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

Publication Links

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

IJACSA

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

IJARAI

  • About the Journal
  • Archives
  • Indexing & Archiving

Special Issues

  • Home
  • Archives
  • Proposals
  • Guest Editors

Future of Information and Communication Conference (FICC)

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

Computing Conference

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

Intelligent Systems Conference (IntelliSys)

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

Future Technologies Conference (FTC)

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

IJACSA Volume 14 Issue 2

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: Organizational Digital Transformations and the Importance of Assessing Theoretical Frameworks such as TAM, TTF, and UTAUT: A Review

Abstract: In this era of Industry 5.0, businesses worldwide are attempting to gain competitive advantages, increase profits, and improve consumer engagement. To achieve their goals, all businesses undergo extensive digital transformations (DT) by implementing cutting-edge technologies such as cloud computing, artificial intelligence (AI), the Internet of Things, and blockchain, among others. DT is a costly journey, including strategy, people, and technology. At the same time, many digitization efforts are failing miserably, resulting in project abandonment, loss of critical stakeholder trust, and the dismissal of important staff. Poor strategy, which may have pre-evaluated organizational flexibility and cultural misfits, is often criticized. As a result, it is critical to extensively investigate theoretical frameworks such as the Technology Acceptance Model (TAM), Task Technology Fit (TTF), and Unified Theory of Acceptance and Use of Technology (UTAUT), which were developed via significant research into various organizational kinds. All of these aspects are covered in this work by evaluating academic papers from the IEEE, Scopus, and Web of Science databases and reaching conclusions in future sections.

Author 1: Bibhu Dash
Author 2: Pawankumar Sharma
Author 3: Swati Swayamsiddha

Keywords: Data growth; digital transformations; TAM; TTF; UTAUT; sustainability; FTM

Download PDF

Paper 2: Adversarial Sampling for Fairness Testing in Deep Neural Network

Abstract: In this research, we focus on the usage of adversarial sampling to test for the fairness in the prediction of deep neural network model across different classes of image in a given dataset. While several framework had been proposed to ensure robustness of machine learning model against adversarial attack, some of which includes adversarial training algorithm. There is still the pitfall that adversarial training algorithm tends to cause disparity in accuracy and robustness among different group. Our research is aimed at using adversarial sampling to test for fairness in the prediction of deep neural network model across different classes or categories of image in a given dataset. We successfully demonstrated a new method of ensuring fairness across various group of input in deep neural network classifier. We trained our neural network model on the original image, and without training our model on the perturbed or attacked image. When we feed the adversarial samplings to our model, it was able to predict the original category/ class of the image the adversarial sample belongs to. We also introduced and used the separation of concern concept from software engineering whereby there is an additional standalone filter layer that filters perturbed image by heavily removing the noise or attack before automatically passing it to the network for classification, we were able to have accuracy of 93.3%. Cifar-10 dataset have ten categories of dataset, and so, in order to account for fairness, we applied our hypothesis across each categories of dataset and were able to get a consistent result and accuracy.

Author 1: Tosin Ige
Author 2: William Marfo
Author 3: Justin Tonkinson
Author 4: Sikiru Adewale
Author 5: Bolanle Hafiz Matti

Keywords: Adversarial machine learning, adversarial attack; adversarial defense; machine learning fairness; fairness testing; adversarial sampling; deep neural network

Download PDF

Paper 3: Text2Simulate: A Scientific Knowledge Visualization Technique for Generating Visual Simulations from Textual Knowledge

Abstract: Recent research has developed knowledge visualization techniques for generating interactive visualizations from textual knowledge. However, when applied, these techniques do not generate precise semantic visual representations, which is imperative for domains that require an accurate visual representation of spatial attributes and relationships between objects of discourse in explicit knowledge. Therefore, this work presents a Text-to-Simulation Knowledge Visualization (TSKV) technique for generating visual simulations from domain knowledge by developing a rule-based classifier to improve natural language processing, and a Spatial Ordering (SO) algorithm to solve the identified challenge. A system architecture was developed to structurally model the components of the TSKV technique and implemented using a Knowledge Visualization application called ‘Text2Simulate’. A quantitative evaluation of the application was carried out to test for accuracy using modified existing information visualization evaluation criteria. Object Inclusion (OI), Object-Attribute Visibility (OAV), Relative Positioning (RP), and Exact Visual Representation (EVR) criteria were modified to include Object’s Motion (OM) metric for quantitative evaluation of generated visual simulations. Evaluation for accuracy on generated simulation results were 90.1, 84.0, 90.1, 90.0, and 96.0% for OI, OAV, OM, RP, and EVR criteria respectively. User evaluation was conducted to measure system effectiveness and user satisfaction which showed that all the participants were satisfied well above average. These generated results showed an improved semantic quality of visualized knowledge due to the improved classification of spatial attributes and relationships from textual knowledge. This technique could be adopted during the development of electronic learning applications for improved understanding and desirable actions.

Author 1: Ifeoluwatayo A. Ige
Author 2: Bolanle F. Oladejo

Keywords: Knowledge visualization; visual simulation; text-to-simulation knowledge visualization technique; natural language processing; electronic learning

Download PDF

Paper 4: A Review on Artificial Intelligence in the Context of Industry 4.0

Abstract: Artificial Intelligence (AI) is seen as the most promising among Industry 4.0 advancements for businesses. Artificial intelligence, defined as computer models that mimic intelligent behavior, is poised to unleash the next wave of digital disruption and bring a competitive advantage to the industry. The value of AI lies not in its models, but in the ways in which we can harness them. It is becoming more common for industry objects to be converted into intelligent objects that can sense, act, adapt, and behave in a given environment. Leaders in the industry will need to make deliberate choices about how, when, and where to deploy these technologies. Our work highlights some of the primary AI emerging trends in Industry 4.0. We also discuss the advantages, challenges, and applications of AI in Industry 4.0.

Author 1: Shadi Banitaan
Author 2: Ghaith Al-refai
Author 3: Sattam Almatarneh
Author 4: Hebah Alquran

Keywords: Artificial intelligence; Industry 4.0; intelligent manufacturing; industry analysis

Download PDF

Paper 5: A Machine Learning Enabled Hall-Effect IoT-System for Monitoring Building Vibrations

Abstract: Vibration monitoring of civil infrastructures is a fundamental task to assess their structural health, which can be nowadays carried on at reduced costs thanks to new sensing devices and embedded hardware platforms. In this work, we present a system for monitoring vibrations in buildings based on a novel, cheap, Hall-effect vibration sensor that is interfaced with a commercially available embedded hardware platform, in order to support communication toward cloud based services by means of IoT communication protocols. Two deep learning neural networks have been implemented and tested to demonstrate the capability of performing nontrivial prediction tasks directly on board of the embedded platform, an important feature to conceive dynamical policies for deciding whether to perform a recognition task on the final (resource constrained) device, or delegate it to the cloud according to specific energy, latency, accuracy requirements. Experimental evaluation on two use cases, namely the detection of a seismic event and the count of steps made by people transiting in a public building highlight the potential of the adopted solution; for instance, recognition of walking-induced vibrations can be achieved with an accuracy of 96% in real-time within time windows of 500ms. Overall, the results of the empirical investigation show the flexibility of the proposed solution as a promising alternative for the design of vibration monitoring systems in built environments.

Author 1: Emanuele Lattanzi
Author 2: Paolo Capellacci
Author 3: Valerio Freschi

Keywords: Vibration sensor; machine learning; hall-effect

Download PDF

Paper 6: Sequence Recommendation based on Deep Learning

Abstract: Sequence recommendation systems have become increasingly popular in various fields such as movies and social media. These systems aim to predict a user's preferences and interests based on their past behavior and provide them with personalized recommendations. Deep learning, particularly Recurrent Neural Networks (RNNs), have emerged as a powerful tool for sequence recommendation. In this research, we explore the effectiveness of RNNs in movie and Instagram recommendation systems. We investigate and compare the performance of different types of RNNs, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in recommending movies and Instagram posts to users based on their browsing history. Additionally, we study the impact of incorporating additional information such as user's demographics and Instagram hashtags on the performance of the recommendation system. We also evaluate the performance of RNN-based movie and Instagram recommendation systems in comparison to traditional approaches, such as collaborative filtering and content-based filtering, in terms of accuracy and personalization. The findings of this research provide insights into the effectiveness of RNNs in movie and Instagram recommendation systems and contribute to the development of more accurate and personalized recommendations for users.

Author 1: Gulsim Rysbayeva
Author 2: Jingwei Zhang

Keywords: Long short-term memory (LSTM) and gated recurrent unit (GRU); RNN; deep learning; recommendation systems

Download PDF

Paper 7: Routing Overhead Aware Optimal Cluster based Routing Algorithm for IoT Network using Heuristic Technique

Abstract: Globally, billion of devices in heterogeneous networks are interconnected by the Internet of Things (IoT). IoT applications require a centralized decision-making system due to the failure-prone connectivity and high latency of such a system. Low-latency communications are a primary characteristic of applications. Since IoT applications usually have small payload sizes, reducing communication overhead is crucial to improving energy efficiency. Researchers have proposed several methods to resolve the load balancing issue of IoT networks and reduce communication overhead. Although these techniques are not effective, in terms of high communication costs, end-to-end delay, packet loss ratio, throughput, and node lifetimes negatively impact network performance. In this paper, we propose a communication overhead aware optimal cluster-based (COOC) routing algorithm for IoT networks based on a hybrid heuristic technique. Using three benchmark algorithms, we form load-balanced clusters using k-means clustering, fuzzy logic, and genetic algorithm. In the next step, compute the rank of each node in a cluster using multiple design constraints, which are optimized by using the improved COOT bird optimum search algorithm (I-COOT). After that, we choose the cluster head (CH) according to the rank condition, thereby reducing the communication overhead in IoT networks. Additionally, we design chaotic golden search optimization algorithm (CGSO) for choosing the optimal best path between IoT nodes among multiple paths to ensure optimal data transfer from CHs. To conclude, we validate our proposed COOC routing algorithm against the different simulation scenarios and compare the results with existing state-of-the-art routing algorithms.

Author 1: Srinivasulu M
Author 2: Shiva Murthy G

Keywords: Internet-of-things; communication overhead; cluster based routing; multipath routing; cluster head

Download PDF

Paper 8: Supply Chain Network Model using Multi-Agent Reinforcement Learning for COVID-19

Abstract: The COVID-19 vaccination management in Japan has revealed many problems. The number of vaccines available was clearly less than the number of people who wanted to be vaccinated. Initially, the system was managed by making reservations with age group utilizing vaccination coupons. After the second round of vaccinations, only appointments for vaccination dates were coordinated and vaccination sites were set up in Shibuya Ward where the vaccine could be taken freely. Under a shortage of vaccine supply, the inability to make appointments arose from a failure to properly estimate demand. In addition, the vaccine expired due to inadequate inventory management, resulting in the vaccine being discarded. This is considered to be a supply chain problem in which appropriate supply could not be provided in response to demand. In response to this problem, this paper examines whether it is possible to avoid shortage and stock discards by a decentralized management system for easy on-site inventory control instead of a centralized management system in real world. Based on a multi-agent model, a model was created to redistribute inventory to clients by predicting future shortage based on demand fluctuations and past inventory levels. The model was constructed by adopting the Kanto region. The validation results of the model showed that the number of discards was reduced by about 70% and out-of-stocks by about 12% as a result of learning the dispersion management and out-of-stock forecasting.

Author 1: Tomohito Okada
Author 2: Hiroshi Sato
Author 3: Masao Kubo

Keywords: Supply chain management; agent based model; multi-agent reinforcement learning; COVID-19 vaccination

Download PDF

Paper 9: An Enhanced MCDM Model for Cloud Service Provider Selection

Abstract: Multi-Criteria Decision-Making (MCDM) techniques are often used to aid decision-makers in selecting the best alternative among several options. However, these systems have issues, including the Rank Reversal Problem (RRP) and decision-making ambiguity. This study aimed to propose a selection model for a Cloud Service Provider (CSP) that addresses these issues. This research used the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to rank the alternatives. The entropy technique is utilized to determine the weight of the criteria, and Single Valued Neutrosophic (SVN) is employed to address uncertainty. To select the best cloud provider based on Quality of Service (QoS) criteria, we used a dataset from Cloud Harmony for this study. The results indicated that the suggested model could effectively resolve the RRP under conditions of uncertainty. This research is novel and is the first to address both the problem of uncertainty in decision-making and RRP in MCDM.

Author 1: Ayman S. Abdelaziz
Author 2: Hany Harb
Author 3: Alaa Zaghloul
Author 4: Ahmed Salem

Keywords: MCDM; TOPSIS; neutrosophic set; single valued neutrosophic; cloud services provider; quality of service

Download PDF

Paper 10: Dynamic Software Architecture Design for Virtual Rehabilitation System for Manual Motor Dexterity

Abstract: The architectural design is fundamental in the construction process of a virtual rehabilitation system since it allows to understand the components and their interaction, and it is a guide to develop the software. This article proposes a dynamic architecture design that could be used independently of software and hardware in a virtual rehabilitation system for motor dexterity. This proposal contributes to the software engineering area since it provides a starting point for the development of virtual rehabilitation systems. The system implementation was done with two tracking devices (hardware) and two rehabilitation games (software). It was validated with the User Experience Questionnaire (UEQ). Results show that the use of a dynamic architecture allowed to use different devices efficiently and quickly, regardless of the game, preventing the user from feeling a change or difficulty in carrying out the tasks.

Author 1: Edwin Enrique Saavedra Parisaca
Author 2: Solansh Jaqueline Montoya Muñoz
Author 3: Elizabeth Vidal Duarte
Author 4: Eveling Gloria Castro Gutierrez
Author 5: Angel Yvan Choquehuanca Peraltilla
Author 6: Sergio Albiol Pérez

Keywords: Software architecture; dynamic architecture; virtual rehabilitation systems; motor dexterity

Download PDF

Paper 11: Insights into Search Engine Optimization using Natural Language Processing and Machine Learning

Abstract: Among the potential tools in digital marketing, Search Engine Optimization (SEO) facilitates the use of appropriate data by providing appropriate results according to the search priority of the user. Various research-based approaches have been developed to improve the optimization performance of search engines over the past decade; however, it is still unclear what the strengths and weaknesses of these methods are. As a result of the increased proliferation of Machine Learning (ML) and Natural Language Processing (NLP) in complex content management, there is potential to achieve successful SEO results. Therefore, the purpose of this paper is to contribute towards performing an exhaustive study on the respective NLP and ML methodologies to explore their strengths and weaknesses. Additionally, the paper highlights distinct learning outcomes and a specific research gap intended to assist future research work with a guideline necessary for optimizing search engine performance.

Author 1: Vinutha M S
Author 2: M C Padma

Keywords: Search engine optimization; google search; natural language processing; machine learning; recommendation

Download PDF

Paper 12: Adaptive Rectified Linear Unit (Arelu) for Classification Problems to Solve Dying Problem in Deep Learning

Abstract: A convolutional neural network (CNN) is a subset of machine learning as well as one of the different types of artificial neural networks that are used for different applications and data types. Activation functions (AFs) are used in this type of network to determine whether or not its neurons are activated. One non-linear AF named as Rectified Linear Units (ReLU) which involves a simple mathematical operations and it gives better performance. It avoids rectifying vanishing gradient problem that inherents older AFs like tanh and sigmoid. Additionally, it has less computational cost. Despite these advantages, it suffers from a problem called Dying problem. Several modifications have been appeared to address this problem, for example; Leaky ReLU (LReLU). The main concept of our algorithm is to improve the current LReLU activation functions in mitigating the dying problem on deep learning by using the readjustment of values (changing and decreasing value) of the loss function or cost function while number of epochs are increased. The model was trained on the MNIST dataset with 20 epochs and achieved lowest misclassification rate by 1.2%. While optimizing our proposed methods, we received comparatively better results in terms of simplicity, low computational cost, and with no hyperparameters.

Author 1: Ibrahim A. Atoum

Keywords: Rectified Linear Unit (ReLU); Convolutional Neural Network; activation function; deep learning; MNIST dataset; machine learning

Download PDF

Paper 13: Espousing AI to Enhance Cost-Efficient and Immersive Experience for Human Computer Interaction

Abstract: Because of recent technological and interface advancements in the field, the virtual reality (VR) movement has entered a new era. Mobility is one of the most crucial behaviours in virtual reality. In this research, popular virtual reality mobility systems are compared, and it is shown that gesture control is a key technology for allowing distinctive virtual world communication paradigms. Gesture based movements are very beneficial when there are a lot of spatial restrictions. With a focus on cost-effectiveness, the current study introduces a gesture-based virtual movement (GVM) system that eradicates the obligation for expensive hardware/controllers for virtual world mobility (i.e., walk/ jump/ hold for this research) using artificial intelligence (AI). Additionally, the GVM aims to prevent users from becoming dizzy by allowing them to change the trajectory by simply turning their head in the intended direction. The GVM was assessed on its interpreted realism, presence, and spatial drift in the actual environment in comparison to the state-of-the-art techniques. The results demonstrated how the GVM outperformed the prevailing methodologies in a number of common interaction components. Additionally, the empirical analysis showed that GVM offers customers a real-time experience with a latency of ~65 milliseconds.

