Accepted Papers

Big Data: Storage, Analysis, and Implementation

Melissa Pula and Omar A-Azzam, Computer Science and Information Technology Department (CSIT), Saint Cloud State, University (SCSU), Saint Cloud, MN, USA

ABSTRACT

We are in an age where data is not only readily available, but abundant. However, it is what we do with this data, through analyzing it, that is most important. While traditional means of data analytics works well for smaller amounts of information, it may not be able to handle larger amounts, called big data. In this paper, we will discuss the different ways in which big data can best be stored, what methods work best in analyzing it, and how the results of this analysis can be implemented in real-world scenarios.

KEYWORDS

Big Data.

Artificial Intelligence Applied to Software Testing

Akshay Singh and Omar Al-Azzam, Computer Science and Information Technology Department (CSIT), Saint Cloud State, University (SCSU), Saint Cloud, MN, USA

ABSTRACT

The study investigates the background, advantages, and difficulties of AI-based testing. The use of artificial intelligence (AI) has shown great promise as a means of enhancing software testing procedures. To improve test case generation, bug prediction, and test result analysis, AI-based testing approaches use machine learning, NLP (Natural Language Processing), graphical user interfaces (GUIs), genetic algorithms, and robotic process automation. We also provide a brief literature review of recent studies in the field, focusing on the various approaches and tools proposed for AI-based software testing. We conclude with a strategy for introducing AI-based testing and a list of possible approaches and resources. Overall, this paper provides a comprehensive survey of AI-based software testing and highlights the potential benefits and challenges of this emerging field.

KEYWORDS

artificial intelligence, software testing, machine learning, natural language processing, computer vision, genetic algorithms, robotics process automation, tools, trends.

A Novel VAPT Algorithm: Enhancing Web Application Security through OWASP Top 10 Optimization

Rui Ventura1, Daniel José Franco2 and Omar Khasro Akram2, 1MSc, at Faculty of Engineering, Institute Polytechnic of Beja,7800-295, Portugal, 2Asst. Prof. at Faculty of Engineering, Institute Polytechnic of Beja,7800-295, Portugal

ABSTRACT

This research study is built upon cybersecurity audits and investigates the optimization of an Open Web Application Security Project (OWASP) Top 10 algorithm for Web Applications (WA) security audits using Vulnerability Assessment and Penetration Testing (VAPT) processes. The study places particular emphasis on enhancing the VAPT process by optimizing the OWASP algorithm. To achieve this, the research utilizes desk documents to gain knowledge of WA cybersecurity audits and their associated tools. It also delves into archives to explore VAPT processes and identify techniques, methods, and tools for VAPT automation. Furthermore, the research proposes a prototype optimization that streamlines the two steps of VAPT using the OWASP Top 10 algorithm through an experimental procedure. The results are obtained within a virtual environment, which employs black box testing methods as the primary means of data acquisition and analysis. In this experimental setting, the OWASP algorithm demonstrates an impressive level of precision, achieving a precision rate exceeding 90%. It effectively covers all researched vulnerabilities, thus justifying its optimization. This research contributes significantly to the enhancement of the OWASP algorithm and benefits the offensive security community. It plays a crucial role in ensuring compliance processes for professionals and analysts in the security and software development fields.

KEYWORDS

Security Audit, Web Applications, Vulnerability Assessment and Penetration Testing, Innovative OWASP Algorithm.

An Empirical Analysis of the Usage of Requirements Attributes in Requirements Engineering Research and Practice

Krzysztof Wnuk and Lech Madeyski, Blekinge Institute of Technology, Sweden

ABSTRACT

Requirements attributes play an important role in storing and managing meta-information about requirements. Despite their importance, there exists a research gap in systematically surveying the current literature on requirements attributes and comparing that with industry practice. This paper occupies this research gap by presenting the results of a systematic literature review and a case study performed at a large organization developing software-intensive products for a global market. We focus on identifying trends in the literature about requirements attributes. We performed seven snowballing iterations and identified 18 studies, where we extracted requirements attributes. Next, we compare these identified attributes with the attributes a large company that is developing software-intensive products for a global market. We identified 57 semantically similar attributes and 25 common attributes that were found in both the case study and the literature review. Apart from describing intrinsic aspects of requirements, attributes are used to support communication, decision making, tracking the status and estimating the business value of requirement.

