding strat-egy based on Genetic Algorithms, applied to mobile robots in static navigation environments. This strategy starts from an image or plan of the environment and is supported by some different image processing algorithms, mainly the image skeletonization. Three different strategies were tested, changing the domain of the optimization target function for the Genetic Algorithm, the first domain was all the points of the environment image less the obstacles or walls, the second domain was similar but using an image with the obstacles dilated, and the final domain was only the points of the skeleton image. The last tested domain is from 99.4% to 99.6% smaller than the others, that implied reductions from 95% to 96% in the overall execution time of the strategy. Likewise, three skeletonization algorithms were tested in order to use the one with less execution time in this proposal. Finally, the proposed path planning strategy was tested on the same environment changing the initial and final points giving as result a valid and optimized path for the mobile robot in all the tested cases, and an overall average optimization time less than 2 minutes. This last, validates this proposal for robotic navigation applications with static obstacles.

Author 1: Fernando Mart´inez Santa
Author 2: Fredy H. Mart´inez Sarmiento
Author 3: Holman Montiel Ariza

Keywords: Genetic algorithms; optimal path; optimization; robotic environment; mobile robots; image skeletonization

Download PDF

Paper 93: Anomaly Detection using Network Metadata

Abstract: The proliferation of numerous network function today gave rise to the importance of network traffic classification against various cyber-attacks. Automatic training with a huge number of representative data necessitates the creation of a model for an efficient classifier. As a result, automatic categorization requires using training techniques capable of assigning classes to data objects based on the activities supplied to learn classes. Predefined classes allow for the detection of new items. However, the analysis and categorization of data activity in intrusion detection systems are vulnerable to a wide range of threats. Thus, New methods of analysis must be developed in order to establish an appropriate approach for monitoring circulating traffic in order to solve this problem. The major goal of this research is to develop and verify a heterogeneous traffic classifier that can classify the collected metadata of networks. In this study, a new model is proposed, which is based on machine learning technique, to increase the accuracy of prediction. Prior to the analysis stage, the gathered traffic is subjected to preprocessing. This paper aims to provide the mathematical validation of a novel machine learning classifier for heterogeneous traffic and anomaly detection.

Author 1: Khaled Mutmbak
Author 2: Sultan Alotaibi
Author 3: Khalid Alharbi
Author 4: Umar Albalawi
Author 5: Osama Younes

Keywords: Anomaly detection; network metadata; packet anal-ysis; intrusion detection system; machine learning; classification; heterogeneous traffic

Download PDF

Paper 94: Correcting Arabic Soft Spelling Mistakes using BiLSTM-based Machine Learning

Abstract: Soft spelling mistakes are a class of mistakes that is widespread among native Arabic speakers and foreign learners alike. Some of these mistakes are typographical in nature. They occur due to orthographic variations of some Arabic letters and the complex rules that dictate their correct usage. Many people forgo these rules, and given the identical phonetic sounds, they often confuse such letters. In this paper, we investigate how to use machine learning to correct such mistakes given that there are no sufficient datasets to train the correction models. Soft errors detection and correction is an active field in Arabic natural language processing. We generate training datasets using proposed transformed input approach and stochastic error injec-tion approach. These approaches are applied to two acclaimed datasets that represent Classical Arabic and Modern Standard Arabic. We treat the problem as character-level, one-to-one sequence transcription problem. This one-to-one transcription of mistakes that include omissions and deletions is possible with adopted simple transformations. This approach permits using bidirectional long short-term memory (BiLSTM) models that are more effective to train compared to other alternatives such as encoder-decoder models. Based on investigating multiple alternatives, we recommend a configuration that has two BiLSTM layers, and is trained using the stochastic error injection approach with error injection rate of 40%. The best model corrects 96.4%of the injected errors and achieves a low character error rate of 1.28% on a real test set of soft spelling mistakes.