Author 1: Deepak Chaturvedi
Author 2: Ashima Arya
Author 3: Mohammad Zubair Khan
Author 4: Eman Aljohani
Author 5: Liyakathunisa
Author 6: Vaishali Arya
Author 7: Namrata Sukhija
Author 8: Prakash Srivastava

Keywords: Artificial intelligence; dizziness; gestures; human computer interaction; user experience; virtual reality

Download PDF

Paper 14: Implementation of Big Data Privacy Preservation Technique for Electronic Health Records in Multivendor Environment

Abstract: Various diagnostic health data formats and standards include both structured and unstructured data. Sensitive information contained in such metadata requires the development of specific approaches that can combine methods and techniques that can extract and reconcile the information hidden in such data. However, when this data needs to be processed and used for other reasons, there are still many obstacles and concerns to overcome. Modern approaches based on machine learning including big data analytics, assist in the information refinement process for later use of clinical evidence. These strategies consist of transforming various data into standard formats in specific scenarios. In fact, in order to conform to these rules, only de-identified diagnostic and personal data may be handled for secondary analysis, especially when information is distributed or transferred across institutions. This paper proposes big data privacy preservation techniques using various privacy functions. This research focused on secure data distribution as well as security access control to revoke the malicious activity or similarity attacks from end-user. The various privacy preservation techniques such as data anonymization, generalization, random permutation, k-anonymity, bucketization, l-diversity with slicing approach have been proposed during the data distribution. The efficiency of system has been evaluated in Hadoop distributed file system (HDFS) with numerous experiments. The results obtained from different experiments show that the computation should be changed when changing k-anonymity and l-diversity. As a result, the proposed system offers greater efficiency in Hadoop environments by reducing execution time by 15% to 18% and provides a higher level of access control security than other security algorithms.

Author 1: Ganesh Dagadu Puri
Author 2: D. Haritha

Keywords: Privacy preservation; data privacy; data distribution; anonymization; slicing; privacy attacks; HDFS

Download PDF

Paper 15: Churn Customer Estimation Method based on LightGBM for Improving Sales

Abstract: Churn customer estimation method is proposed for improving sales. By analyzing the differences between customers who churn and customers who do not churn (returning), we will conduct a customer churn analysis to reduce customer churn and take steps to reduce the number of unique customers. By predicting customers who are likely to defect using decision tree models such as LightGBM, which is a machine learning method, and logistic regression, we will discover important feature values in prediction and utilize the knowledge obtained through Exploratory Data Analysis: EDA. As results for experiments, it is found that the proposed method allows estimation and prediction of churn customers as well as characteristics and behavior of churn customers. Also, it is found that the proposed method is superior to the conventional method, GradientBoostingClassifier: GBC by around 10%.

Author 1: Kohei Arai
Author 2: Ikuya Fujikawa
Author 3: Yusuke Nakagawa
Author 4: Ryuya Momozaki
Author 5: Sayuri Ogawa

Keywords: LightGBM (light gradient boosting machine); EDA (exploratory data analysis); churn prediction; linear regression; gradient boosting method; GradientBoostingClassifier: GBC

Download PDF

Paper 16: Privacy Preservation Modelling for Securing Image Data using Novel Ethereum-based Ecosystem

Abstract: The broad usage of images in real-time applications demands a cloud infrastructure due to its advantages. Many use cases are built where the image data is shared, sharing becomes the core function, and the medical domain takes its broad advantage. The cloud is a centralized infrastructure for its all-operation usages; it depends mainly on the trusted third party to handle security concerns. Therefore, the privacy preservation of the image data or any data becomes an issue of concern. The distrusted system advantages are achieved using blockchain technology for image data security and privacy concerns. The traditional approaches of the security and privacy models raise many apprehensions as these are designed on the centralized systems of the data sharing mechanisms. It is also observed that large data files are not wisely handled, which demands building a framework model that takes image data and any other data of any size to ensure a dependable optimal security system. This paper presents a framework model to achieve optimal time complexity for securing the privacy aspects of the image data or any other data that uses space optimal file system using distributed security mechanism for both the storage and sharing of the data. The proposed framework model for optimal time complexity and security uses a duplication algorithm using stakeholder agreement to ensure efficient access control to the resources using the cryptographic approach to the Ethereum ecosystem. The performance metric used in the model evaluation includes the degree of availability and efficiency. On benchmarks, it performs well compared to the traditional cloud-built distributed systems. The quantified outcome of the proposed scheme exhibits a 42.5% of reduction in time for data repositioning, a 41.1% of reduction in time for data retrieval, a 34.8% of reduction in operational cost, a 73.9% of reduction in delay, and a 61% faster algorithm execution time in contrast to conventional blockchain method.

Author 1: Chhaya S Dule
Author 2: Roopashree H. R

Keywords: Blockchain; data security; Ethereum; image data; privacy; security

Download PDF

Paper 17: Music Note Feature Recognition Method based on Hilbert Space Method Fused with Partial Differential Equations

Abstract: Hilbert space method is an old mathematical theoretical model developed based on linear algebra and has a high theoretical value and practical application. The basic idea of the Hilbert space method is to use the existence of some stable relationship between variables and to use the dynamic dependence between variables to construct the solution of differential equations, thus transforming mathematical problems into algebraic problems. This paper firstly studies the denoising model in the process of music note feature recognition based on partial differential equations, then analyzes the denoising method based on partial differential equations and gives an algorithm for fused music note feature recognition in Hilbert space; secondly, this paper studies the commonly used music note feature recognition methods, including linear predictive cepstral coefficients, Mel frequency cepstral coefficients, wavelet transform-based feature extraction methods and Hilbert space-based feature extraction methods. Their corresponding feature extraction processes are given.

Author 1: Liqin Liu

Keywords: Partial differential equation; Hilbert space method; musical note feature recognition method; cepstral coefficients; empirical modal

Download PDF

Paper 18: Hyperparameter Optimization of Support Vector Regression Algorithm using Metaheuristic Algorithm for Student Performance Prediction

Abstract: Improving student learning performance requires proper preparation and strategy so that it has an impact on improving the quality of education. One of the preparatory steps is to make a prediction modeling of student performance. Accurate student performance prediction models are needed to help teachers develop the potential of diverse students. This research aims to create a predictive model of student performance with hyperparameter optimization in the Support Vector Regression Algorithm. The hyperparameter optimization method used is the Metaheuristic Algorithm. The Metaheuristic Algorithms used in this study are Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). After obtaining the best SVR hyperparameter, the next step is to model student performance predictions, which in this study produced two models, namely PSVR Modeling and GSVR Modeling. The resulting predictive modeling will also be compared with previous researchers' prediction modeling of student performance using five models: Support Vector Regression, Naïve Bayes, Neural Network, Decision Tree, and Random Forest. The regression performance metric parameter, Root Mean Square Error (RMSE), evaluates modeling results. The test results show that predictive student performance using PSVR Modeling produces the smallest RMSE value of 1.608 compared to predictions of student performance by previous researchers so that the proposed prediction model can be used to predict student performance in the future.

Author 1: M. Riki Apriyadi
Author 2: Ermatita
Author 3: Dian Palupi Rini

Keywords: Student performance; feature selection; particle swarm optimization; genetic algorithm; support vector regression

Download PDF

Paper 19: Experimental Analysis and Monitoring of Photovoltaic Panel Parameters

Abstract: In this article, we establish a technique based on the internet of things to simultaneously monitor the main values that characterize a photovoltaic solar panel. This technique allows to discover the problems and the monstrosities during the operation. This study also allows to collect the parameters and quantities measured for analysis. This method is based on exploiting the advantages of IoT technology. For this it will be a good choice to use and exploit the Esp32 microcontroller, because the two WIFI and Bluetooth modules are integrated. The design process began by creating a system to measure the intensity of the electric current delivered by the photovoltaic panel. A current sensor was implemented for this purpose. To prevent damage to the microcontroller, a voltage divider was proposed to decrease the voltage at the pin level of the Esp32 for measurement. Next, the power and energy values were calculated to estimate the production capacity. In the final stage, a low-power Bluetooth link was created to transmit the four quantities to a smartphone or other compatible device. Real-time values were presented as graphs on the free ThingSpeak platform and displayed on both, an LCD screen and the serial monitor of the Esp32 microcontroller. The system was tested without any problems or errors.

Author 1: Zaidan Didi
Author 2: Ikram El Azami

Keywords: Current sensor; bluetooth low consumption; photovoltaic panel; Esp32 microcontroller

Download PDF

Paper 20: Hybrid Feature Selection Algorithm and Ensemble Stacking for Heart Disease Prediction

Abstract: In cardiology, as in other medical specialties, early and accurate diagnosis of heart disease is crucial as it has been the leading cause of death over the past few decades. Early prediction of heart disease is now more crucial than ever. However, the state-of-the-art heart disease prediction strategy put more emphasis on classifier selection in enhancing the accuracy and performance of heart disease prediction, and seldom considers feature reduction techniques. Furthermore, there are several factors that lead to heart disease, and it is critical to identify the most significant characteristics in order to achieve the best prediction accuracy and increase prediction performance. Feature reduction reduces the dimensionality of the information, which may allow learning algorithms to work quicker and more efficiently, producing predictive models with the best rate of accuracy. In this study, we explored and suggested a hybrid of two distinct feature reduction techniques, chi-squared and analysis of variance (ANOVA). In addition, using the ensemble stacking method, classification is performed on selected features to classify the data. Using the optimal features based on hybrid features combination, the performance of a stacking ensemble based on logistic regression yields the best result with 93.44%. This can be summarized as the feature selection method can take into account as an effective method for the prediction of heart disease.

Author 1: Nureen Afiqah Mohd Zaini
Author 2: Mohd Khalid Awang

Keywords: Heart disease prediction; feature selection; stacking; accuracy

Download PDF

Paper 21: Automatic Extraction of Indonesian Stopwords

Abstract: The rapid growth of the Indonesian language content on the Internet has drawn researchers’ attention. By using natural language processing, they can extract high-value information from such content and documents. However, processing large and numerous documents is very time-consuming and computationally expensive. Reducing these computational costs requires attribute reduction by removing some common words or stopwords. This research aims to extract stopwords automatically from a large corpus, about seven million words, in the Indonesian language downloaded from the web. The problem is that Indonesian is a low-resource language, making it challenging to develop an automatic stopword extractor. The method used is Term Frequency – Inverse Document Frequency (TF-IDF) and presents a methodology for ranking stopwords using TFs and IDFs, which is applicable to even a small corpus (as low as one document). It is an automatic method that can be applied to many different languages with no prior linguistic knowledge required. There are two novelties or contributions in this method: it can show all words found in all documents, and it has an automatic cut-off technique for selecting the top rank of stopwords candidates in the Indonesian language, overcoming one of the most challenging aspects of stopwords extraction.

Author 1: Harry Tursulistyono Yani Achsan
Author 2: Heru Suhartanto
Author 3: Wahyu Catur Wibowo
Author 4: Deshinta A. Dewi
Author 5: Khairul Ismed

Keywords: Stopwords extraction; attributes reduction; TF-IDF; large corpus; Indonesian stopwords; NLP

Download PDF

Paper 22: Software Effort Estimation through Ensembling of Base Models in Machine Learning using a Voting Estimator

Abstract: For a long time, researchers have been working to predict the effort of software development with the help of various machine learning algorithms. These algorithms are known for better understanding the underlying facts inside the data and improving the prediction rate than conventional approaches such as line of code and functional point approaches. According to no free lunch theory, there is no single algorithm which gives better predictions on all the datasets. To remove this bias our work aims to provide a better model for software effort estimation and thereby reduce the distance between the actual and predicted effort for future projects. The authors proposed an ensembling of regressor models using voting estimator for better predictions to reduce the error rate to over the biasness provide by single machine learning algorithm. The results obtained show that the ensemble models were better than those from the single models used on different datasets.

Author 1: Beesetti Kiran Kumar
Author 2: Saurabh Bilgaiyan
Author 3: Bhabani Shankar Prasad Mishra

Keywords: Machine learning; software effort estimation; voting; regression; evolutionary algorithms

Download PDF

Paper 23: An Effective Heart Disease Prediction Framework based on Ensemble Techniques in Machine Learning

Abstract: To design a framework for effective prediction of heart disease based on ensemble techniques, without the need of feature selection, incorporating data balancing, outlier detection and removal techniques, with results that are still at par with cutting-edge research. In this study, the Cleveland dataset, which has 303 occurrences, is used from the UCI repository. The dataset comprises 76 raw attributes, however only 14 of them are listed by the UCI repository as significant risk factors for heart disease when the dataset is uploaded as an open source dataset. Data balancing strategies, such as random over sampling, are used to address the issue of unbalanced data. Additionally, an isolation forest is used to find outliers in multivariate data, which has not been explored in previous research. After eliminating anomalies from the data, ensemble techniques such as bagging, boosting, voting, stacking are employed to create the prediction model. The potential of the proposed model is assessed for accuracy, sensitivity, and specificity, positive prediction value (PPV), negative prediction value (NPV), F1 score, ROC-AUC and model training time. For the Cleveland dataset, the performance of the suggested methodology is superior, with 98.73% accuracy, 98% sensitivity, 100% specificity, 100% PPV, 97% NPV, 1 as F score, and AUC as 1 with comparatively very less training time. The results of this study demonstrate that our proposed approach significantly outperforms the existing scholarly work in terms of accuracy and all the stated performance metrics. No earlier research has focused on these many performance parameters.

Author 1: Deepali Yewale
Author 2: S. P. Vijayaragavan
Author 3: V. K. Bairagi

Keywords: Machine learning; heart disease; ensemble techniques; random over sampling, isolation forest

Download PDF

Paper 24: Explaining the Outputs of Convolutional Neural Network - Recurrent Neural Network (CNN-RNN) based Apparent Personality Detection Models using the Class Activation Maps

Abstract: This study aims to use the Class Activation Map (CAM) visualisation technique to understand the outputs of apparent personality detection models based on a combination of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The ChaLearn Looking at People First Impression (CVPR'17) dataset is used for experimentation in this study. The dataset consists of short video clips labelled with the Big Five personality traits. Two deep learning models were designed to predict apparent personality with VGG19 and ResNet152 as base models. Then the models were trained using the raw frames extracted from the videos. The highest accurate models from each architecture were chosen for feature visualisation. The test dataset of the CVPR'17 dataset is used for feature visualisation. To identify the feature's contribution to the network's output, the CAM XAI technique was applied to the test dataset and calculated the heatmap. Next, the bitwise intersection between the heatmap and background removed frames was measured to identify how much features from the human body (including facial and non-facial data) affected the network output. The findings revealed that nearly 35%-40% of human data contributed to the output of both models. Additionally, after analysing the heatmap with high-intensity pixels, the ResNet152 model was found to identify more human-related data than the VGG19 model, achieving scores of 46%-51%. The two models have different behaviour in identifying the key features which influence the output of the models based on the input.

Author 1: WMKS Ilmini
Author 2: TGI Fernando

Keywords: Apparent personality detection (APD); convolutional neural network based recurrent neural network (CNN-RNN); class activation map (CAM); explainable AI (XAI)

Download PDF

Paper 25: Landmark Recognition Model for Smart Tourism using Lightweight Deep Learning and Linear Discriminant Analysis

Abstract: Scene recognition algorithm is crucial for landmark recognition model development. Landmark recognition model is one of the main modules in the intelligent tour guide system architecture for the use of smart tourism industry. However, recognizing the tourist landmarks in the public places are challenging due to the common structure and the complexity of scene objects such as building, monuments and parks. Hence, this study proposes a super lightweight and robust landmark recognition model by using the combination of Convolutional Neural Network (CNN) and Linear Discriminant Analysis (LDA) approaches. The landmark recognition model was evaluated by using several pretrained CNN architectures for feature extraction. Then, several feature selections and machine learning algorithms were also evaluated to produce a super lightweight and robust landmark recognition model. The evaluations were performed on UMS landmark dataset and Scene-15 dataset. The results from the experiments have found that the Efficient Net (EFFNET) with CNN classifier are the best feature extraction and classifier. EFFNET-CNN achieved 100% and 94.26% classification accuracy on UMS-Scene and Scene-15 dataset respectively. Moreover, the feature dimensions created by EFFNet are more compact compared to the other features and even have significantly reduced for more than 90% by using Linear Discriminant Analysis (LDA) without jeopardizing classification performance but yet improved its performance.

Author 1: Mohd Norhisham Razali
Author 2: Enurt Owens Nixon Tony
Author 3: Ag Asri Ag Ibrahim
Author 4: Rozita Hanapi
Author 5: Zamhar Iswandono

Keywords: Scene recognition; convolutional neural network; smart tourism; feature selections

Download PDF

Paper 26: Performance Comparison of the Kernels of Support Vector Machine Algorithm for Diabetes Mellitus Classification

Abstract: Diabetes Mellitus is a disease where the body cannot use insulin properly, so this disease is one of the health problems in various countries. Diabetes Mellitus can be fatal, cause other diseases, and even lead to death. Based on this, it is essential to have prediction activities to find out a disease. The SVM algorithm is used in classifying Diabetes Mellitus diseases. This study aimed to compare the accuracy, precision, recall, and F1-Score values of the SVM algorithm with various kernels and data preprocessing. Data preprocessing included data splitting, normalization, and data oversampling. This research has the benefit of solving health problems based on the percentage of Diabetes Mellitus and can be used as material for accurate information. The results of this study are that the highest accuracy was obtained by 80% (obtained from the polynomial kernel), the highest precision was obtained by 65%, which was also obtained from the polynomial kernel, and the highest recall was obtained by 79% (obtained from the RBF kernel) and the highest F1-score was obtained by 70% (which was also obtained from the RBF kernel).