KEYWORDS

requirements attributes, empirical study, literature review, requirements management.

Conceptual Analysis of the Mapping of Mathematics Teaching Activities and Algorithms and Reactive Games in the Primary and Middle School Cycle

Belarbi Mostefa, Menzoul Meriem, Merouane Razika, Department of Computer Engineering, Ibn Khaldoun University, ALGERIA, Tiaret

ABSTRACT

In general, mathematics is perceived as a difficult and even boring subject, without attractions. Based on this observation, it was necessary to show the students that it was possible to take pleasure in solving exercises and other problems by proposing rich and motivating situations which allow them to understand this subject less and feel more pleasure in doing it. Its richness and the multiple possibilities it offers to the teacher in his relationship with the pupils make it possible to reconcile pleasure and mathematical activity. Since technological tools are ubiquitous in society and their use is increasing in classrooms, we propose a combination between games and technology by addressing various mathematical problems by transforming them into games on the one hand, and on the other hand, trying to draw these games through 3D software where the student will find a solution when he is drawing.

KEYWORDS

Mathematics, teaching, learning, algorithms, reactive games, mapping, ICT.

Bridging the Gap: Unveiling the Multifaceted Dynamics of Nba Player Evaluation and Compensation Through Feature Engineering and Importance Analysis

Tianzi Zheng, University of Texas at Arlington, USA

ABSTRACT

This research harnesses intricate feature engineering methodologies to intricately dissect the symbiotic relationship between NBA players multifaceted attributes, their digital footprint on social media, and the consequent salary allocations. Grounded in the foundational tenets of the tournament and human capital theories, our investigation stands as an avant-garde endeavor, predominantly due to its recourse to the unprecedented dataset derived from the NBA 2K Sports game. This dataset uniquely amalgamates both on-court prowess and off-court digital personas.Our analysis delves deeper, moving beyond the conventional scope of prior studies, which often had a myopic focus on a constrained suite of skill-centric variables. It meticulously assesses the metrics tied to each player, unraveling the nuanced tapestry of their on-field performance juxtaposed with their off-field digital engagements. Central to our exploration is the demystification of the relative gravitas of inherent skill attributes vis-à-vis their digital aura in steering salary determinations. The revelations from our study not only furnish invaluable insights pivotal for sports managers and industry stakeholders in sculpting player evaluations and charting career trajectories but also echo in the broader corridors of human resource and leadership management. Our study champions the cause of a nuanced, quantifiable paradigm for assessing individual talents and their holistic contributions, laying a robust groundwork for future research endeavors in the domain.

KEYWORDS

NBA, sports game, human resource, human capital, video game, salary determination, social media, tournament theory, feature engineering, feature importance.

Big Data: Storage, Analysis, and Implementation

Melissa Pula and Omar A-Azzam, Computer Science and Information Technology Department (CSIT), Saint Cloud State, University (SCSU), Saint Cloud, MN, USA

ABSTRACT

We are in an age where data is not only readily available, but abundant. However, it is what we do with this data, through analyzing it, that is most important. While traditional means of data analytics works well for smaller amounts of information, it may not be able to handle larger amounts, called big data. In this paper, we will discuss the different ways in which big data can best be stored, what methods work best in analyzing it, and how the results of this analysis can be implemented in real-world scenarios.

KEYWORDS

Big Data.

