Accepted Papers

Full-song Scale Music Generation With Transformer-based Models

Ruiyu Zhang and Shanshan Zhao, School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang),Xi’an Jiaotong-Liverpool University, Suzhou, China

ABSTRACT

Creating a complex piece of art, such as music generation, necessitates actual creativity, which is dependent on several elements connected to the hierarchy of musical language. In recent years, music generation using Artificial Intelligence is a new domain that has received much attention. This project reviews the development of music generation and discuss the key factors of music composition for both Deep Machine Learning and human, where important deep-learning models and methods of music representation were covered. The objective of this project is to generate full-song music through some transformer-based models against the shortcomings of poorly structured music generated by some recurrent neural networks. We propose to integrate Compound Word music representation to multiple transformer-based models, including Linear Transformer, Compressive Transformer, and TransformerXL, along with Long Short-Term Memory model. The performances of different models are evaluated by training proposed models on the Pop1K7 music dataset. Meanwhile the generated music is evaluated in training process and music evaluation metrics, respectively. Finally, we demonstrate some selected decent full-song scale music generated by our models in a web page1.

KEYWORDS

Deep learning; music generation; attention mechanism; music representation.

Technologies for Information Use Prob-lems Solving

Alexander S. Geyda, St. Petersburg Federal Research Center of the Russian Academy of Sciences, 14 Line 39, St. Petersburg Russia

ABSTRACT

The article is devoted to models, methods, and technologies required for solving problems related to the use of information in systems. These types of problems are, in general, a continuation and extension of Solows Paradox of Information technologies, which were described almost half a cen-tury ago. For example, such problems still arise during the Digital Transformation of Economy and Society or during the Sustainable Digital Development of Society. The solution to these problems requires the creation of models for the application of information in system functioning, with meth-ods applied based on available data. Once the information application is modelled, it is suggested to use a set of information technologies developed to solve these kinds of problems related to in-formation use. Candidates for such models, methods, and technologies will be considered.

KEYWORDS

Information use, Information quality, Efficiency, Capability, Models, Methods, Technology.

Unmasking the Misconceptions: the Power of Test Design in Automation

Rohit Khankhoje, Avon, Indiana, USA

ABSTRACT

This article explores the prevailing misconception in the realm of test automation the notion that automation harbors the exceptional potential to convert subpar test design into streamlined and dependable procedures.The paper highlights the inseparable connection between test design and successful test automation, emphasizing that the ef ectiveness of automation is dependent on the quality of the tests it automates. The paper argues that inadequate test design cannot be rectified by automation. By employing tangible instances from the real world and insightful perspectives that are applicable in practice, it emphasizes the importance of robust principles for designing tests. Additionally, it delves into the potential consequences that can arise from neglecting the design aspect of testing and of ers strategies for aligning test design with automation in order to maximize the ef ectiveness of testing endeavors. This paper serves as a cautionary message to the testing community, underscoring the fact that automation is merely a tool and not a universal solution. It further asserts that the key to success lies in establishing a solid foundation of well-crafted tests.

KEYWORDS

Test Automation , Test Design,Best Practices ,Ef iciency, Quality Assurance.

Cnn-optimized Text Recognition With Binary Embeddings for Arabic Expiry Date Recognition

Mohamed Lotfy1 and Ghada Soliman2, 1Data Scientist, dept. Software Engineering, Kafr El-sheikh University, 2Data Scientist Lead, dept. Environmental Engineering, Ain Shams University

ABSTRACT

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can be also extended to text recognition tasks, such as text classification and sentiment analysis.

Artificial Intelligence Aspect of Transportation Analysis Using Large Scale Systems

Tiechuan Hu1, Wenbo Zhu2, and Yuqi Yan3, 1Department of Computer Science, Johns Hopkins University, Baltimore, US, 2Department of Computer Science, University of Chicago, Chicago, US, 3Olin Business School, Washington University in St.Louis, Saint Louis, US

ABSTRACT

Modern transportation systems, based on large amounts of data, face the complex challenge of understanding the interaction between weather conditions and traf ic patterns. The emerging potential of artificial intelligence provides unprecedented opportunities to delve deeper into this dif icult problem [1]. This article leverages the synergistic power of advanced deep learning, natural language processing (NLP), and optimization technologies to conduct a comprehensive exploration. Our journey begins with real-time observational insights from convolutional neural networks (CNNs) and progresses to nuanced time series forecasts provided by long short-term memory networks (LSTMs). By leveraging transfer learning, we enrich our model by integrating pre-trained knowledge from relevant domains, thereby improving prediction accuracy. Sentiment analysis using BERT (Bidirectional Encoder Representations from Transformers), combined with semantic analysis of traf ic reports, provides a multi-dimensional view of traf ic dynamics. Advanced optimization techniques further refine our forecasts, ensuring they are not only accurate but also computationally ef icient. Our results illustrate the progressive increase in the predictive power of each ensemble technique. While highlighting the transformative potential of multifaceted AI approaches in transportation research, this article also highlights the promise of optimization and transfer learning in driving data-driven innovation. As we stand at the crossroads of deep learning, natural language processing, transfer learning, and transportation, this research provides a blueprint for leveraging these tools to shape the future of intelligent transportation systems.

KEYWORDS

Performance Analysis, Sentiment Analysis, Machine Learning, Transfer learning.

Use Ofkappacoefficient Toevaluatecourtcaseclassificationsystem

Leandro de Oliveira Ferreira1, Marcelo Lisboa Rocha2, David Nadler Prata2andAngela Issa Haonat1, 1Court of Justice of the State of Tocantins (TJTO)-Tocantins, Brazil, 2Graduate Program in Governance and Digital Transformation, UFT, Tocantins, Brazil

ABSTRACT

Each court case has its procedure determined by the classification of the subject matter that it deals with.Currently, the determination of the subject matter of a case is a manual task, depending on a court official to read the case and classify it according to a relevant subject matter. In order to automate thisprocess, the MinerJus was developed, which uses natural language processing techniques and the SVM machine learning technique for this purpose. This work aims to evaluate the level of agreement betweenthe classification of court cases with respect to their subject matter. For this, comparisons and subsequent evaluations were carried out between the classification of court cases provided by theoriginal MinerJus system (MinerJus SVM) and two jurists, against a new version of MinerJus using more sophisticated machine learning techniques (MinerJus XGBoost). To carry out this evaluation, the Kappaconcordance coefficient was used. It sought to verify if the system is able to classify court cases, based on their initial petition, according to the Unified Procedural Tables of the National Council of Justice, whichseeks to unify the form of classification regarding class and subject matter and procedural movements among Brazilian courts of justice. Despite many efforts for this uniformity, there are still manyclassification errors, due exclusively to human activity in this process. Therefore, a tool that can perform this task efficiently and speed up the judicial process has become essential. For this tool to be trulyefficient, it is necessary to evaluate the level of agreement, accuracy and precision of its analysis in relation to the cases. For this, the court cases were also analyzed by two jurists and the Kappaconcordance coefficient was applied to measure the level of agreement with the results presented by the original MinerJus (MinerJus SVM) and the new version of MinerJus (MinerJus XGBoost).

