IJACSA Volume 12 Issue 4 - thesai.org

IJACSA Volume 12 Issue 4

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: Road Detection Method based on Online Learning

Abstract: Road detection is always the key problem of re-searches on areas of unmanned ground vehicle and computer vision. A road detection method is proposed based on online learning and multi-sensor fusion. First of all, the Lidar point clouds are projected onto the images via the joint calibration of these two kinds of sensors. Then Simple Linear Iterative Clustering is used to segment images into many superpixles. Based on that, a multilayer online learning method is proposed, in which 2 Support Vector Machines are trained to detect the road. To be specific, the superpixel layer Support Vector Machine is used to detect road roughly, and the pixel layer Support Vector Machine is then trained to classify the edge pixels of the road areas, which is classified by the upper-layer Support Vector Machine. These 2 Support Vector Machines are updated online at each frame to be adapted to the changing environment. At last, some experiments are carried out on KITTI RAW dataset and an autonomous land vehicle, and the results show the effectiveness of proposed method. The main contributions of this work lie on as follows: 1) a multilayer learning model is proposed to detect road more robustly and accurately; 2) an online learning method is proposed which can be adapted to the changing environment.

Author 1: Wenbo Wang

Author 2: Yong Ma

Keywords: Road detection; data fusion; unmanned ground vehicle; online learning; image segmentation

Paper 2: Autonomous Reusing Policy Selection using Spreading Activation Model in Deep Reinforcement Learning

Abstract: This paper describes a policy transfer method of a reinforcement learning agent based on the spreading activation model of cognitive psychology. This method has a prospect of increasing the possibility of policy reuse, adapting to multiple tasks, and assessing agent mechanism differences. In the existing methods, policies are evaluated and manually selected depending on the target–task. The proposed method generates a policy network that calculates the relevance between policies in order to select and transfer a specific policy that is presumed to be effective based on the current situation of the agent while learning. Using a policy network graph structure, the proposed method decides the most effective policy while repeating probabilistic selection, activation, and spread processing. In the experiment section, this study describes experiments conducted to evaluate usefulness, conditions of use, and the usable range of the proposed method. Tests using CartPole and MountainCar, which are classical reinforcement learning tasks, are described and transfer learning is compared between the proposed method and a Deep Q–Network without transfer. As the experimental results, usefulness was suggested in the transfer learning of the same task without manual compared with previous method with various conditions.

Author 1: Yusaku Takakuwa

Author 2: Hitoshi Kono

Author 3: Hiromitsu Fujii

Author 4: Wen Wen

Author 5: Tsuyoshi Suzuki

Keywords: Reinforcement learning; transfer learning; deep learning; cognitive psychology; spreading activation theory

Paper 3: The Adoption of Mobile Health Applications by Patients in Developing Countries: A Systematic Review

Abstract: Mobile health (m-health) apps adoption in developing countries is a new research area in the healthcare industry. M-health is comparatively recent in information systems, with little attention being paid to it developing countries in the previous years. Applications of the m-health strategies in developing nations are considered one of the best platforms for guaranteeing the citizenry's safety and healthcare security. A systematic review was conducted of m-health apps adoption by patients in developing countries to evaluate the current results. It reviews 22 papers that were published on the topic of m-health adoption in developing countries in academic journals and conferences over the last decade. It identifies the research in terms of research methodologies, theories and models adopted, significant factors identified, limitations and recommendations. Findings show there is a limited contribution to m-health apps adoption in developing countries. Most studies employed TAM and focused on the technological and individual levels; very low intention has been made to health-related factors, levels, and theories. The review presents a broad overview of previous academic studies with a view to future research.

Author 1: Nasser Aljohani

Author 2: Daniel Chandran

Keywords: M-health; mobile health; apps; adoption; review; developing countries

Paper 4: Method for Most Appropriate Plucking Date Determination based on the Elapsed Days after Sprouting with NIR Reflection from Sentinel-2 Data

Abstract: Method for most appropriate plucking date determination based on the elapsed days after sprouting with Near Infrared: NIR reflection from Sentinel-2 data is proposed. Depending on the elapsed days after sprouting, tealeaf quality is decreasing. On the other hand, tealeaf yield is increasing with increasing of the days after sprouting. Therefore, there is most appropriate plucking date is very important. Usually, it is determined by the normalized Difference Vegetation Index: NDVI derived from handheld NDVI cameras, drone mounted NDVI cameras, and visible to NIR radiometer onboard satellites because NIR reflection and NDVI depend on tealeaf quality and yield. It, however, does not work well in terms of poor regression performance and species dependency. Moreover, it takes time consumable works for finding appropriate tealeaves from the acquired camera images. The proposed method uses only the days after sprouting. Next thing it has to do is to determination of sprouting date. In order to determine the date, optical sensor onboard Sentinel-2 data is used. Through experiment with the truth data taken at the intensive study area of the Oita Prefectural Agriculture, Forestry and Fisheries Research Guidance Center: OPAFFRGC, it is found that the proposed method is validated.

Author 1: Kohei Arai

Author 2: Yoshiko Hokazono

Keywords: Plucking date; elapsed days after sprouting; NIR reflection; sentinel-s; normalized difference vegetation index: NDVI

Paper 5: Systems Security Affectation with the Implementation of Quantum Computing

Abstract: Current security systems use cryptographic robust tools that have been of great help in regulating information. During its time the implementation of these tools abolished the classic security systems, as by means of cryptanalysis they allowed decryption of information in a fast, automated, and simple mode from these systems. Considering this scenario, the same happens when quantum cryptographic systems are implemented, insomuch as the current security systems could be abolished, as tools exist that permit its encryption in a simple way, but with the risk of putting the data of worldwide organizations in danger. With the purpose of mitigating these risks, it is necessary to consider the upgrade of the available security systems, by security systems and quantic encryption, before a massive implementation of the quantum computer’s use as an everyday tool. With this it does not mean that quantum computing would be a disadvantage, on the contrary, the advantages from this technology will mean that security information and data are almost invulnerable, which is a meaningful advance in the IT field. With security information professionals are obliged to recommend and perform an appropriate migration of new technologies to avoid existing exposition risks as data as well as transactions. If this were not the case, the same scenario presented in the classic security systems would occur.

Author 1: Norberto Novoa Torres

Author 2: Juan Carlos Suarez Garcia

Author 3: Erik Alexis Valderrama Guancha

Keywords: Quantum computing; encryption; cryptography; cryptanalysis; data security

Paper 6: Energy Storage and Electric Vehicles: Technology, Operation, Challenges, and Cost-Benefit Analysis

Abstract: With ever-increasing oil prices and concerns for the natural environment, there is a fast-growing interest in electric vehicles (EVs) and renewable energy resources (RERs), and they play an important role in a gradual transition. However, energy storage is the weak point of EVs that delays their progress. The world’s EV industry is accelerating to faster adoption with appropriate incentives to the EV owners, policy support, and encouraging local manufacturing. The increasing demand for EV’s has presented itself as an authentic alternative to internal combustion engines (ICE). The main feature of the RERs is their variability and intermittency. These drawbacks are overcome by integrating more than one renewable energy source including backup sources and storage systems. This paper presents various technologies, operations, challenges, and cost-benefit analysis of energy storage systems and EVs.

Author 1: Surender Reddy Salkuti

Keywords: Energy storage; electric vehicles; cost-benefit analysis; demand-side management; renewable energy; smart grid

Paper 7: Detecting Unauthorized Network Intrusion based on Network Traffic using Behavior Analysis Techniques

Abstract: Nowadays, network intrusion detection is an essential problem because cyber-attacks are increasing in both the number and extent of the danger. Network intrusion techniques often use various methods to bypass the oversight of anomaly detection and surveillance systems. This paper proposes to use behavior analysis techniques, machine learning, and deep learning algorithms for the task of detecting network intrusions. The practical and scientific significance of our paper includes two issues: (1) Regarding the process of selecting and extracting features: instead of using typical abnormal behaviors of attacks, this study will use statistical behaviors that are easy to calculate and extract while still ensuring the effectiveness of the method; (2) Regarding the detection process, this study proposes to use the Random Forest (RF) classification algorithm, the Multilayer Perceptron (MLP) and the Convolutional Neural Network (CNN) deep learning model. The experimental results in Section IV have proven that our proposal in this paper is completely correct and reasonable. Based on the results shown in Section IV, this study has provided network surveillance systems with a number of abnormal behaviors as the basis for detecting network intrusions.

Author 1: Nguyen Tung Lam

Keywords: Network intrusion detection; abnormal behaviors; IDS 2018 dataset; deep learning and machine learning

Paper 8: An Integrated Implementation Framework for an Efficient Transformation to Online Education

Abstract: The least developed countries have been tasked with introducing effective e-learning frameworks as they look to overcome technology inadequacies and lack of research support or vision. Ongoing efforts are reliant upon a mixed-methods approach. A systematic literature analysis and a quantitative examination have been undertaken to achieve a thorough assessment of the available data taken from educational facilities in Kuwait. Results show clear support for embracing e-learning, with most participants recognizing its positives when faced with the scope of challenges its practice may incorporate. Consequently, the authors recommend a framework that is integrated to support a smooth upgrade to online teaching in a manner that furthers the efficacy and understanding of e-learning potential in the context of education in Kuwait and neighboring countries, with a particular focus on how to function during a pandemic lockdown. The proposed framework is structured according to five key tiers: infrastructure, e-learning delivery, LMS, e-Content, and user portal. In support of this, a model of e-Content development is proposed to assist with the establishment and execution of educational materials, in particular, to cope with the lack of digital learning materials in Arabic.

Author 1: Ahmed Al-Hunaiyyan

Author 2: Salah Al-Sharhan

Author 3: Rana Alhajri

Author 4: Andrew Bimba

Keywords: Distance learning; e-learning framework; COVID-19 pandemic; e-learning delivery; e-Content

Paper 9: Development and Print of Clothing through Digitalized Designs of Natural Patterns with Flexible Filaments in 3D Printers

Abstract: This study proposes clothing development by digitalizing natural patterns with flexible filaments in 3D printers. The motivation to carry out this research was the similarity and evenness features of fractals. For this purpose, three natural exemplars have been selected and subsequently digitized: Snowflake, Honeycomb, and Flower of Life, with line variants and infill density at 12%. The garment was printed with Thermoplastic polyurethane (TPU) and Thermoplastic Elastomer (TPE) in two 3D printers: Anet A8 and M3D Crane Quad. Lastly, the combination of filaments, printers, line variant, and infill density resulted in forty-eight (48) samples. Two tests were carried out on the printed patterns for the research: The elongation and tensile strength test. The elongation test consists of applying a variable force to each exemplar in order to obtain the percentage of its elastic limit before reaching its fracture point. The tensile test applies a variable vertical power to each design to determine how it will behave under particular pressure. Results show that the snowflake pattern with line variant obtained the best performance in the elongation test compared to the tensile test. Subsequently, four clothing samples were printed with TPU and TPE materials on the two printers mentioned above. The garments are composed of twenty-nine (29) pieces respectively which were connected with a 3D pen. Finally, the item of clothing was worn by five volunteers of different sizes, as shown in the following pages.

Author 1: Jean Roger Farfán Gavancho

Author 2: Wilber Antonio Figueroa Quispe

Author 3: Dayvis Victor Farfán Gavancho

Author 4: Beto Puma Huamán

Author 5: Victor Manuel Lima Condori

Author 6: George Jhonatan Cahuana Alca

Keywords: Natural pattern; fractal; garment; digital design; flexible filament; 3D printing

Paper 10: Smartphone-based Recognition of Human Activities using Shallow Machine Learning

Abstract: The human action recognition (HAR) attempts to classify the activities of individuals and the environment through a collection of observations. HAR research is focused on many applications, such as video surveillance, healthcare and human computer interactions. Many problems can deteriorate the performance of human recognition systems. Firstly, the development of a light-weight and reliable smartphone system to classify human activities and reduce labelling and labelling time; secondly, the features derived must generalise multiple variations to address the challenges of action detection, including individual appearances, viewpoints and histories. In addition, the relevant classification should be guaranteed by those features. In this paper, a model was proposed to reliably detect the type of physical activity conducted by the user using the phone's sensors. This includes review of the existing research solutions, how they can be strengthened, and a new approach to solve the problem. The Stochastic Gradient Descent (SGD) decreases the computational strain to accelerate trade iterations at a lower rate. SGD leads to J48 performance enhancement. Furthermore, a human activity recognition dataset based on smartphone sensors are used to validate the proposed solution. The findings showed that the proposed model was superior.

Author 1: Maha Mohammed Alhumayyani

Author 2: Mahmoud Mounir

Author 3: Rasha Ismael

Keywords: Data preprocessing; data mining; classification; genetic programming; Naïve Bayes; decision tree

Paper 11: Deep Learning Approaches for Intrusion Detection in IIoT Networks – Opportunities and Future Directions

Abstract: In recent years, the Industrial Internet of things (IIoT) is a fastest advancing innovative technology with a poten-tial to digitize and interconnect many industries for huge business opportunities and development of global GDP. IIoT is used in diverse range of industries such as manufacturing, logistics, transportation, oil and gas, mining and metals, energy utilities and aviation. Although IIoT provides promising opportunities for the development of different industrial applications, they are prone to cyberattacks and demands for higher security require-ments. The enormous number of sensors present in the IIoT network generates a large amount of data and has attracted the attention of cybercriminals across globe. The intrusion detection system (IDS) that monitors the network traffic and detects the behaviour of the network is considered as one of the key security solution for securing IIoT application from attacks. Recently, the application of machine and deep learning techniques have proved to mitigate multiple security threats and enhance the performance of intrusion detection. In this paper, we present a survey of deep learning-based IDS technique for IIoT. The main objective of this research is to provide the various deep learning-based IDS detection methods, datasets and comwparative analysis. Finally, this research aims to identify the limitations and challenges of existing studies, solutions and future directions.

Author 1: Thavavel Vaiyapuri

Author 2: Zohra Sbai

Author 3: Haya Alaskar

Author 4: Nourah Ali Alaseem

Keywords: Industrial Control System; Industrial Internet of Things (IIoT); cybersecurity; intrusion detection system and deep learning

Paper 12: Sensing and Detection of Traffic Status through V2V Routing Hop Count and Route Energy

Abstract: New approach to manage congestion using vehicular communication is presented in this work. The research work using MATLAB simulation, tracked communicating vehicles travelling on roads with constant registration of changes in routes, number of hops, and energy consumed as a function of travelled distances. The area of travel and simulation is divided into blocks or zones to enable sufficient allocation and distribution of Road Side Units (RSUs) that are used to relay communication signals and transmission of Basic Safety Messages (BSMs). The successfully concluded simulation is based on the assumption that as congestion occurs, the number of hops per route and associated energy consumption per transmitted packets will change patterns in terms of hops, routes and consumed energy as traffic passes from low to smooth (optimal) to high density (congestion) states, where at the start of congestion, vehicles start to slow down and become closer to each other in a two dimensional space. The output is used as input to traffic status pattern characterization algorithm (management system) that uses the data to indicate the start of traffic accumulation, thus pre-emptive measures can be taken to avoid congestion and reduction in mobility. The presented analysis proved that it is possible to predict congestion as a function of both hops sequences and consumed energy, depending on the hops pattern which is shown to be symmetric in the case of optimum traffic that flows smoothly. The analysis also showed that when congestion starts to occur, asymmetric hops pattern occurs with hops sequences elements switch and swap places within the identified pattern. Further analysis and polynomial curve fitting proved that congestion control and smooth traffic management using the proposed approach is achievable.