Artificial Intelligence Applied to Software Testing

Akshay Singh and Omar Al-Azzam, Computer Science and Information Technology Department (CSIT), Saint Cloud State, University (SCSU), Saint Cloud, MN, USA

ABSTRACT

The study investigates the background, advantages, and difficulties of AI-based testing. The use of artificial intelligence (AI) has shown great promise as a means of enhancing software testing procedures. To improve test case generation, bug prediction, and test result analysis, AI-based testing approaches use machine learning, NLP (Natural Language Processing), graphical user interfaces (GUIs), genetic algorithms, and robotic process automation. We also provide a brief literature review of recent studies in the field, focusing on the various approaches and tools proposed for AI-based software testing. We conclude with a strategy for introducing AI-based testing and a list of possible approaches and resources. Overall, this paper provides a comprehensive survey of AI-based software testing and highlights the potential benefits and challenges of this emerging field.

KEYWORDS

artificial intelligence, software testing, machine learning, natural language processing, computer vision, genetic algorithms, robotics process automation, tools, trends.

Extrapolating the Experimental Data to Predict the Longevity of Li- Battery

Jia Guo1, Hesheng Gong2, Bo Gao3, 1Taizi Education and Technology, Co. Ltd., Beijing, China, 2Eindhoven University of Technology, Netherland, 3Beijing Jiaotong University, Beijing China

ABSTRACT

In search of a particular lithium battery with reliable safety and high energy, quantities of research have been focused on the chemical substances for the Anode and Cathode, respectively. In Cui’s laboratory, an efficiency of 98.54% for more than 600 cycles as well as long lifespan beyond 900h in a LiCu-Ag@Li cell can be realized. A high cyclability of 98% capacity can be achieved after 1000 cycles along with a long lifespan of 1500h in a SiOxCy@Li cell, which both prevents electrons from piercing through a separator, and leverages the efficacy of the lithium-ions via a binder. Thanks to Cui et al. and Severson et al., we either have got approved for or searched for the published data regarding the lithium-ion battery’s lifespan and chart a series of diagrams that reveal the curve-shaped trendline and unexpected surges in the first, middle and last few cycles of a cell’s life. The more a shocking cusp (outliers) surfaces, the more a decline steepens. We compare the data from the laboratory to on-board batteries and build a polynomial regression in order to predict the life end of those cells. While the non-linear regression is unable to best fit every moment of a cell’s decrepitude, our team create a regression model to increase the accuracy of predication to an average of 97.693% in the primary test according to the first 30-225 cycles, then seek the optimization for longevity forecast by programming solver and hyperparameter, and finally find a (non-fixed) relationship between the speed and acceleration during the period of a cell’s degradation. SVM model has also been created along with its corresponding 3D pattern with Temperature considered and so has the model Multiple Regression but the cost/benefit analysis will be continued in future study of relevant subject for prediction on newly-bonded cells or all-purpose commercial batteries.

KEYWORDS

prediction accuracy, non-linear regression, speed, acceleration, optimization.

Extrapolating the Experimental Data to Predict Thelongevity of Li-battery

Hemmak Allaoua, Department of computer science, faculty of mathematics and informatics, Laboratory of Informatics and its Applications (LIAM), Mohamed Boudiaf university of 28000, M’sila, Algeria.

ABSTRACT

The Grover algorithm, celebrated for its quantum speedup in unsorted database search, has inspired significant exploration. This study delves into its efficacy within lists containing repeated elements. Through rigorous analysis, we ascertain the algorithms performance threshold in the presence of repetitions. Leveraging theoretical insights and practical experimentation, we highlight the delicate balance between quantum search strategies and combinatorial intrica- cies. Notably, we discuss our implementation of the algorithm in Q# and its im- plications. This work advances our comprehension of quantum search algorithms and their real-world viability amidst recurring elements.

KEYWORDS

Grover Algorithm, Quantum Search, Lists with Repetition, Quan-tum Computing, Combinatorial Complexity, Q# Implementation.

Simulation and Analyze of Grover Algorithm.

A Review on Machine Learning Approaches to Classify Edible Mushrooms

Purna Peramune and John Sriskandarajah, Department of Computer Science and Engineering, University of Westminster, UK.