Author 1: Dimas Aryo Anggoro
Author 2: Dian Permatasari

Keywords: Diabetes mellitus; kernel; normalization; oversampling; SVM

Download PDF

Paper 27: Deep Study of CRF Models for Speech understanding in Limited Task

Abstract: In this paper, we propose to evaluate in depth CRF models (Conditional Random Fields) for speech-understanding in limited task. To evaluate these models, we design several models that differ according to the level of integration of local dependencies in the same turn. As we propose to evaluate these models on different types of processed data. We perform our study on a corpus where turns are not segmented into utterances. In fact, we propose to use the whole turn as one unit during training and testing of CRF models. This represents the natural way of conversation. The language used in this work is the Tunisian Arabic dialect. The obtained results prove the robustness of CRF models when dealing with raw data. They are able to detect the semantic dependency between words in the same speech turn. Results are important when CRF models are designed to take into account the words with deep dependencies in the same turn and with advanced preprocessed data.

Author 1: Marwa Graja

Keywords: Speech understanding; Arabic dialect; CRF models

Download PDF

Paper 28: Paw Search – A Searching Approach for Unsorted Data Combining with Binary Search and Merge Sort Algorithm

Abstract: Searching is one of the oldest core mechanism of nature. Nature is changing gradually along with searching approaches too. Data Mining is one of the most important industrials topic now-a-days. Under this area all social networks, governmental or non-governmental institutions and ecommerce industries produce a huge number of unsorted data and they are to utilize it. For utilizing this huge number of unsorted data there needs some specific features based unsorted data structure tools like searching algorithm. At present there are several sorted data based searching algorithms like Binary Search, Linear Search, Jump Search and Interpolation Search and so on. In this paper of Paw Search Algorithm, it is fully focused to develop a new approach of searching that can work on unsorted data merging several searching techniques and sorting techniques. This algorithm starts its operation by breaking down the given unsorted array into several blocks by making the square root of the length of the given array. Then these blocks will be searched within its specific formula till the target data is found or not, and in the inner side of each block there will be performed Merge Sort and Binary Search approach gradually. Time and Space Complexity of this Paw Search algorithm is comparatively optimal.

Author 1: Md. Harun Or Rashid
Author 2: Ahmed Imtiaz

Keywords: Paw; search; unsorted; data; blocks; square root

Download PDF

Paper 29: A Survey of Forensic Analysis and Information Visualization Approach for Instant Messaging Applications

Abstract: Instant messaging applications, including WhatsApp, Viber, and WeChat, are moving beyond text messages to videos and voice calls, which are proportioned to current media, files, and locations. In this study, we surveyed existing forensic visualization and forensic analysis techniques for instant messaging applications, with the aim of contributing to the knowledge in the discussion of these research issues. A total of 61 publications were reviewed after searching various academic databases, including the IEEE, ACM Digital Library, Google Scholar, and Science Direct during the last five years. Our observation from research trends indicates that both forensic analysis and information visualization are relatively mature research areas. However, there is a growing interest in forensic visualization and automated IM forensic analysis. We also identified the lack of discussion on forensic selection criteria in existing forensic visualization works and the needs of benchmarking the evaluation method of automate forensic analysis tools.

Author 1: Shahnaz Pirzada
Author 2: Nurul Hidayah Ab Rahman
Author 3: Niken Dwi Wahyu Cahyani
Author 4: Muhammad Fakri Othman

Keywords: Forensic analysis; forensic visualization; instant messaging apps; mobile forensics; and mobile communication apps

Download PDF

Paper 30: Driving Maneuvers Recognition and Classification Using A Hyprid Pattern Matching and Machine Learning

Abstract: Since most of the road and traffic accidents are related to human errors or distraction, the study of irregular driving behaviors is considered one of the most important research topics in this field. To prevent road accidents and assess driving competencies, there is an urgent need to evaluate driving behavior through the design of a driving maneuvers assessment system. In this study, the recognition and classification of highway driving maneuvers using smartphones’ build-in sensors are presented. The paper examines the performance of three classical machine learning techniques and a novel hybrid system. The proposed hybrid system combines the pattern machining Dynamic Time Warping (DTW) technique for recognizing driving maneuvers and the machine learning techniques for classification. Results obtained from both approaches show that the performance of the hybrid system is superior to that obtained by using classical machine learning techniques. This enhancement in the performance of the hybrid system is due to the elimination of the overlapping in the target classes due to the separation, the recognition and the classification processes.

Author 1: Munaf Salim Najim Al-Din

Keywords: Driving behavior classification; driving maneuvers; pattern matching; machine learning

Download PDF

Paper 31: An Approach to Automatic Garbage Detection Framework Designing using CNN

Abstract: This paper proposes a system for automatic detection of litter and garbage dumps in CCTV feeds with the help of deep learning implementations. The designed system named Greenlock scans and identifies entities that resemble an accumulation of garbage or a garbage dump in real time and alerts the respective authorities to deal with the issue by locating the point of origin. The entity is labelled as garbage if it passes a certain similarity threshold. ResNet-50 has been used for the training purpose alongside TensorFlow for mathematical operations for the neural network. Combined with a pre-existing CCTV surveillance system, this system has the capability to hugely minimize garbage management costs via the prevention of formation of big dumps. The automatic detection also saves the manpower required in manual surveillance and contributes towards healthy neighborhoods and cleaner cities. This article is also showing the comparison between applied various algorithms such as standard TensorFlow, inception algo and faster-r CNN and Resnet-50, and it has been observed that Resnet-50 performed with better accuracy. The study performed with this study proved to be a stress reliever in terms of the garbage identification and dumping for any country. At the end of the article the comparison chart has been shown.

Author 1: Akhilesh Kumar Sharma
Author 2: Antima Jain
Author 3: Deevesh Chaudhary
Author 4: Shamik Tiwari
Author 5: Hairulnizam Mahdin
Author 6: Zirawani Baharum
Author 7: Shazlyn Milleana Shaharudin
Author 8: Ruhaila Maskat
Author 9: Mohammad Syafwan Arshad

Keywords: Garbage detection; resnet; tensorflow; CNN

Download PDF

Paper 32: Tamper Proof Air Quality Management System using Blockchain

Abstract: One of the most important concerns facing urban regions across the world is air pollution. As a result, it's critical to monitor pollution levels and notify the public on the state of the air. An indicator called the Air Quality Index (AQI) does this by mapping the concentration of different contaminants into a single number. Because the examination of pollutant data is frequently opaque to outsiders, poor environmental control judgments may result. This has led to a need for a tamper-proof pollution management system for use by authorities, like the state and central pollution boards. To address these challenges, a model using machine learning algorithms to predict the air quality and store that information in the blockchain is proposed. Machine learning algorithms are used to categorize the air quality, and blockchain technology guarantees a permanent, tamper-proof record of all air quality data. Such a system might address the persistent issues with data dependability, immutability and trust in pollution control. The execution time of two main operations on blockchain are measured. The execution time of the put block is measured as 10 ms and the get block gets executed in 1 ms that fetches data from the blockchain ledger.

Author 1: Vaneeta M
Author 2: Deepa S R
Author 3: Sangeetha V
Author 4: Kamalakshi Naganna
Author 5: Kruthika S Vasisht
Author 6: Ashwini J
Author 7: Nikitha M
Author 8: Srividya H. R

Keywords: Air pollution; air quality index; machine learning; blockchain technology

Download PDF

Paper 33: Optimized Strategy for Inter-Service Communication in Microservices

Abstract: In the last decade, many enterprises have moved their software deployments to the cloud. As a result of this transmission, the cloud providers stepped ahead and introduced various new technologies for their offerings. People cannot gain the expected advantages from cloud-based solutions merely by transferring monolithic architecture-based software to the cloud since the cloud is natively designed for lightweight artifacts. Nowadays, the end user requirements rapidly change. Hence, the software should accommodate those accordingly. On the contrary, with Monolithic architecture, meeting that requirement change based on extensibility, scalability, and modern software quality attributes is quite challenging. The software industry introduced microservice architecture to overcome such challenges. Therefore, most backend systems are designed using this architectural pattern. Microservices are designed as small services, and those services are deployed in the distributed environment. The main drawback of this architecture is introducing additional latency when communicating with the inter-services in the distributed environment. In this research, we have developed a solution to reduce the interservice communication latency and enhance the overall application performance in terms of throughput and response time. The developed solution uses an asynchronous communication pattern using the Redis Stream data structure to enable pub-sub communication between the services. This solution proved that the most straightforward implementation could enhance the overall application performance.

Author 1: Sidath Weerasinghe
Author 2: Indika Perera

Keywords: Microservices; software architecture; inter-service communication; performance; streams

Download PDF

Paper 34: Deep Learning based Analysis of MRI Images for Brain Tumor Diagnosis

Abstract: This Identification and examination of brain tumour are critical components of any indication system, as evidenced by extensive research and methodological advancement over the years. As part of this approach, an efficient automated system must be put in place to enhance the rate of tumor identification. Today, manually examining thousands of MRI images to locate a brain tumor is arduous and imprecise. It may impair patient care. Since it incorporates several picture datasets, it might be time-consuming. Tumor cells present in the brain look a lot like healthy tissue, making it hard to distinguish between the two while doing segmentation. In this study, we present an approach for classification and prediction of MRI images of the brain using a convolutional neural network, conventional classifiers, and deep learning. Here we have proposed a new method for the automatic and exact categorization of brain tumour utilizing a two-stage feature composition of deep convolutional neural networks (CNNs). We used a deep learning approach to categorize MRI scans into several pathologies, including gliomas, meningiomas, benign lesions, and pituitary tumour, after first extracting characteristics from the scans. Additionally, the most accurate classifier is selected from a pool of five possible classifiers. The principal components analysis (PCA) is used to identify the most important characteristics from the retrieved features, which are then used to train the classifier. We develop our proposed model in Python, utilizing TensorFlow and Keras since it is an effective language for programming and performing work quickly. In our work, CNN got a 98.6% accuracy rate, which is better than what has been done so far.

Author 1: Srinivasarao Gajula
Author 2: V. Rajesh

Keywords: Convolutional neural networks (CNN); magnetic resonance imaging (MRI); principal components analysis (PCA)

Download PDF

Paper 35: Classification of Psychological Disorders by Feature Ranking and Fusion using Gradient Boosting

Abstract: Negative emotional regulation is a defining element of psychological disorders. Our goal was to create a machine-learning model to classify psychological disorders based on negative emotions. EEG brainwave dataset displaying positive, negative, and neutral emotions. However, negative emotions are responsible for psychological health. In this paper, research focused solely on negative emotional state characteristics for which the divide-and-conquer approach has been applied to the feature extraction process. Features are grouped into four equal subsets and feature selection has been done for each subset by feature ranking approach based on their feature importance determined by the Random Forest-Recursive Feature Elimination with Cross-validation (RF-RFECV) method. After feature ranking, the fusion of the feature subset is employed to obtain a new potential dataset. 10-fold cross-validation is performed with a grid search created using a set of predetermined model parameters that are important to achieving the greatest possible accuracy. Experimental results demonstrated that the proposed model has achieved 97.71% accuracy in predicting psychological disorders.

Author 1: Saba Tahseen
Author 2: Ajit Danti

Keywords: Electroencephalograph (EEG); psychological disorders; negative state emotions; gridSearchCV; gradient boosting classifier

Download PDF

Paper 36: Public Response to the Legalization of The Criminal Code Bill with Twitter Data Sentiment Analysis

Abstract: The Criminal Code Bill, also known as Rancangan Kitab Undang-undang Hukum Pidana (RKUHP), passed in the House of Representatives (DPR) on December 6, 2022, is being debated because several issues need to be fixed. Therefore, research was conducted to determine the public's reaction to the ratification of the Criminal Code Bill by analyzing Twitter data. This study aims to obtain a general response to the legalized RKUHP. We use sentiment analysis, a text-processing method, to get data from the public. To do this, we used N-grams (unigrams, bigrams, and trigrams) along with three algorithms: Naïve Bayes, Classification and Regression Tree (CART), and Support Vector Machine (SVM). The result of sentiment analysis found that 51% of tweets were positive about the ratification of the RKUHP, and 49% were negative. In addition, it was also found that SVM has the best accuracy compared to other algorithms, with an accuracy value of 0.81 on the unigram combination.

Author 1: Deny Irawan
Author 2: Dana Indra Sensuse
Author 3: Prasetyo Adi Wibowo Putro
Author 4: Aji Prasetyo

Keywords: Sentiment analysis; RKUHP; support vector Machine (SVM); Naïve Bayes; classification and regression tree (CART)

Download PDF

Paper 37: Evaluation of QoS over IEEE 802.11 Wireless Network in the Implementation of Internet Protocols Mobility Supporting

Abstract: Now-a-days, the internet is an essential part of our digital lives. With the growing number of users, the ultimate goal is to enable all users to stay connected to the internet at anytime and anywhere, regardless of their mobility. Any delay or jitter in the system can cause a deterioration in the performance of multimedia services, such as video streaming, or cause websites to partially load. The current Internet Protocol version 4 (IPv4) cannot handle all the IP addressing requirements, while the next generation Internet Protocol version 6 (IPv6) has been developed to solve some of these problems by improving the quality of service and providing many other features. The primary contribution of this paper is to investigate the evaluation of Quality of Service (QoS) functionality, including end-to-end delay, throughput, jitter, and packet loss, in WLAN mobility environments for MIPv4 to MIPv6 using the OMNeT++ simulator.

Author 1: Narimane Elhilali
Author 2: Mostapha Badri
Author 3: Mouncef Filali Bouami

Keywords: QoS; MIPv4; MIPv6; handover; mobility; priority

Download PDF

Paper 38: Using Deep Learning Algorithms to Diagnose Coronavirus Disease (COVID-19)

Abstract: With the rapid development in the area of Machine Learning (ML) and Deep learning, it is important to exploit these tools to contribute to mitigating the effects of the coronavirus pandemic. Early diagnosis of the presence of this virus in the human body can be crucially helpful to healthcare professionals. In this paper, three well-known Convolutional Neural Network deep learning algorithms (VGGNet 16, GoogleNet and ResNet50) are applied to measure their ability to distinguish COVID-19 patients from other patients and to evaluate the best performance among these algorithms with a large dataset. Two stages are conducted, the first stage with 14994 x-ray images and the second one with 33178. Each model has been applied with different batch sizes 16, 32 and 64 in each stage to measure the impact of data size and batch size factors on the accuracy results. The second stage achieved accuracy better than the first one and the 64 batch size gain best results than the 16 and 32. ResNet50 achieves a high rate of 99.31, GoogleNet model achieves 95.55, while VGG16 achieves 96.5. Ultimately, the results affect the process of expediting the diagnosis and referral of these treatable conditions, thereby facilitating earlier treatment, and resulting in improved clinical outcomes.

Author 1: Nfayel Alanazi
Author 2: Yasser Kotb

Keywords: Component; COVID-19; transfer learning; deep learning; ResNet50; VGG16; GoogleNet

Download PDF

Paper 39: Enhanced Optimized Classification Model of Chronic Kidney Disease

Abstract: Chronic kidney disease (CKD) is one of the leading causes of death across the globe, affecting about 10% of the world's adult population. Kidney disease affects the proper function of the kidneys. As the number of people with chronic kidney disease (CKD) rises, it is becoming increasingly important to have accurate methods for detecting CKD at an early stage. Developing a mechanism for detecting chronic kidney disease is the study's main contribution to knowledge. In this study, preventive interventions for CKD can be explored using machine learning techniques (ML). The Optimized deep belief network (DBN) based on Grasshopper's Optimization Algorithm (GOA) classifier with prior Density-based Feature Selection (DFS) algorithm for chronic kidney disease is described in this study, which is called "DFS-ODBN." Prior to the DBN classifier, whose parameters are optimized using GOA, the proposed method eliminates redundant or irrelevant dimensions using DFS. The proposed DFS-ODBN framework consists of three phases, preprocessing, feature selection, and classification phases. Using CKD datasets, the suggested approach is also tested, and the performance is evaluated using several assessment metrics. Optimized-DBN achieves its maximum performance in terms of sensitivity, accuracy, and specificity, the proposed DFS-ODBN demonstrated accuracy of 99.75 percent using fewer features comparing with other techniques.

Author 1: Shahinda Elkholy
Author 2: Amira Rezk
Author 3: Ahmed Abo El Fetoh Saleh

Keywords: Machine learning (ML); feature selection (FS); chronic kidney disease (CKD); deep belief network (DBN); grasshopper's optimization algorithm (GOA)

Download PDF

Paper 40: Automated Categorization of Research Papers with MONO Supervised Term Weighting in RECApp

Abstract: Natural Language Processing, specifically text classification or text categorization, has become a trend in computer science. Commonly, text classification is used to categorize large amounts of data to allocate less time to retrieve information. Students, as well as research advisers and panelists, take extra effort and time in classifying research documents. To solve this problem, the researchers used state-of-the-art supervised term weighting schemes, namely: TF-MONO and SQRTF-MONO and its application to machine learning algorithms: K-Nearest Neighbor, Linear Support Vector, Naive Bayes Classifiers, creating a total of six classifier models to ascertain which of them performs optimally in classifying research documents while utilizing Optical Character Recognition for text extraction. The results showed that among all classification models trained, SQRTF-MONO and Linear SVC outperformed all other models with an F1 score of 0.94 both in the abstract and the background of the study datasets. In conclusion, the developed classification model and application prototype can be a tool to help researchers, advisers, and panelists to lessen the time spent in classifying research documents.