Author 1: Gheith Abandah
Author 2: Ashraf Suyyagh
Author 3: Mohammed Z. Khedher

Keywords: Arabic text; natural language processing; spelling mistakes; recurrent neural networks; bidirectional long short-term memory

Download PDF

Paper 95: Prediction of Presence of Brain Tumor Utilizing Some State-of-the-Art Machine Learning Approaches

Abstract: A brain tumor is a kind of abnormal development caused by unregularized cell reproduction and it is increasing day-by-day. The Magnetic Resonance Imaging (MRI) tools are the most often used diagnostic tool for brain tumor detection. However, ample amount of information contained in MRI makes the detection and analysis process tedious and time consuming. The ability to accurately identify the exact size and proper location of a brain tumor is a tough task for radiologists. Medical image processing is an interdisciplinary discipline in which image processing is a tough research. Image segmentation is the prime requirement in image processing as it separates dubious regions from biomedical images thereby enhancing the treatment reliability. In this regard, our article reviews eight existing binary classifiers to compare their results for designing an automated Computer Aided Diagnosis (CAD) system. The proposed classification models can analyze T1-weighted brain MRI images to reach at a conclusion. The classification accuracy advocates the quality of our work.

Author 1: Mitrabinda Khuntia
Author 2: Prabhat Kumar Sahu
Author 3: Swagatika Devi

Keywords: Brain tumor classification; MRI; SVM; decision tree; random forest; CAD

Download PDF

Paper 96: Mining Hidden Partitions of Voice Utterances using Fuzzy Clustering for Generalized Voice Spoofing Countermeasures

Abstract: The high level of usability achieved by voice biomet-rics compared to other biometric authentication modalities has promoted the widespread use of automatic speaker verification (ASV) systems as authentication tools for several services in various domains. Despite their satisfactory performance, ASV systems are vulnerable to malicious voice spoofing attacks. Hence, voice spoofing countermeasures have emerged as essential solutions to stop such harmful attacks and protect ASV systems as well as users’ confidentiality. Typically, these countermeasures classify utterances into genuine and spoofing categories. In this research, we propose two voice spoofing countermeasures that mainly aim to improve the generalization of supervised learning models. This goal is achieved through the adaptive handling of the high variance of both utterance classes, i.e., genuine and spoofing classes. The proposed spoofing countermeasure addresses the poor generalization problem by identifying the hidden structure of each utterance category prior to the classification task. Specif-ically, fuzzy clustering algorithms were deployed to mine the hidden partitions of utterance classes. The conducted experiments showed that the proposed approach outperforms the state-of-the-art approaches in the ASVspoof 2017 dataset, with a testing EER equal to 1.07%.

Author 1: Sarah Mohammed Altuwayjiri
Author 2: Ouiem Bchir
Author 3: Mohamed Maher Ben Ismail

Keywords: Voice spoofing; spoofing countermeasure; classifi-cation; clustering

Download PDF

Paper 97: PhishRepo: A Seamless Collection of Phishing Data to Fill a Research Gap in the Phishing Domain

Abstract: Machine learning-based anti-phishing solutions face various challenges in collecting diverse multi-modal phishing data. As a result, most previous works have trained with little or no multi-modal data, which opens several drawbacks. Therefore, this study aims to develop a phishing data repository to meet the diverse data needs of the anti-phishing domain. As a result, a gap-filling solution named PhishRepo was proposed as an online data repository that collects, verifies, disseminates, and archives phishing data. It includes innovative design aspects such as automated submission, deduplication filtering, automated verification, crowdsourcing-based human interaction, an objection reporting window, and target attack prevention techniques. Moreover, the deduplication filter, used for the first time in phishing data collection, significantly impacted the collection process. It eliminated the duplicate data, which causes one of the most common machine learning errors known as data leakage. In addition, PhishRepo enables researchers to apply modern machine learning techniques effectively and supports them by eliminating phishing data hassle. Therefore, more thoughtful use of PhishRepo will lead to effective anti-phishing solutions in the future, minimising the social engineering crime called phishing.