KEYWORDS

Artificial Intelligence. Court Case Classification & Kappa Coefficient.

Machine Learning Algorithms in Judiciary: an Extrajudicial Monitoring Application

Harly Carreiro Varão1, Marcelo Lisboa Rocha2, Gentil Veloso Barbosa2, Angela Issa Haonat1 and David Nadler Prata2, 1Court of Justice of the State of Tocantins (TJTO)-Tocantins, Brazil, 2Graduate Program in Governance and Digital Transformation, UFT, Tocantins, Brazil

ABSTRACT

In the judicial and extrajudicial spheres, the Tocantins Court of Justice (TJTO) - Brazil has achieved high levels of computerization. The conduct of such procedures requires transparency in this scenario. The analysis of data resulting from inspections of extrajudicial services is an aspect that needs attention with regard to extrajudicial services. To analyze data resulting from on-site extrajudicial inspections, a data mining technique based on association rules was proposed. Due to the large number of association rules in general, a second step was taken in order to optimize/reduce the number of rules. The proposed method performed better than other classic techniques of the literature, such as decision trees, Support Vector Machines, and Naive Bayes.

KEYWORDS

Association Rules, Data Mining, Extrajudicial Inspection & Optimization.

Covid-19 Chest X-ray Image Classificationusing Deeplearning

Siwar Abdallah1, Manel Sekma2 and Wady Naanaa3, 1Higher Institute of Computer Sciences and Mathematics of Monastir, Monastir, Tunisia, 2Higher Institute of Computer Sciences and Mathematics of Monastir, Monastir, Tunisia, 3University of Tunis El Manar

ABSTRACT

The present method uses COVID-19 chest x-ray as an input to convolutional neural network (CNN), in addition non-negative matrix factorization (NMF) elements are used as an additional feature to improve the performance of the CNN model. The proposed method is tested on 2 public datasets collected from Kaggle and compared with CNN model equally to NMF for COVID-19 identification.

KEYWORDS

Non-Negative Matrix Factorization, Deep Learning, Covid-19 Chest X-Ray Classification.

Machine Learning Algorithms in Judiciary: an Extrajudicial Monitoring Application

Harly Carreiro Varão1, Marcelo Lisboa Rocha2, Gentil Veloso Barbosa2, Angela Issa Haonat1 and David Nadler Prata2, 1Court of Justice of the State of Tocantins (TJTO)-Tocantins, Brazil, 2Graduate Program in Governance and Digital Transformation, UFT, Tocantins, Brazil

ABSTRACT

In the judicial and extrajudicial spheres, the Tocantins Court of Justice (TJTO) - Brazil has achieved high levels of computerization. The conduct of such procedures requires transparency in this scenario. The analysis of data resulting from inspections of extrajudicial services is an aspect that needs attention with regard to extrajudicial services. To analyze data resulting from on-site extrajudicial inspections, a data mining technique based on association rules was proposed. Due to the large number of association rules in general, a second step was taken in order to optimize/reduce the number of rules. The proposed method performed better than other classic techniques of the literature, such as decision trees, Support Vector Machines, and Naive Bayes.

KEYWORDS

Association Rules, Data Mining, Extrajudicial Inspection & Optimization.

Job Runtime Prediction: Categorization for Better Regression

Rémi Lacaze-Labadie,Altair engineering,France

ABSTRACT

In this work, we propose a solution to the problem of predicting job runtimes by improving the existing Predicting Query Runtime 2 (PQR2) approach. Our solution relies on two alternatives to PQR2 that include new mechanisms to solve identified PQR2 issues. First, we propose a fallback mechanism that uses a global regression model instead of a categorical regression model when confidence in first-phase categorization is below a given threshold. Second, we propose an extension mechanism to solve what we call the boundary problem of PQR2, where predictions of lower-than-average quality result when jobs are close to category borders. Finally, we propose two new optimization metrics specially adapted to regression problems with time intervals. We demonstrate using experimental results and comparison with PQR2 that our two alternatives can significantly improve the prediction accuracy. In addition, we show that our proposed extension mechanism can increase model performance up to 10%.

KEYWORDS

Deep Learning, Machine Learning, Regression, Categorization, Job runtime, Optimization Metric.

Mental Health Testing and Exercise Intervention of Li and Han High School Students Under Heuristic and Artificial Intelligence Planning Strategies

Ye Xiangdong1, Wang Fei2, Hao Wenting3, Zhang Yaling4, Zhu Xiaohui5, 1Hainan Vocational College of Political Science and Law,Haikou, Hainan571100China, 2, 4Hainan Normal University, Haikou, Hainan, 571158，China, 3,Hainan Institute of Trade,Haikou, Hainan, 571127，China, 5,Hainan Tropical Ocean College, Sanya, Hainan, 572000，China

ABSTRACT

65 Li high school students and 99 Han high school students were randomly selected from 3 middle schools in Haikou City and Wuzhishan City of Hainan Province as research objects. scl-90 was used to test their mental health status, and according to the statistical inference of the data, artificial intelligence planning intervention strategies were proposed to achieve the purpose of mental health education.

KEYWORDS

heuristic; Artificial intelligence; Planning strategy; The Li nationality, living in Yunnan; The Han Nationality; Mental health.

Knowledge Transmission and the Concept of System in 18th C British Corpora

John Regan, Department of English, Royal Holloway, University of London, UK

ABSTRACT

This study of knowledge transmission continues with the method used by Dr Regan in his book Semantic Change and Collective Knowledge in 18th C Britain, which was published by Bloomsbury in August 2023. What it means to transmit knowledge is always historically contingent. Across 18th C British corpora, significant evidence suggests that to ‘transmit knowledge’ meant to preserve what was known. As I will demonstrate, knowledge transmission was overwhelmingly ‘to posterity’. In this paper I will present information from the historical record about the terms within which this way of knowing was contextualised: reliable evidence of how most people possessed the concepts knowledge, posterity, memory, transmission and preservation. In presenting a significant amount of hitherto-unseen evidence about how these word-concepts were used, I will also explain in plain language how the measure of lexical association in this book works. In the second half of the paper, I will delve into the example of the word-concept system to chart that word’s remarkable semantic transformation, and its implications.

KEYWORDS

Corpus, semantic, change, episteme, collective knowledge, 18th C, Britain, ECCO, system, knowledge, posterity.