Author 1: Mahmoud Zaki Iskandarani

Keywords: V2V; consumed energy; congestion; hops; VANET; routing

Paper 13: Annotated Corpus of Mesopotamian-Iraqi Dialect for Sentiment Analysis in Social Media

Abstract: Research on Sentiment Analysis in social media by using Mesopotamian-Iraqi Dialect (MID) of Arabic language was rarely found, there is no reliable dataset developed in MID neither an annotated corpus for the sentiment analysis of social media in this dialect. Therefore, this gap was the main stumbling block for researchers of sentiment analysis in MID, for this reason, this paper introduced the development of an annotated corpus of Mesopotamian-Iraqi Dialect for sentiment analysis in social media and named it as (ACMID) stands for (the annotated corpus of Mesopotamian-Iraqi Dialect) to help researchers in future for using this corpus for their studies, to the best of our knowledge this is the first annotated corpus that both classify polarity as well as emotion classification in MID. Likewise, Facebook as the most popular social platform among Iraqis was used to extract the data from its popular Iraqi pages. 5000 comments were extracted from these pages classified by its polarity (Positive, Negative, Neutral, Spam) by two Iraqi annotators, these annotators were simultaneously classifying the same comments according to Ekman seven universal emotions (Anger, Fear, Disgust, Happiness, Sadness, Surprise, Contempt) or no emotion. Cohen's kappa coefficient was then used to compare the two annotators’ results to find the reliability of these results. The data shows a comparable value among the two annotators for the polarity classification as high as 0.82, while for the emotion classification the result was 0.65.

Author 1: Al-Khafaji Ali J Askar

Author 2: Nilam Nur Amir Sjarif

Keywords: Sentiment analysis; Mesopotamian dialect; Iraqi dialect; social media; annotated corpus; emotion classification; Arabic language

Paper 14: Exploring Parkinson’s Disease Predictors based on Basic Intelligence Quotient and Executive Intelligence Quotient

Abstract: It is important to identify the risk factors of dementia and prevent them for the health of patients and caregivers. This study (1) explored sampling methods that could minimize overfitting due to data imbalance using a data-level approach, (2) developed nine ensemble learning models for predicting Parkinson's Disease–Mild Cognitive Impairment (PD-MCI) ((undersampling, oversampling, and SMOTE) × (boosting, bagging, and random forest)=9), and (3) compared the accuracies, sensitivities, and specificities of these models to understand the prediction performance of the developed models. We examined 368 subjects: 320 healthy elderly people (≥60 and ≤74 years old) without Parkinson's disease (168 men and 152 women) and 48 subjects with PD-MCI (20 men and 28 women). This study used the Cognition Scale for Olde Adults (CSOA), which could measure cognitive functions comprehensively while considering age and education level, to determine the specific cognitive level of the subject. Our study developed nine prediction models ((undersampling, oversampling, and SMOTE) × (boosting, bagging, and random forest)=9) for developing a model to predict PD-MCI based on basic intelligence quotient and executive intelligence quotient. The analysis results showed that a random forest classifier with SMOTE had the best prediction performance with a sensitivity of 69.2%, a specificity of 75.7%, and a mean overall accuracy of 74.0%. In this final model, digit span test-backward, stroop test-interference trial, verbal memory test-delayed recall, verbal fluency test, and confrontation naming test were identified as the key variables with high weight in predicting PD-MCI. The results of this study implied that a random forest classifier with SMOTE could produce models with higher accuracy than a bagging classifier with SMOTE or a boosting classifier with SMOTE when analyzing imbalanced data.

Author 1: Haewon Byeon

Keywords: Undersampling; oversampling; SMOTE; random forest; Parkinson's disease–mild cognitive impairment

Paper 15: Is Deep Learning Better than Machine Learning to Predict Benign Laryngeal Disorders?

Abstract: It is important in otolaryngology to accurately understand the etiology of a laryngeal disorder, diagnose it early, and provide appropriate treatment accordingly. The objectives of this study were to develop models for predicting benign laryngeal mucosal disorders based on deep learning, naive Bayes model, generalized linear model, a Classification and Regression Tree (CART), and random forest using laryngeal mucosal disorder data obtained from a national survey and confirm the best classifier for predicting benign laryngeal mucosal disorders by comparing the prediction performance and runtime of the developed models. This study analyzed 626 subjects (313 people with a laryngeal disorder and 313 people without a laryngeal disorder). In this study, deep learning was the best model with the highest accuracy (0.84). However, the runtime of deep learning was 39min 41sec, which was a 10 times longer development time than CART (3min 7sec). This model confirmed that subjective voice problem recognition, pain and discomfort in the last two weeks, education level, occupation, mean monthly household income, high-risk drinker, and current smoker were major variables with high weight for the benign laryngeal mucosal disorders of Korean adults. Among them, subjective voice problem recognition was the most important factor with the highest weight. The results of this study implied that the prediction performance of deep learning could be better than that of machine learning for structured data, such as health behavior and demographic factors as well as video and image data.

Author 1: Haewon Byeon

Keywords: Benign laryngeal mucosal disorder; voice disorder; deep learning; Naive Bayes model; generalized linear model

Paper 16: Distance Education during COVID-19 Pandemic: The Perceptions and Preference of University Students in Malaysia Towards Online Learning

Abstract: The sudden shift from the brick-and-mortar approach to online distance learning due to the coronavirus pandemic greatly impacted everyone involved, particularly students. Hence, it is critical to identify the perception of students regarding the challenges they faced, their satisfaction with remote learning, as well as their preferences and recommendations for improvement which are the objectives of this research. A survey taken by 408 diploma students with 377 valid answers for the quantitative study showed that the most common difficulties they encountered were in terms of interaction, concentration and motivation. The mean of the perceived challenges was found to be significantly different depending on the respondents’ prior e-learning experience and area of residence. With regard to the relevant activities to be conducted virtually, most participants approved of assessments such as quiz, assignments and tests. Animation and gamification received the highest votes as the elements that students wished were incorporated to boost their online learning engagement. The findings from this research contribute to existing studies on the perceptions and preference of students towards distance education by shedding light on the perspective of diploma students.

Author 1: Husna Hafiza Razami

Author 2: Roslina Ibrahim

Keywords: COVID; distance learning; education; online learning; student; perception; preference

Paper 17: VG4 Cipher: Digital Image Encryption Standard

Abstract: When it comes to providing security to information systems, encryption emerges as an indispensable tool, as it has been used extensively in the past few decades for securing stationary data as well as data in motion. With the rapid data transmission techniques and multimedia options available for data representation, the field of information security has become very significant. The state-of-art cryptographic technique is DNA encryption, which uses biological principles for safeguarding data. The use of Bio-inspired ciphers is becoming the de-facto safety standard, especially for digital images as they are a key source of extracting crucial information. Hence, image encoding becomes of ultimate importance when there is a need to send them via an insecure communication channel. The purpose of this research paper is to present a DNA- inspired cryptosystem that can be employed in the domain of image encryption that provides superior security with enhanced efficiency. The experimental outcomes prove that this novel cryptographic algorithm not only provides better security but also at a reasonable pace.

Author 1: Akhil Kaushik

Author 2: Vikas Thada

Keywords: DNA cryptography; cipher; information security; encryption; decryption

Paper 18: Formulation of Association Rule Mining (ARM) for an Effective Cyber Attack Attribution in Cyber Threat Intelligence (CTI)

Abstract: In recent year, an adversary has improved their Tactic, Technique and Procedure (TTPs) in launching cyberattack that make it less predictable, more persistent, resourceful and better funded. So many organisation has opted to use Cyber Threat Intelligence (CTI) in their security posture in attributing cyberattack effectively. However, to fully leverage the massive amount of data in CTI for threat attribution, an organisation needs to spend their focus more on discovering the hidden knowledge behind the voluminous data to produce an effective cyberattack attribution. Hence this paper emphasized on the research of association analysis in CTI process for cyber attack attribution. The aim of this paper is to formulate association ruleset to perform the attribution process in the CTI. The Apriori algorithm is used to formulate association ruleset in association analysis process and is known as the CTI Association Ruleset (CTI-AR). Interestingness measure indicator specially support (s), confidence (c) and lift (l) are used to measure the practicality, validity and filtering the CTI-AR. The results showed that CTI-AR effectively identify the attributes, relationship between attributes and attribution level group of cyberattack in CTI. This research has a high potential of being expanded into cyber threat hunting process in providing a more proactive cybersecurity environment.

Author 1: Md Sahrom Abu

Author 2: Siti Rahayu Selamat

Author 3: Robiah Yusof

Author 4: Aswami Ariffin

Keywords: Cyber threat intelligence (CTI); association rule mining; apriori algorithm; attribution; interestingness measures

Paper 19: Integrated Pairwise Testing based Genetic Algorithm for Test Optimization

Abstract: Generation of Test cases in software testing is an important and a complex activity as it deals with diversified range of inputs. Fundamentally, test case generation is considered to be a multi-objective problem as it aims to cover many targets. Deriving test cases for the Web Applications has become critical to the most of the enterprises. In this paper, a solution for generating test cases for web applications is proposed; the solution uses the System Graph (consisting of links and data dependencies) considering that test cases were based on a combination of input values and data dependencies. Pairwise testing is used to derive the test cases to be executing from entire test cases and then a genetic algorithm is proposed to generate test cases specific to functional testing. The proposed approach was tested through two distinct experiments by measuring the code coverage at every generation and results show that genetic algorithm used increased the fitness value and code coverage. Overall, the results of the paper validate the proposed approach and algorithm, having potential in further construct an automated integrated solution for generating test cases for the entire process.

Author 1: Baswaraju Swathi

Author 2: Harshvardhan Tiwari

Keywords: Test case generation; genetic algorithm; multi objective optimization; pairwise testing; test optimization; fitness value

Paper 20: Iterative Decoding of Chase Pyndiah Decoder Utilizing Multiple Relays Network

Abstract: In this paper, a distributed Encoding and decoding of Turbo Product Code (TPC) over single and multiple relays network are proposed. The information message matrix is encoded at source by Bose Chaudhuri Hochquenghem (BCH) as component code and transmitted to destination and relays in the midway between source and destination. The coded source message is decoded by simple chase П decoder at relay and encoded again horizontally and vertically by BCH component code to construct TPC. Two scenarios were investigated. First scenario, utilizing one relay in cooperative network, where the vertical parity part of TPC is transmitted to destination to be the input of row decoder for original chase pyndiah decoder, while the received encoded horizontally matrix from source is the input of the column decoder. In the second scenario multiple relays are utilized and multiple copies of vertical parity part of TPC are sent to destination to be decoded by the proposed modified iterative chase pyndiah decoder with multiple integrated stages for each iteration. Simulation results for the first scenario over Additive White Gaussian (AWGN) and Rayleigh fading channels and using original chase Pyndiah decoder at destination shows 2dB gain improvement at BER= 〖10〗^(-5) and 4dB gain improvement at BER=〖10〗^(-4) respectively over BER performance of un cooperative system. While results for distributed TPC decoding for the second scenario and using the proposed modified iterative chase Pyndiah decoder at destination shows 2.7 dB and 3 dB gain at BER =〖10〗^(-4) for AWGN and Rayleigh fading channels respectively over the first scenario.

Author 1: Saif E. A. Alnawayseh

Keywords: Turbo product code (TPC); modified iterative chase Pyndiah decoding algorithm; relay; source; Bit Error Rate (BER); vertical parities; horizontal parities

Paper 21: An Efficient Privacy Preserving Approach for e-Health

Abstract: Immense Procreation of large amounts of data in medical field and health care domain, benefitting society is at risk with sensitive attributes being disclosed. Access to Medical Information made feasible over internet with an intension of serving the people related to medical community is triggering a challenge for researchers in norms of Privacy and security. The medical data at cloud is vulnerable to unpredictable threats with evolving technology, and the threat landscape sounds resilient with sensitive attributes. In this contemporary stretch, Organizations fail to hold the reputation and are unable to preserve public confidence. The austerity of sophisticated security attacks compromise the privacy of patient data and security of healthcare units. The fruitful approaches by several researches and practitioners provided an up heal resolutions, but the demand for an optimal solution remains unanswered. In this paper we present a solution for addressing the security issues in health care management. We propose a hybrid framework using enhanced Attribute Based Encryption (ABE) with Anonymity approach based on access primitives of sensitive attributes. The proposed mechanism is evaluated in terms of performance, encryption time, decryption time and Memory utilization using Jsim simulator which envisage drastic performance expedition in the presented model.

Author 1: Supriya Menon M

Author 2: Rajarajeswari Pothuraju

Keywords: e-Health; Attribute Based Encryption (ABE); secure hash algorithm (SHA-1); anonymity; privacy; sensitive parameters

Paper 22: Indonesian Speech Emotion Recognition using Cross-Corpus Method with the Combination of MFCC and Teager Energy Features

Abstract: Emotion recognition is one of the widely studied topics in speech technology. Emotions that come from speech can contain useful information for many purposes. The main aspects in speech emotion recognition are speech features, speech corpus, and machine learning algorithms as the classifier method. In this paper, cross-corpus method is used to conduct Indonesian Speech Emotion Recognition (SER) along with the combination of Mel Frequency Cepstral Coefficients (MFCC) and Teager Energy features. Using Support Vector Machine (SVM) as classifier, the experiment result shows that applying cross-corpus method by adding corpora from other languages to the training dataset improves the emotion classification accuracy by 4.16% on MFCC Statistics feature and 2.09% on Teager-MFCC Statistics feature.

Author 1: Oscar Utomo Kumala

Author 2: Amalia Zahra

Keywords: Cross corpus; Indonesian speech emotion recognition; Mel Frequency Cepstral Coefficients; Teager Energy

Paper 23: NetAI-Gym: Customized Environment for Network to Evaluate Agent Algorithm using Reinforcement Learning in Open-AI Gym Platform

Abstract: The growing size of the network imposes computational overhead during network route establishment using conventional approaches of the routing protocol. The alternate approach in contrast to the route table updating mechanism is the rule-based method, but this also provides a limited scope in the dynamic networks. Therefore, reinforcement learning promises a better way of finding the route, but it requires an evaluation platform to build a model synchronization between route and agent. Unfortunately, the de-facto platform for agent evaluation, namely Open-AI Gym, does not provide a suitable networking environment. Therefore, this paper aims to propose a networking environment as a novel contribution by designing a suitable customized environment for a network synchronically with Open-AI Gym. The successful deployment of the proposed network environment: NetAI-Gym provides a functional and practical result that can be used further to develop routing mechanisms based on Q-learning. The validation of the proposed NetAI-Gym is carried out with different nodes in the network regarding Episodes Vs. Reward. The experimental outcome justifies the validity of the proposed NetAI-Gym that it is suitable for solving network-related problems.