Author 1: Subhash Ariyadasa
Author 2: Shantha Fernando
Author 3: Subha Fernando

Keywords: Cyberattack; crowdsourcing; internet security; phishing; machine learning; multi-modal data

Download PDF

Paper 98: A Novel Code Completion Strategy

Abstract: Programmers rely on a multitude of techniques to speed up the development process. Among these techniques is code completion, a productivity improvement technique widely used by developers to explore APIs and automatically complete a word being typed by providing a progressively refined list of candidate words (or recommendations). Still called auto-completion, it reduces incorrect calls to APIs. Several techniques have been developed to obtain the list of candidates. Some methods use the history of the code, others neural networks or artificial intelligence; some exploit the program’s structure through AST. Often the recommendation list is long, and finding suitable candidates comes at a cost. In this work, we propose a strategy that improves the accuracy of recommendation list offered by code completion. We present a sorting approach based on the popularity and importance of the elements (suggestions) of the list by analyzing the usage data of classes, methods, and variables of projects in the same development environment. We implemented our sorting strategy in Pharo (IDE and language), an immersive modern programming environment to show its applicability. The empirical evaluation results of this strategy show that our approach improves the quality of the suggestions.

Author 1: Hayatou Oumarou
Author 2: Ousmanou Dahirou

Keywords: Integrated development environment; code comple-tion; API; code completion tool; pharo

Download PDF

Paper 99: Revisiting Polyglot Persistence: From Principles to Practice

Abstract: To cope with the rapid advancements in information technologies, many database systems have been developed in the last decade to satisfy various data storage requirements, such as NoSQL databases. In many cases, using a single database system cannot be an option because of the limitations posed on the functionalities of the software application. Therefore, applications may use multiple distributed storage databases that complement each other to satisfy the conflicting requirements. Such applications that are called polyglot persistent applications. However, the practical implementation of polyglot persistence and its complexities have not been studied enough. In this paper, the most recent studies related to polyglot persistence are reviewed. Database systems are classified based on their data storage model, and their use cases are discussed. The principles of polyglot persistence and its challenges are expounded. The implementation architectures of polyglot persistence applications are categorized into Application-coordinated Polyglot Persistence, Service-oriented Polyglot Persistence, Polyglot- Persistence-as-a-Service, and Multi-models Databases. An analysis of the issues related to each architecture is presented. In light of the study findings, a practical polyglot persistence implantation strategy is proposed. The outcomes of this work can help design future polyglot persistence applications and influence future research on how to resolve the complexity involved in polyglot persistence solutions.

Author 1: Omar Lajam
Author 2: Salahadin Mohammed

Keywords: Database system; database architecture; relational database; NoSQL; distributed storage; multi-model database; review; classification

Download PDF

Paper 100: Computer Vision: The Effectiveness of Deep Learning for Emotion Detection in Marketing Campaigns

Abstract: As businesses move towards more customer-centric business models, marketing functions are becoming increasingly interested in gathering natural, unbiased feedback from cus-tomers. This has led to increased interest in computer vision studies into emotion recognition from facial features, for appli-cation in marketing contexts. This research study was conducted using the publicly-available Facial Emotion Recognition 2013 data-set, published on Kaggle. This article provides a comparative study of four deep learning algorithms for computer vision application in emotion recognition, namely, Convolution Neural Network (CNN), Multilayer Perceptron (MLP), Recurring Neural Network (RNN), Generative Adversarial Networks (GAN) and Long Short-Term Memory (LSTM) models. Comparisons be-tween these models were done quantitatively using the metrics of accuracy, precision, recall and f1-score; as well and qualitatively by determining goodness-of-fit and learning rate from accuracy and loss curves. The results of the study show that the CNN, GAN and MLP models surpassed the data, and the LSTM model failed to learn at all. Only the RNN adequately learnt from the data. The RNN was found to exhibit a low learning rate, and the computational intensiveness of training the model resulted in a premature termination of the training process. However, the model still achieved a test accuracy of up to 72%, the highest of all models studied, and it is possible that this could be increased through further training. The RNN also had the best F1-score (0.70), precision (0.73) and recall (0.73) of all models studied.