Toward Identifying Customer Complaints of Microsoft Azure and Digital Ocean Cloud Service Providers Using Topic Modeling and Sentiment Analysis

SALEM ALGHAMDI, Institute of Public Administration, Saudi Arabia

ABSTRACT

Cloud computing has become a powerful tool recently, partly due to the high increase in the volume of data and demand for storage around the world. Cloud service providers present numerous advantages to their customers such as lower cost, and efficiency. This has exponentially increased demand. However, as they scale to meet the demands, they face a lot of challenges which reduces customer satisfaction. This paper presents an analysis of customer complaints in two major cloud services, Microsoft Azure, and DigitalOcean. The study aims to identify the common issues customers face while using cloud services and provide insights to the cloud providers for improving customer satisfaction. The study uses BERTopic for Topic Modeling and VADER Sentiment Analysis to better understand and cluster customer complaints. By examining the frequency of complaints, the study contributes to the existing literature on cloud computing and offers recommendations for enhancing the quality of cloud services.

KEYWORDS

Cloud Service Providers, Topic Modeling, Sentiment Analysis, Customer Complaints.

The European University Alliances Challenges and Acceleration Services Solutions

Farnaz Haji Mohammadali1 and Jesus Alcober2, 1Department of Network Engineering, Universitat politecnic de catalunya , Barcelona,Spain, 2C Esteve Terradas, 7, 08860 Castelldefels, Spain

ABSTRACT

University alliances have appeared as leading mechanisms for promoting collaboration and addressing complex challenges in higher education. However, these alliances face numerous obstacles that must be understood and addressed to maximise their effectiveness. This paper aims to explore and synthesise existing research on the challenges encountered in university alliances. The review identifies key themes and provides insights into strategies that can help overcome these challenges. By understanding the challenges and potential solutions, universities and policymakers can enhance the effectiveness of alliances and foster fruitful collaborations. Currently, there are 44 university alliances that exist in European countries. These university alliances are established with different missions, and their goals are to meet their objectives. While these partners are gathered from different countries and backgrounds, there are obviously some challenges that exist in their partnership. As a result, we discuss how all these challenges have an effect on the sustainability of their partnerships and how projects such as aUPaEU can overcome some of these challenges.

KEYWORDS

Education, university alliance, challenges, partnership.

Children Facing Earthquakes in Mexico City: an Educational Strategy to Promote Prevention Awareness

Daniela Pérez-Sosa, Wulfrano Arturo Luna-Ramírez and Sara Margarita Bustamante-Loya, Universidad Autónoma Metropolitana-Cuajimalpa, Mexico

ABSTRACT

Mexico is a country with high seismic activity, and its capital, Mexico City, is considered especially vulnerable due to its geographical characteristics, urbanization and dense population. In this context, risk awareness coupled with education focused on emergency and prevention management is key in minimizing the negative effects of such disasters. Increasing seismic preparation in the Mexican population requires disseminating solid theoretical knowledge in addition to actionable and practical recommendations, i.e. life-saving action protocols, as early as childhood. We focus on an educational strategy co-designed with children, through an agile development process, to promote preparedness via a meaningful communication system that is relevant and efficient. Our contribution is two-fold, namely: a workshop involving children, teachers, and emergency staff to encourage interest in risk prevention during earthquakes; and an autonomous and self-managing workshop manual that allows an iterative improvement each time it is performed as required by everyone involved.

KEYWORDS

Natural Disasters, Risk Preparedness, Co-design, Children, Adaptability, Risk Reduction, Security, Earthquakes.

Analyzing the Influence of Technostress on Students: a Systematic Literature Review

Zahra Pourahmad and Hasan Ko¸c, Berlin International University of Applied Sciences Salzufer 6, 10587 Berlin Germany

ABSTRACT

Technostress is the stress experienced by individuals due to the use of technology. In today’s digital age, students are increasingly exposed to technology, which, with many benefits, can also lead to technostress. This can harm students’ overall well-being and academic performance. We thus argue that the impact of technology use on students should be better understood, and perform a systematic literature review (SLR), following the guidelines outlined in Okoli’s 8-step procedure. Reviewing the articles addressing technostress among students, the findings indicate that technostress can lead to decreased focus and concentration, impaired sleep patterns, social isolation, and a decline in mental health. It can also contribute to a negative attitude towards technology, hindering students’ ability to effectively leverage its potential for learning and productivity. The findings also suggest that the experience of stress is influenced by an individual’s perception of a stressful situation. Different individuals may perceive the same situation as stressful or non-stressful, depending on various factors such as time, place, and personal interpretation. This SLR provides a comprehensive and dependable resource for researchers, identifies existing research gaps, and proposes directions for future investigations.

KEYWORDS

Technostress, Education, Systematic Literature Review, Students, ICT use.

Cybersecurity-enhanced Gamebased Learning for Clinical Decision-making: a Comparative Study

Kelvin Ovabor1, Adeyinka Adams-Momoh2, Travis Atkison3, 1Department of Computer Science, University of Alabama, USA, 2School of Nursing, Western Illinois University, Illinois, USA, 3Department of Computer Science, University of Alabama, USA

ABSTRACT

The purpose of this research is to determine whether medical professionals may benefit from gamebased learning to enhance their decision-making abilities. The research included 200 medical professionals from renowned institutions such as St. Peters Hospital Albany, MedStar Union Memorial Hospital, Baltimore, St. Vincent Charity Medical Center, Cleveland, and Kindred Hospital, Los Angeles, who had prior experience with game-based learning systems. Both a pre-and post-test assessing the participants ability to make difficult clinical decisions were done. Participants were exposed to an online game-based learning intervention available on MediSim Clinic, which offers a virtual simulation platform, and they demonstrated a considerable increase in their ability to make sound decisions. The results of the research provide preliminary evidence that game-based learning may be an efficient method for enhancing clinical decision-making abilities, including those related to cybersecurity challenges. Limitations and ideas for further research are presented, along with the studys consequences and recommendations for practice. This research contributes to the expanding literature on game-based learning and its potential for enhancing clinical decision-making abilities in the medical profession.

KEYWORDS

Game-based learning, Clinical Decision Making, cybersecurity Education.

Threshold Key Storage via Fuzzy Extractors With Applications

Ciarán Mullan, Adva Network Security GmbH

ABSTRACT

We present a threshold key storage scheme whereby user keys are derived from biometric fuzzy extractors. The work builds upon previous password-protected secret sharing constructions, yet removes requirements on users having to recall often forgotten or insecure credentials, i.e. low entropy passwords. In cases where password recovery is not possible, the scheme offers a new mechanism for online private key storage.

KEYWORDS

Key management, secret sharing, threshold cryptography, fuzzy extractors.