Author 1: Ivic Jan A. Biol
Author 2: Rhey Marc A. Depositario
Author 3: Glenn Geo T. Noangay
Author 4: Julian Michael F. Melchor
Author 5: Cristopher C. Abalorio
Author 6: James Cloyd M. Bustillo

Keywords: Text classification; supervised tern weighting schemes; optical character recognition; machine learning algorithms

Download PDF

Paper 41: R-Diffset vs. IR-Diffset: Comparison Analysis in Dense and Sparse Data

Abstract: The mining of concealed information from databases using Association Rule Mining seems to be promising. The successful extraction of this information will give a hand to many areas by aiding them in the process of finding solutions, economic projecting, commercialization policies, medical inspections, and numbers of other problems. ARM is the most outstanding method in the mining of remarkable related configurations from any groups of information. The important patterns encountered are categorized as recurrent/frequent and non-recurrent/infrequent. Most of the previous data mining methods concentrated on horizontal data set-ups. Nevertheless, recent studies have shown that vertical data formats are becoming the main concerns. One example of vertical data format is Rare Equivalence Class Transformation (R-Eclat). Due to its efficacy, R-Eclat algorithms have been commonly applied for the processing of large datasets. The R-Eclat algorithm is actually comprised of four types of variants. However, our work will only focus on the R-Diffset variant and Incremental R-Diffset (IR-Diffset). The performance analysis of the R-Diffset and IR-Diffset algorithms in the mining of sparse and dense data are compared. The processing time for R-Diffset algorithm, especially for sequential processing is very long. Thus, the incremental R-Diffset (IR-Diffset) has been established to solve this problem. While R-Diffset may only process the non-recurrent itemsets mining process in sequential form, IR-Diffset on the other hand has the capability to execute sequential data that have been fractionated. The advantages of this newly developed IR-Diffset may become a potential candidate in providing a time-efficient data mining process, especially those involving the large sets of data.

Author 1: Julaily Aida Jusoh
Author 2: Sharifah Zulaikha Tengku Hassan
Author 3: Wan Aezwani Wan Abu Bakar
Author 4: Syarilla Iryani Ahmad Saany
Author 5: Mohd Khalid Awang
Author 6: Norlina Udin @ Kamaruddin

Keywords: R-Diffset; IR-Diffset; dense data; sparse data; comparison analysis

Download PDF

Paper 42: A Fully Immersive Virtual Reality Cycling Training (vProCycle) and its Findings

Abstract: Virtual reality (VR) technology is popularly applied in various sports training such as cycling, rowing, soccer, tennis and many more. In VR cycling, however, cyclists are not able to fully immerse themselves during the training due to the hardware and applications limitations required in the setup. In order to be fully immersed during the training, cyclists need to have similar effects to an outdoor training where they will experience cycling resistance, temperature effect, altitude, visual, and audio. For this reason, dedicated stimulus effectors or hardware are required to create these expected effects. On cycling resistance, a realistic cycling experience can be simulated by using a special device that simulates a resistance to the back wheel when cycling uphill in the VR simulation. In addition, the back wheel resistance would need to match the view displayed while paddling on an elevation slope. For higher immersion purposes, and the effect of temperature must be created that matches with the view visible in the display. For example, while the cyclist is on top of a virtual mountain, the cyclist would want to feel the effects of high altitude and low temperature. These stimulus effectors affect the realism experience while cycling in the VR simulation training. In the authors’ previous papers, the setup using a combination of stimulus effectors including uphill elevation climb, altitude, temperature, interaction, visual, and audio were integrated into a product called vProCycle. The study tested on vProcycle was conducted with an assumption that virtual reality can enhance the experience of physical cycling training. The objective of this study is to determine whether or not vProCycle may improve cyclists’ performance. This paper will discuss in detail the findings from data gathered during the experiment using vProCycle. More specifically, the findings are focused on the speed and the heart rate beats per minute which determine their performance improvement.

Author 1: Imran Bin Mahalil
Author 2: Azmi Bin Mohd Yusof
Author 3: Nazrita Binti Ibrahim
Author 4: Eze Manzura Binti Mohd Mahidin
Author 5: Ng Hui Hwa

Keywords: Virtual Reality (VR); presence level; technology acceptance; cycling performance; VR cycling training; vProCycle

Download PDF

Paper 43: First Responders Space Subdivision Framework for Indoor Navigation

Abstract: Indoor navigation is crucial, particularly during indoor disasters such as fires. However, current spatial subdivision models struggle to adapt to the dynamic changes that occur in such situations, making it difficult to identify the appropriate navigation space, and thus reducing the accuracy and efficiency of indoor navigation. This study presents a new framework for indoor navigation that is specifically designed for first responders, with a focus on improving their response time and safety during rescue operations in buildings. The framework is an extension of previous research and incorporates the combustibility factor as a critical variable to consider during fire disasters, along with definitions of safe and unsafe areas for first responders. An algorithm was developed to accommodate the framework and was evaluated using Pyrosim and Pathfinder software. The framework calculates walking speed factors that affect the path and walking speed of first responders, enhancing their chances of successful evacuation. The framework captures dynamic changes, such as smoke levels, that may impact the navigation path and walking speed of first responders, which were not accounted for in previous studies. The experimental results demonstrate that the framework can identify suitable navigation paths and safe areas for first responders, leading to successful evacuation in as little as 148 to 239 seconds. The proposed framework represents a significant improvement over previous studies and has the potential to enhance the safety and effectiveness of first responders during emergency situations.

Author 1: Asep Id Hadiana
Author 2: Safiza Suhana Kamal Baharin
Author 3: Zahriah Othman

Keywords: Space subdivision; indoor navigation; first responders; indoor disaster

Download PDF

Paper 44: Leaf Diseases Identification and Classification of Self-Collected Dataset on Groundnut Crop using Progressive Convolutional Neural Network (PGCNN)

Abstract: A healthy crop is required to provide high-quality food for daily consumption. Crop leaf diseases have more influence on agronomic production and our country. Earlier, many scholars relied on traditional techniques to detect and classify leaf diseases. Furthermore, classification at an early stage is impossible when there are not enough experts and inadequate research facilities. As technology progresses into our day to day life, an Artificial Intelligence subset called Deep Learning (DL) models plays a vital role in the automatic identification of groundnut leaf diseases. The essential for controlling diseases that are spread to the healthy development of groundnut farming. Deep Learning can resolve the issues of finding leaf diseases early and effectively. Most of the researchers concentrate on detecting leaf diseases by doing research in Machine Learning (ML) approaches, which leads to low accuracy and high loss. To achieve better accuracy and decreases the loss in the DL model by identifying the leaf diseases of groundnut crops at an early stage, we propose the Progressive Groundnut Convolutional Neural Network (PGCNN) model. This paper mainly focuses on identifying and classifying groundnut leaf diseases with a self-collected dataset which is collected from the various climatic conditions around the village located nearby Pudukkottai district, Tamil Nadu, India. The common diseases that occurred in those areas were gathered namely early spot, late spot, rust, and rosette. Model Performance metrics analysis was done to evaluate the model performance and also compared with the various DL architectures like AlexNet, VGG11, VGG13, VGG16, and VGG19. The proposed models have achieved a training accuracy of 99.39% and a validation accuracy of 97.58%, continuing with an overall accuracy of 97.58%.

Author 1: Anna Anbumozhi
Author 2: Shanthini A

Keywords: Leaf Diseases Identification (LDI); Progressive Groundnut Convolutional Neural Networks (PGCNN); Self-Collected Dataset; AlexNet; VGG Models

Download PDF

Paper 45: Enhancing Image for CNN-based Diagnostic of Pediatric Pneumonia through Chest Radiographs

Abstract: In underdeveloped nations, severe lower respiratory infections are the principal reasons of infant mortality. The best treatments and early diagnosis are now being used to alleviate this issue. In developing nations, better treatment and prevention approaches are still required. Clinical, microbial, and radiographic clinical studies have a broad range of applicability within and across populations, and it much depends on the knowledge and resources that are made accessible in different situations. The most appropriate procedure is a chest radiograph (CXR), although pediatric chest X-ray techniques using machine intelligence are uncommon. A strong system is required to diagnose pediatric pneumonia. Authors provide a computer-aided diagnosis plan for the chest X-ray scans to address this. This investigation provides a deep learning-based intelligent healthcare that can reliably diagnose pediatric pneumonia. In order to improve the appearance of CXR pictures, the suggested technique also employs white balancing accompanied with contrast enhancement as a preliminary step. With an AUC of 99.1 on the testing dataset, the suggested approach outscored other state-of-the-art approaches and produced impressive results. Additionally, the suggested approach correctly classified chest X-ray scans as normal and pediatric pneumonia with a classification accuracy of 98.4%.

Author 1: Vaishali Arya
Author 2: Tapas Kumar

Keywords: Contrast enhancement; convolution neural network; pediatric pneumonia; radiography; white balancing

Download PDF

Paper 46: Long Short-Term Memory for Non-Factoid Answer Selection in Indonesian Question Answering System for Health Information

Abstract: Providing reliable health information to a community can help raise awareness of the dangers of diseases, their causes, methods of prevention, and treatment. Indonesians are facing various health problems partly due to the lack of health information; hence, the community needs media that can effectively provide reliable health information, namely a question answering (QA) system. The frequently asked questions are non-factoid questions. The development of answer selection based on the classical approach requires distinctive engineering features, linguistic tools, or external resources. It can be solved using deep learning approach such as Convolutional Neural Networks (CNN). However, this model cannot capture the sequence of words in both questions and answers. Therefore, this study aims to implement a long short-term memory (LSTM) model to effectively exploit long-range sequential context information for an answer selection task. In addition, this study analyses various hyper-parameters of Word2Vec and LSTM, such as the dimension, context window, dropout, hidden unit, learning rate, and margin; the corresponding values that yield the best mean reciprocal rank (MRR) and mean average precision (MAP) are found to be 300, 15, 0.25, 100, 0.01, and 0.1, respectively. The best model yields MAP and MRR values of 82.05% and 91.58%, respectively. These results experienced an increase in MAP and MRR of 18.68% and 46.11%, respectively, compared to CNN as the baseline model.

Author 1: Retno Kusumaningrum
Author 2: Alfi F. Hanifah
Author 3: Khadijah Khadijah
Author 4: Sukmawati N. Endah
Author 5: Priyo S. Sasongko

Keywords: Answer selection; health information; long short-term memory; LSTM; question answering

Download PDF

Paper 47: Assessment of the Healthcare Administration of Senior Citizens from Survey Data using Sentiment Analysis

Abstract: Healthcare is most frequently used by older people and understanding how they feel about the way healthcare administration gives them the attention and support they need, is crucial to building a healthcare system that is effective in meeting their needs. This study determined the seniors' opinions on the healthcare administration by employing SurveyMonkey, a robust online survey tool as an opinion miner. The study used the Orange application, which made data processing simple, to gauge the seniors' opinions toward healthcare administration by analyzing text sentiment using the VADER Sentiment Analysis, which may distinguish between the polarity of positive, negative, or neutral emotions as well as their intensity. Results showed that the majority of seniors (51.1%) had a negative response to healthcare administration, whereas 47.9% had a neutral response and 1.0% had a positive response. Based on the study, the government should enhance its senior citizens’ healthcare services to better satisfy their demands and ensure their happiness. This is clear from the respondents' feedback regarding the services they would like to utilize and how they believe they may be improved. Additionally, the findings provided sufficient information for future consideration to enhance seniors' satisfaction with developmental activities and programs and improve healthcare administration.

Author 1: Ramona Michelle M. Magtangob
Author 2: Thelma D. Palaoag

Keywords: Sentiment analysis; opinion mining; senior citizen; healthcare services

Download PDF

Paper 48: Hierarchical Pretrained Deep Learning Features for the Breast Cancer Classification

Abstract: Breast cancer is a common and fatal disease among women worldwide. Accurately and early diagnosing of breast cancer plays a pivotal role in improving the prognosis of patients. Recently, advanced techniques of artificial intelligence and natural image classification have been used for the breast cancer image classification task and have become a hot topic for research in machine learning. This paper proposes a fully automatic computerized method for breast cancer classification using two well-established pretrained CNN models, namely VGG16 and ResNet50. Next, the feature extraction process is used to extract features in a hierarchical manner to train a support vector machine classifier. Evaluating the proposed model shows achieving 92% accuracy. In addition, this paper investigates the effect of different factors, highlights its findings, and provides future directions for the research to develop more advanced models.

Author 1: Abeer S. Alsheddi

Keywords: Feature extraction; CNN models; Pretrained models; breast cancer classification

Download PDF

Paper 49: A Survey on Attention-Based Models for Image Captioning

Abstract: Image captioning task is highly used in many real-world applications. The captioning task is concerned with understanding the image using computer vision methods. Then, natural language processing methods are used to produce a description for the image. Different approaches were proposed to solve this task, and deep learning attention-based models have been proven to be the state-of-the-art. A survey on attention-based models for image captioning is presented in this paper including new categories that were not included in other survey papers. The attention-based approaches are classified into four main categories, further classified into subcategories. All categories and subcategories of the attention-based approaches are discussed in detail. Furthermore, the state-of-the-art approaches are compared and the accuracy improvements are stated especially in the transformer-based models, and a summary of the benchmark datasets and the main performance metrics is presented.

Author 1: Asmaa A. E. Osman
Author 2: Mohamed A. Wahby Shalaby
Author 3: Mona M. Soliman
Author 4: Khaled M. Elsayed

Keywords: Image captioning; attention model; deep learning; computer vision; natural language processing

Download PDF

Paper 50: Towards an Automatic Speech-to-Text Transcription System: Amazigh Language

Abstract: Various studies inside the domain of research and the development of automatic speech recognition (ASR) technologies for several languages have not yet been published and thoroughly investigated. Nevertheless, the unique acoustic features of the Amazigh language, for example, Amazigh's consonant emphasis, pose many obstacles to the development of automatic speech recognition systems. In this study, we examine Amazigh language voice recognition. We treat the problem by focusing on transitions in vowel and consonant sounds and formant frequencies of phonemes. We present a hybrid strategy for phoneme separation based on energy differences. This includes analysis of consonant and vowel features, and identification methods based on formant analysis.

Author 1: Ahmed Ouhnini
Author 2: Brahim Aksasse
Author 3: Mohammed Ouanan

Keywords: Speech recognition system; Amazigh language; analyzing formants and pitch; speech corpus; artificial intelligence

Download PDF

Paper 51: Graphical User Interfaces Generation from BPMN (Business Process Model and Notation) via IFML (Interaction Flow Modeling Language) up to PSM (Platform Specific Model) Level

Abstract: The fundamental concept behind the MDA (Model Driven Architecture) approach is the development of many models, first the Computation Independent Model (CIM), then the Platform Independent Model (PIM), and lastly the Platform Specific Model (PSM) for the concrete implementation of the system. Web applications are just one example of customized software that is now being developed at an increasing rate. Interaction Flow Modeling Language (IFML) was developed to represent the front end of any program that necessitates a powerful interaction with a user through the use of an interface, regardless of the technical details of its implementation. There are various modeling tools for IFML; the Webratio tool is an illustration that facilitates the generation of the entire web application. This article discusses the model transformations in the MDA’s approach, starting from the CIM level up to the PSM level through the PIM level. To begin, we created the Business Process Model and Notation (BPMN) and IFML metamodels in Eclipse tool, we created also the BPMN model, and we get the IFML model by applying the shift rules in Atlas Transformation Language (ATL). Finally, we generated the application using a standard tool that implements IFML Webratio tool. A CRUD (Create, Read, Update, and Delete) features for the after-sales service case study were provided to illustrate the conversion strategy from the CIM level via the PIM level to the PSM level.

Author 1: Abir Sajji
Author 2: Yassine Rhazali
Author 3: Youssef Hadi

Keywords: MDA (Model Driven Architecture); CIM (Computation Independent Model); PIM (Platform Independent Model); PSM (Platform Specific Model); Model transformations; Graphical User Interfaces; BPMN (Business Process Model and Notation); IFML (Interaction Flow Modeling Language); Webratio tool

Download PDF

Paper 52: A Fuzzy Logic based Solution for Network Traffic Problems in Migrating Parallel Crawlers

Abstract: Search engines are the instruments for website navigation and search, because the Internet is big and has expanded greatly. By continuously downloading web pages for processing, search engines provide search facilities and maintain indices for web documents. Online crawling is the term for this process of downloading web pages. This paper proposes solution to network traffic problem in migrating parallel web crawler. The primary benefit of a parallel web crawler is that it does local analysis at the data's residence rather than inside the web search engine repository. As a result, network load and traffic are greatly reduced, which enhances the performance, efficacy, and efficiency of the crawling process. Another benefit of moving to a parallel crawler is that as the web gets bigger, it becomes important to parallelize crawling operations in order to retrieve web pages more quickly. A web crawler will produce pages of excellent quality. When the crawling process moves to a host or server with a specific domain, it begins downloading pages from that domain. Incremental crawling will maintain the quality of downloaded pages and keep the pages in the local database updated. Java is used to implement the crawler. The model that was put into practice supports all aspects of a three-tier, real-time architecture. An implementation of a parallel web crawler migration is shown in this paper. The method for efficient parallel web migration detects changes in the content and structure using neural network-based change detection techniques in parallel web migration. This will produce high-quality pages and detection for changes will always download new pages. Either of the following strategies is used to carry out the crawling process: either crawlers are given generous permission to speak with one another, or they are not given permission to communicate with one another at all. Both strategies increase network traffic. Here, a fuzzy logic-based system that predicts the load at a specific node and the path of network traffic is presented and implemented in MATLAB using the fuzzy logic toolbox.