Author 1: Shaldon Wade Naidoo
Author 2: Nalindren Naicker
Author 3: Sulaiman Saleem Patel
Author 4: Prinavin Govender

Keywords: Computer vision; deep learning; emotion detection; generative adversarial networks; marketing campaigns component

Download PDF

Paper 101: Using Machine Learning Techniques to Predict Bugs in Classes: An Empirical Study

Abstract: Software bug prediction is an important step in the software development life cycle that aims to identify bug-prone software modules. Identification of such modules can reduce the overall cost and effort of the software testing phase. Many approaches have been introduced in the literature that have investigated the performance of machine learning techniques when used in software bug prediction activities. However, in most of these approaches, the empirical investigations were conducted using bug datasets that are small or have erroneous data leading to results with limited generality. Therefore, this study empirically investigates the performance of 8 commonly used machine learning techniques based on the Unified Bug Dataset which is a large and clean bug dataset that was published recently. A set of experiments are conducted to construct bug prediction models using the considered machine learning techniques. Each constructed model is evaluated using three performance metrics: accuracy, area under the curve, and F-measure. The results of the experiments show that logistic regression has better performance for bug prediction compared to other considered techniques.

Author 1: Musaad Alzahrani

Keywords: Software bugs; bug prediction; machine learning techniques; software metrics; unified bug dataset

Download PDF

Paper 102: Transformer-based Models for Arabic Online Handwriting Recognition

Abstract: Transformer neural networks have increasingly be-come the neural network design of choice, having recently been shown to outperform state-of-the-art end-to-end (E2E) recurrent neural networks (RNNs). Transformers utilize a self-attention mechanism to relate input frames and extract more expressive sequence representations. Transformers also provide parallelism computation and the ability to capture long dependencies in contexts over RNNs. This work introduces a transformer-based model for the online handwriting recognition (OnHWR) task. As the transformer follows encoder-decoder architecture, we investigated the self-attention encoder (SAE) with two different decoders: a self-attention decoder (SAD) and a connectionist temporal classification (CTC) decoder. The proposed models can recognize complete sentences without the need to integrate with external language modules. We tested our proposed mod-els against two Arabic online handwriting datasets: Online-KHATT and CHAW. On evaluation, SAE-SAD architecture per-formed better than SAE-CTC architecture. The SAE-SAD model achieved a 5% character error rate (CER) and an 18%word error rate (WER) against the CHAW dataset, and a 22% CER and a 56% WER against the Online-KHATT dataset. The SAE-SAD model showed significant improvements over existing models of the Arabic OnHWR.

Author 1: Fakhraddin Alwajih
Author 2: Eman Badr
Author 3: Sherif Abdou

Keywords: Selft attention; Transformer; deep Learning; con-nectionist temporal classification; convolutional neural networks; Arabic online handwriting recognition

Download PDF

Paper 103: Detection of Android Malware App through Feature Extraction and Classification of Android Image

Abstract: Android apps have security risks due to rapid development in android devices. In the Android ecosystem, there are many challenges to detecting Android malware. Traditional techniques such as static, dynamic, and hybrid approach, most of the existing approaches require a high rate of human intervention to detect Android malware. Most of the current techniques have the most significant security challenges to detect Android malware, the inspection of Android Package Kit(APK) file structures, increased complexity, high processing power, more storage space, and much human intervention. This paper proposed Machine Learning(ML)based algorithms to detect Android malware apps through feature extraction and classification of grayscale images. In our proposed approach, convert most of the files of APK such multiDex, resources, certificate, and manifest files transform into a grayscale image, using the image algorithm to extract the local feature of the image. In the paper used different ML models to classify the local features with the help of multiple images of malware families. This approach deals with the obfuscation attack.it can hide in any files of APK. The proposed approach enhanced accuracy reached up to 96.86%, and computation time did not increase more than the existing techniques. The quality of that proposed worked; it has a high classification accuracy and less complexity validation loss.