Private and Secure Post-quantum Verifiable Random Function With Nizk Proof and Ring-lwe Encryption in Blockchain

Bong Gon Kim1, Dennis Wong2, and Yoon Seok Yang3, 1Department of Computer Science, Stony Brook University, New York, USA, 2Department of Computer Science, Macao Polytechnic University, Macao, China, 3Department of Computer Science, SUNY Korea University, Incheon, South Korea

Full-song Scale Music Generation With Transformer-based Models

Ruiyu Zhang and Shanshan Zhao, School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang),Xi’an Jiaotong-Liverpool University, Suzhou, China

ABSTRACT

Creating a complex piece of art, such as music generation, necessitates actual creativity, which is dependent on several elements connected to the hierarchy of musical language. In recent years, music generation using Artificial Intelligence is a new domain that has received much attention. This project reviews the development of music generation and discuss the key factors of music composition for both Deep Machine Learning and human, where important deep-learning models and methods of music representation were covered. The objective of this project is to generate full-song music through some transformer-based models against the shortcomings of poorly structured music generated by some recurrent neural networks. We propose to integrate Compound Word music representation to multiple transformer-based models, including Linear Transformer, Compressive Transformer, and TransformerXL, along with Long Short-Term Memory model. The performances of different models are evaluated by training proposed models on the Pop1K7 music dataset. Meanwhile the generated music is evaluated in training process and music evaluation metrics, respectively. Finally, we demonstrate some selected decent full-song scale music generated by our models in a web page1.

KEYWORDS

Deep learning; music generation; attention mechanism; music representation.

Technologies for Information Use Prob-lems Solving

Alexander S. Geyda, St. Petersburg Federal Research Center of the Russian Academy of Sciences, 14 Line 39, St. Petersburg Russia

ABSTRACT

The article is devoted to models, methods, and technologies required for solving problems related to the use of information in systems. These types of problems are, in general, a continuation and extension of Solows Paradox of Information technologies, which were described almost half a cen-tury ago. For example, such problems still arise during the Digital Transformation of Economy and Society or during the Sustainable Digital Development of Society. The solution to these problems requires the creation of models for the application of information in system functioning, with meth-ods applied based on available data. Once the information application is modelled, it is suggested to use a set of information technologies developed to solve these kinds of problems related to in-formation use. Candidates for such models, methods, and technologies will be considered.

KEYWORDS

Information use, Information quality, Efficiency, Capability, Models, Methods, Technology.

Unmasking the Misconceptions: the Power of Test Design in Automation

Rohit Khankhoje, Avon, Indiana, USA

ABSTRACT

This article explores the prevailing misconception in the realm of test automation the notion that automation harbors the exceptional potential to convert subpar test design into streamlined and dependable procedures.The paper highlights the inseparable connection between test design and successful test automation, emphasizing that the ef ectiveness of automation is dependent on the quality of the tests it automates. The paper argues that inadequate test design cannot be rectified by automation. By employing tangible instances from the real world and insightful perspectives that are applicable in practice, it emphasizes the importance of robust principles for designing tests. Additionally, it delves into the potential consequences that can arise from neglecting the design aspect of testing and of ers strategies for aligning test design with automation in order to maximize the ef ectiveness of testing endeavors. This paper serves as a cautionary message to the testing community, underscoring the fact that automation is merely a tool and not a universal solution. It further asserts that the key to success lies in establishing a solid foundation of well-crafted tests.

KEYWORDS

Test Automation , Test Design,Best Practices ,Ef iciency, Quality Assurance.

Cnn-optimized Text Recognition With Binary Embeddings for Arabic Expiry Date Recognition

Mohamed Lotfy1 and Ghada Soliman2, 1Data Scientist, dept. Software Engineering, Kafr El-sheikh University, 2Data Scientist Lead, dept. Environmental Engineering, Ain Shams University

ABSTRACT

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can be also extended to text recognition tasks, such as text classification and sentiment analysis.

Artificial Intelligence Aspect of Transportation Analysis Using Large Scale Systems

Tiechuan Hu1, Wenbo Zhu2, and Yuqi Yan3, 1Department of Computer Science, Johns Hopkins University, Baltimore, US, 2Department of Computer Science, University of Chicago, Chicago, US, 3Olin Business School, Washington University in St.Louis, Saint Louis, US

ABSTRACT

Modern transportation systems, based on large amounts of data, face the complex challenge of understanding the interaction between weather conditions and traf ic patterns. The emerging potential of artificial intelligence provides unprecedented opportunities to delve deeper into this dif icult problem [1]. This article leverages the synergistic power of advanced deep learning, natural language processing (NLP), and optimization technologies to conduct a comprehensive exploration. Our journey begins with real-time observational insights from convolutional neural networks (CNNs) and progresses to nuanced time series forecasts provided by long short-term memory networks (LSTMs). By leveraging transfer learning, we enrich our model by integrating pre-trained knowledge from relevant domains, thereby improving prediction accuracy. Sentiment analysis using BERT (Bidirectional Encoder Representations from Transformers), combined with semantic analysis of traf ic reports, provides a multi-dimensional view of traf ic dynamics. Advanced optimization techniques further refine our forecasts, ensuring they are not only accurate but also computationally ef icient. Our results illustrate the progressive increase in the predictive power of each ensemble technique. While highlighting the transformative potential of multifaceted AI approaches in transportation research, this article also highlights the promise of optimization and transfer learning in driving data-driven innovation. As we stand at the crossroads of deep learning, natural language processing, transfer learning, and transportation, this research provides a blueprint for leveraging these tools to shape the future of intelligent transportation systems.

KEYWORDS

Performance Analysis, Sentiment Analysis, Machine Learning, Transfer learning.

Use Ofkappacoefficient Toevaluatecourtcaseclassificationsystem

Leandro de Oliveira Ferreira1, Marcelo Lisboa Rocha2, David Nadler Prata2andAngela Issa Haonat1, 1Court of Justice of the State of Tocantins (TJTO)-Tocantins, Brazil, 2Graduate Program in Governance and Digital Transformation, UFT, Tocantins, Brazil

ABSTRACT

Each court case has its procedure determined by the classification of the subject matter that it deals with.Currently, the determination of the subject matter of a case is a manual task, depending on a court official to read the case and classify it according to a relevant subject matter. In order to automate thisprocess, the MinerJus was developed, which uses natural language processing techniques and the SVM machine learning technique for this purpose. This work aims to evaluate the level of agreement betweenthe classification of court cases with respect to their subject matter. For this, comparisons and subsequent evaluations were carried out between the classification of court cases provided by theoriginal MinerJus system (MinerJus SVM) and two jurists, against a new version of MinerJus using more sophisticated machine learning techniques (MinerJus XGBoost). To carry out this evaluation, the Kappaconcordance coefficient was used. It sought to verify if the system is able to classify court cases, based on their initial petition, according to the Unified Procedural Tables of the National Council of Justice, whichseeks to unify the form of classification regarding class and subject matter and procedural movements among Brazilian courts of justice. Despite many efforts for this uniformity, there are still manyclassification errors, due exclusively to human activity in this process. Therefore, a tool that can perform this task efficiently and speed up the judicial process has become essential. For this tool to be trulyefficient, it is necessary to evaluate the level of agreement, accuracy and precision of its analysis in relation to the cases. For this, the court cases were also analyzed by two jurists and the Kappaconcordance coefficient was applied to measure the level of agreement with the results presented by the original MinerJus (MinerJus SVM) and the new version of MinerJus (MinerJus XGBoost).