Author 1: Varshini Vidyadhar

Author 2: Nagaraj R

Author 3: D V Ashoka

Keywords: Open-AI Gym; network; environment; agent; reinforcement learning

Paper 24: Service Outages Prediction through Logs and Tickets Analysis

Abstract: Service outage or downtime is a growing challenge to the service providers and end users. The major cause for the unavailability firstly is failure of equipments and applications at various places and secondly failure for proactive diagnosis and rectification. The system activities that are logged and the response of customers and providers in the form of trouble tickets could be studied for minimizing network faults. The downtime can be reduced when the failures are predicted well in time and proactively corrected. Accurate prediction of faults helps in responding to downtime even before the customer tickets are raised or network trouble is encountered. Most of the research focuses on trouble shooting through forecasting the quantity of trouble tickets using the historical ones. If these tickets can be supported with the warning in the form of Syslogs and the technical support of network tickets the predictive models would be more efficient and accurate. Dynamic and truly adaptive machine learning algorithms are essentially required for processing the torrent of data and formulating predictions based on the trends and the patterns existing in it. The work refers to i) identifying number of trouble tickets that are related to the device a few days before the network component fails, ii) predicting fault will occur in broadband networks. Lasso and Ridge regression are used for the first and Bayesian structural time series analysis and prophet are used for the latter.

Author 1: Sunita A Yadwad

Author 2: V. Valli Kumari

Author 3: S Venkata Lakshmi

Keywords: Failure prediction; linear regression technique; network fault prediction; lasso; ridge regression; Bayesian structural time series; prophet

Paper 25: Recent Themes of Colombian Scientific Engineering Journals in Scopus

Abstract: Through a co-occurrence bibliometric and citation analysis of 1.272 texts published in the four Colombian engineering journals available in Scopus between 2014 and 2018, this paper identified that most articles belong to supply chain optimization and logistics and involve work with information that requires minimal laboratory experimentation. Works applying artificial neural networks, clustering, and genetic algorithms are also prominent. Results from researching on biomass analysis on bioenergy and sustainability are more recent and are present to a lesser extent. Most of the reference texts of the articles published come from Spanish-speaking countries and mostly cite DYNA, the European Journal of Operational Research, the Journal of Food Engineering, and Ingeniería e Investigación.

Author 1: Marco Aguilera-Prado

Author 2: Octavio José Salcedo Parra

Author 3: Eduardo Avendaño Fernández

Keywords: Co-occurrence words; bibliometric analysis; bibliometrics; Colombian journals

Paper 26: Book Recommendation for Library Automation Use in School Libraries by Multi Features of Support Vector Machine

Abstract: This paper proposed the algorithms of book recommendation for the open source of library automation by using machine learning method of support vector machine. The algorithms consist of using multiple features (1) similarity measures for book title (2) The DDC for systematic arrangement combination of Association Rule Mining (3) similarity measures for bibliographic information of book. To evaluate, we used both qualitative and quantitative data. For qualitative, sixty four students of Banpasao Chiang Mai school reported the satisfaction questionnaire and interview. For Quantitative, we used web monitoring and precision measures to effectively use the system. The results show that books recommended by our algorithms can suggest books to students “Very interested” and “interested” by 14.5% and 22.5% and improve usage of the OPAC system's highest average of 52 per day. Therefore, these systems suitable for library automation of Thai language and small library with not much book resource.

Author 1: Kitti Puritat

Author 2: Phichete Julrode

Author 3: Pakinee Ariya

Author 4: Sumalee Sangamuang

Author 5: Kannikar Intawong

Keywords: Library automation; book recommendation system; library integrated system; title similarity; support vector machine; open source

Paper 27: Econometric Analysis of Stock Market Performance during COVID-19 Pandemic: A Case Study of Uzbekistan Stock Market

Abstract: This article highlights the impact of the Coronavirus disease (COVID-19). COVID-19 pandemic on the stock market of Uzbekistan on the basis of empirical research and the main factors affecting the stock market are identified as well. Secondary statistical data were collected from the Tashkent Stock Exchange, the Central Bank of the Republic of Uzbekistan, the State Statistics Committee of the Republic of Uzbekistan and other public funds, and the regression equation of the SEM-model of the impact of the Covid-19 pandemic on the stock market of Uzbekistan was formed. In particular, indicators such as the latest daily and total number of people infected with Covid-19 in the Republic of Uzbekistan, the total number of recovered people after being infected with Covid-19, the total number of people who died of the disease, the daily number of recovered people post-infection, the stock market index of Uzbekistan, Uzbekistan Indicators such as the number of daily securities traded on the Republican Stock Exchange "Tashkent", the exchange rate of the US dollar set by the Central Bank of the Republic of Uzbekistan were selected as the main factors. The constructed regression equation was examined using F-statistics, Student’s t-test, and multicorrelation tests to determine the level of adequacy. The authors identify factors based on a systematic analysis of the scientific work of world-renowned scientists on major stock markets and creates a SEM-model of the factors affecting the Uzbek stock market during the pandemic.

Author 1: Mansur Eshov

Author 2: Walid Osamy

Author 3: Ahmed Aziz

Author 4: Ahmed M. Khedr

Keywords: Stock market; factors; SEM-model; COVID-19; global economy

Paper 28: Deep Learning based Anomaly Detection in Images: Insights, Challenges and Recommendations

Abstract: Deep learning-based anomaly detection in images has recently been considered a popular research area with numerous applications worldwide. The main aim of anomaly detection (i.e., Outlier detection), is to identify data instances that deviate considerably from the majority of data instances. This paper offers a comprehensive analysis of previous works that have been proposed in the area of anomaly detection in images through deep learning generally and in the medical field specifically. Twenty studies were reviewed, and the literature selection methodology was defined based on four phases: keyword filter, publish filter, year filter, and abstract filter. In this review, we highlight the differences among the studies included by considering the following factors: methodology, dataset, prepro-cessing, results and limitations. Besides, we illustrate the various challenges and potential future directions relevant to anomaly detection in images

Author 1: Ahad Alloqmani

Author 2: Yoosef B. Abushark

Author 3: Asif Irshad Khan

Author 4: Fawaz Alsolami

Keywords: Anomaly detection; outlier detection; deep learning

Paper 29: The Evaluation of User Experience Testing for Retrieval-based Model and Deep Learning Conversational Agent

Abstract: The use of a conversational agent to relay information on behalf of individuals has gained worldwide acceptance. The conversational agent in this study was developed using Retrieval-based Model and Deep Learning to enhance the user experience. Nevertheless, the successfulness of the conversational agent could only be determined upon the evaluation. Thus, the testing was performed in the quantitative approach via questionnaire survey to capture user experience upon the usage of the conversational agent in terms of Usability, Usefulness and Satisfaction. The questionnaire survey was tested via statistical tool for reliability and validation test and proven to be carried out. The test results indicate positive experience towards the usage of the conversational agent and the outcome of the testing showed promising results and proof the success of this study, with immense contributions to the field of conversational agent.

Author 1: Pui Huang Leong

Author 2: Ong Sing Goh

Author 3: Yogan Jaya Kumar

Author 4: Yet Huat Sam

Author 5: Cheng Weng Fong

Keywords: Conversational agent; retrieval-based model; deep learning; user experience testing; usability; usefulness; satisfaction

Paper 30: Survey of Tools and Techniques for Sentiment Analysis of Social Networking Data

Abstract: Social media has rapidly expanded over a period of time and generated a huge repository of content. Sentiment analysis of this data has a vast scope in decision support and attracted many researchers to explore various possibilities for technique enhancement and accuracy improvement. Twitter is one of the social media platforms that are widely explored in the area of sentiment analysis. This paper presents a systematic survey related to Social Networking Sites Sentiment Analysis and mainly focus on Twitter sentiment analysis. The paper explores and identifies the techniques and tools used in a well-structured approach to find out the research gaps and identify future scope in this area of research. The techniques evolved over time to improve the efficiency of classification. Total 55 research papers are included in this survey. The result reflects that Twitter is the most explored social networking site for opinion mining. Naïve Bayes and SVM machine learning algorithms are implemented in maximum researches. As the latest advancements, Stack based ensemble, fuzzy based and neural network based classifiers are also implemented to enhance the efficiency of classification. WEKA, R Studio, Python are mostly used tools by research scholars for implementation. The overall evolution of the research goes through various changes in terms of technologies, tools, social media platforms and data corpus targeted.

Author 1: Sangeeta Rani

Author 2: Nasib Singh Gill

Author 3: Preeti Gulia

Keywords: Social networking sites sentiment analysis; twitter sentiment analysis; opinion mining; ensemble classifier; stack based ensemble

Paper 31: Efficient Security Model for RDF Files Used in IoT Applications

Abstract: The openness environment of IoT ecosystem arises several security and privacy issues. However, the huge amount of data produced by several IoT devices restricts using traditional security methods. Another security challenge for IoT system is the interoperability between heterogeneous IoT devices. Semantic Web has risen as a promising technology that provides semantic annotations allowing interoperability between IoT devices. Semantic web uses RDF triples to allow semantic data exchange between heterogeneous applications. Hence, RDF files used in IoT systems require specific security mechanism that regards large data size as well as rapidly data updates. The proposed work introduces a security novel that provides RDF files with a fine grained partial encryption. The proposed method allows applying security for the sensitive parts of RDF files without affecting the public parts. Encryption metadata is stored in a container related to each individual sensitive triple. Thus accessing public data in RDF file is not affected with the encryption overheads. A motivation scenario for privacy in a smart city is used to evaluate the proposed method. Experimental results showed that the proposed methodology enhances the access time of RDF triples from 10.4 msec to 6.2 msec. Moreover the proposed method facilitates integration of separated parts of a RDF graph together. The empirical evaluation proved the enhancement in efficiency and flexibility by applying the proposed method to RDF files used in IoT systems. Moreover the insensitive triples in RDF files are not affected with the security overheads.

Author 1: Mohamed El kholy

Author 2: Abdel baes Mohamed

Keywords: Semantic Web; Internet of Things (IoT); resource description framework (RDF); smart cities; security mechanism; web ontology language (OWL); partial encryption; SPARQL protocol and RDF query language (SPARQL); data encryption standard (DES) component

Paper 32: Predictive Analysis of Ransomware Attacks using Context-aware AI in IoT Systems

Abstract: Ransomware attacks are emerging as a major source of malware intrusion in recent times. While so far ransomware has affected general-purpose adequately resourceful computing systems, there is a visible shift towards low-cost Internet of Things systems which tend to manage critical endpoints in industrial systems. Many ransomware prediction techniques are proposed but there is a need for more suitable ransomware prediction techniques for constrained heterogeneous IoT systems. Using attack context information profiles reduces the use of resources required by resource-constrained IoT systems. This paper presents a context-aware ransomware prediction technique that uses context ontology for extracting information features (connection requests, software updates, etc.) and Artificial Intelligence, Machine Learning algorithms for predicting ransomware. The proposed techniques focus and rely on early prediction and detection of ransomware penetration attempts to resource-constrained IoT systems. There is an increase of 60 % of reduction in time taken when using context-aware dataset over the non-context aware data.

Author 1: Vytarani Mathane

Author 2: P.V. Lakshmi

Keywords: Ransomware; IoT; context-aware; machine learning; ontology

Paper 33: Contribution to the Improvement of Cryptographic Protection Methods for Medical Images in DICOM Format through a Combination of Encryption Method

Abstract: This paper proposes a method for storing and securing medical images in DICOM format. Other methods offered affect the quality of the image. The solution proposed here is based on the AES256 algorithm in Galois/Counter Mode (GCM) which already integrates authentication and signature processes to ensure the integrity of the images manipulated. This solution is implemented by using the Phyton programming language under the DJANGO framework, libraries such as NUMPHY, PYDICOM, MYSQLCLIENT, and PYCRYPTODOME. The results obtained after experimental tests give us a good average encryption and decryption time. The difference in the mean value of time between encryption and decryption is quite small in view of the tests carried out. We obtain saving on storage space owing to the fact that the proposed solution directly stores the encrypted image. The manipulated image is not altered.

Author 1: Maka Maka Ebenezer

Author 2: Pauné Félix

Author 3: Malong Yannick

Author 4: Simo Ntso Pascal Junior

Author 5: Nnemé Nnemé Léandre

Keywords: Medical images; DICOM; advanced encryption standard (AES); GCM; authentication

Paper 34: Birds Identification System using Deep Learning

Abstract: Identifying birds is one of challenging role for bird watchers due to the similarity of the birds’ forms/image background and the lack of experience for watchers. So, it needs a computer system based images to help birdwatchers in order to identify birds. This study aims at investigating the use of deep learning for birds’ identification using convolutional neural network for extracting features from images. The investigation was performed on database contained 4340 images that collected by the paper author from Jordan. The Principal Component Analysis (was applied on layer 6 and 7, as well as on the statistical operations of merging the two layers like: average, minimum, maximum and combine of both layers. The datasets were investigated by the following classifiers: Artificial neural networks, K-Nearest Neighbor, Random Forest, Naïve Bayes and Decision Tree. Whereas, the metrics used in each classifier are: accuracy, precision, recall, and F-Measure. The results of investigation include and not limited to the following, the PCA used on the deep features does not only reduce the dimensionality, and therefore, the training/testing time is reduced significantly, but also allows for increasing the identification accuracy, particularly when using the Artificial Neural Networks classifier. Based on the results of classifiers; Artificial neural networks showed high classification accuracy (70.9908), precision (0.718), recall (0.71) and F-Measure (0.708) compared to other classifiers.

Author 1: Suleyman A. Al-Showarah

Author 2: Sohyb T. Al-qbailat

Keywords: Birds identification; deep learning convolutional neural networks (CNN); VGG-19; principal component analysis (PCA)

Paper 35: Feature Engineering Algorithms for Traffic Dataset

Abstract: As a result of an increase in the human popula-tion globally, traffic congestion in the urban area is becoming worse, which leads to time-consuming, waste of fuel, and, most importantly, the emission of pollutants. Therefore, there is a need to monitor and estimate traffic density. The emergence of an automatic traffic management system allows us to record and monitor motor vehicles’ movement in a road segment. One of the challenges researchers face is when the historical traffic data is given as an annual average that contains incomplete data. The annual average daily traffic (AADT) is an average number of traffic volumes at the roadway segment in a specific location over a year. An example of AADT data is the one given by Road Traffic Volume Malaysia (RTVM), and this data is incomplete. The RTVM provides an average of daily traffic data and one peak hour. The recorded traffic data is for sixteen hours, and the only hourly data given is one hour, from 8.00 am to 9.00 am. Hence there is a need to estimate hourly traffic volume for the remaining hours. Feature engineering can be used to overcome the issue of incomplete data. This paper proposed feature engineering algorithms that can efficiently estimate hourly traffic volume and generate features from the existing dataset for all traffic census stations in Malaysia using queuing theory. The proposed feature engineering algorithms were able to estimate the hourly traffic volume and generate features for three years in Jalan Kepong census station, Kuala Lumpur, Malaysia. The algorithms were evaluated using the Random Forest model and Decision Tree Models. The result shows that our feature engineering algorithms improve machine learning algorithms’ performance except for the prediction of N􀀀2 using Random Forest, which shows the highest MAE, MSE, and RMSE when traffic data was included for prediction. The algorithm is applied in one of the traffic census stations in Kuala Lumpur, and it can be used for the other stations in Malaysia. Additionally, the algorithm can also be used for any annual average daily traffic data if it includes average hourly data.