Author 1: Mohd Abdul Rahim Khan
Author 2: Nand Kumar
Author 3: R C Tripathi

Keywords: Android malware; obfuscation attack machine learning; android application package (APK); android malware app; grayscale images

Download PDF

Paper 104: A Hybrid Heuristic for a Two-Agent Multi-Skill Resource-Constrained Scheduling Problem

Abstract: This paper addresses an industrial case of the two-agent scheduling problem with a global objective function. Each agent manages one or several projects and competes with another agent for the use of common multi-skilled employees. There is a pool of employees, each of which can perform a set of skills with heterogeneous performance levels. The objectives of the two agents are both to minimize the total weighted tardiness of its tasks. Furthermore, We assume that some constraints (soft constraints) can be violated when there is no feasible schedule for the problem. Thus, the global objective function minimizes the constraint violations by reducing the undesirable deviations in the soft constraints from their respective goals. The overall objective is to find a schedule that minimizes both agents objective functions (local objectives) and the global objective function. We provide a mixed-integer goal programming (MIGP) formulation for the problem. In addition, we present a hybrid algorithm combining an exact procedure, a greedy heuristic, and a genetic algorithm to find an approximate Pareto solution set. We compare the performance of the hybrid algorithm against the corresponding MIGP formulation with simulated instances derived from real-world instances.

Author 1: Meya Haroune
Author 2: Cheikh Dhib
Author 3: Emmanuel Neron
Author 4: Ameur Soukhal
Author 5: Hafed Mohamed Babou
Author 6: Farouk Mohamedade Nanne

Keywords: Two agents; multi-skilled employees; multi-project scheduling; hybrid genetic algorithm; MIGP

Download PDF

Paper 105: Transformer based Model for Coherence Evaluation of Scientific Abstracts: Second Fine-tuned BERT

Abstract: Coherence evaluation is a problem related to the area of natural language processing whose complexity lies mainly in the analysis of the semantics and context of the words in the text. Fortunately, the Bidirectional Encoder Representation from Transformers (BERT) architecture can capture the aforemen-tioned variables and represent them as embeddings to perform Fine-tunings. The present study proposes a Second Fine-Tuned model based on BERT to detect inconsistent sentences (coherence evaluation) in scientific abstracts written in English/Spanish. For this purpose, 2 formal methods for the generation of inconsistent abstracts have been proposed: Random Manipulation (RM) and K-means Random Manipulation (KRM). Six experiments were performed; showing that performing Second Fine-Tuned improves the detection of inconsistent sentences with an accuracy of 71%. This happens even if the new retraining data are of different language or different domain. It was also shown that using several methods for generating inconsistent abstracts and mixing them when performing Second Fine-Tuned does not provide better results than using a single technique.

Author 1: Anyelo-Carlos Gutierrez-Choque
Author 2: Vivian Medina-Mamani
Author 3: Eveling Castro-Gutierrez
Author 4: Rosa Nunez-Pacheco
Author 5: Ignacio Aguaded

Keywords: Coherence evaluation; inconsistent sentences detec-tion; BERT; second fine-tuned

Download PDF

Paper 106: Modeling and Simulation of Adaptive Traffic Control System for Multi-Intersection Management using Cellular Automaton and Queuing System

Abstract: During last years, urban traffic has become one of the most studied research topics. This is mainly due to the enlargement of the cities and the growing number of vehicles traveling in this road network. One of the most sensitive problems is to verify if the intersections are congestion-free. Another related problem is the automatic reconfiguration of the network without building new roads to alleviate congestions. These problems require an accurate model to determine the steady state of the traffic. The present article proposes an adaptive traffic light system based on the BCMP network queuing and cellular automata. The aim of this work is to predict the best red and green time span by combining three important factors: The queue length, the evacuation time and the capacity of the destination roads. This approach can maximize the number of vehicles passing intersection and at the same time can minimize the average waiting time of vehicles as a result reducing the congestion and keep the fluency in intersections. To validate our results, we compared our model with a fixed model to explain the strengths of our proposed algorithm.