KEYWORDS

Artificial Intelligence. Court Case Classification & Kappa Coefficient.

Machine Learning Algorithms in Judiciary: an Extrajudicial Monitoring Application

Harly Carreiro Varão1, Marcelo Lisboa Rocha2, Gentil Veloso Barbosa2, Angela Issa Haonat1 and David Nadler Prata2, 1Court of Justice of the State of Tocantins (TJTO)-Tocantins, Brazil, 2Graduate Program in Governance and Digital Transformation, UFT, Tocantins, Brazil

ABSTRACT

In the judicial and extrajudicial spheres, the Tocantins Court of Justice (TJTO) - Brazil has achieved high levels of computerization. The conduct of such procedures requires transparency in this scenario. The analysis of data resulting from inspections of extrajudicial services is an aspect that needs attention with regard to extrajudicial services. To analyze data resulting from on-site extrajudicial inspections, a data mining technique based on association rules was proposed. Due to the large number of association rules in general, a second step was taken in order to optimize/reduce the number of rules. The proposed method performed better than other classic techniques of the literature, such as decision trees, Support Vector Machines, and Naive Bayes.

KEYWORDS

Association Rules, Data Mining, Extrajudicial Inspection & Optimization.

Covid-19 Chest X-ray Image Classificationusing Deeplearning

Siwar Abdallah1, Manel Sekma2 and Wady Naanaa3, 1Higher Institute of Computer Sciences and Mathematics of Monastir, Monastir, Tunisia, 2Higher Institute of Computer Sciences and Mathematics of Monastir, Monastir, Tunisia, 3University of Tunis El Manar

ABSTRACT

The present method uses COVID-19 chest x-ray as an input to convolutional neural network (CNN), in addition non-negative matrix factorization (NMF) elements are used as an additional feature to improve the performance of the CNN model. The proposed method is tested on 2 public datasets collected from Kaggle and compared with CNN model equally to NMF for COVID-19 identification.

KEYWORDS

Non-Negative Matrix Factorization, Deep Learning, Covid-19 Chest X-Ray Classification.

Machine Learning Algorithms in Judiciary: an Extrajudicial Monitoring Application

Harly Carreiro Varão1, Marcelo Lisboa Rocha2, Gentil Veloso Barbosa2, Angela Issa Haonat1 and David Nadler Prata2, 1Court of Justice of the State of Tocantins (TJTO)-Tocantins, Brazil, 2Graduate Program in Governance and Digital Transformation, UFT, Tocantins, Brazil

ABSTRACT

In the judicial and extrajudicial spheres, the Tocantins Court of Justice (TJTO) - Brazil has achieved high levels of computerization. The conduct of such procedures requires transparency in this scenario. The analysis of data resulting from inspections of extrajudicial services is an aspect that needs attention with regard to extrajudicial services. To analyze data resulting from on-site extrajudicial inspections, a data mining technique based on association rules was proposed. Due to the large number of association rules in general, a second step was taken in order to optimize/reduce the number of rules. The proposed method performed better than other classic techniques of the literature, such as decision trees, Support Vector Machines, and Naive Bayes.

KEYWORDS

Association Rules, Data Mining, Extrajudicial Inspection & Optimization.

Job Runtime Prediction: Categorization for Better Regression

Rémi Lacaze-Labadie,Altair engineering,France

ABSTRACT

In this work, we propose a solution to the problem of predicting job runtimes by improving the existing Predicting Query Runtime 2 (PQR2) approach. Our solution relies on two alternatives to PQR2 that include new mechanisms to solve identified PQR2 issues. First, we propose a fallback mechanism that uses a global regression model instead of a categorical regression model when confidence in first-phase categorization is below a given threshold. Second, we propose an extension mechanism to solve what we call the boundary problem of PQR2, where predictions of lower-than-average quality result when jobs are close to category borders. Finally, we propose two new optimization metrics specially adapted to regression problems with time intervals. We demonstrate using experimental results and comparison with PQR2 that our two alternatives can significantly improve the prediction accuracy. In addition, we show that our proposed extension mechanism can increase model performance up to 10%.

KEYWORDS

Deep Learning, Machine Learning, Regression, Categorization, Job runtime, Optimization Metric.

Mental Health Testing and Exercise Intervention of Li and Han High School Students Under Heuristic and Artificial Intelligence Planning Strategies

Ye Xiangdong1, Wang Fei2, Hao Wenting3, Zhang Yaling4, Zhu Xiaohui5, 1Hainan Vocational College of Political Science and Law,Haikou, Hainan571100China, 2, 4Hainan Normal University, Haikou, Hainan, 571158，China, 3,Hainan Institute of Trade,Haikou, Hainan, 571127，China, 5,Hainan Tropical Ocean College, Sanya, Hainan, 572000，China

ABSTRACT

65 Li high school students and 99 Han high school students were randomly selected from 3 middle schools in Haikou City and Wuzhishan City of Hainan Province as research objects. scl-90 was used to test their mental health status, and according to the statistical inference of the data, artificial intelligence planning intervention strategies were proposed to achieve the purpose of mental health education.

KEYWORDS

heuristic; Artificial intelligence; Planning strategy; The Li nationality, living in Yunnan; The Han Nationality; Mental health.

Knowledge Transmission and the Concept of System in 18th C British Corpora

John Regan, Department of English, Royal Holloway, University of London, UK

ABSTRACT

This study of knowledge transmission continues with the method used by Dr Regan in his book Semantic Change and Collective Knowledge in 18th C Britain, which was published by Bloomsbury in August 2023. What it means to transmit knowledge is always historically contingent. Across 18th C British corpora, significant evidence suggests that to ‘transmit knowledge’ meant to preserve what was known. As I will demonstrate, knowledge transmission was overwhelmingly ‘to posterity’. In this paper I will present information from the historical record about the terms within which this way of knowing was contextualised: reliable evidence of how most people possessed the concepts knowledge, posterity, memory, transmission and preservation. In presenting a significant amount of hitherto-unseen evidence about how these word-concepts were used, I will also explain in plain language how the measure of lexical association in this book works. In the second half of the paper, I will delve into the example of the word-concept system to chart that word’s remarkable semantic transformation, and its implications.