Author 1: Akibu Mahmoud Abdullah

Author 2: Raja Sher Afgun Usmani

Author 3: Thulasyammal Ramiah Pillai

Author 4: Ibrahim Abaker Targio Hashem

Author 5: Mohsen Marjani

Keywords: Feature engineering algorithm; queuing theory; Road Traffic Volume Malaysia (RTVM); machine learning algo-rithms

Paper 36: PlexNet: An Ensemble of Deep Neural Networks for Biometric Template Protection

Abstract: The security of biometric systems, especially pro-tecting the templates stored in the gallery database, is a primary concern for researchers. This paper presents a novel framework using an ensemble of deep neural networks to protect biometric features stored as a template. The proposed ensemble chooses two state-of-the-art CNN architectures i.e., ResNet and DenseNet as base models for training. While training, the pre-trained weights enable the learning algorithm to converge faster. The weights obtained through the base model is further used to train other compatible models, generating a fine-tuned model. Thus, four fine-tuned models are prepared, and their learning are fused to form an ensemble named as PlexNet. To analyze biometric templates’ security, the rigorous learning of ensemble is collected using a smart box i.e., application programming interface (API). The API is robust and correctly identifies the query image without referring to a template database. Thus, the proposed framework excludes the templates from database and performed predictions based on learning that is irrevocable.

Author 1: Ashutosh Singh

Author 2: Ranjeet Srivastva

Author 3: Yogendra Narain Singh

Keywords: Biometrics; template protection; deep learning; transfer learning; ensemble

Paper 37: A Multi-layer Machine Learning-based Intrusion Detection System for Wireless Sensor Networks

Abstract: With the increase relay on the internet, and the shift of most business to provide remote services, the burdens of protecting the network and detecting any attack quickly become more significant, as the attack surface and Cyberattack increases in return. Most current Wireless Sensor Networks (WSNs) intrusion detection models that use machine learning methods to identify non-previously seen attacks utilize one layer of detection, meaning that a costly algorithm should be run before detecting any suspicious activity. In this paper, we propose a multi-layer intrusion detection framework for WSN; in which we adopt a defense-in-depth security strategy, where two layers of detection are deployed. The first layer is located on the network edge sensors are distributed; it uses a Naive Bayes classifier for real-time decision making of the inspected packets. The second layer is located on the cloud and utilizes a Random Forest multi-class classifier for an in-depth analysis of the inspected packets. The results demonstrate that our proposed multi-layer detection model gives a relatively high performance of the TPR, TNR, FPR, and FNR, additionally achieving a high Precision rate with values of, 100%, 90.4%, 99.5%, 97%, 99.9% for the Normal, Flooding, Scheduling, Grayhole, and Blackhole attacks, respectively

Author 1: Nada M. Alruhaily

Author 2: Dina M. Ibrahim

Keywords: Intrusion detection; wireless sensor networks; ma-chine learning; defence in depth strategy

Paper 38: ParaDist-HMM: A Parallel Distributed Implementation of Hidden Markov Model for Big Data Analytics using Spark

Abstract: Big Data is an extremely massive amount of hetero-geneous and multisource data which often requires fast processing and real time analysis. Solving big data analytics problems needs powerful platforms to handle this enormous mass of data and efficient machine learning algorithms to allow the use of big data full potential. Hidden Markov models are statistical models, rich and widely used in various fields especially for time varying data sequences modeling and analysis. They owe their success to the existence of many efficient and reliable algorithms. In this paper, we present ParaDist-HMM, a parallel distributed imple-mentation of hidden Markov model for modeling and solving big data analytics problems. We describe the development and the implementation of the improved algorithms and we propose a Spark-based approach consisting in a parallel distributed big data architecture in cloud computing environment, to put the proposed algorithms into practice. We evaluated the model on synthetic and real financial data in terms of running time, speedup and prediction quality which is measured by using the accuracy and the root mean square error. Experimental results demonstrate that ParaDist-HMM algorithms outperforms other implementations of hidden Markov models in terms of processing speed, accuracy and therefore in efficiency and effectiveness.

Author 1: Imad Sassi

Author 2: Samir Anter

Author 3: Abdelkrim Bekkhoucha

Keywords: Big data; machine learning; Hidden Markov model; forward; backward; baum-welch; parallel distributed computing; spark; cloud computing; ParaDist-HMM

Paper 39: Performance Assessment of Context-aware Online Learning for Task Offloading in Vehicular Edge Computing Systems

Abstract: Vehicular Edge Computing (VEC) systems have recently become an essential computing infrastructure to support a plethora of applications entailed by smart and connected vehicles. These systems integrate the computing resources of edge and cloud servers and utilize them to execute computational tasks offloaded from various vehicular applications. However, the highly fluctuating status of VEC resources besides the varying characteristics and requirements of different application types introduce extra challenges to task offloading. Hence, this paper presents, implements and evaluates various task offloading algorithms based on the Multi-Armed Bandit (MAB) theory for VEC systems with predefined application types. These algorithms seek to make use of available contextual information to better steer task offloading. These information include application type, application characteristics, network status and server utilization. The proposed algorithms are based on having either a single MAB learner with application-dependent reward assignment, multiple application-dependent MAB learners or dedicated contextual bandits implemented as an array of incremental learning models. They have been implemented and extensively evaluated using the EdgeCloudSim simulation tool. Their performance has been assessed based on task failure rate, service time and Quality of Experience (QoE) and compared to that of recently reported algorithms. Simulation results demonstrate that the proposed contextual bandit-based algorithm outperforms its counterparts in terms of failure rate and QoE while having comparable service time values. It has achieved up to 73.4% and 21.7% average improvements in failure rate and QoE, respectively, among all application types. In addition, it efficiently utilizes the available contextual information to make appropriate offloading decisions for tasks originating from different application types achiev-ing more balanced utilization of the available VEC resources. Ultimately, employing incremental learning to implement the proposed contextual bandit algorithm has shown a profound potential to cope with dynamic changes of the simulated VEC systems.

Author 1: Mutaz A. B. Al-Tarawneh

Author 2: Saif E. Alnawayseh

Keywords: Vehicular edge computing; task offloading; multi-armed bandits; contextual bandits

Paper 40: Body Weight Estimation using 2D Body Image

Abstract: Two dimensional images of a person implicitly contain several useful biometric information such as gender, iris colour, weight, etc. Among them, body weight is a useful metric for a number of usecases such as forensics, fitness and health analysis, airport dynamic luggage allowance, etc. Most current solutions for body weight estimation from images make use of additional apparatus like depth sensors and thermal cameras along with predefined features such as gender and height which generally make them more computationally intensive. Motivated by the need to provide a time and cost efficient solution, a novel computer-vision based method for body weight estimation using only 2D images of people is proposed. Considering the anthropometric features from the two most common types of images, facial and full body, facial landmark measurements and body joint measurements are used in deep learning and XG boost regression models to estimate the person’s body weight. The results obtained, though comparable to previous approaches, perform much faster due to the reduced complexities of the proposed models, with facial models performing better than full body models.

Author 1: Rohan Soneja

Author 2: Prashanth S

Author 3: R Aarthi

Keywords: Body weight estimation; deep learning; xgboost regressor; anthropometric features; computer vision

Paper 41: A Detailed Study on the Choice of Hyperparameters for Transfer Learning in Covid-19 Image Datasets using Bayesian Optimization

Abstract: For many years, the area of health care has evolved, mainly using medical images to detect and evaluate diseases. Nowadays, the world is going through a pandemic due to COVID- 19, causing a severe effect on the health system and the global economy. Researchers, both in health and in different areas, are focused on improving and providing various alternatives for rapid and more effective detection of this disease. The main objective of this study is to automatically explore as many configurations as possible to recommend a smaller starting hyperparameter space. Because the manual selection of these hyperparameters can lose configurations that generate more efficient models, for this, we present the MKCovid-19 workflow, which uses chest x-ray images of patients with COVID-19. We use knowledge transfer based on convolutional neural networks and Bayes optimization. A detailed study was conducted with different amounts of training data. This automatic selection of hyperparameters allowed us to find a robust model with an accuracy of 98% in test data.

Author 1: Miguel Miranda

Author 2: Kid Valeriano

Author 3: Jos´e Sulla-Torres

Keywords: Transfer Learning; COVID-19; X-ray image; deep learning; Bayes optimization; machine learning; hyperparameter optimization

Paper 42: Impact of Deep Learning on Localizing and Recognizing Handwritten Text in Lecture Videos

Abstract: Now-a-days, the video recording technologies have turned out to be more and more forceful and easier to utilize. Therefore, numerous universities are recording and publishing their lectures online in order to make them reachable for learners or students. These lecture videos encapsulate the handwritten text written either on a paper or blackboard or on a tablet using a stylus. On the other hand, this mechanism of recording the lecture videos consumes huge quantity of multimedia data in a faster manner. Thus, handwritten text recognition on the lecture video portals has turned out to be an incredibly significant and demanding task. Thus, this paper intends to develop a novel handwritten text detection and recognition approach on the video lecture dataset by following four major phases, viz. (a) Text Localization, (b) Segmentation (c) Pre-processing and (d) Recognition. The text localization in the lecture video frames is the initial phase and here the arbitrarily oriented text on video frames is localized using the Modified Region Growing (MRG) algorithm. Then, the localized words are subjected to segmentation via the K-means clustering, in which the words from the detected text regions are segmented out. Subsequently, the segmented words are pre-processed to avoid the blurriness artifacts as well. Finally, the pre-processed words are recognized using the Deep Convolutional Neural Network (DCNN). The performance of the proposed model is analyzed in terms of the performance measures like accuracy, precision, sensitivity and specificity to exhibit the supremacy of the text detection and recognition in lecture video. Experimental results reveal that at Learning Percentage of 70, the presented work has the highest accuracy of 89.3% for 500 count of frames.

Author 1: Lakshmi Haritha Medida

Author 2: Kasarapu Ramani

Keywords: Lecture video; text localization; segmentation; word recognition; deep convolutional neural network (DCNN)

Paper 43: A Vehicle Routing Problem for the Collection of Medical Samples at Home: Case Study of Morocco

Abstract: This paper aims to solve the problem of sampling and collecting blood and/ or urine tubes from sick people at home via a medical staff (nurse/ caregiver) to the laboratory in an optimal way. To ensure good management, several constraints must be taken into account, namely: staff schedules, patient preferences, the maximum delay time for a blood sample, etc. This problem is considered as a vehicle routing problem with time windows, preference and priority according to urgent cases. We first proposed a mathematical formulation of the problem by using a mixed integer linear programming (MILP) as well as various metaheuristics. Also, we applied this method to a real instance of a laboratory in Morocco (Témara) named Laboratory BioGuich, which gave the most optimal results.

Author 1: Ettazi Haitam

Author 2: Rafalia Najat

Author 3: Jaafar Abouchabaka

Keywords: Optimization; metaheuristics; vehicle routing problem; allocation and planning; home care

Paper 44: A Computer-Assisted Collaborative Reading Model to Improve Reading Fluency of EFL Learners in Continuous Learning Programs in Saudi Universities

Abstract: Reading is not synonymous to comprehension; rather it is a prerequisite that doesn’t, by itself, guarantee comprehension. This is to say that being efficient in decoding letters, syllables and whole words and recognizing vocabulary does not ensure natural r automatic comprehension. Fluency seems to be the bridge between the mastery of the mechanics of reading and the dynamics of comprehension. Abundant research exists that explores how to improve reading skills of EFL learners at Saudi universities. However little, if any, of this array of research sought to discern the potential effects of educational technology on the fluency of struggling readers in continuous learning programs. To fill this gap, this study seeks to probe the multi dimensions of the problem and suggest ways to solve it. For this purpose, 24 EFL lecturers from three Saudi universities were selected and interviewed. A suggested computer-assisted collaborative reading model was put forth to be applied in the three universities. Students were diagnosed by their instructors as gaining relatively enough grasp of decoding skills at the multi-levels of orthographic knowledge, mono and polysyllabic words, but exhibit slow and inaccurate reading indicating reprehensive symptoms for a fluency problem. The lecturers explained that the disappointment resulting from learners’ inability to reach comprehension despite mastering decoding skills influences their attitudes towards reading and language learning, bringing about reading apathy and low self-esteem. The proposed model is designed to enhance reading fluency which is perceived as the underlying problem that makes the reader struggle. It is to be delivered partly individually and partly collaboratively online. Collaboration also is operated via face to face instruction especially in teaching the reading strategy. In doing so, the procedures followed are in line with the blended learning. The findings indicate clearly that the proposed model was successfully used to improve reading fluency through accelerating the different reading subskills for decoding and create positive attitudes toward reading. The results highlight the importance of establishing a level of automaticity that gives rise to the higher skills of comprehension.

Author 1: Abdulfattah Omar

Author 2: Mohamed Saad Mahmoud Hussein

Author 3: Fahd Shehail Alalwi

Keywords: Collaborative reading model; computer-assisted language learning (CALL); computer-based instruction; EFL learners; fluency; Saudi Universities; struggling readers

Paper 45: Optimal Allocation of DG and D-STATCOM in a Distribution System using Evolutionary based Bat Algorithm

Abstract: In this work, a methodology to find the optimal allocation (i.e., sizing and location) of Distributed Generators (DGs) and Distribution-static compensators (D-STATCOM) in a radial distribution system (RDS) is proposed. Here, the voltage stability index (VSI) is utilized to find the optimal location for the D-STATCOM, and loss sensitivity factor (LSF) method is utilized to find the optimal location for distributed generation. In this work, the proposed work is formulated as a non-linear optimization problem and it is solved using the meta-heuristic/evolutionary-based algorithm. The evolutionary-based Bat algorithm is used to find optimal sizes of D-STATCOM and DGs in RDSs. To check the validity and feasibility and validity of the proposed optimal allocation approach, two standard IEEE 34 and 85 bus RDSs are considered in this paper. The simulation results show reduction in power losses and enhancement in bus voltages in the RDSs.

Author 1: Surender Reddy Salkuti

Keywords: Bat algorithm; distributed generation; voltage stability index; loss sensitivity; optimal location and size; radial distribution system

Paper 46: Analysis of Load Variation Consideration for Optimal Distributed Generation Placement

Abstract: Distributed generation (DG) devices offered usefully for power losses minimization, grid reinforcement, bus voltages improvement and efficiency of a distribution system. Usually, the DG placement problem considers the predefined DG number and sizes that might result in many small DGs. However, a better solution could be reached with a minimum number of DGs, reducing installation and maintenance costs. Furthermore, the increment of load and vice versa may affect the voltage profile below or upper the tolerable limit and distribution feeders. Thus, this paper aims to analyze the impact of the variation of the load level with the DG connection in the power system by using the improved gravitational search algorithm (IGSA) as an optimization technique. The multi-objective function target reduces the total power loss, average total voltage harmonic distortion and voltage deviation in the distribution system. This study is considering six different load levels as in percentage of load. This proposed technique compares with the particle swarm optimization (PSO) and the gravitational search algorithm (GSA). This efficiency of the proposed technique tests on the 33-bus radial distribution system with six case studies.