Author 1: Salma EL BAKKAL
Author 2: Abdallah LAKHOUILI
Author 3: El Hassan ESSOUFI

Keywords: Traffic light systems; cellular automaton; BCMP; queuing systems; traffic congestion; waiting time; adaptive systems

Download PDF

Paper 107: Non-Parametric Stochastic Autoencoder Model for Anomaly Detection

Abstract: Anomaly detection is a widely studied field in computer science with applications ranging from intrusion de-tection, fraud detection, medical diagnosis and quality assurance in manufacturing. The underlying premise is that an anomaly is an observation that does not conform to what is considered to be normal. This study addresses two major problems in the field. First, anomalies are defined in a local context, that is, being able to give quantitative measures as to how anomalies are categorized within its own problem domain and cannot be generalized to other domains. Commonly, anomalies are mea-sured according to statistical probabilities relative to the entire dataset with several assumptions such as type of distribution and volume. Second, the performance of a model is dependent on the problem itself. As a machine learning problem, each model has to have parameters optimized to achieve acceptable performance specifically thresholds that are either defined by domain experts of manually adjusted. This study attempts to address these problems by providing a contextual approach to measuring anomaly detection datasets themselves through a quantitative approach called categorical measures that provides constraints to the problem of anomaly detection and proposes a robust model based on autoencoder neural networks whose parameters are dynamically adjusted in order to avoid parameter tweaking on the inferencing stage. Empirically, the study has conducted a relatively exhaustive experiment against existing and state of the art anomaly detection models in a semi-supervised learning approach where the assumption is that only normal data is available to provide insight as to how well the model performs under certain quantifiable anomaly detection scenarios.

Author 1: Raphael Alampay
Author 2: Patricia Angela Abu

Keywords: Neural networks; autoencoders; machine learning; anomaly detection; semi-supervised learning

Download PDF

Paper 108: COVID-19 Cases Detection from Chest X-Ray Images using CNN based Deep Learning Model

Abstract: COVID-19 has recently manifested as one of the most serious life-threatening infections and is still circulating globally. COVID-19 can be contained to a considerable extent if a patient can know their COVID-19 infection at a possible earlier time, and they can be isolated from other individuals. Recently, researchers have explored AI (Artificial Intelligence) based technologies like deep learning and machine learning strategies to identify COVID-19 infection. Individuals can detect COVID-19 disease using their phones or computers, dispensing with the need for clinical specimens or visits to a diagnostic center. This can significantly reduce the risk of spreading COVID-19 farther from a probably infected patient. Motivated by the above, we propose a deep-learning model using CNN (Convolutional Neural Networks) to autonomously diagnose COVID-19 disease from CXR (Chest X-ray) images. The dataset used to train our model includes 10293 X-ray images, with 875 X-ray images from COVID-19 cases. The dataset contains three different classes of the tuple: COVID-19, pneumonia, and normal cases. The empirical outcomes show that the proposed model achieved 97%specificity, 96.3% accuracy, 96% precision, 96% sensitivity, and 96% F1-score, respectively, which are better than the available works, despite using a CNN with fewer layers than those.

Author 1: Md Amirul Islam
Author 2: Giovanni Stea
Author 3: Sultan Mahmud
Author 4: Kh. Mustafizur Rahman

Keywords: COVID-19; CNN; deep learning; machine learning; chest X-ray

Download PDF

Paper 109: BERT-based Approach to Arabic Hate Speech and Offensive Language Detection in Twitter: Exploiting Emojis and Sentiment Analysis

Abstract: The user-generated content on the internet including that on social media may contain offensive language and hate speech which negatively affect the mental health of the whole internet society and may lead to hate crimes. Intelligent models for automatic detection of offensive language and hate speech have attracted significant attention recently. In this paper, we propose an automatic method for detecting offensive language and fine-grained hate speech from Arabic tweets. We compare between BERT and two conventional machine learning techniques (SVM, logistic regression). We also investigate the use of sentiment analysis and emojis descriptions as appending features along with the textual content of the tweets. The experiments shows that BERT-based model gives the best results, surpassing the best benchmark systems in the literature, on all three tasks:(a) offensive language detection with 84.3% F1-score, (b) hate speech detection with 81.8% F1-score, and (c) fine-grained hatespeech recognition (e.g., race, religion, social class, etc.) with 45.1% F1-score. The use of sentiment analysis slightly improves the performance of the models when detecting offensive language and hate speech but has no positive effect on the performance of the models when recognising the type of the hate speech. The use of textual emoji description as features can improve or deteriorate the performance of the models depending on the size of the examples per class and whether the emojis are considered among distinctive features between classes or not.