KEYWORDS

Corpus, semantic, change, episteme, collective knowledge, 18th C, Britain, ECCO, system, knowledge, posterity.

Toward Identifying Customer Complaints of Microsoft Azure and Digital Ocean Cloud Service Providers Using Topic Modeling and Sentiment Analysis

SALEM ALGHAMDI, Institute of Public Administration, Saudi Arabia

ABSTRACT

Cloud computing has become a powerful tool recently, partly due to the high increase in the volume of data and demand for storage around the world. Cloud service providers present numerous advantages to their customers such as lower cost, and efficiency. This has exponentially increased demand. However, as they scale to meet the demands, they face a lot of challenges which reduces customer satisfaction. This paper presents an analysis of customer complaints in two major cloud services, Microsoft Azure, and DigitalOcean. The study aims to identify the common issues customers face while using cloud services and provide insights to the cloud providers for improving customer satisfaction. The study uses BERTopic for Topic Modeling and VADER Sentiment Analysis to better understand and cluster customer complaints. By examining the frequency of complaints, the study contributes to the existing literature on cloud computing and offers recommendations for enhancing the quality of cloud services.

KEYWORDS

Cloud Service Providers, Topic Modeling, Sentiment Analysis, Customer Complaints.

The European University Alliances Challenges and Acceleration Services Solutions

Farnaz Haji Mohammadali1 and Jesus Alcober2, 1Department of Network Engineering, Universitat politecnic de catalunya , Barcelona,Spain, 2C Esteve Terradas, 7, 08860 Castelldefels, Spain

ABSTRACT

University alliances have appeared as leading mechanisms for promoting collaboration and addressing complex challenges in higher education. However, these alliances face numerous obstacles that must be understood and addressed to maximise their effectiveness. This paper aims to explore and synthesise existing research on the challenges encountered in university alliances. The review identifies key themes and provides insights into strategies that can help overcome these challenges. By understanding the challenges and potential solutions, universities and policymakers can enhance the effectiveness of alliances and foster fruitful collaborations. Currently, there are 44 university alliances that exist in European countries. These university alliances are established with different missions, and their goals are to meet their objectives. While these partners are gathered from different countries and backgrounds, there are obviously some challenges that exist in their partnership. As a result, we discuss how all these challenges have an effect on the sustainability of their partnerships and how projects such as aUPaEU can overcome some of these challenges.

KEYWORDS

Education, university alliance, challenges, partnership.

Children Facing Earthquakes in Mexico City: an Educational Strategy to Promote Prevention Awareness

Daniela Pérez-Sosa, Wulfrano Arturo Luna-Ramírez and Sara Margarita Bustamante-Loya, Universidad Autónoma Metropolitana-Cuajimalpa, Mexico

ABSTRACT

Mexico is a country with high seismic activity, and its capital, Mexico City, is considered especially vulnerable due to its geographical characteristics, urbanization and dense population. In this context, risk awareness coupled with education focused on emergency and prevention management is key in minimizing the negative effects of such disasters. Increasing seismic preparation in the Mexican population requires disseminating solid theoretical knowledge in addition to actionable and practical recommendations, i.e. life-saving action protocols, as early as childhood. We focus on an educational strategy co-designed with children, through an agile development process, to promote preparedness via a meaningful communication system that is relevant and efficient. Our contribution is two-fold, namely: a workshop involving children, teachers, and emergency staff to encourage interest in risk prevention during earthquakes; and an autonomous and self-managing workshop manual that allows an iterative improvement each time it is performed as required by everyone involved.

KEYWORDS

Natural Disasters, Risk Preparedness, Co-design, Children, Adaptability, Risk Reduction, Security, Earthquakes.

Analyzing the Influence of Technostress on Students: a Systematic Literature Review

Zahra Pourahmad and Hasan Ko¸c, Berlin International University of Applied Sciences Salzufer 6, 10587 Berlin Germany

ABSTRACT

Technostress is the stress experienced by individuals due to the use of technology. In today’s digital age, students are increasingly exposed to technology, which, with many benefits, can also lead to technostress. This can harm students’ overall well-being and academic performance. We thus argue that the impact of technology use on students should be better understood, and perform a systematic literature review (SLR), following the guidelines outlined in Okoli’s 8-step procedure. Reviewing the articles addressing technostress among students, the findings indicate that technostress can lead to decreased focus and concentration, impaired sleep patterns, social isolation, and a decline in mental health. It can also contribute to a negative attitude towards technology, hindering students’ ability to effectively leverage its potential for learning and productivity. The findings also suggest that the experience of stress is influenced by an individual’s perception of a stressful situation. Different individuals may perceive the same situation as stressful or non-stressful, depending on various factors such as time, place, and personal interpretation. This SLR provides a comprehensive and dependable resource for researchers, identifies existing research gaps, and proposes directions for future investigations.

KEYWORDS

Technostress, Education, Systematic Literature Review, Students, ICT use.

Cybersecurity-enhanced Gamebased Learning for Clinical Decision-making: a Comparative Study

Kelvin Ovabor1, Adeyinka Adams-Momoh2, Travis Atkison3, 1Department of Computer Science, University of Alabama, USA, 2School of Nursing, Western Illinois University, Illinois, USA, 3Department of Computer Science, University of Alabama, USA

ABSTRACT

The purpose of this research is to determine whether medical professionals may benefit from gamebased learning to enhance their decision-making abilities. The research included 200 medical professionals from renowned institutions such as St. Peters Hospital Albany, MedStar Union Memorial Hospital, Baltimore, St. Vincent Charity Medical Center, Cleveland, and Kindred Hospital, Los Angeles, who had prior experience with game-based learning systems. Both a pre-and post-test assessing the participants ability to make difficult clinical decisions were done. Participants were exposed to an online game-based learning intervention available on MediSim Clinic, which offers a virtual simulation platform, and they demonstrated a considerable increase in their ability to make sound decisions. The results of the research provide preliminary evidence that game-based learning may be an efficient method for enhancing clinical decision-making abilities, including those related to cybersecurity challenges. Limitations and ideas for further research are presented, along with the studys consequences and recommendations for practice. This research contributes to the expanding literature on game-based learning and its potential for enhancing clinical decision-making abilities in the medical profession.

KEYWORDS

Game-based learning, Clinical Decision Making, cybersecurity Education.