Author 1: Mohammed Faizan Farooqui
Author 2: Mohammad Muqeem
Author 3: Sultan Ahmad
Author 4: Jabeen Nazeer
Author 5: Hikmat A. M. Abdeljaber

Keywords: Web crawler; incremental crawling; fuzzy logic-based system; fuzzy logic toolbox

Download PDF

Paper 53: A Privacy-Centered Protocol for Enhancing Security and Authentication of Academic Certificates

Abstract: Academic certificate authentication is crucial in safeguarding the rights and opportunities of individuals who have earned academic credentials. This authentication helps prevent fraud and forgery, ensuring that only those who have genuinely earned certificates can use them for education and career opportunities. With the increased use of online education and digital credentials in the digital age, the importance of academic certificate authentication has significantly grown. However, traditional techniques for authentication, such as QR code, barcode, and watermarking, have limitations regarding security and privacy. Therefore, proposing a privacy-centred protocol to enhance the security and authentication of academic certificates is vital to improve the trust and credibility of digital academic certificates, ensuring that individuals' rights and opportunities are protected. In this context, we adopted the Challenge Handshake Authentication (CHA) protocol to propose the Certificate Verification Privacy Control Protocol (CVPC). We implemented it using Python and Flask with a Postgres database and an MVT structure for the application. The results of the implementation demonstrate that the proposed protocol effectively preserves privacy during the academic certificate issuance and verification process. Additionally, we developed a proof of concept to evaluate the proposed protocol, demonstrating its functionality and performance. The PoC provided insights into the strengths and weaknesses of the proposed protocol and highlighted its potential to prevent forgery and unauthorised access to academic certificates. Overall, the proposed protocol has the potential to significantly enhance the security and authenticity of academic certificates, improving the overall trust and credibility of the academic credentialing system.

Author 1: Omar S. Saleh
Author 2: Osman Ghazali
Author 3: Norbik Bashah Idris

Keywords: Academic certificates; privacy-centered protocol; privacy preservation; challenge handshake authentication protocol

Download PDF

Paper 54: A Systematic Literature Review on AI Algorithms and Techniques Adopted by e-Learning Platforms for Psychological and Emotional States

Abstract: Computers are becoming increasingly commonplace in educational settings. As a result of these advancements, a new field known as CEHL (Computing Environment for Human Learning) or e-learning has emerged, where students have access to a variety of services at their convenience. Using an e-learning platform facilitates more efficient, optimized, and successful education. They allow for personalized instruction and on-demand access to relevant, up-to-date material. These e-learning strategies significantly impact learners' emotional and psychological states, which in turn affect their abilities and motivations. Because of the learner's physical and temporal detachment from their tutor, encouraging learners can be challenging, leading to frustration, doubt, and ambivalence. The learner's drive to learn will be weakened, and their emotional and psychological state will be badly impacted as a result, both during and after the learning session. This research aimed to learn about the methods currently used by research facilities to analyze human emotions and mental states. The findings reveal that only e-learning has been used in education and other fundamental technologies, including machine learning, deep learning, signal processing, and mathematical approaches. A wide variety of e-learning-focused real-world applications make use of these methods. Each study subject is explained in depth, and the most frequently used methods are also examined. Finally, we provide a comprehensive analysis of the prior art, our contributions, their ramifications, and a discussion of our shortcomings and suggestions for future research.

Author 1: Lubna A. Alharbi

Keywords: Psychological states; emotional states; e-learning; online platforms; solutions

Download PDF

Paper 55: Privacy and Integrity Verification Model with Decentralized ABE and Double Encryption Storage Scheme

Abstract: To support a wide range of applications, cloud computing has a variety of services. It has a number of positive acceptance tales as well as a couple of negative ones including security breaches. The versatile usage of cloud services to store Sensitive and personal data in cloud become hesitated by many organizations because of security issues. A new model of relying on a third-party auditor (TPA) has been adopted to improve trust and entice adoption between cloud clients (CC). Hence, we require a dynamic approach to control the privacy and integrity problem that occur across the cloud computing. Decentralized Attribute based encryption techniques and FHE approach is used to overwhelmed the issues. In this proposed scheme, the integrity checking is verified and auditor by the TPA without have any knowledge of the data content and double encryption is performed on the data stored in cloud. the data owner encrypts the data using ABK-XE (Attribute Based Key generation with XOR encryption) technique and send it to tag server whose encrypt the data again using ECEA (Elliptical Curve Elgamal) algorithm and generate the signature and unique ID using SHA-1 algorithm then store the data in Cloud Environment. The proposed algorithm is an integration of auditing scheme with Symmetric key Encryption and Homomorphic Encryption.

Author 1: Amrutha Muralidharan Nair
Author 2: R Santhosh

Keywords: Cloud computing; data integrity; ABK-XE; ECEA Algorithm; SHA1

Download PDF

Paper 56: Design of a Hybrid Recommendation Algorithm based on Multi-objective Collaborative Filtering for Massive Cloud Data

Abstract: The current recommendation technology has some problems, such as lack of timeliness, the contradiction between recommendation diversity and accuracy. In order to solve the problem of lack of timeliness, the time factor is introduced when constructing the self-preference model. The cold start problem in the collaborative filtering algorithm is solved by the hybrid similarity calculation method, and the potential preference model is constructed. The two are fused to obtain a hybrid recommendation algorithm to improve the recommendation performance of the algorithm. For the problem of multi-objective contradiction, the NNIA algorithm is used to further optimize the candidate results of mixed recommendation, and the final recommendation list is obtained. Through verification experiments, the results show that the recall rate and accuracy of the fused preference model are better than those of the non-fused model, and the accuracy is 9.57% and 8.23% higher than that of SPM and PPM, and the recall rate is 9.97% and 7.65% higher, respectively. CBCF-NNIA algorithm has high accuracy and diversity of recommendation, and can provide users with rich and diverse text content to meet their own needs.

Author 1: Xiaoli Zhou

Keywords: Self preference; collaborative filtering; potential preferences; mixed recommendation; multi-objective optimization

Download PDF

Paper 57: Equally Spread Current Execution Load Modelling with Optimize Response Time Brokerage Policy for Cloud Computing

Abstract: Cloud computing is one of the significant technologies that is used to provide seamless internet surfing for large-scale applications and data storing purposes. The cloud is described as a large platform that enables users to access data from the internet without needing to buy storing space in their equipment such as a computer. Many studies have analysed the load-balancing technique on the cloud to distribute tasks equally between servers using the Equally Spread Current Execution (ESCE) algorithm. ESCE, which is a dynamic load balancer, has quite a few problems such as average level performance and too long of response time which affected the Quality of Services. This research has simulated a cloud computing concept using the ESCE Load Modelling technique with the CloudAnalyst simulator for three servers of Data Center (DC) locations. The ESCE was simulated to enhance its algorithm’s performance as a load balancer and higher throughput in the cloud environment. The result shows that ESCE average overall response time is shortest when the DC is located at R0 with response times of 15.05s, 13.05s with 10 VMs, and 8.631s with the Optimize Response Time brokerage policy. This research is significant to promote notable load-balancing technique testing for virtualized cloud machines data centers on Quality of Services (QoS) aware tasks for Internet of Things (IoT) services.

Author 1: Anisah Hamimi Zamri
Author 2: Nor Syazwani Mohd Pakhrudin
Author 3: Shuria Saaidin
Author 4: Murizah Kassim

Keywords: Equally spread current execution (ESCE); optimize response time brokerage; cloud computing; load balancer; data modelling

Download PDF

Paper 58: Research on the Derivative Rule and Estimation Methods of Intelligent High-Speed Railway Investment Estimation

Abstract: Taking the investment estimation of intelligent construction of high-speed railway as the research object, based on the historical data of investment of similar high-speed railway projects, this paper builds an explanatory structure model, establishes an system dynamic (SD) model of investment estimation of intelligent construction of high-speed railway, and puts forward suggestions for supplementing the labor value theory and improving the value-added tax. The paper carries out in-depth research and analysis in the following aspects: 1) the list of influencing factors for investment estimation of intelligent construction of high-speed railway in the feasibility study stage is constructed, and the interpretative structural model (ISM) is constructed to sort out the relationship between the influencing factors; 2) the SD model of intelligent construction cost estimation of high-speed railway is established to improve the accuracy of investment estimation of intelligent high-speed railway construction; 3) put forward suggestions and schemes for improving investment estimation content of intelligent construction of high-speed railway under high intelligence; 4) improve and supplement the labor value theory and the value-added tax base.

Author 1: Yang Meng
Author 2: Chuncheng Meng
Author 3: Xiaochen Duan

Keywords: High-speed railway; intelligent construction; investment estimation; interpretative structural model; system dynamics

Download PDF

Paper 59: Early Warning for Sugarcane Growth using Phenology-Based Remote Sensing by Region

Abstract: It is crucial to know crop growing in order to increase agricultural productivity. In sugarcane's case, monitoring growth can be supported by remote sensing. This research aimed to develop an early warning for sugarcane growth using remote sensing with Landsat 8 satellite at a crucial phenological time. The early warning was developed by identifying regional sugarcane growth patterns by analyzing seasonal trends using linear and harmonic regression models. Identification of growth patterns aims to determine the crucial phenological time by calculating the statistical value of the NDVI spectral index. Finally, monitoring the sugarcane growth conditions with various spectral indices for verification: NDVI, NDBaI, NDWI, and NDDI. All processes used Google Earth Engine (GEE) as a cloud-based platform. The results showed that sugarcane phenology from January to June is crucial for monitoring and assessment. The value of the four corresponding indices indicated the importance of monitoring conditions to ensure a healthy sugarcane region. The results showed that two of the four regions were unhealthy during particular periods; unhealthy vegetation values were below 0.489 and vice versa, one due to excess water and the other due to drought.

Author 1: Sudianto Sudianto
Author 2: Yeni Herdiyeni
Author 3: Lilik Budi Prasetyo

Keywords: Google earth engine; landsat 8; monitoring and assessment; sugarcane health

Download PDF

Paper 60: Fault Tolerance Smart Egg Incubation System with Computer Vision

Abstract: Reliability of incubators is one of their most important specifications. Development of wireless, cloud and computer vision based technologies gives new possibilities for work process control and increasing fault tolerance. Regardless of whether the hatching is in the field of mass production or in the breeding of rare species of birds, detecting a critical situation and sending timely notifications can prevent serious losses. Experience shows that network isolated solutions are not reliable enough and good management requires complex algorithms that are beyond the capabilities of a local, single controller. Even with the duplication of some sensors and actuators, incubators without external connection are high risk due to the fact that their controller is a central point in the architecture and can fail, leaving the farmer with no alert about the accident. The report presents a solution that uses periodic checks from cloud structures on the condition and operability of the incubator. In parallel, a video surveillance system analyzes the internal environment and the condition of hatching chicks. When potential and real risks occur, the system sends notifications to the responsible persons even to his or her wrist. Additionally, the proposed smart egg incubation methodology has been found to reduce the amount of time required for farmers to oversee the incubation process by up to 50%, allowing them to focus on other important tasks while still ensuring optimal hatching conditions for their eggs. Overall, the proposed methodology offers a significant improvement in egg incubation efficiency and reliability, with potential applications in both commercial and personal settings.

Author 1: Emiliyan Petkov
Author 2: Teodor Kalushkov
Author 3: Donika Valcheva
Author 4: Georgi Shipkovenski

Keywords: Hatching; incubation; computer vision; cloud architecture; sending alerts; smart farming; internet of things

Download PDF

Paper 61: A Novel Hybrid Deep Learning Framework for Detection and Categorization of Brain Tumor from Magnetic Resonance Images

Abstract: Cellular abnormality leads to brain tumour formation. This is one of the foremost reasons of adult death all over the world. The typical size of a brain tumour increases within 25 days due to its rapid growth. Early brain tumour diagnosis can save millions of lives. For the purpose of early brain tumour identification, an automatic method is necessary. MRI brain tumour detection improves the survival of patients. Tumour visibility is improved in MRI, which facilitates subsequent treatment. To distinguish between brain MRI images with tumour and images without tumour is suggested in this paper. Many approaches in the field of machine learning including Support Vector Machine, Artificial Neural Networks, and KNN classifier have been developed for solving these issues. But these methods are time consuming, inefficient and require complex procedures. For a Computer Assisted Diagnosis system to aid physicians and radiologists in the identification and categorization of tumours, artificial intelligence is used. Deep learning has demonstrated an encouraging efficiency in computer vision systems over the past decade. In this paper, identification and classification of brain tumour from MR images employing BGWO-CNN-LSTM method is proposed. The proposed method on a testing set with 6100 MRI images of four different kinds of brain tumours is utilized. In comparison to earlier research on the same data set, the suggested approach achieved 99.74% accuracy, 99.23% recall and 99.54% specificity which are greater than the other techniques.

Author 1: Yousef Methkal Abd Algani
Author 2: B. Nageswara Rao
Author 3: Chamandeep Kaur
Author 4: B. Ashreetha
Author 5: K. V. Daya Sagar
Author 6: Yousef A. Baker El-Ebiary

Keywords: Brain tumour; BGWO; LSTM; CNN; MRI dataset

Download PDF

Paper 62: Multi Feature DCR based Drug Compound Selection and Recommendation System for Efficient Decision-Making using Genetic Algorithm

Abstract: The performance of treating the cardiac diseases is dependent on the kind of drug being selected. There exist numerous decisive support systems which work according to certain characteristics and factors like drug availability, and popularity. Still, they struggle to achieve expected performance in supporting the medical practitioner. To handle this issue, a multi feature drug curing rate based drug compound selection and recommendation system (MDCRSR) is presented. The method utilizes medical histories and data set of various medical organization around the disease considered. Using the traces, the method identifies the drug compounds and features to perform preprocessing which eliminates the noisy data points. Further, the features of the traces are extracted to perform training with genetic algorithm. At the test phase, the method estimates the fitness measure for different drug combination and compounds by measuring their Drug Curing Rate (DCR). The method performs cross over and mutation to produce various populations of drug compounds. According to the curing rate, the drug compound pattern or population is selected and ranked. The ranked results are populated to the medical practitioner. The method improves the performance of recommendation system as well as drug compound selection.

Author 1: ST. Aarthy
Author 2: J. L. Mazher Iqbal

Keywords: Decisive support Systems; GA; DCR; drug selection; compound selection; fitness; recommendation system; cardiac disease; RMDCRSR

Download PDF

Paper 63: The Predictors of Mobile Banking Usage: A Systematic Literature Review

Abstract: Mobile banking has become an essential method to conduct banking transaction. However, number of users worldwide are still limited. The purpose of this study is to review the literature and understand the status of m-banking adoption, usage, and loyalty. Keywords were used to search for related articles in three databases namely, Web of Science (WoS), Scopus, and Google scholar. Filtering process was conducted to select the most related articles. This has resulted in reviewing 45 articles. The findings showed that number of articles pertaining to m-banking is increasing. Malaysia and Indonesia have the largest number of articles. The technology acceptance model (TAM) is being used widely in the m-banking literature and most of the reviewed studies are empirical with adequate sample size. This explains the increased usage of structural equation model (SEM). The most critical factors for m-banking adoption, usage, and loyalty are service quality, trust, perceived usefulness, perceived ease of use, security, risk, privacy, and social influence. Future research is suggested to examine the m-banking in different region and using mediating and moderating variables to explain the variation in the adoption.

Author 1: Mohammed Abd Al-Munaf Hashim
Author 2: Zainuddin Bin Hassan

Keywords: M-banking; TAM; Service quality; Loyalty; UTAUT

Download PDF

Paper 64: A Novel Approach: Tokenization Framework based on Sentence Structure in Indonesian Language

Abstract: This study proposes a new approach in the sentence tokenization process. Sentence tokenization, which is known so far, is the process of breaking sentences based on spaces as separators. Space-based sentence tokenization only generates single word tokens. In sentences consisting of five words, tokenization will produce five tokens, one word each. Each word is a token. This process ignores the loss of the original meaning of the separated words. Our proposed tokenization framework can generate one-word tokens and multi-word tokens at the same time. The process is carried out by extracting the sentence structure to obtain sentence elements. Each sentence element is a token. There are five sentence elements that is Subject, Predicate, Object, Complement and Adverbs. We extract sentence structures using deep learning methods, where models are built by training the datasets that have been prepared before. The training results are quite good with an F1 score of 0.7 and it is still possible to improve. Sentence similarity is the topic for measuring the performance of one-word tokens compared to multi-word tokens. In this case the multiword token has better accuracy. This framework was created using the Indonesian language but can also use other languages with dataset adjustments.