Author 1: Maha Jarallah Althobaiti

Keywords: Deep learning; hate speech detection; offensive language detection; sentiment analysis; transformer-based model; BERT; emoji

Download PDF

Paper 110: A Survey of Sink Mobility Models to Avoid the Energy-Hole Problem in Wireless Sensor Networks

Abstract: Wireless Sensor Networks (WSN) refer to networks where the sensors are deployed in an environment to sense and select data. WSN sensor nodes have limited power and cannot be recharged easily. Consequently, the faster sensor nodes to deplete their energy budget are those close to the sink as they have to relay all data emanating from any sensor in the network. Thus, a hole of energy around the sink is created as the sink coverage nodes have drained their initial energy thus leading to sink unreachability. The WSN lifetime maximization problem has always been a hot research topic. Collecting data in WSN using a mobile sink is an efficient approach for achieving WSN longevity and preventing the energy hole problem. However, finding the optimal trajectory along with its appropriate flow routing is a challenging problem since many constraints should be considered. This paper discusses and compares several existing WSN-lifetime-maximization using sink mobility solutions. These solutions are mainly classified into two types: Linear Programming and Artificial Intelligence-based solutions. The state-of-the-art solutions are compared in terms of network topology, sojourn points and duration, buffer size, and overhearing. Finally, a discussion of the WSN lifetime maximization constraints is provided to define a promising sink mobility model.

Author 1: Ghada Al-Mamari
Author 2: Fatma Bouabdallah
Author 3: Asma Cherif

Keywords: Energy hole problem; mobile sink; wireless sensor networks; linear programming; artificial intelligence

Download PDF

Paper 111: End-to-End Car Make and Model Classification using Compound Scaling and Transfer Learning

Abstract: Recently, Morocco has started to invest in IoT systems to transform our cities into smart cities that will promote economic growth and make life easier for citizens. One of the most vital addition is intelligent transportation systems which represent the foundation of a smart city. However, the problem often faced in such systems is the recognition of entities, in our case, car and model makes. This paper proposes an approach that identifies makes and models for cars using transfer learning and a workflow that first enhances image quality and quantity by data augmentation and then feeds the newly generated data into a deep learning model with a scaling feature–that is, compound scaling. In addition, we developed a web interface using the FLASK API to make real-time predictions. The results obtained were 80%accuracy, fine-tuning it to an accuracy rate of 90% on unseen data. Our framework is trained on the commonly used Stanford Cars dataset.

Author 1: Omar BOURJA
Author 2: Abdelilah MAACH
Author 3: Zineb ZANNOUTI
Author 4: Hatim DERROUZ
Author 5: Hamza MEKHZOUM
Author 6: Hamd AIT ABDELALI
Author 7: Rachid OULAD HAJ THAMI
Author 8: Francois BOURZEIX

Keywords: Vehicles classification; deep learning; compound scaling; transfer learning; IoT

Download PDF

Paper 112: Cache Complexity of Cache-Oblivious Approaches: A Review and Extension

Abstract: The latest direction in cache-aware/cache-efficient algorithms is to use cache-oblivious algorithms based on the cache-oblivious model, which is an improvement of the external-memory model. The cache-oblivious model utilizes memory hierarchies without knowing memories’ parameters in advance since algorithms of this model are automatically tuned according to the actual memory parameters. As a result, cache-oblivious algorithms are particularly applied to multi-level caches with changing parameters and to environments in which the amount of available memory for an algorithm can fluctuate. This paper shows the state of the art in cache-oblivious algorithms and data structures; each with its complexity concerning cache misses, which is called cache complexity. Additionally, this paper intro-duces an extension to minimize the cache complexity of neural networks by applying an appropriate cache-oblivious approach to neural networks.