ABSTRACT

Mushrooms have been one of the captivated interests of humans for centuries because of its culinary benefits, medicinal benefits, and ecological significance. Mushrooms can be divided as edible and poisonous. At present, edible mushroom identification depends on traditional methods, and field guides, which can be error-prone. Growing cases of food poisonings due to the consumption of poisonous mushrooms shows that traditional methods are incompetent. This paper explores different methods to automate the process of identification of edible mushrooms with different types of machine learning techniques such as decision trees, SVM, logistic regression and deep learning techniques such as CNN. Finally, the paper critically discusses existing works, carried out by past researchers, limitations and improvements that can be made in future studies. The paper helps to bridge the gap between traditional mycology and cutting-edge technology, find a safer, and efficient method to classify edible mushrooms.

KEYWORDS

Edible Mushroom, Machine Learning, Deep Learning, Image Classification, Text Classification, Computer Vision.

Ai and Banking Sector: Impact and Risk

Mohamed Bechir Chenguel, Department of Finance and Accounting, University of Kairouan, Tunisia

ABSTRACT

In finance and banking, artificial intelligence tools can help improve the efficiency of banking services. AI and machine learning are among the technological tools that have radically changed certain financial and banking services, especially in customer relations, trading and risk management. Artificial intelligence for banks has been able to automate repetitive tasks, improve process efficiency and use machine learning, deep learning, predictive analytics and natural language processing to power more robust features such as chatbots and robo-advisors. But the adoption of this cutting-edge technology still c o m e s w i t h a number of risks and negative impacts, especially on the human side, such as job losses and the elimination of certain jobs replaced by robots. Our work will take a closer look at the impact of AI on the banking sector, the different risks dealt with by AI, and we will focus on the risks developed by AI in banking.

KEYWORDS

Artificial Intelligence, Fintech, innovation, technology, digitisation.

Vvoip Quality Improvement Over Ims Network Based on Background Subtraction

Hanafy M. Ali1, Waled M Ismail2, Aziza I. Hussein3,Yahia B.Hassan4, 1Computers and Systems Engineering Depart., -Faculty of Engineering, Minia University, El Minia, Egypt, 2Mobile core back office engineer ,Telecom Egypt CO. , Egypt, 3Electrical and Computer Eng. Dept. Effat University, Jeddah, Saudi Arabia, 4Electrical Eng. Dept, Higher Institute of Engineering, Minia, Egypt

ABSTRACT

The dependence on making Voice and Video over Internet Protocol (VVoIP) calls has increased dramatically in recent times. The use of VVoIP applications is not limited to social applications only but extended to business applications. The improvement of VVoIP call quality is one of the most important factors that enhance the spread of VVoIP services. In many cases, the high network traffic prevents the possibility of sending high data rate live video streams as sending high data rate live stream over high-trafficnetworks causes an increase in the data loss rate. In this paper, The codec switching techniques used to improve the quality under live networks with high traffic are discussed. In addition, Atechnique based on background subtraction to improve the quality of VVoIP calls using Python code to detect the moving pixels (foreground) and subtract them from the frame to discard the background is proposed. The proposed technique was tested on large scale live network. The tested parameters impacting the Quality of Service (QoS) were packet loss and delay variation (Jitter). The study based on the comparison of packet loss and Jitter for the three common resolutions 480P, 720P and, 1080P over high traffic network without using background subtraction vs. using background subtraction.The results showed a significant improvement in different rates for each resolution and network condition.

KEYWORDS

VVOIP, QoE, QoS, IMS, Background subtraction.

A Comprehensive Review of Trust Management in Blockchain-based Iot

Younghun Chae, Department of Computer Science, Kent State University, North Canton, Ohio, USA

ABSTRACT

The Internet of Things (IoT) has emerged as a transformative technology, enabling various applications in diverse fields. However, its distributed nature and massive scale present significant challenges, particularly in trust management, identity management, and access control. Traditional access control systems often rely on a centralized entity, which can become a single point of failure or a target for attackers. With its inherent properties of decentralization, transparency, traceability, and tamper resistance, blockchain technology offers a promising solution to these challenges. However, its integration into IoT networks is challenging, particularly in selecting miners and the consensus protocols to validate and add new blocks to the chain. This paper presents a comprehensive review of trust management in blockchain for IoT. It discusses the potential of blockchain technology in enhancing IoT applications, the challenges associated with integrating blockchain and IoT, and the current state-of-the art solutions. It delves into the specifics of consensus protocols, miner selection, and the role of trust in securing IoT networks. The paper concludes by highlighting the need for a comprehensive approach that combines technological solutions with appropriate policies and regulations to fully realize the potential of blockchain technology in enhancing the security and functionality of IoT networks. This work contributes significantly to the ongoing discourse on securing IoT networks and paves the way for future research.