Author 1: Aida Fazliana Abdul Kadir

Author 2: Mohamad Fani Sulaima

Author 3: Noor Ropidah Bujal

Author 4: Mohd Nazri Bin Abd Halim

Author 5: Elia Erwani Hassan

Keywords: Distribution generation; optimization techniques; IGSA; losses minimization; optimal placement and sizing

Paper 47: Resource Utilization Prediction in Cloud Computing using Hybrid Model

Abstract: In cloud environment, maximum utilization of resource is possible with good resource management strategies. Workload prediction plays a vital role in estimating the actual resource required for successful execution of an application on cloud. Most of the existing works concentrated on predicting workloads which either showed clear seasonality/trend or for irregular workload patterns. This paper presents a new perspective in forecasting both seasonal and non-seasonal workloads. To accomplish this, a hybrid prediction model which is a combination of statistical and machine learning technique is proposed. Suppose the seasonality exists in the workload pattern, Seasonal Auto Regressive Integrated Moving Average (SARIMA) model is applied for prediction. For non-seasonal workloads Long Short-Term Memory networks (LSTM) or AutoRegressive Integrated Moving Average (ARIMA) model is used based on the results of normality test. This paper presents a prediction model which forecasts the actual resource required for diverse time intervals of daily, hourly and minutes utilization. The experimental results confirm that accuracy of the prediction of LSTM model outperformed ARIMA for irregular workload patterns. The SARIMA model accurately forecasts the resource usage for forthcoming days. This work actually helps the cloud service provider (CSP) to analyze the workload and predict accordingly to avoid over or under provisioning of the cloud resources.

Author 1: Anupama K C

Author 2: Shivakumar B R

Author 3: Nagaraja R

Keywords: Workload prediction; SARIMA; LSTM; ARIMA; cloud service provider

Paper 48: An Experiment for Outdoor GPS Localization Enhancement using Kalman Filter with Multiantenna Consumer-Grade Sensors

Abstract: Consumer-Grade global positioning system (GPS) is widely used in many domains. The obvious issue of this consumer-grade device is low accuracy and reading fluctuation results. In terms of using an application that requires a more precise location, the output could be difficult. In this study, the authors deploy various methods to reduce the global positioning system data fluctuation and present field test results. Two main types of the device worked together to collect data from global positioning systems, such as Microcontroller for algorithm processing and presenting data and global positioning system receivers for receiving data from a satellite. We combine three global positioning system modules to received signals in a single device and test calculated data compared with the Kalman filtering methods in many cases, including moving and static devices. Implementing the Standard Kalman Filter to multiple global positioning system Modules has improved the constancy of cheap global positioning system equipment. The experiment algorithm is presented significant improvement to overcome the retrieved data fluctuation problem. This study's contribution will enable creating a cheap global positioning system locator device for various applications that require more accuracy than the standard consumer-grade receiver.

Author 1: Phudinan Singkhamfu

Author 2: Parinya Suwansrikham

Keywords: Global positioning systems accuracy; kalman; multi global positioning systems; global positioning systems pointer; global positioning systems enhance; filtering algorithm

Paper 49: Artificial Intelligence Model based on Grey Clustering for Integral Analysis of Industrial Hygiene Risk

Abstract: The article proposes a model with an artificial intelligence approach that integrates risks through the Grey Clustering method applying the "Triangulation of center-point based on Whitening functions -CTWF", for this, the data established is standard data (minimum standards that the four workshops of a company in the industrial sector must meet) and sampled data (real data obtained in the field) to test the grey classes. In this study, the different types of risks (lighting, noise and hand-arm vibration) were globally evaluated and analyzed in the four workshops of a heavy machinery maintenance services company in the industrial sector (welding shop, hydraulic shop, machine shop 1 and machine shop 2), located in Lima, Peru. According to the results obtained from the level of hygienic quality in each workshop, the welding workshop is at a very poor-quality level, while the others are at a good and very good level; regarding the four workshops, it was determined that the noise level is not recommended as they do not meet the minimum required standards. Therefore, control measures were proposed in the four workshops where the level of irrigation is bad and very bad. This study will benefit companies in the industrial sector that need to analyze the level of hygienic quality in their work areas with a global approach in order to apply control measures with prevention, protection of health and physical integrity of workers.

Author 1: Alexi Delgado

Author 2: Diana Aliaga

Author 3: Cristian Carlos

Author 4: Lisseth Vergaray

Author 5: Chiara Carbajal

Keywords: Artificial intelligence; grey clustering; industrial hygiene; lighting; noise

Paper 50: Intelligent Traffic Light Controller using Fuzzy Logic and Image Processing

Abstract: Today's traffic congestion in the big city is a serious problem, as it causes a lot of environmental pollution and difficulty in transportation, which leads to difficult daily life for the human beings in addition to material losses. In this work a smart traffic light controller was designed using fuzzy logic and image processing with MATLAB, to control movement in two ways, aided by a camera and auto sensors. The Fuzzy logic has two inputs and six outputs designed, the console input is the number of cars on each road and the time of the assumed red, yellow and green signal according to the vehicles congestion. The simulation result is similar to the proposed control unit, as it deals with the lights simultaneously according to the number of cars in each branch of the road, which leads to the use of all the time to operate the stoplights. Our system can be employed in solving the problem of traffic congestion in the big cities or the smart cities.

Author 1: Abdelkader Chabchoub

Author 2: Ali Hamouda

Author 3: Saleh Al-Ahmadi

Author 4: Adnen Cherif

Keywords: Traffic congestion; smart city; traffic light; fuzzy logic; image processing; objects detections

Paper 51: Private LTE Network Service Management Model, based on Agile Methodologies, for Big Mining Companies

Abstract: Information technology (IT) services must generate added value for any business, either by enhancing its processes, automating its activities, or managing its resources. Using Long Term Evolution (LTE) Networks, IoT solutions and devices are able to be deployed in order to prevent safety incidents and or to online monitor performance and maintenance indicators produced by field equipment. Under the same context, implementing a private LTE network Service Management Model becomes a basic need for any company. Proposed Service Management model must be flexible enough to changes in order to accomplish high productivity demands like the ones that a Big Mining Company requires. Proposed model is based on Information Technology Infrastructure Library (ITIL) as the best known, disseminated and proven framework; additionally, it uses well known agile methodologies such as Scrum and DevOps. Along with the deployment for each of the proposed stages, a visual scheme is generated which, when it comes to a conclusion at the final stage, allows to visualize model interactions in its entirety. In addition to describing the expected results, model validation has been accomplished by an expert panel judgment under the developed topic. As a conclusion, proposed model involves a holistic approach, that is, a comprehensive approach that addresses various aspects of service management supported by a private LTE platform.

Author 1: José Valdivia-Bedregal

Author 2: Norka Bedregal-Alpaca

Author 3: Elisa Castañeda-Huaman

Keywords: IT service management; agile methodology; ITIL; expert judgment; LTE network

Paper 52: Speeding up Natural Language Text Search using Compression

Abstract: Text search is a well-known problem in computer science where the valid shifts of a pattern P in a text string T are found. This paper shows how to speed up text search by searching for P in a compressed version of T. A fast compression algorithm was designed for this aim. This algorithm is based on the assumption that T is restricted to the letters of a single natural language. Relying on this assumption, a letter, in T or P, is encoded into a single byte instead of the two-byte unicode which shortens the string on which a text search algorithm works. The main disadvantage of this approach is the restriction of the alphabet of T to be from a single natural language. However, wide range of text documents comply to this assumption. Another issue is the overhead that is required to compress P and T, but it was found that the proposed compression algorithm is so fast such that its run-time can be paid for and still save text search time. Different approaches to store compressed T are also explored. The conducted experimental study showed that this approach does actually reduce the text search time.

Author 1: Majed AbuSafiya

Keywords: Text compression; text search; unicode

Paper 53: Developing an IoT Platform for the Elderly Health Care

Abstract: The health care of elderly people addresses the necessity for services that utilize recent technologies and devices. Now-a-days, both loneliness and psychological depressions are typical problems which elderly people face because of living alone/abandoned or reduced communication with their children and relatives. This paper presents the development of an integrated platform using the Internet of Things to manage and provide extensive services for elderly people to address the aforementioned issues. The proposed platform relies on wearable sensor devices to collect real-time data and store it in a cloud server via a developed smartphone application. The cloud server is accessed to retrieve data stored using the OAuth protocol. A web-based database-driven application is developed that facilitates the management of helpful information about elderly people to an authorized person. The doctors can perform real-time monitoring of the health condition of their elder patients remotely, and the system generates an alarm and sends notifications to caregivers and doctors in case of emergency. The conducted experiments and the achieved results showed that the developed platform has remarkable features of accessibility, security, efficiency, and cost.

Author 1: Medhat Awadalla

Author 2: Firdous Kausar

Author 3: Razzaqul Ahshan

Keywords: Internet of things; healthcare; sensor network; real-time monitoring; wearable sensors; wireless sensor networks

Paper 54: Study and Analysis for the Choice of Optical Fiber in the Implementation of High-Capacity Backbones in Data Transmission

Abstract: Fiber optic implementation projects for backbones today have become a necessity, where in many cases failures due to cable stress breaks have been reported. Due to this, it is necessary to carry out a study and analysis of the zone and area prior to implementation. In this research work, through a method based on theory and analysis, the geographical and climatological conditions where the optical fiber will be installed in the Lima region, Peru, will be evaluated, as well as the study of mechanical loads and electric fields associated with the installation of fiber optics on existing electrical network lines will also be carried out. The results of this study showed that for regional backbone projects in the city of Lima, Peru, the use of the type of optical fiber should be considered under the recommendation of the International Telecommunications Union (ITU) -T G.652.D All -Dielectric Self-Supporting (ADSS). The studies and results obtained in this research may also help the various companies in the sector, in future implementations of high-capacity fiber optic backbones in data transmission, to make the best decision on the type of cable and its recommended characteristics for the region.

Author 1: Wilmer Vergaray-Mendez

Author 2: Brian Meneses-Claudio

Author 3: Alexi Delgado

Keywords: Mechanical loads; electric fields; backbones; optical fiber; data transmission

Paper 55: On State-of-the-art of POS Tagger, ‘Sandhi’ Splitter, ‘Alankaar’ Finder and ‘Samaas’ Finder for Indo-Aryan and Dravidian Languages

Abstract: Computational Linguistic refers to the development of the computer systems that deal with human languages. In this paper, different Computational Linguistic Techniques such as Parts of Speech (POS) tagger, ‘Sandhi’ Splitter, ‘Alankaar’ Finder and ‘Samaas’ Finder were considered. After a thorough literature review, it was found that fifteen techniques were used for POS tagging, nine techniques were used for ‘Sandhi’ splitting, one work is done for ‘Alankaar’ finder and absolutely no techniques are available for ‘Samaas’ finder for the Indo-Aryan as well as Dravidian languages. Analysis shows that Rule Based Approach (RBA) and Hidden Markov Model (HMM) are frequently used for POS tagging, RBA is most frequently used for ‘Sandhi’ Splitter, the general Human Intelligence (HI) is used for ‘Alankaar’ Finder and no ‘Samaas’ finder technique is available for any Indian language.

Author 1: Hema Gaikwad

Author 2: Jatinderkumar R. Saini

Keywords: ‘Alankaar’; ‘samaas’; ‘sandhi’; parts of speech tagger (POST)

Paper 56: The Development of Students’ Spatial Orientation through the use of 3D Graphics

Abstract: The purpose of this research is to determine to what extent the use of 3D graphics in the educational process improves the spatial orientation skills of secondary school students. The research follows a qualitative approach of experimental type, the population is constituted by 300 students of Secondary Education of which through a simple random sampling 25 students were chosen. Four sessions of 50 minutes each have been developed, in which three-dimensional models were used, in order to determine if spatial skills are developed. A psychometric pre-test and post-test of spatial reasoning was taken in order to determine how much the spatial skills of the selected sample members are developed based on the measurement of five criteria: Construction of three-dimensional objects (intermediate level), Construction of three-dimensional objects (advanced level), Rotation of objects from references (intermediate level), Rotation of objects from references (advanced level) and deconstruction of three-dimensional objects. For the data analysis, the data from the scores obtained by the students in both the pre-test and the post-test are processed. The results allow us to visualize that the use of 3D graphics in the teaching-learning processes allows us to improve spatial orientation skills to a great extent. The result is evidenced in the increase of the total scores obtained in the post-test in comparison with the results of the pre-test. Likewise, an increase from 47.9% to 75.1% of items answered correctly was observed on average, which was corroborated with the Student's t-test that gave a P value of less than 0.05, demonstrating the reliability of the research developed and therefore significantly improving spatial orientation skills in students through the use of 3D graphics technology.

Author 1: Benjamín Maraza-Quispe

Keywords: Orientation; reasoning; spatial; technology; 3D graphics; education; processes; educational

Paper 57: Symptoms-Based Fuzzy-Logic Approach for COVID-19 Diagnosis

Abstract: The coronavirus (COVID-19) pandemic has caused severe adverse effects on the human life and the global economy affecting all communities and individuals due to its rapid spreading, increase in the number of affected cases and creating severe health issues and death cases worldwide. Since no particular treatment has been acknowledged so far for this disease, prompt detection of COVID-19 is essential to control and halt its chain. In this paper, we introduce an intelligent fuzzy inference system for the primary diagnosis of COVID-19. The system infers the likelihood level of COVID-19 infection based on the symptoms that appear on the patient. This proposed inference system can assist physicians in identifying the disease and help individuals to perform self-diagnosis on their own cases.

Author 1: Maad Shatnawi

Author 2: Anas Shatnawi

Author 3: Zakarea AlShara

Author 4: Ghaith Husari

Keywords: COVID-19; coronavirus diagnosis; fuzzy inference system; fuzzy logic; fuzzy rules; expert systems

Paper 58: An Optimization Approach for Multiple Sequence Alignment using Divide-Conquer and Genetic Algorithm

Abstract: Multiple Sequence Alignment (MSA) is a very effective tool in bioinformatics. It is used for the prediction of the structure and function of the protein, locating DNA regulatory elements like binding sites, and evolutionary analysis. This research paper proposed an optimization method for the improvement of multiple sequence alignment generated through progressive alignment. This optimization method consists of a fusion of two problem-solving techniques, divide-conquer and genetic algorithms in which the initial population of MSAs was generated through progressive alignment. Each multiple alignment was then divided vertically into four parts, three genetic operators were applied on each part of the MSA, recombination was done to reconstruct the full MSA. To estimate the performance of the method the results generated through the method are compared with well-known existing MSA methods named Clustal Ω, MUSCLE, PRANK, and Clustal W. Experimental results showed an 11-26% increase in sum_of_pair score (SP score) in the proposed method in comparison to the above-mentioned methods. SP score is the cumulative score of all possible pairs of alignment within the MSA.

Author 1: Arunima Mishra

Author 2: Sudhir Singh Soam

Author 3: Bipin Kumar Tripathi

Keywords: Multiple sequence alignment; divide; and conquer; genetic algorithm; optimization method

Paper 59: Proposed Design of White Sugar Industrial Supply Chain System based on Blockchain Technology

Abstract: The white crystal sugar agro-industry is an industry with dynamic characteristics characterized by a sustainable relationship between actors ranging from farmers to consumers. An inefficient supply chain system will affect the flow of products, information, and finance because many actors are involved and have influence. Hence, complicating the system in the tracking process flow, product flow and creating problems that occur in business processes. The main objective of this research is to propose the design of an integrated white crystal sugar agro-industrial supply chain system based on blockchain technology so that it can increase competitiveness in realizing food security and resilience; by proposing a search for the problem of mismatches that occur along the supply chain from upstream to downstream. The variables that will be identified in the supply chain flow include quality, quantity, and price, with the suitability of transaction information data ranging from farmers, sugar factories, warehouses, distribution, retailers to the final consumer. It is hoped that consumers will feel happy to consume trusted local sugar with the best safety and quality, as well as ensure transparency of information between actors. Previous traditional methods, which were still centralized, would be transformed into decentralized information, to create trust among stakeholders. With a blockchain-based traceability architecture design, it is hoped that the proposed design can be implemented in the white crystal sugar agro-industry.