Author 1: Johannes Petrus
Author 2: Ermatita
Author 3: Sukemi
Author 4: Erwin

Keywords: Token; tokenization; multi-word; sentence structure; sentence elements

Download PDF

Paper 65: An Efficient Real-Time Weed Detection Technique using YOLOv7

Abstract: Since farming is becoming increasingly more expensive, efficient farming entails doing so without suffering any losses, which is what the current situation desires. Weeds are a key issue in agriculture since they contribute significantly to agricultural losses. To control the weed, pesticides are now evenly applied across the entire area. This approach not only costs a lot of money but also harms the environment and people's health. Therefore, spot spray requires an automatic system. When a deep learning embedded system is used to operate a drone, herbicides can be sprayed in the desired location. With the continuous advancement of object identification technology, the YOLO family of algorithms with extremely high precision and speed has been applied in a variety of scene detection applications. We propose a YOLOv7-based object detection approach for creating a weed detection system. Finally, we used the YOLOv7 model with different parameters for training and testing analyzed on the early crop weed dataset and 4weed dataset. Experimental results revealed that the YOLOv7 model achieved the mAP@0.50, f1score, Precision, and Recall values for the bounding boxes as 99.6,97.6, 99.8, and 95.5 respectively on the early crop weed dataset and 78.53, 79.83, 86.34, and 74.24 on 4weed dataset. The Agriculture business can benefit from using the suggested YOLOv7 model with high accuracy in terms of productivity, efficiency, and time.

Author 1: Ch. Lakshmi Narayana
Author 2: Kondapalli Venkata Ramana

Keywords: Weed detection; YOLOv7; early crop weed; deep learning

Download PDF

Paper 66: Sobel Edge Detection Algorithm with Adaptive Threshold based on Improved Genetic Algorithm for Image Processing

Abstract: In this paper, a novel adaptive threshold Sobel edge detection algorithm based on the improved genetic algorithm is proposed to detect edges. Because of the influence of external factors in actual detection process, the result of detection is often not accurate enough when the configured threshold of the target image is far away from the real threshold. Different thresholds of images are calculated by improved genetic algorithm for different images. The calculated threshold is used in edge detection. The experimental results show that the image processed by the improved algorithm has stronger edge continuity. It is shown that proposed algorithm has a better detection effect and applicability than the traditional Sobel algorithm.

Author 1: Weibin Kong
Author 2: Jianzhao Chen
Author 3: Yubin Song
Author 4: Zhongqing Fang
Author 5: Xiaofang Yang
Author 6: Hongyan Zhang

Keywords: Genetic algorithm; Sobel operator; edge detection; adaptive threshold

Download PDF

Paper 67: Compiler Optimization Prediction with New Self-Improved Optimization Model

Abstract: Users may now choose from a vast range of compiler optimizations. These optimizations interact in a variety of sophisticated ways with one another and with the source code. The order in which optimization steps are applied can have a considerable influence on the performance obtained. As a result, we created a revolutionary compiler optimization prediction model. Our model comprises three operational phases: model training, feature extraction, as well as model exploitation. The model training step includes initialization as well as the formation of candidate sample sets. The inputs were then sent to the feature extraction phase, which retrieved static, dynamic, and improved entropy features. These extracted features were then optimized by the feature exploitation phase, which employs an improved hunger games search algorithm to choose the best features. In this work, we used a Convolutional Neural Network to predict compiler optimization based on these selected characteristics, and the findings show that our innovative compiler optimization model surpasses previous approaches.

Author 1: Chaitali Shewale
Author 2: Sagar B. Shinde
Author 3: Yogesh B. Gurav
Author 4: Rupesh J. Partil
Author 5: Sandeep U. Kadam

Keywords: Compiler optimization prediction; feature extraction; feature exploitation; improved hunger games search algorithm; convolutional neural network

Download PDF

Paper 68: Design of an English Web-based Teaching Resource Sharing Platform based on Mobile Web Technology

Abstract: Thanks to the booming technology of computers and multimedia, student-centered online teaching resource platforms have become an important way for students to learn. However, English teaching resource platforms at the present stage fail to effectively integrate the massive and scattered learning resources. Based on this, the study proposes an English online teaching resource sharing platform based on mobile Web technology, using the SOAP protocol to deploy heterogeneous data resources as Web services to achieve interchangeability between heterogeneous resources. In addition, to enhance the efficient use of learning resources by students, the study proposes a hybrid algorithm based on collaborative filtering algorithm and sequential pattern mining algorithm to achieve personalized sequential recommendation for students. The results show that the platform created by the study exhibits excellent performance in terms of resource transfer capability, achieves efficient teaching resource sharing in a short response time and also shows that the proposed recommendation algorithm is highly accurate.

Author 1: Yan Zhang

Keywords: Web service; SOAP; English teaching resources; sharing platform; personalised recommendation

Download PDF

Paper 69: A Study of Encryption for Multimedia Digital Audio Security

Abstract: Driven by the development of multimedia, the encryption of multimedia digital audio has received more attention; however, cryptography-based encryption methods have many shortcomings in encryption of multimedia information, and new encryption methods are urgently needed. This paper briefly introduced cryptography and chaos theory, designed a chaos-based encryption algorithm that combined Logistic mapping and Sine mapping for confusion and used a Hopfield chaos neural network for diffusion, explained the encryption and decryption process of the algorithm, and tested the algorithm. It was found that the keys obtained by the proposed algorithm passed the SP800-22 test, and the correlation between the three encrypted audio and the original audio was 0.0261, -0.0536, and 0.0237, respectively, all of which were small, and the peak signal-to-noise ratio (PSNR) values were -0.348 dB, -7.645 dB, and -3.636 dB, respectively, which were significantly different from the original audio. The NSCR and UACI were also closer to the original values. The results prove that the proposed algorithm has good security and can encrypt the actual multimedia digital audio.

Author 1: Xiaodong Zhou
Author 2: Chao Wei
Author 3: Xiaotang Shao

Keywords: Multimedia digital audio; chaotic theory; encryption; logistic mapping; sine mapping; security

Download PDF

Paper 70: Digital Twins for Smart Home Gadget Threat Prediction using Deep Convolution Neural Network

Abstract: Digital twin is one of the most important innovations in the Internet of Things (IoT) era and business disruption. Digital twins are a growing technology that bridges the gap between the real and the digital. Home automation in the IoT refers to the practice of automatically managing and monitoring smart home electronics by use of a variety of control system methods. The geysers, refrigerators, fans, lighting, fire alarms, kitchen timers, and other electrical and electronic items in the home can all be managed and monitored with the help of a variety of control methods. Digital twins replicate the physical machine in real time and produce data, such as asset degradation, product performance level that may be used by the predictive maintenance algorithm to identify the product functionality levels. The purpose of this research is to design the framework of Digital Twin using machine learning and state estimation algorithms model to assess and predict home appliances based on the probability rate of smart home system gadgets functionality. The main goal of this research is to create a digital twin for smart home gadgets that are used to monitor the health status of these devices for increasing the life time and to reduce maintenance costs. This research presents a Deep Convolution Neural Network based Logistic Regression Model with Digital Twins (DCNN-LR-DT) for accurate prediction of smart home gadget functionality levels and to predict the threats in advance. The proposed model is compared with the traditional models and the results represent that the proposed model performance is better than traditional models.

Author 1: Valluri Padmapriya
Author 2: Muktevi Srivenkatesh

Keywords: Digital twins; deep learning; convolution neural network; logistic regression; internet of things; smart home; IoT gadget functionality; threat prediction

Download PDF

Paper 71: A New Privacy-Preserving Protocol for Academic Certificates on Hyperledger Fabric

Abstract: Academic certificates are integral to an individual's education and career prospects, yet conventional paper-based certificates pose challenges with their transport and vulnerability to forgery. In response to this predicament, institutions have taken measures to release e-certificates, though ensuring authenticity remains a pressing concern. Blockchain technology, recognised for its attributes of security, transparency, and decentralisation, presents a resolution to this problem and has garnered attention from various sectors. While blockchain-based academic certificate management systems have been proposed, current systems exhibit some security and privacy limitations. To address these issues, this research proposes a new Decentralised Control Verification Privacy-Centered (DCVPC) protocol based on Hyperledger Fabric blockchain for preserving the privacy of academic certificates. The proposed protocol aims to protect academic certificates' privacy by granting complete authority over all network nodes, creating channels for universities to have their private environment, and limiting access to the ledger. The protocol is highly secure, resistant to attacks, and allows improved interoperability and automation of the certificate verification process. A proof-of-concept was developed to demonstrate the protocol's functionality and performance. The proposed protocol presents a promising solution for enhancing security, transparency, and privacy of academic certificates. It guarantees that the certificate's rightful owner is correctly identified, and the issuer is widely recognised. This research makes a valuable contribution to the area of blockchain-based academic certificate management systems by introducing a new protocol that addresses the present security and privacy limitations.

Author 1: Omar S. Saleh
Author 2: Osman Ghazali
Author 3: Norbik Bashah Idris

Keywords: Blockchain technology; hyperledger fabric blockchain; privacy preservation; decentralized control verification privacy-centered (DCVPC) protocol; academic certificates

Download PDF

Paper 72: Breast Cancer Prediction using Machine Learning Models

Abstract: Breast cancer is a type of cancer that develops in the cells of the breast. Treatment for breast cancer usually involves X-ray, chemotherapy, or a combination of both treatments. Detecting cancer at an early stage can save a person's life. Artificial intelligence (AI) plays a very important role in this area. Therefore, predicting breast cancer remains a very challenging issue for clinicians and researchers. This work aims to predict the probability of breast cancer in patients. Using machine learning (ML) models such as Multilayer Perceptron (MLP), K-Nearest Neightbot (KNN), AdaBoost (AB), Bagging, Gradient Boosting (GB), and Random Forest (RF). The breast cancer diagnostic medical dataset from the Wisconsin repository has been used. The dataset includes 569 observations and 32 features. Following the data analysis methodology, data cleaning, exploratory analysis, training, testing, and validation were performed. The performance of the models was evaluated with the parameters: classification accuracy, specificity, sensitivity, F1 count, and precision. The training and results indicate that the six trained models can provide optimal classification and prediction results. The RF, GB, and AB models achieved 100% accuracy, outperforming the other models. Therefore, the suggested models for breast cancer identification, classification, and prediction are RF, GB, and AB. Likewise, the Bagging, KNN, and MLP models achieved a performance of 99.56%, 95.82%, and 96.92%, respectively. Similarly, the last three models achieved an optimal yield close to 100%. Finally, the results show a clear advantage of the RF, GB, and AB models, as they achieve more accurate results in breast cancer prediction.

Author 1: Orlando Iparraguirre-Villanueva
Author 2: Andrés Epifanía-Huerta
Author 3: Carmen Torres-Ceclén
Author 4: John Ruiz-Alvarado
Author 5: Michael Cabanillas-Carbonell

Keywords: Prediction; models; machine learning, cells; breast cancer

Download PDF

Paper 73: Placement of Edge Servers in Mobile Cloud Computing using Artificial Bee Colony Algorithm

Abstract: Utilizing smart mobile devices for entertainment, education, and social networking has grown recently. Even though mobile applications are getting more sophisticated and resource-intensive, the computing power of mobile devices is still constrained. Mobile phone applications can perform better by shifting parts of their functions to cloud servers. However, because the cloud is frequently positioned far from mobile phone users, there may be a significant and unpredictable delay in the data transfer between users and the cloud. It is crucial for mobile applications since customers value rapid responses greatly. Users of mobile phones can get close-up access to information technology and cloud computing services thanks to mobile edge computing. In this article, the main goal is to use an artificial bee colony meta-innovative algorithm to solve the problem of placing edge servers in mobile edge computing. Moreover, load balancing between servers is one of the challenges discussed in this article. To deal with this issue, determination the locations of the servers using considering the distribution of workload between servers as a cost function in the artificial bee colony algorithm is a focused issue in this study. The results of the proposed method are compared with the load balancing criteria. The results of K-means compared to the clustering method show the superiority of the proposed method with regard to the loading criteria compared to this clustering method.

Author 1: Bing Zhou
Author 2: Bei Lu
Author 3: Zhigang Zhang

Keywords: Artificial bee colony algorithm, k-means, server placement, mobile cloud computing

Download PDF

Paper 74: Erythemato-Squamous Disease Detection using Best Optimized Estimators of ANN

Abstract: Medical area focused on automating skin cancer detection after the pandemic era of "Monkey Pox". Previous works proposed ANN mechanisms to classify the type of skin cancer. However, all those models implement layers of ANN with standard estimator components like hidden layers implemented using the ReLu activation function, several neurons are generally a power of two and others, but these values are not always perfect. Few researchers implemented optimization techniques for tuning the estimators of A.I. algorithms, but all those mechanisms require more resources and don't guarantee the best values for each estimator. The proposed method analyzes all the essential estimators of every possible neural network layer. Then it applies a modified version of Bayesian optimization because it avoids the disadvantages of Grid and Random optimization techniques. It picks the best estimator by using the conditional probability of naive Bayesian for every combination.

Author 1: Rajashekar Deva
Author 2: G .Narsimha

Keywords: Conditional probability; naive Bayesian; bayesian optimization; grid search; optimization techniques; estimators

Download PDF

Paper 75: Realizing the Quantum Relative Entropy of Two Noisy States using the Hudson-Parthasarathy Equations

Abstract: The idea of noisy states can be derived through a quantum relative entropy over a given time period and construct the average value of X at time based on the system variables. A random Hermitian matrix is used to represent the quantum system observables with BATH states. The Hudson-Parthasarathy (HP equation) context for stochastic processes allows us to simulate quantum relative entropy using quantum Brownian motion. The Sudarshan-Lindblad's density evolution matrix equation was already derivable in generalized form in my previous work. This paper's goal is to illustrate how the HP equation may be used to estimate the density matrix for noise in a perturbed quantum system of a stochastic process. The last stage involves using MATLAB to estimate and simulate a random density matrix and measure the quantum average T_r (ρ(t)X) at various times. These formulas would be helpful in determining how sensitive the evolving/evolved states are to changes in the Hamiltonian of the noise operators in a sensitivity/robustness study of quantum systems.

Author 1: Bhaveshkumar B. Prajapati
Author 2: Nirbhay Kumar Chaubey

Keywords: Schrödinger equation; Ito calculus; quantum relative entropy; Hudson-Parthasarathy equation; quantum noise

Download PDF

Paper 76: Research on Automatic Detection Algorithm for Pedestrians on the Road Based on Image Processing Method

Abstract: Accurate detection of pedestrian targets can effectively improve the performance level of intelligent transportation and surveillance projects. In order to effectively enhance the accuracy of detecting pedestrian targets on the road, this paper first introduced the traditional pedestrian target detection algorithm, proposed the faster recurrent convolutional neural network (RCNN) algorithm to detect pedestrian targets, and improved it to make good use of the convolutional features at different scales. Finally, support vector machine (SVM), traditional Faster RCNN, and optimized Faster RCNN algorithms were compared by simulation experiments. The results showed that the optimized Faster RCNN algorithm had higher detection accuracy and recall rate, obtained a more accurate target localization frame, and detected faster than SVM and traditional Faster RCNN algorithms; the traditional Faster RCNN algorithm had higher detection accuracy and target frame localization accuracy than the SVM algorithm.

Author 1: Qing Zhang

Keywords: Pedestrian detection; recurrent convolutional neural network; scale-invariant feature transform; support vector machine; characteristic scale; Difference of Gaussians operator

Download PDF

Paper 77: Enhanced Multi-Verse Optimizer (TMVO) and Applying it in Test Data Generation for Path Testing

Abstract: Data testing is a vital part of the software development process, and there are various approaches available to improve the exploration of all possible software code paths. This study introduces two contributions. Firstly, an improved version of the Multi-verse Optimizer called Testing Multi-Verse Optimizer (TMVO) is proposed, which takes into account the movement of the swarm and the mean of the two best solutions in the universe. The particles move towards the optimal solution by using a mean-based algorithm model, which guarantees efficient exploration and exploitation. Secondly, TMVO is applied to automatically develop test cases for structural data testing, particularly path testing. Instead of automating the entire testing process, the focus is on centralizing automated procedures for collecting testing data. Automation for generating testing data is becoming increasingly popular due to the high cost of manual data generation. To evaluate the effectiveness of TMVO, it was tested on various well-known functions as well as five programs that presented unique challenges in testing. The test results indicated that TMVO performed better than the original MVO algorithm on the majority of the tested functions.