Threshold Key Storage via Fuzzy Extractors With Applications

Ciarán Mullan, Adva Network Security GmbH

ABSTRACT

We present a threshold key storage scheme whereby user keys are derived from biometric fuzzy extractors. The work builds upon previous password-protected secret sharing constructions, yet removes requirements on users having to recall often forgotten or insecure credentials, i.e. low entropy passwords. In cases where password recovery is not possible, the scheme offers a new mechanism for online private key storage.

KEYWORDS

Key management, secret sharing, threshold cryptography, fuzzy extractors.

Private and Secure Post-quantum Verifiable Random Function With Nizk Proof and Ring-lwe Encryption in Blockchain

Bong Gon Kim1, Dennis Wong2, and Yoon Seok Yang3, 1Department of Computer Science, Stony Brook University, New York, USA, 2Department of Computer Science, Macao Polytechnic University, Macao, China, 3Department of Computer Science, SUNY Korea University, Incheon, South Korea

ABSTRACT

In this study, we present a secure smart contract-based Verifiable Random Function (VRF) model, addressing the shortcomings of existing systems. As quantum computing emerges, conventional public key cryptography faces potential vulnerabilities. To enhance our VRF’s robustness, we employ post-quantum Ring-LWE encryption for generating pseudo-random sequences. Given the computational intensity of this approach and associated onchain gas costs, we propose a hybrid architecture of VRF system where onchain and offchain can communicate in a scalable and secure way. We employ a unique ring signature scheme with NIZK proof and also delegated key generation, inspired by Chaum-Pedersen proof of logarithm equalty and Fiat-Shamir Heuristic. Our decentralized VRF employs multi-party computation (MPC) with blockchain-based decentralized identifiers (DID), ensuring enhanced randomness and security. We show the security and privacy advantages of our proposed VRF model with approximated estimation of overall time and space complexities. We also evaluate our VRF MPC model’s entropy and outline its Solidity smart contract integration. This research also provides a method to produce and verify the VRF output’s proof, optimal for scenarios necessitating randomness and validation. Lastly, using NIST SP800-22 test suite for randomness, we demonstrate the commendable result with 98.86% of overall pass rate on 11 standard tests and 0.5459 of average p-value for the total 176 tests.

KEYWORDS

Ring-LWE, Verifiable Random Function, DID, MPC, Blockchain, Smart Contract, Ring Signature, Entropy, NIZK proo.

Trust-based Approaches Towards Enhancing Iot Security: a Systematic Literature Review

Oghenetejiri Okporokpo, Funminiyi Olajide, Nemitari Ajienka and Xiaoqi Ma, Department of Computer Science, Nottingham Trent University, Clifton Lane, Nottingham NG11 8NS

ABSTRACT

The continuous rise in the adoption of emerging technologies such as Internet of Things (IoT) by businesses has brought unprecedented opportunities for innovation and growth. However, due to the distinct characteristics of these emerging IoT technologies like real-time data processing, Self-configuration, interoperability, and scalability, they have also introduced some unique cybersecurity challenges, such as malware attacks, advanced persistent threats (APTs), DoS /DDoS (Denial of Service & Distributed Denial of Service attacks) and insider threats. As a result of these challenges, there is an increased need for improved cybersecurity approaches and efficient management solutions to ensure the privacy and security of communication within IoT networks. One proposed security approach is the utilization of trust-based systems and is the focus of this study. This research paper presents a systematic literature review on the Trust-based cybersecurity security approaches for IoT. A total of 23 articles were identified that satisfy the review criteria. We highlighted the common trust-based mitigation techniques in existence for dealing with these threats and grouped them into three major categories, namely: Observation-Based, Knowledge-Based & Cluster-Based systems. Finally, several open issues were highlighted, and future research directions presented.

KEYWORDS

IoT Networks, Internet of Things (IoT), Trust, Privacy, Cybersecurity & IoT Security.

Preserving Confidential Information: a Comprehensive Analysis of Security and Privacy Concerns in Internet of Things (Iot) Systems

Elshan Tanriverdiyev, National Defense University of the Ministry of Defense of the Republic of Azerbaijan

ABSTRACT

The Internet of Things (IoT) is a wireless network that facilitates data exchange among smart nodes (IoT devices). While IoT technology has enabled improved communication and smart systems, it has also become a target for attackers seeking to exploit users sensitive information. This survey paper highlights security and privacy issues within IoT systems, supported by a literature review of related research. The paper delves into security attacks, categorizing them into layer attacks, providing a detailed analysis within the context of IoT layers. Additionally, it presents potential solutions and strategies to safeguard IoT systems against threats. This comprehensive overview aims to shed light on IoT security challenges and offer insights into protecting these systems from potential attacks.

KEYWORDS

Internet of Things, IoT, IoT Systems, RFID, WSN, IoT Security Issues, IoT Security Attacks.

Lightweight Public Key Encryption in Post-quantum Computing Era

Peter Hillmann, University of the Bundeswehr Munich, Department of Computer Science, Werner-Heisenberg-Weg 39, 85577 Neubiberg, Germany

ABSTRACT

Confidentiality in our digital world is based on the security of cryptographic algorithms. These are usually executed transparently in the background, with people often relying on them without further knowledge. In the course of technological progress with quantum computers, the protective function of common encryption algorithms is threatened. This particularly affects public-key methods such as RSA and DH based on discrete logarithms and prime factorization. Our concept describes the transformation of a classical asymmetric encryption method to a modern complexity class. Thereby the approach of Cramer-Shoup is put on the new basis of elliptic curves. The system is provable cryptographically strong, especially against adaptive chosen-ciphertext attacks. In addition, the new method features small key lengths, making it suitable for Internet-of-Things. It represents an intermediate step towards an encryption scheme based on isogeny elliptic curves. This approach shows a way to a secure encryption scheme for the post-quantum computing era.

KEYWORDS

Cryptography, Public-Key Encryption, Post-Quantum Cryptography, Elliptic Curve, Isogeny Curve.

Quantifying Success: Measuring Roi in Test Automation

Rohit Khankhoje, Indianapolis, USA

ABSTRACT

The strategic decision to implement test automation is a favored approach for organizations seeking to improve the quality of their software, expedite delivery, and mitigate testing expenses. In order to make this decision with precision, it is imperative to accurately assess the return on investment (ROI) of test automation. The present paper , titled "Quantifying Success: Measuring ROI in Test Automation," delves deeply into the fundamental aspects of ROI evaluation within the realm of test automation. It outlines the methodology behind ROI calculation, explores the cost factors and advantages associated with automation, and sheds light on the optimal strategies for achieving a favorable ROI. By presenting real-world case studies and examples, this paper ef ectively demonstrates the practical application of ROI measurement in test automation, The formula for Return on Investment (ROI) typically falls under the category of being "basic". While costs are relatively simple to measure, assessing the worth of potential advantages proves to be considerably more challenging. Approaches to calculating ROI often oversimplify various aspects of test automation, subsequently resulting in inaccurate outcomes. These inaccuracies, in turn, foster impractical expectations among management in relation to test automation, ultimately culminating in failure at individual, team, and occasionally project levels. thereby of ering valuable insights to organizations seeking to optimize the ef icacy of their testing endeavors.