Author 1: Ratna Ekawati

Author 2: Yandra Arkeman

Author 3: Suprihatin

Author 4: Titi Candra Sunarti

Keywords: Blockchain technology; supply chain; white crystal sugar

Paper 60: Fraud Detection in Shipping Industry using K-NN Algorithm

Abstract: The shipment industry is going through tremendous growth in volume thanks to technological innovation in e-commerce and global trade liberalization. Volume growth also means a rise in fraud cases involving smuggling and false declaration of shipments. Shipping companies and customs are mostly relying on routine random inspection thus finding fraud is often by chance. As the volume increases dramatically it would no longer be sustainable and effective for both shipment companies and customs to pursue traditional fraud detection strategies. Other related papers on this area have proven that intelligent data-driven fraud detection is proven to be far more effective than routine inspections. However, the challenge in data-driven detection is its effectiveness are often reliant on the availability of data and the various fraud mechanism used by fraudsters to commit shipment related fraud. As such in this paper, we review and subsequently identify the most optimized approaches and algorithms to detect fraud effectively within the shipping industry. We also identify factors that influence fraud activity, review existing fraud detection models, develop the detection framework and implement the framework using the Rapidminer tool.

Author 1: Ganesan Subramaniam

Author 2: Moamin A. Mahmoud

Keywords: Fraud detection; shipping industry; k-nn algorithm

Paper 61: Generating Test Cases using Eclipse Environment – A Case Study of Mobile Application

Abstract: In Software Development Life Cycle (SDLC), there are four phases involved. They are analysis, design, implement and testing. Testing is done to ensure the functionalities of the system are correct. There are many approaches to software testing. It is usually divided into two approaches: manual testing or automatic testing. However, these days, with the rapidly advanced technology, performing software testing manually has become hugely laborious but still doable. Therefore, experts of the software development field are beginning to go for automatic testing. This paper presents a case study of mobile application and discusses how test cases can be generated automatically from the application using different automatic tools. Three software testing tools have been used to generate test cases automatically. The results from generating test cases automatically from these three tools are then being compared together with the results of generating test cases using manual testing technique.

Author 1: Rosziati Ibrahim

Author 2: Nurul Ain Aswini Abdul Jan

Author 3: Sapiee Jamel

Author 4: Jahari Abdul Wahab

Keywords: Software testing; automation testing; test cases; Eclipse Environment

Paper 62: Traffic Accidents Detection using Geographic Information Systems (GIS)

Abstract: The mission of reducing the number and severity of traffic accidents becomes the dominant target of road traffic safety management worldwide. The main objective of this work is to analyze traffic accidents in temporal and spatial frameworks in the capital city Amman and identify hotspot zones in the study area. Several statistical analyses are conducted using SQL to give insight into the temporal distribution of accidents and to identify the most revealing accidents based on several attributes such as the year of accidents, the severity of accidents, road type, and lighting environment which enables the authors to do further investigations on the more frequent accidents. GIS-based statistical and spatial analysis tools are utilized to examine the spatial pattern of accident distribution in the study area for three successive years, hotspots are identified for clusters of high concentrations. The Nearest Neighbor Index (NNI) is used to analyze the pattern of traffic accident distribution based on selective parameters. This was followed by identifying hotspot zones for regions that showed clustering using the optimal hotspot analysis tool. Experimental results showed clustering for all tested groups, and thus hotspots were detected for these accidents in the study area. The importance of this work is in providing a spatial understanding of accident distribution in the capital city of Amman which can help policymakers of road safety setting out efficient strategies for traffic safety management and find optimal solutions as required for factors causing such accidents.

Author 1: Wesam Alkhadour

Author 2: Jamal Zraqou

Author 3: Adnan Al-Helali

Author 4: Sajeda Al-Ghananeem

Keywords: Geographic Information System (GIS); statistical tools; hotspots; spatial analysis; temporal analysis; road safety; traffic accidents; spatial correlation

Paper 63: An Agent-Based Evaluation Model of Students' Emotional Engagement in Classroom

Abstract: This study proposes an agent-based evaluation model of students’ emotional engagement in a classroom. The proposed model consists of four main elements in a classroom which are, the selected strategy to control engagement, the engagement level of students, the emotional state of a lecturer, and the emotional states of students. The process starts with a lecturer selecting a strategy, which in turn influences the students’ emotional state. By utilizing the three variables, students’ misbehaviors, motivation, and participation, the engagement level of students is measured that eventually influences the lecturer’s emotion either positively or negatively. If negatively, the lecturer proposes another strategy that would trigger the students’ emotions and eventually improves the students’ engagement level. We simulate our model to validate the applicability and functionality of the model. The simulation result shows a promising application to simulate a classroom environment with very flexible settings that leads to results in less time and cost. It also shows to be widely utilized by researchers in the field of social studies for further investigation of the problem of students’ engagement by conducting experiments and report the results.

Author 1: Moamin A. Mahmoud

Author 2: Latha Subramainan

Author 3: Ihab L Hussein Alsammak

Author 4: Mahmood H. Hussein

Keywords: Students’ emotional engagement; agent-based evaluation; computational model

Paper 64: Wireless Body Area Sensor Networks for Wearable Health Monitoring: Technology Trends and Future Research Opportunities

Abstract: Today, there is an emerging interest in Wireless Body Area Sensor Networks (WBASNs) for the real-time monitoring of patients and early chronic disease detection. In this context, this paper presents a synopsis survey of healthcare monitoring via the IEEE 802.15.6 (UWB) protocol. We intend to propose a survey of the current issues of wearable physiological monitoring signals and devices, application areas, and reliability in WBASNs. To help elderly and disabled people, it would be beneficial to use a wireless transportable gadget at home to gather useful data in traditional human activities. This will manage regular hospital and emergency department appointments and will monitor crucial physiological signals real-time. This paper will also present a study on new wireless technologies intended for body area sensor networks, including signal processing problems, spectral allocation, security, and future research challenges of WBASNs.

Author 1: Malek ALRASHIDI

Author 2: Nejah NASRI

Keywords: Healthcare; physiological signals; security; UWB; wireless technologies; WBASN

Paper 65: A-SA SOS: A Mobile- and IoT-based Pre-hospital Emergency Service for the Elderly and Village Health Volunteers

Abstract: In Thailand, emergency illnesses are life-threatening conditions that constitute serious health problems and quick access to definitive care can improve the survival rate of the elderly dramatically. Currently, the pre-hospital emergency medical services have limitations which prevent the treatment from getting to the accident site on time. In this research, we proposed the A-SA SOS application, a mobile-and IoT-based pre-hospital emergency service for the elderly. The system helps the elderly to send the request to the nearest village health volunteers via a mobile application and smart device. After reaching the elderly, the village health volunteers help carry out basic life support to increase the survival rate before sending the patients directly to the Emergency Management System (EMS) agency. To evaluate the system, we tested it for three months in the Sub-district of Suthep in Chiang Mai city. Finally, the incident report showed that the average time to reach the scene (4.91±0.56) to help elderly patients was less than the standard criteria of an average 3 minutes.

Author 1: Kannikar Intawong

Author 2: Waraporn Boonchieng

Author 3: Peerasak Lerttrakarnnon

Author 4: Ekkarat Boonchieng

Author 5: Kitti Puritat

Keywords: Pre–hospital emergency service; mobile healthcare; IoT-based healthcare system; elderly; healthcare volunteer

Paper 66: An Effective Approach for Detecting Diabetes using Deep Learning Techniques based on Convolutional LSTM Networks

Abstract: The most common disorder affecting millions of population worldwide due to insufficient release of insulin by pancreas is diabetes. Early detection or precaution of diabetes is necessary, otherwise leads to many complicated problems. Predicting diabetes at early stages with appropriate treatment, individuals can maintain a happy life. If the conventional diabetes detection method is tedious, the identification of diabetes from clinical and physical data requires an automated system. This paper proposes an approach to enhance diabetes prediction using deep learning techniques. Based on the Convolutional Long Short-term Memory (CLSTM), we developed a diabetes classification model and compared with the existing methods on the Pima Indians Diabetes Database (PIDD). We assessed the findings of various classification approaches in this study. The proposed approach is further improved by an efficient pre-processing mechanism called multivariate imputation by chained equations. The outcomes are promising compared to existing machine learning approaches and other research models.

Author 1: P. Bharath Kumar Chowdary

Author 2: R. Udaya Kumar

Keywords: Convolutional long short-term memory; diabetes prediction; machine learning; pre-processing

Paper 67: Identification of Babbitt Damage and Excessive Clearance in Journal Bearings through an Intelligent Recognition Approach

Abstract: Journal bearings play an important role on many rotating machines placed on industrial environments, especially in steam turbines of thermoelectric power plants. Babbitt damage (BD) and excessive clearance (C) are usual faults of steam turbine journal bearings. This paper is focused on achieving an effective identification of these faults through an intelligent recognition approach. The work was carried out through the processing of real data obtained from an industrial environment. In this work, a feature selection procedure was applied in order to choose the features more suitable to identify the faults. This feature selection procedure was performed through the computation of typical testors, which allows working with both quantitative and qualitative features. The classification tasks were carried out by using Nearest Neighbors, Voting Algorithm, Naïve Associative Classifier and Assisted Classification for Imbalance Data techniques. Several performance measures were computed and used in order to assess the classification effectiveness. The achieved results (e.g., six performance measures were above 0.998) showed the convenience of applying pattern recognition techniques to the automatic identification of BD and C.

Author 1: Joel Pino Gómez

Author 2: Fidel E. Hernández Montero

Author 3: Julio C. Gómez Mancilla

Author 4: Yenny Villuendas Rey

Keywords: Journal bearing; babbitt damage; excessive clearance; fault identification; feature selection; supervised classification

Paper 68: An Empirical Investigation of the Relationship Between Business Process Transparency and Business Process Attack

Abstract: Business Process Management (BPM) is a management approach to discover, analyze, redesign, execute and monitor business processes. Implementing BPM concepts help and benefit organizations by increasing their productivity, achieving their strategies and operational excellence, and saving costs. Rosemann et al. identify business process transparency as one of the key values of BPM, and essential to achieving other BPM benefits. Business process transparency provides visibility about how operations/activities are conducted in a detailed way, sometimes with technical details, within an organization; which facilitates the identification of structural issues of the process model. A conducted content analysis of the literature shows that fraudsters have leveraged structural issues of the business process model to commit fraud. Such fraud can be labeled as a Business Process Attack (BPA). In analogy to information system security attack, BPA can be defined as the exploitation of a vulnerability in a business process model to commit fraudulent activities that influence the business negatively such as achieving invalid or unwanted results. This research aims to investigate the relationship between the degree of business process transparency and exposure to BPA. If the relationship is positive, appropriate security controls shall be implemented on the business process transparency to avoid BPA. The main research question is: What is the relationship between an organization's degree of business process transparency and exposure to BPA. A quantitative research method is employed to measure and understand the impact of business process transparency on BPA. An experiment is designed and conducted to assess the awareness of the existence of vulnerabilities in various process models and how to exploit them to commit BPA. Results show that there is a positive significant relationship between increased business process transparency and exposure to BPA. This research contributes towards understanding and highlights the negative impact of business process transparency, which motivates researchers to investigate this phenomenon and find appropriate solutions.

Author 1: Alhanouf Aldayel

Author 2: Ahmad Alturki

Keywords: Business Process Management (BPM); business process; transparency; business process attack; fraud

Paper 69: A Tree-profile Shape Ultra Wide Band Antenna for Chipless RFID Tags

Abstract: In this article, a new small size planar microstrip tree profile shaped Ultra-Wide Band (UWB) antenna with partial ground plane has been presented. The antenna is designed for chipless RFID tags that are working in UWB region. The operating frequency of the antenna is between 2.72 GHz to 11.1 GHz which covers the entire UWB frequency band. The antenna exhibits comparatively high realized gain of 4.2 dBi with respect to its small size of 27 × 40 mm2 and have a gain to aperture ratio of 0.243 which is comparatively higher than other existing retransmission-based chipless RFID antennas. Another aspect of this antenna is its total efficiency which never goes below 80% throughout the entire bandwidth whereby it reaches as high as 96% at 3.5GHz. This design will motivate the chipless RFID designers to produce small size and cost effective tags.

Author 1: A K M Zakir Hossain

Author 2: Nurulhalim Bin Hassim

Author 3: Jamil Abedalrahim Jamil Alsayaydeh

Author 4: Mohammad Kamrul Hasan

Author 5: Md. Rafiqul Islam

Keywords: Planar microstrip; UWB antenna; chipless RFID; realized gain; total efficiency

Paper 70: Non-Hodgkin Type Lymphoma Cancer Cell Detection using Connected Components Labeling and Moments of Image

Abstract: Cancers are one of the deadliest diseases with a costly treatment system in the world at present. In this paper a cost-effective, autonomous system of cancer-cell detection was proposed using several efficient image processing methods to develop an early stage non-Hodgkin type lymphoma which is a type of blood cancer. The system is implemented automatically to detect the traits of cancer in microscopy images of biopsy samples. Recent attempts have previously lacked flexibility in characteristics and the accuracy level is not consistent with the individual cancer type. The framework consisted three stages for detecting cancer on the basis of various detected traits including cell segmentation, quantification, area measurement analysis of cells, a center clump detection using the moment of image, identification of 4-connected components and Moore-Neighbor tracing algorithm. This methodology has been used in several sets of images and Feedback from these test executions has been used to improve the system. Subsequently, the proposed method can be used efficiently for used for autonomous non-hodgking type lymphoma cancer cell detection, which has an accuracy of 93.75%.

Author 1: Monirul Islam Pavel

Author 2: Mohsinul Bari Shakir

Author 3: Dewan Ahmed Muhtasim

Author 4: Omar Faruk

Keywords: Non-hodgking; lymphoma; moment of image; connected components labeling; otsu thresholding

Paper 71: Grey Clustering Method for Water Quality Assessment to Determine the Impact of Mining Company, Peru

Abstract: Mining operations have a significant impact on environment, where the quality of water is an important affected issue that need to be controlled. In that way, the Grey Clustering Method based on center-point triangular whitenization weight (CTWF), is an artificial intelligence criterion that evaluates water samples according to selected parameters, in order to realize an effective water quality assessment. In the present study, the analysis is made on the Crisnejas River Basin, by using fifteen monitoring points based on an investigation realized by the National Water Authority (ANA) in 2019, based on the Peruvian law (ECA) about water quality standards. The results reveal that almost all of the monitoring points on the Crisnejas River Basin were classified as “irrigation of vegetables unrestricted”, but only one point was classified as “animal drink”, which is ubicated in an urbanized area. This implies that mining discharges are being well treated by the company, but another deal is the contamination generated in towns. Further, the present study might be helpful to audit processes made by the state or companies, to justify the quality of surface waters using a more accurate methodology.