Author 1: Inas Abuqaddom
Author 2: Sami Serhan
Author 3: Basel A. Mahafzah

Keywords: Cache complexity; cache-oblivious algorithm; mem-ory hierarchy; neural network

Download PDF

Paper 113: OvSbChain: An Enhanced Snowball Chain Approach for Detecting Overlapping Communities in Social Graphs

Abstract: Overlapping Snowball Chain is an extension to Snowball Chain, which is based on the concept of community formation in line to the snowball chaining process. The inspiration behind this approach is from the snowball sampling process, wherein a snowball grows to form chain of nodes, leading to the formation of mutually exclusive communities in Snowball Chain. In the current work, the nodes are allowed to be shared among different snowball chains in a graph, leading to the formation of overlapping communities. Unlike its predecessor Snowball Chain, the proposed technique does not require the use of any hyper-parameter which is often difficult to tune for most of the existing methods. The proposed algorithm works in two phases, where overlapping chains are formed in the first phase, and then they are combined using a similarity-based criteria in the second phase. The communities identified at the end of the second phase are evaluated using different measures, including modularity, overlapping NMI and running time over both real-world and synthetic benchmark datasets. The proposed Overlapping Snowball Chain method is also compared with eleven state-of-the-art community detection methods.

Author 1: Jayati Gulati
Author 2: Muhammad Abulaish
Author 3: Sajid Yousuf Bhat

Keywords: Clustering coefficient; community detection; over-lapping communities; snowball sampling; social graph

Download PDF

Paper 114: Improving the Computational Complexity of the COOL Screening Tool

Abstract: Autoimmune disorder, such as celiac disease and type 1 diabetes, is a condition in which the immune system attacks body tissues by mistake. This might be triggered by abnormality in the development of biomarkers such as autoantibodies, which are generated by unhealthy beta cells. Therefore, screening of such biomarkers is crucial for early diagnosis of autoimmune diseases. However, one of the fundamental questions of screening is when to screen subjects who might be at a higher risk of au-toimmune disorder. This requires an exhaustive search to find the optimal ages of screening in retrospective cohorts. Very recently, a comprehensive tool was developed for screening in autoimmune disease. In this paper, we improved the computational time of the algorithm used in the screening tool. The new algorithm is more than 100 times faster than the original one. This improvement would help to increase the utility of the tool among clinicians and research scientists in the community.

Author 1: Mohamed Ghalwash

Keywords: Software engineering; screening tool; autoimmune disorder

Download PDF

Paper 115: A Lightweight Verifiable Secret Sharing in Internet of Things

Abstract: Verifiable Secret Sharing (VSS) is a fundamental tool of cryptography and distributed computing in Internet of Things. Since network bandwidth is a scarce resource, minimizing the number of verification data will improve the performance of VSS. Existing VSS schemes, however, face limitations in meeting the number of verification data and energy consumptions for low-end devices, which make their adoption challenging in resource-limited IoTs. To address above limitations, we propose a VSS scheme according to Nyberg’s one-way Accumulator for one-way Hash Functions (NAHFs). The proposed VSS has two distinguished features: first, the security of the scheme is based on NAHFs whose computational requirements are the basic criteria for known IoT devices and, second, upon receiving only one veri-fication data, participants can verify the correctness of both their shares and the secret without any communication. Experimental results show that, compared to the Feldman scheme and Rajabi-Eslami scheme, the energy consumption of a participant in the proposed scheme is respectively reduced by at least 24% and 83% for a secret.

Author 1: Likang Lu
Author 2: Jianzhu Lu

Keywords: Verifiable secret sharing; one-way function; inter-net of things; security

Download PDF

The Science and Information (SAI) Organization
BACK TO TOP

Computer Science Journal

  • About the Journal
  • Call for Papers
  • Submit Paper
  • Indexing

Our Conferences

  • Computing Conference
  • Intelligent Systems Conference
  • Future Technologies Conference
  • Communication Conference

Help & Support

  • Contact Us
  • About Us
  • Terms and Conditions
  • Privacy Policy

© The Science and Information (SAI) Organization Limited. Registered in England and Wales. Company Number 8933205. All rights reserved. thesai.org