KEYWORDS

Blockchain, IoT, IIoT, trust, review.

A The Role of Dependability in Iot Systems

Mohammad Ibraigheeth, Department of Software Engineering, Bethlehem University, Bethlehem, Palestine

ABSTRACT

The advances in the Internet of Things (IoT) have contributed to the automation of various industries by enabling devices and systems to effectively connect and collect data remotely over the internet. This progress has led to the creation of an intelligent society where physical things are becoming increasingly innovative and undoubtedly, the IoT systems will continue to impact real life by providing efficient data collection and sharing. The successful implementation of IoT systems relies on their dependability, which is closely tied to several factors such as their reliability, resilience, and security. This paper explores the crucial role of dependability in IoT system, emphasizing challenges such as real-time analysis, resource constrains, connection redundancy, and quick fault recovery. The paper also provides some strategies for overcoming dependability challenges, such as efficient algorithms, edge computing, prioritization of resources, and AI techniques integration. Additionally, the paper presents a case study of an IoT system that faced dependability problems, highlighting the importance of rigorous testing and redundancy in ensuring reliable IoT deployments. As a result of this research, we suggest that by addressing the challenges related to dependability aspects, stakeholders can unlock the full potential of IoT, empowering industries and individuals with transformative, efficient, and reliable technologies. For future work, a frame work for evaluating and enhancing the IoT dependability will be developed. Several factors will be considered in developing this framework, such as reliability, availability, safety, security, resilience, and fault management. The framework will define a quantifiable metrics to measure these factors.

KEYWORDS

Internet of Things (IoT), Dependability; Reliability, resource constrains, fault management, failure recovery.

Harnessing Rule-based Approaches for Cancer Pathology Report Classification: a Review.

OUCHENE Hiba, MEZZI Melyara, OUKID Lamia, BENBLIDIA Nadjia, LRDSI Laboratory, Faculty of Sciences,Department of Computer Sciences, University Blida 1, BLIDA, ALGERIA

ABSTRACT

Cancer pathology reports are integral to cancer diagnosis and treatment. The growing volume of these reports necessitates automated classification, prompting a shift towards rule-based Natural Language Processing (NLP) systems due to their capacity for more contextualized processing. This review examines these rule-based approaches, highlighting the key features extracted from the pathology reports, and evaluating the benefits they offer. Despite certain limitations, rule-based methods demonstrate considerable promise in the classification of cancer pathology reports. We conclude by identifying future research opportunities aimed at addressing these limitations to further enhance the benefits of the classification process.

KEYWORDS

Cancer Pathology Reports, Rule-Based Systems, Natural Language Processing, Classification Techniques, Information Extraction.

ptimized Dbscan Parameter Selection: Stratified Sampling for Epsilon and Gridsearch for Minimum Samples

Gloriana Joseph Monko and Masaomi Kimura, Department of Functional Control Systems and Department of Computer Science and Engineering, Shibaura Institute of Technology, Tokyo, Japan

ABSTRACT

This research presents an advanced methodology for estimating the epsilon and minimum samples parameters in the DBSCAN clustering algorithm using a Stratified Sampling and Grid-Search approach. Our method showcased notable improvement in eps estimation precision across nine diverse datasets compared to conventional techniques. By accounting for dataset variations in structure and density, stratified sampling leads to superior cluster formations. The k-nearest distance graph further refines these relationships, ensuring a comprehensive understanding of data densities. Additionally, our method underscores the importance of each dataset s unique stratum, providing holistic insights. We also introduced a Grid-Search technique for MinPts estimation with the help of silhouette score, challenging traditional rule-of-thumb settings. Our approach suggests setting MinPts flexibly, considering the dataset s specific attributes and has proven its efficacy by enhancing clustering results, with implications for both SS-DBSCAN and traditional DBSCAN frameworks. This study highlights the potential of parameter estimation in optimizing clustering outcomes and computational efficiency.