Author 1: Alexi Delgado

Author 2: Jhoel Andy Gauna Achata

Author 3: Jorge Alfredo Barreda Valdivia

Author 4: Julio Cesar Junior Santivañez Montes

Author 5: Chiara Carbajal

Keywords: Grey clustering method; mining company; water quality; artificial intelligence

Paper 72: Analysis of Speech Signal Data of Mising Vowels using Logistic Regression and K-Means Clustering

Abstract: In this paper, an attempt has been made to study and analyze speech signal data. Here, the sound or speech data has different attributes like time, pitch, formant frequencies, speaker type, Vowel No etc. The dataset used here is speech signal data which are analog in nature and has been converted to digital format. After converting the data into digital format we want to establish a Logit model to predict the speaker gender on the basis of the pitch signal values which is also considered as fundamental formant frequency. That is our objective is to predict whether a speaker is male or female by looking at the pitch value by using logistic regression. We have applied clustering techniques to visualize and interpret how it works in speech signal data. The logistic model gives us 91% accuracy rate with low and efficient AIC value where as in case of the clustering algorithm we get a 93% accuracy for the whole sample.

Author 1: Ujjal Saikia

Author 2: Jiten Hazarika

Keywords: Clustering methods; formant frequency; logit model; pitch; stype

Paper 73: Hybrid SFLA-UBS Algorithm for Optimal Resource Provisioning with Cost Management in Multi-cloud Computing

Abstract: Multi-cloud is a vendor-based heterogeneous cloud paradigm in recent era of computing with dynamic infrastructural deployment. Multi-cloud provides all the essential and on-demand requirements of a virtual environment from various domains under a single service level agreement (SLA). Consumers from multitier domains can access all the available resources placed in a shared pool on service provider’s side, as per their requirement. The shared pool of resources creates complexity in assigning the best and suitable resource to a particular virtual instance under the same services provider end. The complexity of resources in terms of accessibility from the various domains, dynamic allocation, security, and quality of services (QoS) raises concerns in the multi-cloud infrastructure. This complexity raise concern relates to optimal provisioning and cost management. In the proposed work a hybrid technique with a shuffled leapfrog algorithm and ubiquitous binary search (SLFA-UBS) to resolve these issues with optimal provisioning, dynamic allocation and better resource selection. The proposed work will help to create a need-based and demand-based resource pool with the appropriate selection of each resource. The proposed model also supports resource optimization with dynamic provisioning, cost-effective solution to achieve QoS in multi-cloud deployment on service provider end.

Author 1: Muhammad Iftikhar Hussain

Author 2: JingSha He

Author 3: Nafei Zhu

Author 4: Fahad Sabah

Author 5: Zulfiqar Ali Zardari

Author 6: Saqib Hussain

Author 7: Fahad Razque

Keywords: Optimal provisioning; resource allocation; multi-cloud; cost management; QoS and selection of resources

Paper 74: Software Engineering Ethics Competency Gap in Undergraduate Computing Qualifications within South African Universities of Technology

Abstract: Computing graduates working as software engineers are expected to demonstrate competencies in various categories of software engineering ethics as a component of non-technical skills that complement technical skills. Therefore, university programme offerings should provide opportunities for students to develop software engineering ethical competence. This study analyses curriculum documents to determine the extent to which entry-level undergraduate computing qualifications of Universities of Technology (UoTs) in South Africa provide opportunities to empower students with software engineering ethical competence. We used summative content analysis to analyze texts within the UoT computing undergraduate qualifications related to software development as retrieved from the South African Qualifications Authority database. ATLAS.ti text analysis tool was used to classify texts according to predetermined software engineering ethics categories to determine the extent to which the qualifications under study expose students to software engineering ethics. The results show that the coverage of the various categories of software engineering ethics by UoT computing qualifications for software development is insufficient, incomplete and superficial, providing only limited opportunities for prospective software engineers to develop software engineering ethical competence. Lack of adequate inclusion of software engineering ethics by UoT qualifications in South Africa deprives prospective software engineers an opportunity to develop ethical competence required to become ethically successful software engineers. Such limited exposure by software development graduates risks the development of potentially unethical software products in the software industry.

Author 1: Senyeki M. Marebane

Author 2: Robert T. Hans

Keywords: Software engineering ethics; software engineer; technical skills; knowledge; curriculum; professional ethics; general ethics; university of technology

Paper 75: Healthcare Logistics Optimization Framework for Efficient Supply Chain Management in Niger Delta Region of Nigeria

Abstract: Optimizing logistics allocation and utilization is essential for effective healthcare management. Apparently, less consideration is given to it in most hospitals in Nigeria where less resources are allocated to health sector in yearly budgetary. Hospital consists of several patient classes, each of which follows different treatment process flow paths over a multiphase and multidimensional requirement with scarce resources and inadequate space. Despite the small budget provision made for healthcare resources, patient’s demands for better service is rapidly experiencing upsurge. Hence, efficient and optimal solutions are required to lessen costs of healthcare service towards enhancing Quality of Care (QoC) and Quality of Experience (QoE) in most public healthcare sector. However, certain control coefficients like the absence of a Dedicated Logistics Department (DLD) in the medical facilities actually limit the efforts of stakeholders. This paper proposed a Computational framework to assess various strategic and operational decisions for optimizing the multiple objectives using Type-1 Fuzzy Logic Model. In phase I, we explore healthcare resource allocation plan. In phase II, we determine a resource utilization schedule by patient class for daily operational level. While in Phase III, we develop a framework capable of evaluating and optimizing healthcare logistics using control coefficients of Logistics Optimization (LO), Integration of Information/Cognitive Technologies (ETA), and Collaboration of all Logistics Stakeholders (COL). We assigned weights between 1 and 10 to the coefficients and modeled the effects on efficient supply chain. Finally, we further explore the effects of separate strategies and their combination to identify the best possible resource supply chain. The computational experiment was considered on the basis of data obtained from a study conducted on a typical public healthcare department. Results shows that our approach significantly evaluate and optimized healthcare logistics.

Author 1: Imeh J. Umoren

Author 2: Ubong E. Etuk

Author 3: Anietie P. Ekong

Author 4: Kingsley C. Udonyah

Keywords: Dedicated logistics department (DLD); Quality of Care (QoC); Quality of Experience (QoE); information/cognitive technologies (ETA) and type-1 fuzzy logic model

Paper 76: A Data Science Framework for Data Quality Assessment and Inconsistency Detection

Abstract: Retracted: After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IJACSA`s Publication Principles. We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

Author 1: Anusuya Ramasamy

Author 2: Berhanu Sisay

Author 3: Amanuel Bahiru

Keywords: Data Science; OMD data model; weight generation; min-sum; dynamic programming algorithm

Paper 77: Investigation of Smart Home Security and Privacy: Consumer Perception in Saudi Arabia

Abstract: One of the fastest and most developing technologies around the globe is the Internet of things (IoT). The research questions in this study focus on the security and privacy challenges for a smart home environment. The geographical region of Saudi Arabia is the selected boundary for the study. The study is focused on finding the problems associated with the Smart Home adaption in Saudi Arabia. However, there is a large phase shift, which is seen towards the increase of threats in smart homes. It is believed that the awareness by humans towards the use of these devices. The level of security offered by the devices, is one of the factors for these threats and privacy issues. This research targets to identify all the facts that can be discarded towards adaption of Smart Homes. It is desirable that a quantitative methodology must be implemented for identification of the population under threat due to IoT devices in smart homes. The views of the users are the major input values to trace the problems. The expected results from this research will provide all the factors which can be improved and provided with proper solution to avoid any security or privacy threats in the Saudi Arabian realm.

Author 1: Omar Almutairi

Author 2: Khalid Almarhabi

Keywords: Smart home; IoT; Saudi Arabia; security; privacy; issues; demographic; perception; consumer

Paper 78: Smart Company System using Hybrid Nomenclature of Neural Network

Abstract: Physically, to manage the data related to the products, CRM, suppliers and Administration warehouse of the company makes us use a lot of human resources, and a time which deals with this, consequently the error rate increases and sometimes everything goes out of control, however, this work designed an intelligent overall management system (an intelligent neural network) which completes and up-date the product management network that presented in one of the previous articles. This new version assembles the three modules, in an order to automate tasks in the real time.

Author 1: Mbida Mohamed

Author 2: Ezzati Abdellah

Keywords: Neural; network; intelligent; CRM; company; warehouse; real time

Paper 79: Handling Sudden and Recurrent Changes in Business Process Variability: Change Mining based Approach

Abstract: Changes are random and unavoidable actions in business processes, and they are frequently overlooked by managers, especially when managers need to deal with a collection of process variants. Because they must manage every single business process variant separately which is a time-consuming task. They exist many approaches to manage a collection of business process and deal with variability. Such as process mining approaches, that can discover configurable business process models, enhancing them and verify conformity automatically. However, those approaches do not cover changes and concept drift that occur over time. This paper presents a novel change mining approach that discovers changes in a collection of event logs and reports them on a change log. This change log can be analyzed to determine whether the changes are sudden or recurrent and recommend afterward some improvement to the configurable process model.

Author 1: Asmae HMAMI

Author 2: Hanae SBAI

Author 3: Mounia FREDJ

Keywords: Component; variability; process variant; configurable process model; process mining; change mining; concept drift

Paper 80: The Effect of Different Dimensionality Reduction Techniques on Machine Learning Overfitting Problem

Abstract: In most conditions, it is a problematic mission for a machine-learning model with a data record, which has various attributes, to be trained. There is always a proportional relationship between the increase of model features and the arrival to the overfitting of the susceptible model. That observation occurred since not all the characteristics are always important. For example, some features could only cause the data to be noisier. Dimensionality reduction techniques are used to overcome this matter. This paper presents a detailed comparative study of nine dimensionality reduction methods. These methods are missing-values ratio, low variance filter, high-correlation filter, random forest, principal component analysis, linear discriminant analysis, backward feature elimination, forward feature construction, and rough set theory. The effects of used methods on both training and testing performance were compared with two different datasets and applied to three different models. These models are, Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest classifier (RFC). The results proved that the RFC model was able to achieve the dimensionality reduction via limiting the overfitting crisis. The introduced RFC model showed a general progress in both accuracy and efficiency against compared approaches. The results revealed that dimensionality reduction could minimize the overfitting process while holding the performance so near to or better than the original one.

Author 1: Mustafa Abdul Salam

Author 2: Ahmad Taher Azar

Author 3: Mustafa Samy Elgendy

Author 4: Khaled Mohamed Fouad

Keywords: Dimensionality reduction; feature subset selection; rough set; overfitting; underfitting; machine learning

Paper 81: A Sentiment Analysis of Egypt’s New Real Estate Registration Law on Facebook

Abstract: In response to the increasing influence of social media networks on shaping the public opinion, sentiment analysis systems and applications have been developed to extract insights and gain an overview of the wider public opinion behind certain topics so as to support businesses, manufacturers, government agencies, and policymakers with their decisions and plans. Despite the importance of sentiment analysis in providing policymakers with effective mechanisms to understand the attitudes of customers and citizens which can be usefully used in decision-making processes and planning for the future, so far studies on sentiment analysis are very limited in Egypt. Much of the work is still done using survey tools such as questionnaires and polls to gather information about the citizens’ attitudes towards given issues and topics. Despite the effectiveness of such methods, citizens’ reflections on social media platforms and networks remain more powerful in providing comprehensive insights and overviews. Furthermore, social media-based sentiment analysis is usually more representative being based on larger numbers of participants, which has positive implications to reliability. Opinions expressed on social media are often the most powerful forms of feedback for businesses because they are given unsolicited. In light of this argument, this study seeks to provide a sentiment analysis of Egypt’s New Real Estate Registration Law on Facebook. To extract information about the users’ sentiment polarity (positive, neutral or negative), Facebook posts were used. The rationale is that Facebook is still the most popular social media platform in Egypt. Text classification was then used for classifying the selected data into three main classes/values: Positive, Negative, and Neutral. The findings indicate that sentiments expressed in the users’ posts and comments have a significant negative attitude towards the new law. Despite the effectiveness of the automatic evaluation and analysis of the sentiments and opinions of the users in social media concerning the new Real Estate Registration Law, linguistic approaches including Critical Discourse Analysis (CDA), functional linguistics, and semiotics need to be incorporated into sentiment analysis applications for gaining a better understanding of people’s attitudes towards specific issues.

Author 1: Abdulfattah Omar

Author 2: Wafya Ibrahim Hamouda

Keywords: Egypt; facebook; opinion; real estate registration law; sentiment analysis; social media

Paper 82: Factors Affecting Mobile Learning Acceptance in Higher Education: An Empirical Study

Abstract: The use of mobile tools to support learning and teaching activities has become a significant part of the informal learning process. Mobile learning (M-learning) is used to considerably develop the forms of learning activities made by learners, and support the learning process. The effective application of M-learning in higher educational institutions, however, is based on the learners’ adoption. It is therefore essential to define and investigate the factors affecting the desire of learners to use and adopt M-learning. Thus, this research investigates the factors affecting students’ intention to adopt M-learning in institutions of higher education. To achieve the objectives of this research, a model is proposed based on the Unified Theory of Acceptance and Use of Technology (UTAUT) model and the Technology Acceptance Model (TAM). The instrument is developed using validated items from previous studies and shreds of literature. Data for this quantitative study are collected from undergraduate and postgraduate students. A Structural Equation Model (SEM) is used to analyze the data collected from 218 participants using a survey questionnaire. The findings show that students’ intention to adopt M-learning is shaped by various variables consisting of personnel innovativeness, self-management, facilitating conditions, social influence, relative advantage, and effort expectancy. The research results also present several practical contributions and implications for M-learning adoption in terms of research and practice. Investigation of the required determinants may contribute to gain learners’ adoption and is important to enhance the learning experience of students and help them improve their knowledge and academic achievement. The contribution of this paper lies in defining the factors influencing the acceptance and use of M-learning systems by students of higher education in Palestine. Hopefully, the results of the study are valuable for policy-makers in designing comprehensive M-learning systems.

Author 1: Nahil Abdallah

Author 2: Odeh Abdallah

Author 3: OM Bohra

Keywords: Mobile learning; UTAUT; structural equation modeling; tam; technology acceptance

Paper 83: Novel Properties for Total Strong - Weak Domination Over Bipolar Intuitionistic Fuzzy Graphs

Abstract: Through this research study, we introduced and discussed total strong (weak) domination concept of bipolar intuitionistic fuzzy graphs and in define strong domination bipolar intuitionistic fuzzy graph also strong domination. Theorems, examples and some properties of these concept are discussed.

Author 1: As’ad Mahmoud As’ad Alnaser

Keywords: Fuzzy sets; bipolar intuitionistic fuzzy sets; strong (weak) bipolar intuitionistic fuzzy sets; total strong (weak) bipolar intuitionistic number

Paper 84: Performance Comparison of Three Hybridization Categories to Solve Multi-Objective Flow Shop Scheduling Problem

Abstract: The industries must preserve a rate of constant productivity; however, weaknesses appear at the level of production system which engenders high manufacturing costs. Scheduling is considered the most significant issue in the production system, the solution to that problem need complex methods to solve it. The goal of this paper is to establish three hybridization categories of the evolutionary methods ABC and PSO to solve multi-objective flow shop scheduling problem: Synchronous parallel hybridization using the weighted sum method of the fitness function, sequential hybridization using or not using the weighted sum method of the fitness function, and asynchronous parallel hybridization using the weighted sum method of the fitness function. Then to test these methods in an automotive multi-objective flow shop and to perform an in-depth comparison for verifying how the multi hybridization and the hybridization categories influence the resolution of multi-objective flow shop scheduling problems. The results are consistent with other studies that have shown that the multi hybridization improve the effectiveness of the algorithm.