Author 1: Mohammad Hashem Ryalat
Author 2: Hussam N. Fakhouri
Author 3: Jamal Zraqou
Author 4: Faten Hamad
Author 5: Mamon S. Alzboun
Author 6: Ahmad K. Al hwaitat

Keywords: MVO; optimization; testing; swarm intelligence; multi-verse optimizer

Download PDF

Paper 78: EFASFMM: A Unique Approach for Early Prediction of Type II Diabetics using Fire Fly and Semi-supervised Min-Max Algorithm

Abstract: Non-insulin-reliant, one of the most serious illnesses is diabetes mellitus, often known as type 2 diabetes, and it affects a large number of people. Between 2 and 5 million individuals worldwide die from diabetes each year. If diabetes is identified sooner, it can be managed, and catastrophic dangers including nephropathy, heart stroke, and other conditions linked to it can be avoided. Therefore, early diabetes diagnosis aids in preserving excellent health. Machine learning (ML), which has recently made strides, is now being used in a number of medical health-related fields. The innovative, nature-inspired Firefly algorithm has been shown to be effective at solving a range of numerical optimization issues. While using alliterations, the traditional firefly method employed a fixed step size models for semi-supervised learning (SSL). The firefly is effective for solving classification issues involving both a sizable number of unlabelled data and a limited number of samples with labels. The fuzzy min-max (FMM) family of neural networks in this regard provide the capability of online learning for tackling both supervised and unsupervised situations. Using a special mix of the two proposed algorithms, one of which is utilised for optimization and the other for making early predictions of type 2 diabetes. The findings for the training and testing phases for the parameter’s accuracy, precision, sensitivity, specificity, and F-score are reported as 97.96%, 97.82%, 98.10%, 97.82%, and 97.95% which, when compared to current state-of-the-art methods, are finer.

Author 1: B. Manikyala Rao
Author 2: Mohammed Ali Hussain

Keywords: Fire Fly Algorithm (FFA); machine learning (ML); Semi-supervised Min-Max (SSMM)

Download PDF

Paper 79: Development of a Mobile Application to Reduce the Rate of People with Text Neck Syndrome

Abstract: Now-a-days, it is no surprise that mobile devices have become a very useful tool in the daily tasks of many people worldwide. This is thanks to their various features such as portability, connectivity, entertainment, work tool, etc. However, due to the bad posture that users have when using them, a syndrome called "Text Neck" is produced. This is caused by prolonged use of the devices looking down and tilting the head at different angles. The degree of inclination of the head causes a detrimental effect on the neck joints, so that the greater the degree of inclination the effect of the weight of the head on the neck increases detrimentally. However, currently mobile devices have sensors that help in monitoring the activities of users, in this sense, there is the gyroscope that allows the completion of the position and the accelerometer that tells us the amount of movement of the device. In this sense, a mobile application has been developed that by monitoring the information of the angle of inclination of the device and the time it remains in the same, allows notifying users to adopt a proper position. The aim is to reduce the number of people affected by text neck syndrome.

Author 1: Rosa Perez-Siguas
Author 2: Hernan Matta-Solis
Author 3: Eduardo Matta-Solis
Author 4: Hernan Matta-Perez
Author 5: Luis Perez-Siguas
Author 6: Randall Seminario Unzueta
Author 7: Victoria Tacas-Yarcuri

Keywords: Accelerometer; android; firebase; gyroscope; mobile devices; sensors; text neck

Download PDF

Paper 80: An Early Warning Model for Intelligent Operation of Power Engineering based on Kalman Filter Algorithm

Abstract: The accurate early warning of intelligent operation of power engineering can find the abnormal operation of substation equipment in time and ensure the safe operation of substation equipment. Thus, an early warning model for intelligent operation of power engineering based on Kalman filter algorithm is constructed. In this model, the noise elimination method of substation equipment inspection image based on particle resampling filter algorithm is introduced. After removing the noise information of operation situation inspection image of substation equipment, the gradient direction histogram feature, lab color space feature and edge contour feature in the image are extracted by the multi-feature extraction method for intelligent operation of power engineering based on multi-feature fusion. These features are combined to form the feature description set of equipment operation situation. The feature description set is used as the identification attribute set of the anomaly identification and early warning model for intelligent operation of electric power engineering based on Kalman filter algorithm to complete the anomaly identification and early warning of equipment operation situation. The test shows that when the model is used to observe the temperature change trend of the top layer of the transformer, the temperature error is very small, and the early warning accuracy for the abnormal temperature of the top layer of the transformer is very high, so the abnormal operation of the substation equipment can be found in time.

Author 1: Haopeng Shi
Author 2: Xiang Li
Author 3: Pei Sun
Author 4: Najuan Jia
Author 5: Qiyan Dou

Keywords: Kalman filter; power engineering; intelligent operation; early warning model; image denoising; feature extraction

Download PDF

Paper 81: Automated Pneumonia Diagnosis using a 2D Deep Convolutional Neural Network with Chest X-Ray Images

Abstract: Tiny air sacs in one or both lungs become inflamed as a result of the lung infection known as pneumonia. In order to provide the best possible treatment plan, pneumonia must be accurately and quickly diagnosed at initial stages. Nowadays, a chest X-ray is regarded as the most effective imaging technique for detecting pneumonia. However, performing chest X-ray analysis may be quite difficult and laborious. For this purpose, in this study we propose deep convolutional neural network (CNN) with 24 hidden layers to identify pneumonia using chest X-ray images. In order to get high accuracy of the proposed deep CNN we applied an image processing method as well as rescaling and data augmentation methods as shear_range, rotation, zooming, CLAHE, and vertical_flip. The proposed approach has been evaluated using different evaluation criteria and has demonstrat-ed 97.2%, 97.1%, 97.43%, 96%, 98.8% performance in terms of accuracy, precision, recall, F-score, and AUC-ROC curve. Thus, the applied deep CNN obtain a high level of performance in pneumonia detection. In general, the provided approach is intended to aid radiologists in making an accurate pneumonia diagnosis. Additionally, our suggested models could be helpful in the early detection of other chest-related illnesses such as COVID-19.

Author 1: Kamila Kassylkassova
Author 2: Batyrkhan Omarov
Author 3: Gulnur Kazbekova
Author 4: Zhadra Kozhamkulova
Author 5: Mukhit Maikotov
Author 6: Zhanar Bidakhmet

Keywords: Pneumonia; deep learning; CNN; chest X-rays; radiology

Download PDF

Paper 82: Classification of Human Sperms using ResNet-50 Deep Neural Network

Abstract: Infertility is a disease which scientists around the world are concerned with. The disease of infertility also is a worldwide health concern of many people in the community. The andrologists are continually searching for further developed techniques for any related problems. The intracytoplasmic sperm injection (ICSI) method is a widely recognized strategy for accomplishing pregnancy and considered as one of the best methods for infertility treatment worldwide. Choosing the best sperms are done using the vision through the specimen which is reliant on the abilities and the cleverness of the embryologists and as such inclined to human errors. Subsequently, a system that detects the normal sperms automatically is required for speedy and more precise outcomes. Deep learning approaches are usually effective for classification and detection purposes. This paper uses the Residential Energy Services Network (ResNet-50) deep learning architecture to recognize human sperms after classification of human sperm heads. The ResNet-50 proposed model achieved an accuracy of 96.66%. This proposed model demonstrated its efficiency at the detection of healthy sperms. The healthy sperms are used for the injection into eggs by the andrologists who always look for easier and more advanced methods in order to increase the success rate of ICSI process.

Author 1: Ahmad Abdelaziz Mashaal
Author 2: Mohamed A. A. Eldosoky
Author 3: Lamia Nabil Mahdy
Author 4: Kadry Ali Ezzat

Keywords: Healthy sperms; sperm heads; infertility; classification; convolution; ResNet-50

Download PDF

Paper 83: Research on Image Sharpness Enhancement Technology based on Depth Learning

Abstract: Image technology is widely used in security, traffic, monitoring, and other social activities. However, these images carrying detailed information will have feature distortion due to various external physical factors in social ingestion, transmission, and storage, resulting in poor image quality and clarity. Resolution determines the definition of an image. Super-resolution reconstruction is the process of transforming a low-resolution picture into a high-resolution image. To enhance the image clarity, this experiment introduces the advantages and disadvantages of the Super Resolution Convolutional Network (SRCNN) and Fast Super Resolution Convolutional Neural Network (FSRCNN) model and then constructs an image super resolution method based on DSRCNN. The algorithm consists of two sub-network blocks, an enhancement block and a purification block. The model first uses two Convolutional Neural Networks (CNN) to obtain complementary low-frequency information that improves the model's learning ability; next, it employs an enhancement block to fuse the image features of two paths via residual operation and sub-pixel convolution to prevent the loss of low-resolution image information; finally, it employs a feature purification block to refine high-frequency information that more accurately represents the predicted high-quality image. It is found that the PSNR and SSIM of the DSRCNN model can reach 33.43dB and 0.9157dB, respectively.

Author 1: Wenbao Lan
Author 2: Chang Che

Keywords: Super resolution convolutional network; fast super resolution convolutional neural network; dual super-resolution convolutional network; deep learning; image definition; super resolution; image enhancement

Download PDF

Paper 84: Fall Detection and Monitoring using Machine Learning: A Comparative Study

Abstract: The detection of falls has emerged as an important topic for the public to discuss because of the prevalence and severity of unintentional falls, particularly among the elderly. A Fall Detection System, known as an FDS, is a system that gathers data from wearable Internet-of-Things (IoT) device and classifies the outcomes to distinguish falls from other activities and call for prompt medical aid in the event of a fall. In this paper, we determine either fall or not fall using machine learning prior to our collected fall dataset from accelerometer sensor. From the acceleration data, the input features are extracted and deployed to supervised machine learning (ML) algorithms namely, Support Vector Machine (SVM), Decision Tree, and Naive Bayes. The results show that the accuracy of fall detection reaches 95%, 97 % and 91% without any false alarms for the SVM, Decision Tree, and Naïve Bayes, respectively.

Author 1: Shaima R. M Edeib
Author 2: Rudzidatul Akmam Dziyauddin
Author 3: Nur Izdihar Muhd Amir

Keywords: Fall detection; machine learning; acceleration data; SVM; decision tree; Naïve Bayes; IoT

Download PDF

Paper 85: Online Teaching Design and Evaluation of Innovation and Entrepreneurship Courses in the Context of Education Internationalization

Abstract: In the context of the internationalization of education nowadays, courses in innovation and entrepreneurship have been strongly promoted, and the content and number of topics, etc. of this type of courses are rapidly climbing. In order to enable target users to quickly select courses that they may be interested in, one changed collaborative filtering algorithm based on a multi-feature ranking model is used to extract and rank the features of online courses based on several factors, and then combine the collaborative filtering algorithm to recommend them to users. The results of experiment show that the numerical valuation of accuracy rate and recall rate of the improved algorithm are more than those of the other algorithm with different conditions, and in most cases higher than those of the LDA algorithm, and the user’s evaluation of the recommendation effect also has the highest rating value of the improved algorithm, with the ratings of 4.3, 4.7 and 4.4 in the three groups, and the overall average score is 4.47, indicating that the improved algorithm has significant optimization performance and is suitable for teaching innovation and entrepreneurship in online courses.

Author 1: Chengshe Xing

Keywords: Online course; Collaborative filtering algorithm; Ranking model

Download PDF

Paper 86: Investigating Group Distributionally Robust Optimization for Deep Imbalanced Learning: A Case Study of Binary Tabular Data Classification

Abstract: One of the most studied machine learning challenges that recent studies have shown the susceptibility of deep neural networks to is the class imbalance problem. While concerted research efforts in this direction have been notable in recent years, findings have shown that the canonical learning objective, empirical risk minimization (ERM), is unable to achieve optimal imbalance learning in deep neural networks given its bias to the majority class. An alternative learning objective, group distributionally robust optimization (gDRO), is investigated in this study for imbalance learning, focusing on tabular imbalanced data as against image data that has dominated deep imbalance learning research. Contrary to minimizing average per instance loss as in ERM, gDRO seeks to minimize the worst group loss over the training data. Experimental findings in comparison with ERM and classical imbalance methods using four popularly used evaluation metrics in imbalance learning across several benchmark imbalance binary tabular data of varying imbalance ratios reveal impressive performance of gDRO, outperforming other compared methods in terms of g-mean and roc-auc.

Author 1: Ismail. B. Mustapha
Author 2: Shafaatunnur Hasan
Author 3: Hatem S Y Nabbus
Author 4: Mohamed Mostafa Ali Montaser
Author 5: Sunday Olusanya Olatunji
Author 6: Siti Maryam Shamsuddin

Keywords: Class imbalance; deep neural networks; tabular data; empirical risk minimization; group distributionally robust optimization

Download PDF

Paper 87: A Biologically Inspired Appearance Modeling and Sample Feature-based Approach for Visual Target Tracking in Aerial Images

Abstract: Visual tracking in uncrewed aerial vehicles is challenging because of the target appearance. Various research has been fulfilled to overcome appearance variations and unpredictable moving target issues. Visual saliency-based approaches have been widely studied in biologically inspired algorithms to detect moving targets based on attentional regions (ARs) extraction. This paper proposes a novel visual tracking method to deal with these issues. It consists of two main phases: spatiotemporal saliency-based appearance modeling (SSAM) and sample feature-based target detection (SFTD). The proposed method is based on a tracking-by-detection approach to provide a robust visual tracking system under appearance variation and unpredictable moving target conditions. Correspondingly, a semi-automatic trigger-based algorithm is proposed to handle the phases' operation, and a discriminative-based method is utilized for appearance modeling. In the SSAM phase, temporal saliency extracts the ARs and coarse segmentation. Spatial saliency is utilized for the object’s appearance modeling and spatial saliency detection. Because the spatial saliency detection process is time-consuming for multiple target tracking conditions, an automatic algorithm is proposed to detect the region saliences in a multithreading implementation that leads to low processing time. Consequently, the temporal and spatial saliencies are integrated to generate the final saliency and sample features. The generated sample features are transferred to the sample feature-based target detection (SFTD) phase to detect the target in different images based on samples. Experimental results demonstrate that the proposed method is effective and presents promising results compared to other existing methods.

Author 1: Lili Pei
Author 2: Xiaohui Zhang

Keywords: Visual tracking; biologically inspired; visual saliency detection; appearance modeling; attention region; spatiotemporal

Download PDF

Paper 88: A Study on Distance Personalized English Teaching Based on Deep Directed Graph Knowledge Tracking Model

Abstract: Despite the continuous development of online education models, the effectiveness of online distance education has never been able to meet people’s expectations due to individual difference of learners. How to personalize teaching in a targeted manner and stimulate learners’ independent learning ability has become a key issue. In this study, the multidimensional features of the learning process are mined with the help of the BORUTA feature selection model, and the DKVMN-BORUTA model incorporating multidimensional features is established. This optimized deep knowledge tracking method is combined with graph structure rules. Then, an intelligent knowledge recommendation algorithm based on reinforcement learning is used to construct a fusion approach-based model for distanced personalized teaching and learning of English. The results show that the research proposed fused deep-directed graph knowledge tracking with graph structure rules for remote personalized English teaching model has the lowest AUC value of 0.893 and the highest AUC value of 0.921 on each dataset. The prediction accuracy of the research model is 94.3% and the F1 score is 0.92, which is the highest among the studied models, indicating that the proposed model has a strong performance. The fusion model proposed in the study has a higher accuracy rate of knowledge personalization recommendation than the traditional deep knowledge tracking model, and it can help learners save revision time effectively and improve their overall English performance.

Author 1: Lianmei Deng

Keywords: Distanced personalized English teaching model; knowledge tracking; deep learning; graph structure rules; DKVMN

Download PDF

Paper 89: A Visual Target Representation using Saliency Detection Approach

Abstract: The task of saliency detection is to identify the most important and informative part of a scene. Saliency detection is broadly applied to numerous vision problems, including image segmentation, object recognition, image compression, content-based image retrieval, and moving object detection. Existing saliency detection methods suffer a low accuracy rate because of missing components of saliency regions. This study proposes a visual saliency detection method for the target representation to represent targets more accurately. The proposed method consists of five modules. In the first module, the salient region is extracted through manifold ranking on a graph, which incorporates local grouping cues and boundary priors. Secondly, using a region of interest (ROI) algorithm and the subtraction of the salient region from the original image, other parts of the image, either related or nonrelated to the interested target, are segmented. Lastly, those related and non-related regions are classified and distinguished using our proposed algorithm. Experimental result shows that proposed salient region accurately represent the interested target which can be used for object detection and tracking applications.

Author 1: Shekun Tong
Author 2: Chunmeng Lu

Keywords: Saliency detection; target representation; vision system; object detection

Download PDF

Paper 90: Building a Machine Learning Powered Chatbot for KSU Blackboard Users

Abstract: Chatbots have attracted the interest of many entities within the public and private sectors locally within Saudi Arabia and also globally. Chatbots have many implementations in the education field and can range from enhancing the e-learning experience to answer students' inquiries about course schedules and grades, tracking prerequisites information and elective courses. This work aim is to develop a chatbot engine that helps with frequently asked questions about the Blackboard system, which could be embedded into the Blackboard website. It contains a machine-learning model trained on Arabic datasets. The engine accepts both Arabic textual content as well as English textual content if needed; for commonly used English terminologies. Rasa framework was chosen as the main tool for developing the Blackboard chatbot. The dataset to serve the current need (i.e. Blackboard system) was requested from Blackboard support staff to build the initial dataset and get a sense of the frequently asked questions by KSU Blackboard student users. The dataset is designed to account for as many as possible of KSU Blackboard related inquires to provide the appropriate answers and reduce the workload of Blackboard system support staff. Testing and evaluating the model was a continuous process before and after the model deployment. The model post-tuning metrics were 93.4%, 92.5%, 92.49% for test accuracy, f1-score and precision, respectively. The average reported accuracy in similar studies were near 90% on average as opposed to results reported here.