In this study, we present a secure smart contract-based Verifiable Random Function (VRF) model, addressing the shortcomings of existing systems. As quantum computing emerges, conventional public key cryptography faces potential vulnerabilities. To enhance our VRF’s robustness, we employ post-quantum Ring-LWE encryption for generating pseudo-random sequences. Given the computational intensity of this approach and associated onchain gas costs, we propose a hybrid architecture of VRF system where onchain and offchain can communicate in a scalable and secure way. We employ a unique ring signature scheme with NIZK proof and also delegated key generation, inspired by Chaum-Pedersen proof of logarithm equalty and Fiat-Shamir Heuristic. Our decentralized VRF employs multi-party computation (MPC) with blockchain-based decentralized identifiers (DID), ensuring enhanced randomness and security. We show the security and privacy advantages of our proposed VRF model with approximated estimation of overall time and space complexities. We also evaluate our VRF MPC model’s entropy and outline its Solidity smart contract integration. This research also provides a method to produce and verify the VRF output’s proof, optimal for scenarios necessitating randomness and validation. Lastly, using NIST SP800-22 test suite for randomness, we demonstrate the commendable result with 98.86% of overall pass rate on 11 standard tests and 0.5459 of average p-value for the total 176 tests.

KEYWORDS

Ring-LWE, Verifiable Random Function, DID, MPC, Blockchain, Smart Contract, Ring Signature, Entropy, NIZK proo.

Trust-based Approaches Towards Enhancing Iot Security: a Systematic Literature Review

Oghenetejiri Okporokpo, Funminiyi Olajide, Nemitari Ajienka and Xiaoqi Ma, Department of Computer Science, Nottingham Trent University, Clifton Lane, Nottingham NG11 8NS

ABSTRACT

The continuous rise in the adoption of emerging technologies such as Internet of Things (IoT) by businesses has brought unprecedented opportunities for innovation and growth. However, due to the distinct characteristics of these emerging IoT technologies like real-time data processing, Self-configuration, interoperability, and scalability, they have also introduced some unique cybersecurity challenges, such as malware attacks, advanced persistent threats (APTs), DoS /DDoS (Denial of Service & Distributed Denial of Service attacks) and insider threats. As a result of these challenges, there is an increased need for improved cybersecurity approaches and efficient management solutions to ensure the privacy and security of communication within IoT networks. One proposed security approach is the utilization of trust-based systems and is the focus of this study. This research paper presents a systematic literature review on the Trust-based cybersecurity security approaches for IoT. A total of 23 articles were identified that satisfy the review criteria. We highlighted the common trust-based mitigation techniques in existence for dealing with these threats and grouped them into three major categories, namely: Observation-Based, Knowledge-Based & Cluster-Based systems. Finally, several open issues were highlighted, and future research directions presented.

KEYWORDS

IoT Networks, Internet of Things (IoT), Trust, Privacy, Cybersecurity & IoT Security.

Preserving Confidential Information: a Comprehensive Analysis of Security and Privacy Concerns in Internet of Things (Iot) Systems

Elshan Tanriverdiyev, National Defense University of the Ministry of Defense of the Republic of Azerbaijan

ABSTRACT

The Internet of Things (IoT) is a wireless network that facilitates data exchange among smart nodes (IoT devices). While IoT technology has enabled improved communication and smart systems, it has also become a target for attackers seeking to exploit users sensitive information. This survey paper highlights security and privacy issues within IoT systems, supported by a literature review of related research. The paper delves into security attacks, categorizing them into layer attacks, providing a detailed analysis within the context of IoT layers. Additionally, it presents potential solutions and strategies to safeguard IoT systems against threats. This comprehensive overview aims to shed light on IoT security challenges and offer insights into protecting these systems from potential attacks.

KEYWORDS

Internet of Things, IoT, IoT Systems, RFID, WSN, IoT Security Issues, IoT Security Attacks.

Lightweight Public Key Encryption in Post-quantum Computing Era

Peter Hillmann, University of the Bundeswehr Munich, Department of Computer Science, Werner-Heisenberg-Weg 39, 85577 Neubiberg, Germany

ABSTRACT

Confidentiality in our digital world is based on the security of cryptographic algorithms. These are usually executed transparently in the background, with people often relying on them without further knowledge. In the course of technological progress with quantum computers, the protective function of common encryption algorithms is threatened. This particularly affects public-key methods such as RSA and DH based on discrete logarithms and prime factorization. Our concept describes the transformation of a classical asymmetric encryption method to a modern complexity class. Thereby the approach of Cramer-Shoup is put on the new basis of elliptic curves. The system is provable cryptographically strong, especially against adaptive chosen-ciphertext attacks. In addition, the new method features small key lengths, making it suitable for Internet-of-Things. It represents an intermediate step towards an encryption scheme based on isogeny elliptic curves. This approach shows a way to a secure encryption scheme for the post-quantum computing era.

KEYWORDS

Cryptography, Public-Key Encryption, Post-Quantum Cryptography, Elliptic Curve, Isogeny Curve.

Quantifying Success: Measuring Roi in Test Automation

Rohit Khankhoje, Indianapolis, USA

ABSTRACT

The strategic decision to implement test automation is a favored approach for organizations seeking to improve the quality of their software, expedite delivery, and mitigate testing expenses. In order to make this decision with precision, it is imperative to accurately assess the return on investment (ROI) of test automation. The present paper , titled "Quantifying Success: Measuring ROI in Test Automation," delves deeply into the fundamental aspects of ROI evaluation within the realm of test automation. It outlines the methodology behind ROI calculation, explores the cost factors and advantages associated with automation, and sheds light on the optimal strategies for achieving a favorable ROI. By presenting real-world case studies and examples, this paper ef ectively demonstrates the practical application of ROI measurement in test automation, The formula for Return on Investment (ROI) typically falls under the category of being "basic". While costs are relatively simple to measure, assessing the worth of potential advantages proves to be considerably more challenging. Approaches to calculating ROI often oversimplify various aspects of test automation, subsequently resulting in inaccurate outcomes. These inaccuracies, in turn, foster impractical expectations among management in relation to test automation, ultimately culminating in failure at individual, team, and occasionally project levels. thereby of ering valuable insights to organizations seeking to optimize the ef icacy of their testing endeavors.