KEYWORDS

Epsilon selection, MinPts determination, statified sampling, grid-search, SS-DBSCAN

A Intuitive System to Facilitate the Creation of Pickup Basketball Games Using Social Networking Systems

Jason Si1, Victor Phan2, 1Southridge School, 2656 160 St, Surrey, BC V3Z 0B7, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768

ABSTRACT

In British Columbia, suburban sprawl has created limitations for basketball players in discovering pick-up gameswithin their community [1]. To address this ongoing issue, Park Rec was developed to of er pick-up games, fosteringa thriving basketball community in BC. Built on a foundation of social media components, Park Rec aims to uniteplayers by facilitating the creation and discovery of pick-up games [2]. We have developed an easy-to-use gameorganization system for the user to customize and play within. The additional chat and highlight feature alsoareused to enhance the experience. Although there were limitations to build a connective system to local Rec Centers, we’ve chosen a few local public outdoor courts to build up the experience of pick up games. –Experiment–. Ultimately Park Rec is here to connect players around the community and bring them together.

KEYWORDS

Social Network, Basketball, Matchmaking, Social Media.

Learning and Flutter to Assist Users in Accomplishing Their Diet/fitness Goals Along With Providing Helpful Advice.

Morgan Li1, Yangxuezhe Sun2, Rayyan Zaid3, 1Los Osos high school, 6001 Milliken Ave, Rancho Cucamonga, CA 91737, 2Rancho cucamonga High School, 7873 Chablis Pl, Rancho Cucamonga, CA 91739, 3Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

We built an AI Fitness Application in hopes of addressing the problem of obesity. Obesity and lack of fitness awareness are major problems in the United States that lead to unhealthy lifestyles and health risks. To solve this problem, we developed an app that bundles together essential components to help a person keep up with their fitness. Our app includes a calorie logging system where you can log your food and exercise, a fitness tip section, and a collection of exercise videos. Our technology uses Flutter Dart as the main programming language for the User Interface. We also use Python from our AI system and Firebase for our database [11]. In our research, we tested out our AI Food Classification Model and Calorie Tracking system. After extensive testing, we realize the need to fine tune our calorie tracking system for exercises and also to expand our AI model’s dataset to recognize more common foods. Some challenges we faced were: (1) Integrating our AI Food Classification Model to the frontend (2) Create a Calorie Calculation Function and connect that with the frontend. Overall, our system provides a simple and friendly interface that anyone can pick up instantly. Our solution is not a large-scale solution to obesity, but rather it’s an option that the everyday person can use quickly.

KEYWORDS

Fitness, Python (AI), Flutter(front-end), Firebase(back-end).

Big Data Security, Privacy, and Trust: an Overview ©.

Alexander A Wodi, Wodi and Wodi

ABSTRACT

The convergence of Big Data, AI, IoT and Smart devices has revolutionized various sectors, including finance, health, education, research, government, business, manufacturing, social media, and ecommerce with the vast amount of data being collected, processed, and stored, in furtherance of a burgeoning global digital economy. The use of Big Data has implications for governance, risk, and compliance across the privacy program framework. The repercussions of non-compliance with data privacy and security standards, a data breach or unauthorized access could be catastrophic, and result in reputational damage, huge financial losses, and dire legal consequences. This paper seeks to examine Big Data: what it is, and why it Matters, through the prism of data privacy, data security and trust. What are the emerging trends in data privacy and Big Data practices? How can governments and companies foster transparency, accountability, and address issues of ethical and responsible use of Big Data?.

KEYWORDS

Big Data, Privacy, Security, Trust, GDPR.