Author 1: Qubayl Alqahtani
Author 2: Omer Alrwais

Keywords: Chatbot; RASA; conversational agents; machine learning

Download PDF

Paper 91: WEB-based Collaborative Platform for College English Teaching

Abstract: At present, colleges and universities are trying to apply online education. The online college English course teaching cooperation platform is an important part of college English teaching. At present, teachers’ scoring method for students’ online examination on this kind of platform is mainly human scoring, which has a low efficiency. In view of this, based on the characteristics of web, this paper constructs an English test paper scoring algorithm based on text matching degree algorithm and improved KNN algorithm. The data analysis type of the algorithm is mainly prescriptive analysis that is, judging whether to give points according to the characteristics of the data. The automation and high efficiency of the algorithm can save a lot of human costs in the field of online education. The experimental results show that the recall rate of the improved KNN scoring algorithm for specific semantic topics is up to 0.9, and only 7.3% of students report that the algorithm misjudges their grades. The results indicate that the algorithm has the potential to be applied to the Web-based college English course teaching collaboration platform and reduce the workload of teachers and improve their efficiency.

Author 1: Yuwan Zhang

Keywords: Web; text similarity; KNN algorithm; vocabulary matching; network teaching

Download PDF

Paper 92: Predictions of Cybersecurity Experts on Future Cyber-Attacks and Related Cybersecurity Measures

Abstract: The Internet interconnections’ exponential growth has resulted in an increase in cyber-attack occurrences with mostly devastating consequences. Malware is a common tool for performing these attacks in cyberspace. The malefactors would either exploit the present weaknesses or employ the distinctive characteristics of the developing technologies. The cybersecurity community should increase their knowledge on the types and arsenals of cyber-attacks, and security measures against cyber-attacks should be in place as well. Also, advanced and effective malware defense mechanisms should be established. Hence, this study reviews cyber-attack types, measures and security precautions, and professional extrapolations on cyber-attacks future and the associated security measures. Semi-structured interviews were performed, involving five IT managers and nine Cybersecurity Consultants, to obtain the data. The study findings demonstrate prevention as key for data breach risk prevention. Knowledge of common attack methods and the use of cybersecurity software can facilitate individuals and organizations in thwarting hackers and in preserving their data privacy. Two-factor authorization by consumers and new back-end security protocols and security methods, including Artificial intelligence (AI) application, will encumber hacking attempts.

Author 1: Ahmad Mtair AL-Hawamleh

Keywords: Cybersecurity; cybercriminals; cyber-attacks; cyber-security techniques; security precautions

Download PDF

Paper 93: BERT Model-based Natural Language to NoSQL Query Conversion using Deep Learning Approach

Abstract: Databases are commonly used to store complex and distinct information. With the advancement of the database system, non-relational databases have been used to store a vast amount of data as traditional databases are not sufficient for making queries on a wide range of massive data. However, storing data in a database is always challenging for non-expert users. We propose a conversion technique that enables non-expert users to access and filter data as close to human language as possible from the NoSQL database. Researchers have already explored a variety of technologies in order to develop more precise conversion procedures. This paper proposed a generic NoSQL query conversion learning method to generate a Non-Structured Query Language from natural language. The proposed system includes natural language processing-based text preprocessing and the Levenshtein distance algorithm to extract the collection and attributes if there were any spelling errors. The analysis of the result shows that our suggested approach is more efficient and accurate than other state-of-the-art methods in terms of bilingual understudy scoring with the WikiSQL dataset. Additionally, the proposed method outperforms the existing approaches because our method utilizes a bidirectional encoder representation from a transformer multi-text classifier. The classifier process extracts database operations that might increase the accuracy. The model achieves state-of-the-art performance on WikiSQL, obtaining 88.76% average accuracy.

Author 1: Kazi Mojammel Hossen
Author 2: Mohammed Nasir Uddin
Author 3: Minhazul Arefin
Author 4: Md Ashraf Uddin

Keywords: Natural language processing; NoSQL query; BERT model; Levenshtein distance algorithm; artificial neural network

Download PDF

Paper 94: Privacy-Preserving and Trustless Verifiable Fairness Audit of Machine Learning Models

Abstract: In the big data era, machine learning has devel-oped prominently and is widely used in real-world systems. Yet, machine learning raises fairness concerns, which incurs discrimination against groups determined by sensitive attributes such as gender and race. Many researchers have focused on developing fairness audit technique of machine learning model that enable users to protect themselves from discrimination. Existing solutions, however, rely on additional external trust as-sumptions, either on third-party entities or external components, that significantly lower the security. In this study, we propose a trustless verifiable fairness audit framework that assesses the fairness of ML algorithms while addressing potential security issues such as data privacy, model secrecy, and trustworthiness. With succinctness and non-interactive of zero knowledge proof, our framework not only guarantees audit integrity, but also clearly enhance security, enabling fair ML models to be publicly auditable and any client to verify audit results without extra trust assumption. Our evaluation on various machine learning models and real-world datasets shows that our framework achieves practical performance.

Author 1: Gui Tang
Author 2: Wuzheng Tan
Author 3: Mei Cai

Keywords: Security and privacy; machine learning; fairness; cryptography; zero knowledge proof

Download PDF

Paper 95: An OCR Engine for Printed Receipt Images using Deep Learning Techniques

Abstract: The digitization of receipts and invoices, and the recording of expenses in industry and accounting have begun to be used in the field of finance tracking. However, 100%success in character recognition for document digitization has not yet been achieved. In this study, a new Optical Character Recognition (OCR) engine called Nacsoft OCR was developed on Turkish receipt data by using artificial intelligence methods. The proposed OCR engine has been compared to widely used engines, Easy OCR, Tesseract OCR, and the Google Vision API. The benchmarking was made on English and Turkish receipts, and the accuracies of OCR engines in terms of character recognition and their speeds are presented. It is known that OCR character recognition engines perform better at word recognition when provided word position information. Therefore, the performance of the Nacsoft OCR engine in determining the word position was also compared with the performance of the other OCR engines, and the results were presented.

Author 1: Cagri Sayallar
Author 2: Ahmet Sayar
Author 3: Nurcan Babalik

Keywords: Optical Character Recognition (OCR); image processing; deep learning; benchmarking; receipt

Download PDF

Paper 96: A Survey on Blockchain Technology Concepts, Applications and Security

Abstract: In the past decade, blockchain technology has become increasingly prevalent in our daily lives. This technology consists of a chain of blocks that contains the history of transactions and information about its users. Distributed digital ledgers are used in blockchain. A transparent environment is created by using this technology, allowing encrypted secure transactions to be verified and approved by all users. As a powerful tool, blockchain can be utilized for a wide range of useful purposes in everyday life including cryptocurrency, Internet-of-Things (IoT), finance, reputation system, and healthcare. This paper aims to provide an overview of blockchain technology and its security issues for users and researchers. In particular, those who conduct their business using blockchain technology. This paper includes a comparison of consensus algorithms and a description of cryptography. Further, most applications used in blockchain are focused on in this paper also analyzing real attacks and then summarizing security measures in blockchain. Even though Blockchain holds a promising scope of development in several sectors, it is prone to several security and vulnerability issues that arise from different types of blockchain networks which represent a challenge to deal with blockchain. Finally, as a research community, we encourage future research challenges that can be addressed to improve security in blockchain systems.

Author 1: Asma Mubark Alqahtani
Author 2: Abdulmohsen Algarni

Keywords: Blockchain; cryptography; cryptocurrency; consensus algorithms; blockchain security

Download PDF

Paper 97: An Autonomous Role and Consideration of Electronic Health Systems with Access Control in Developed Countries: A Review

Abstract: The electronic healthcare system (EHS) nowadays is essential to access, maintain, store, and share the electronic health records (EHR) of patients. It should provide safer, more efficient, and cost-effective healthcare. There are several challenges with EHS, notably in terms of security and privacy. Nonetheless, many approaches can be utilized to tackle it, and one of them is access control. Even though numerous access control models were presented, traditional methods of access control, such as role-based access control (RBAC), were extensively employed and are still in use today. Currently, the number of EHS equipped with access control keeps growing, and some previous works utilize RBAC only or an autonomous role. However, relying only on a role in today’s advanced technology may jeopardize security and privacy. The previous work also has flaws because of using an ineffective instrument that is costly to maintain and will burden organizations, particularly in developed countries. In this paper, the background and emphasis on the challenges associated with an autonomous role in the EHS are discussed. Following that, this paper provides recommendations and analytical discussion on existing EHSs with access control mechanisms for securing and protecting EHR in developed countries. Finally, instrument information in the form of a SWOT analysis is recommended to replace the present instrument utilized by the previous work for a notion to the organizations in the developed countries to select the best environment for their future or upgrade EHS.

Author 1: Mohd Rafiz Salji
Author 2: Nur Izura Udzir

Keywords: Access control; security; privacy; electronic health-care system; electronic health record; developed countries

Download PDF

Paper 98: Semi-supervised Method to Detect Fraudulent Transactions and Identify Fraud Types while Minimizing Mounting Costs

Abstract: Financial fraud is a complex problem faced by financial institutions, and existing fraud detection systems are often insufficient, resulting in significant financial losses. Researchers have proposed various machine learning-based techniques to enhance the performance of these systems. In this work, we present a semi-supervised approach to detect fraudulent transactions. First, we extract and select features, followed by the training of a binary classification model. Secondly, we apply a clustering algorithm to the fraudulent transactions and use the binary classification model with the SHAP framework to analyze the clusters and associate them with a particular fraud type. Finally, we present an algorithm to detect and assign a fraud type by leveraging a multi-fraud classification model. To minimize the mounting cost of the model, we propose an algorithm to choose an optimal threshold that can detect fraudulent transactions. We work with experts to adapt a risk cost matrix to estimate the mounting cost of the model. This risk cost matrix takes into account the cost of missing fraudulent transactions and the cost of incorrectly flagging a legitimate transaction as fraudulent. In our experiments on a real dataset, our approach achieved high accuracy in detecting fraudulent transactions, with the added benefit of identifying the fraud type, which can help financial institutions better understand and combat fraudulent activities. Overall, our approach offers a comprehensive and efficient solution to financial fraud detection, and our results demonstrate its effectiveness in reducing financial losses for financial institutions.

Author 1: Chergui Hamza
Author 2: Abrouk Lylia
Author 3: Cullot Nadine
Author 4: Cabioch Nicolas

Keywords: Machine learning; semi-supervised learning; fraud; finance; cost analysis

Download PDF

Paper 99: Liver Disease Prediction and Classification using Machine Learning Techniques

Abstract: Recently liver diseases are becoming most lethal disorder in a number of countries. The count of patients with liver disorder has been going up because of alcohol intake, breathing of harmful gases, and consumption of food which is spoiled and drugs. Liver patient data sets are being studied for the purpose of developing classification models to predict liver disorder. This data set was used to implement prediction and classification algorithms which in turn reduces the workload on doctors. In this work, we proposed apply machine learning algorithms to check the entire patient’s liver disorder. Chronic liver disorder is defined as a liver disorder that lasts for at least six months. As a result, we will use the percentage of patients who contract the disease as both positive and negative information We are processing Liver disease percentages with classifiers, and the results are displayed as a confusion matrix. We proposed several classification schemes that can effectively improve classification performance when a training data set is available. Then, using a machine learning classifier, good and bad values are classified. Thus, the outputs of the proposed classification model show accuracy in predicting the result.

Author 1: Srilatha Tokala
Author 2: Koduru Hajarathaiah
Author 3: Sai Ram Praneeth Gunda
Author 4: Srinivasrao Botla
Author 5: Lakshmikanth Nalluri
Author 6: Pathipati Nagamanohar
Author 7: Satish Anamalamudi
Author 8: Murali Krishna Enduri

Keywords: Machine learning algorithms; classification model; classifier; liver disease

Download PDF

Paper 100: Image Super-Resolution using Generative Adversarial Networks with EfficientNetV2

Abstract: The image super-resolution is utilized for the image transformation from low resolution to higher resolution to obtain more detailed information to identify the targets. The super-resolution has potential applications in various domains, such as medical image processing, crime investigation, remote sensing, and other image-processing application domains. The goal of the super-resolution is to obtain the image with minimal mean square error with improved perceptual quality. Therefore, this study introduces the perceptual loss minimization technique through efficient learning criteria. The proposed image reconstruction technique uses the image super-resolution generative adversarial network (ISRGAN), in which the learning of the discriminator in the ISRGAN is performed using the EfficientNet-v2 to obtain a better image quality. The proposed ISRGAN with the EfficientNet-v2 achieved a minimal loss of 0.02, 0.1, and 0.015 at the generator, discriminator, and self-supervised learning, respectively, with a batch size of 32. The minimal mean square error and mean absolute error are 0.001025 and 0.00225, and the maximal peak signal-to-noise ratio and structural similarity index measure obtained are 45.56985 and 0.9997, respectively.

Author 1: Saleh AlTakrouri
Author 2: Norliza Mohd Noor
Author 3: Norulhusna Ahmad
Author 4: Taghreed Justinia
Author 5: Sahnius Usman

Keywords: Single image super-resolution (SISR); generative adversarial networks (GAN); convolutional neural networks (CNN); EfficientNetv2

Download PDF

Paper 101: A Transformer Seq2Seq Model with Fast Fourier Transform Layers for Rephrasing and Simplifying Complex Arabic Text

Abstract: Text simplification is a fundamental unsolved problem for Natural Language Understanding (NLU) models, which is deemed a hard-to-solve task. Recently, this hard task has aimed to simplify texts with complex linguistic structures and improve their readability, not only for human readers but also for boosting the performance of many natural language processing (NLP) applications. Towards tackling this hard task for the low-resource Arabic NLP, this paper presents a text split-and-rephrase strategy for simplifying complex texts, which depends principally on a sequence-to-sequence Transformer-based architecture (which we call TSimAr). For evaluation, we created a new benchmarking corpus for Arabic text simplification (so-called ATSC) containing 500 articles besides their corresponding simplifications. Through our automatic and manual analyses, experimental results report that our TSimAr evidently outperforms all the publicly accessible state-of-the-art text-to-text generation models for the Arabic language as it achieved the best score on SARI, BLEU, and METEOR metrics of about 0.73, 0.65, and 0.68, respectively.

Author 1: Abdullah Alshanqiti
Author 2: Ahmad Alkhodre
Author 3: Abdallah Namoun
Author 4: Sami Albouq
Author 5: Emad Nabil

Keywords: Text simplification; sequence-to-sequence; split-and-rephrase; natural language understanding; NLP; TSimAr; ATSC

Download PDF

Paper 102: Unsupervised Feature Learning Methodology for Tree based Classifier and SVM to Classify Encrypted Traffic

Abstract: Presently, sample social applications have emerged, and each one is trying to knock down the other. They expand their game by bringing novelty to the market, being ingenious and providing advanced level of security in the form of encryption. It has become significant to manage the network traffic and analyze it; hence we are performing a network traffic binary classification on one of the globally used application – WhatsApp. Also, this will be helpful to evaluate the sender-receiver system of the application alongside stipulate the properties of the network traces. By analyzing the behavior of network traces, we can scrutinize the type and nature of traffic for future maintenance of the network. In this study, we have carried out three different objectives. First, we have classified between the WhatsApp network packets and other applications using different ML classifiers, secondly, we have segmented the WhatsApp application files into image and text and third, we have incorporated a deep learning module with the same ML classifiers to understand and boost the performance of the previous experiments. Following the experiments, we have also highlighted the difference in the performance of both tree-based and vector-based classifiers of Machine Learning. Based on our findings, XGBoost classifier is a pre-eminent algorithm in the identification of WhatsApp network traces from the dataset. Whereas in the experiment of WhatsApp media segmentation, Random Forest has outperformed the other ML algorithms. Similarly, SVM when clubbed with a Deep Learning Auto encoder boosts the performance of this vector-based classifier in the binary classification task.

Author 1: RAMRAJ S
Author 2: Usha G

Keywords: Network traffic; encrypted network traffic; tree based classifiers; SVM

Download PDF

Paper 103: Indoor Pollutant Classification Modeling using Relevant Sensors under Thermodynamic Conditions with Multilayer Perceptron Hyperparameter Tuning

Abstract: Air pollutants that are generated from indoor sources such as cigarettes, cleaning products, air fresheners, etc. impact human health. These sources are usually safe but exposure beyond the recommended standards could be hazardous to health. Due to this fact, people started to use technology to monitor indoor air quality (IAQ) but have no capability of recognizing pollutant sources. This research is an improvement in building a classification model for recognizing pollutant sources using the multilayer perceptron. The current research model receives four data parameters under warm & humid and cool & dry conditions compared to nine parameters of the previous literature in detecting five pollutant sources. The classification model was optimized using GridSearchCV to obtain the best combination of hyperparameters while giving the best-fit model accuracy, loss, and computational time. The tuned classification model gives an accuracy of 98.9% and a loss function value of 0.0986 under the number of epochs equal to 50. In comparison with the previous research, the accuracy was 100% with the number of epochs equal to 1000. Computational time was greatly reduced at the same time giving the best-fit accuracy and loss function values without incurring the problem of overfitting.

Author 1: Percival J. Forcadilla

Keywords: Indoor air pollutants; pollutant sources; indoor air quality; IAQ; sensors; multilayer perceptron; classification modeling; gridSearchCV; hyperparameter tuning

Download PDF

The Science and Information (SAI) Organization
BACK TO TOP

Computer Science Journal

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

Our Conferences

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

Help & Support

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

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