Author 1: Jebari Hakim

Author 2: Siham Rekiek

Author 3: Rahali El Azzouzi Saida

Author 4: Samadi Hassan

Keywords: Scheduling; multi-objective; flow shop; multi hybridization; artificial bee colony ABC; particle swarm optimization PSO

Paper 85: Learners Classification for Personalized Learning Experience in e-Learning Systems

Abstract: The investigators are inspired by the increasing need and the demand for educational applications and the Learning Management Systems which provide learning objects centered on the learning style of the learners. The technique in which the learners acquire, process, gain the information is unique; these unique characteristics affect their learning process. Hence it is essential to consider and understand the uniqueness among the learners to deliver learner-centric learning objects. The investigators present a system to classify the learners based on the time spent by the learner on learning content of different types. The types of learning content are identified with the percentage of visual, auditory, read/write and kinesthetic in learning object. The prominent learning style called VARK (Visual, Auditory, Read/Write and Kinesthetic) is used to classify the learners. This system classifies the learner and recommends the learning objects based on their learning preference, it also facilitates the faculty members or the content creators to prepare and provide personalized learning objects based on the learning style of the learners.

Author 1: A. JOHN MARTIN

Author 2: M. MARIA DOMINIC

Author 3: F. Sagayaraj Francis

Keywords: Learning style; learning profile; learning objects; e-Learning; personalization

Paper 86: Efficient Security Solutions for IoT Devices

Abstract: The Internet of Things (IoT) is a technological innovation that has revolutionized society. The IoT will forever change the way we use simple things that do very little things to smart, fully capable things. IoT devices can process and automate everyday household and workplace tasks through simple sensors. Yet despite the benefits of these devices, they are vulnerable to violations such as privacy issues and security breaches. This paper aims to provide a clearer understanding of the IoT and current threats to it by explaining why IoT devices are susceptible to attack. Moreover, the technologies used in the IoT are examined, as well as the different communication layers of the IoT and their functioning. The findings reveal that IoT devices are prone to many software and hardware vulnerabilities, not to mention the challenges that come with IoT. Solutions to these challenges are proposed, notably through the use of anomaly-based intrusion detection systems, which are critical components of network security. Using machine learning (ML) to detect potential attacks is recommended. Many proposed anomaly-based detection systems use different ML algorithms and techniques. However, there is no standard benchmark to compare these in terms of power consumption. A benchmark that measures both accuracy and power consumption to calculate and evaluate each algorithm’s implementation is proposed.

Author 1: Faleh Alfaleh

Author 2: Salim Elkhediri

Keywords: Efficient; IoT; Systems on a Chip (SoC); ML; Network

Paper 87: Internet of Things (IoT) based Smart Vehicle Security and Safety System

Abstract: The Internet of Things (IoT) is making human life easy in all aspects. The applications it offers are beyond com-prehension. IoT is an abstract idea, a notion which interconnects all devices, tools, and gadgets over the Internet to enable these devices to communicate with one another. IoT finds application in various areas, such as intelligent cars and their safety, security, navigation, and efficient fuel consumption. This project puts forth a solution to achieve the desired outcome of saving precious human lives that are lost to road crashes .In this context, we propose to develop a system, we are designing and deploying a system that not only avoids accidents but also to take action accordingly. This research aims at dealing with the issues that cause fatal crashes and also integrates measures to ensure safety. Life without transportation is impossible to imagine; it makes far off places easy to reach and greatly reduces the travel time. But the problems which surface due to the ever-increasing number of vehicles on the road cannot be ignored. The project aims to eradicate a few of the major reasons of car crashes and also aims to integrate post-crash measures.

Author 1: Yassine SABRI

Author 2: Aouad Siham

Author 3: Aberrahim Maizate

Keywords: Smart vehicle security; safety system; Internet of Things (IoT)

Paper 88: Permissioned Blockchain: Securing Industrial IoT Environments

Abstract: With the significantly increased use of the Industrial Internet of Things (IIoT), it is believed that this technology will revolutionize industrial applications and infrastructures by connecting several industrial assets. But it is getting prone to many cyberattacks and security issues. The emerging security challenges of IIoT can have a devastating effect since it deals with mission and safety-critical systems. Thus, it becomes extremely important to address the security vulnerabilities and susceptibilities of this technology. Blockchain, being one of the most significant solutions to several technologies' security problems, can play a vital role in improving the security of IIoT. Therefore, this paper proposes to use a Hyperledger Fabric Blockchain-enabled IIoT that guarantees the security of the communication medium, data storage, access, and sharing between the IIoT devices and ensures to provide limited access to the authorized identities only. This system also monitors the user access and makes sure that the transactions are performed according to their roles defined by the Certificate Authority (CA) and Membership Service Provider (MSP). Moreover, this paper presents the findings on the implementation of the blockchain network and addresses the key challenges. It evaluates the performance of the proposed network and discusses the key areas to be improved. Finally, the paper describes the benefits of the permissioned blockchain for IIoT and presents a future direction for further research and study.

Author 1: Samira Yeasmin

Author 2: Adeel Baig

Keywords: Industrial Internet of Things; IIoT; permissioned blockchain; hyperledger fabric; information security; device communication; data sharing; access control

Paper 89: A Hybrid Technique based on RSA and Data Hiding for Securing Handwritten Signature

Abstract: Data exchange has been significantly encouraged by the development of communication technology and the wide use of social media over the Internet. Therefore, it is important to hide the data transmitted, especially the data that requires a person’s signature. Where the signature is an increasingly needed item that is used in our daily life to achieve some paper-based authentication in departments, the individual himself needs the signature. Cryptography and steganography are commonly considered to be the most important data hiding methodologies. Steganography is used to hide the secret message in the carrier media, such as text, audio, video, and image files, without the carrier media being distorted, and cryptography is used to conceal the purpose of the secret message. A hybrid data hiding (image steganography) and encryption technique is implemented in this research on the time domain. The secret handwritten signature image is first encrypted using the public key algorithm (RSA) in the proposed technique, then randomly inserted using Embedding data process to be concealed in one of the last three bits of that pixel(1st Least Significant Bit, 2nd LSB, and 3rd LSB) based on mathematical randomized formula over all pixels of the carrier media (image). It is assumed that the process of randomization will increase the protection provided by the technique. The suggested technique is implemented on gray level cover images. As a consequence of the random scattering of bits and using encryption, it is noted that the proposed technique achieves enhanced data hiding results in terms of performance, protection, and imperceptibility properties and the histogram of the proposed technique is better and provides more protection and security than the ordinary sequential Least Significant Bit (LSB).

Author 1: Yaser Maher Wazery

Author 2: Shimaa Gamal Haridy

Author 3: AbdElmegeid Amin Ali

Keywords: Image Steganography; LSB; Data Hiding; Security; Embedding data; Cryptography; RSA; Handwritten signature

Paper 90: Design and Performance Measurement of Energy-based Acoustic Signal Detection with Autonomous Underwater Vehicles

Abstract: The Autonomous Underwater Vehicles (AUVs) in-dustry is still awaiting its Henry Ford to bring to the market solutions that are well adapted to the challenge of underwater exploration. This will certainly be done by the advent of small connected drones equipped with small sensors and embedded devices, allowing AUVs to operate in a coordinated swarm, at a unit price so affordable that we can consider deploying hundreds, or even thousands simultaneously, to be able to observe the ocean with an instrument of a size finally adapted to its immensity. The scope of this work is to build a high performance and low-cost embedded device easy to mount onboard small AUVs and implementing energy-based spectrum sensing algorithms in order to detect targets underwater using acoustic waves. The principle of design, hardware architecture and real-time implementation of the acoustic signal processing chain are described in this paper. Simulations and sea experiments have been conducted successfully and qualified the performance of the realized system to detect acoustic pings underwater depending on the signal-to-noise ratio (SNR). Moreover, this paper proposes methods to improve the measured detection range and accuracy.

Author 1: Redouane Es-sadaoui

Author 2: Jamal Khallaayoune

Author 3: Tamara Brizard

Keywords: Autonomous Underwater Vehicles (AUVs); acoustic signal processing; spectrum sensing; energy detection

Paper 91: A New Corner Detection Operator for Multi-Spectral Images

Abstract: Corner detection is a crucial image processing technique that has a wide range of application, including motion detection, image registration, video tracking, and object recogni-tion. Most proposed approaches for corner detection are based on gray-scale images, despite it has been shown that color infor-mation can greatly improve the quality of corners detection. This paper aims to introduce a new operator that identifies the second-order image information for multi-spectral images. The operator is developed using the multi-spectral gradient and differential structures of the image. Consequently, the eigenvectors of the proposed operator are used for detecting corners. A comparative study is conducted using synthetic and real images, and the result confirms that the proposed approach performs better compared with two other approaches for detecting corners.

Author 1: Hassan El Houari

Author 2: Ahmed Fouad El Ouafdi

Keywords: Corner detection; multi-spectral; operator

Paper 92: Fast Fractal Coding of MRI Images using Deep Reinforcement Learning

Abstract: This paper presents an algorithm based on Fractal theory by using Iterated Function Systems (IFS). An efficient and fast coding mechanism is proposed by exploiting the self similarity nature in the Brain MRI images. The proposed algorithm utilizes Deep Reinforcement Learning (DRL) technique to learn the transformations required to recreate the original image. We avail of the Adaptive Iterated Function System (AIFS) as the encoding scheme. The proposed algorithm is trained and customized to compress the Medical images, especially Magnetic Resonance Imaging (MRI). The algorithm is tested and evaluated by using the original MR head scan test images. It learns from an existing biomedical dataset viz The Internet Brain Segmentation Repository (IBSR) to predict the new local affine transformations. The empirical analysis shows that the proposed algorithm is at least 4 times faster than the competitive methods and the decoding quality is far distinct with a reduction in the bit rate.

Author 1: Bejoy Varghese

Author 2: S. Krishnakumar

Keywords: Fractal compression; deep reinforcement learning; MRI image compression; deep learning; adative fractal coding

Paper 93: Comprehensive Analysis of Two Malicious Arabic-Language Twitter Campaigns

Abstract: Fake malicious accounts are one of the primary causes of the deterioration of social network content quality. Numerous such accounts are generated by attackers to achieve multiple nefarious goals, including phishing, spamming, spoof- ing, and promotion. These practices pose significant challenges regarding the availability of credible data that reflect real- world social media interactions. This has led to the development of various methods and approaches to combat spammers on social media networks. Previous studies, however, have almost exclusively focused on studying and identifying English-language spam profiles, whereas the problem of malicious Arabic-language accounts remains under-addressed in the literature. In this paper, therefore, we conduct a comprehensive investigation of malicious Arabic-language campaigns on Twitter. The study involves analyzing the accounts of these campaigns from several perspectives, including their number, content, social interaction graphs, lifespans, and day-to-day activities. In addition to expos- ing their spamming tactics, we find that these spam accounts are more successful in avoiding Twitter suspensions that has been previously reported in the literature.

Author 1: Reem Alharthi

Author 2: Areej Alhothali

Author 3: Kawthar Moria

Keywords: Social network security; social spammers; arab twitter users; malicious campaigns on twitter; data mining

Paper 94: Integrating Cost-231 Multiwall Propagation and Adaptive Data Rate Method for Access Point Placement Recommendation

Abstract: A new approach has been developed to provide an overview about signal behavior in indoor environments using Cost-231 Multiwall Model (Cost-231 MWM) and Adaptive Data Rate (ADR) method. This approach used as a reference for access point (AP) placement for campus building. The Cost-231 MWM plays a role in estimating the measured power received by user (usually called as Received Signal Strength Indicator/RSSI) by considering the existence of obstacles around the transmitter (AP). We used Institut Asia Malang environments as the case study and gave some recommendations for AP placement: ten optimal placements for the first, third and fourth floor, also seven optimal placements for the second floor. These recommendations were based on the RSSI for good and excellent level signal (-50 dBm until -10dBm). This research also uses the Adaptive Data Rate (ADR) mechanism approach to reduce the amount of packet loss (kbps) resulting from obstacles that cause attenuation (-dB). With the Adaptive Data Rate mechanism, it means increasing the number of access points, the signal attenuation (-dB) occurs from the obstacles (Walls) that are penetrated by the Radio Frequency device and causes attenuation (-dB), the more Access points on the Multi-Wall, will allow communication and data transmitting stability.

Author 1: Fransiska Sisilia Mukti

Author 2: Puput Dani Prasetyo Adi

Author 3: Dwi Arman Prasetya

Author 4: Volvo Sihombing

Author 5: Nicodemus Rahanra

Author 6: Kristia Yuliawan

Author 7: Julianto Simatupang

Keywords: Access point placement; indoor propagation; Cost- 231 Multiwall; ADR; RSSI

Paper 95: A Comparative Analysis of Hadoop and Spark Frameworks using Word Count Algorithm

Abstract: With the advent of the Big Data explosion due to the Information Technology (IT) revolution during the last few decades, the need for processing and analyzing the data at low cost in minimum time has become immensely challenging. The field of Big Data analytics is driven by the demand to process Machine Learning (ML) data, real-time streaming data, and graphics processing. The most efficient solutions to Big Data analysis in a distributed environment are Hadoop and Spark administered by Apache, both these solutions are open-source data management frameworks and they allow to distribute and compute the large datasets across multiple clusters of computing nodes. This paper provides a comprehensive comparison between Apache Hadoop & Apache Spark in terms of efficiency, scalability, security, cost-effectiveness, and other parameters. It describes primary components of Hadoop and Spark frameworks to compare their performance. The major conclusion is that Spark is better in terms of scalability and speed for real-time streaming applications; whereas, Hadoop is more viable for applications dealing with bigger datasets. This case study evaluates the performance of various components of Hadoop-such, MapReduce, and Hadoop Distributed File System (HDFS) by applying it to the well-known Word Count algorithm to ascertain its efficacy in terms of storage and computational time. Subsequently, it also provides an analysis of how Spark’s in-line memory processing could reduce the computational time of the Word Count Algorithm.

Author 1: Yassine Benlachmi

Author 2: Abdelaziz El Yazidi

Author 3: Moulay Lahcen Hasnaoui

Keywords: Big data; hadoop; spark; machine learning; Hadoop Distributed File System (HDFS)); mapreduce; word count

Paper 96: Security Aspects of Electronic Health Records and Possible Solutions

Abstract: Health related information of a person in systematic format using information and Communication technology is definitely required. Storing patient information according to guidelines provided by government will help to achieve the concept of one person one record. There is also need to share the personal health record whenever necessary. If patient record (History) is readily available, it will help to make correct decisions related to patient’s treatment. In our country (India) Ministry of Health and Family Welfare have recommended to eliminate conventional health record system. The major focus of this paper is to represent various methodologies that are adopted to implement web based health record system. As there is need of security while accessing and sharing of health related information, security is the major factor. Use of block chain, cryptography and timestamp based log record method is discussed. To assure the sharing of records, Inter Planetary File System (IPFS) is also discussed. Major purpose is to provide systematic and easy to use interoperable electronic health Record system.

Author 1: Prashant Vilas Kanade

Author 2: Arun Kumar

Keywords: Patient history; cryptography; blockchain; timestamp based record; IPFS; electronic health records