Computer Science Research Articles

Cancer diagnosis and prognosis using multi-Omics data: A data science and machine learning approach

Cancer remains one of the leading causes of morbidity and mortality worldwide, demanding innovative approaches for early diagnosis and accurate prognosis. Recent advances in multi-omics technologies, which integrate genomics, transcriptomics, proteomics, metabolomics, and epigenomics, provide comprehensive insights into the complex biological mechanisms underlying cancer. By capturing molecular signatures at multiple levels, multi-omics data offers unparalleled potential for identifying cancer biomarkers, stratifying patients, and predicting therapeutic responses. However, the volume, complexity, and heterogeneity of multi-omics data present significant analytical challenges, necessitating robust data science and machine learning techniques. Machine learning algorithms, including supervised, unsupervised, and deep learning approaches, are increasingly being utilized to unravel the patterns embedded in multi-omics datasets. These methods enable feature selection, dimensionality reduction, and the integration of multi-modal data, facilitating the identification of precise biomarkers and the development of predictive models for cancer progression. Furthermore, advanced frameworks such as explainable AI (XAI) provide interpretability to these models, ensuring their clinical applicability and enhancing trust among healthcare professionals. This review highlights recent breakthroughs in cancer diagnosis and prognosis using multi-omics data, emphasizing the synergy between data science and machine learning in transforming oncology research. It also explores the challenges in data integration, algorithmic bias, and model validation, proposing solutions to enhance predictive accuracy and generalizability. By bridging molecular biology and computational sciences, this interdisciplinary approach has the potential to revolutionize precision oncology, paving the way for personalized treatment strategies and improved patient outcomes.

Using genomic data and machine learning to predict antibiotic resistance: A tutorial paper.

Antibiotic resistance is a global public health concern. Bacteria have evolved resistance to most antibiotics, which means that for any given bacterial infection, the bacteria may be resistant to one or several antibiotics. It has been suggested that genomic sequencing and machine learning (ML) could make resistance testing more accurate and cost-effective. Given that ML is likely to become an ever more important tool in medicine, we believe that it is important for pre-health students and others in the life sciences to learn to use ML tools. This paper provides a step-by-step tutorial to train 4 different ML models (logistic regression, random forests, extreme gradient-boosted trees, and neural networks) to predict drug resistance for Escherichia coli isolates and to evaluate their performance using different metrics and cross-validation techniques. We also guide the user in how to load and prepare the data used for the ML models. The tutorial is accessible to beginners and does not require any software to be installed as it is based on Google Colab notebooks and provides a basic understanding of the different ML models. The tutorial can be used in undergraduate and graduate classes for students in Biology, Public Health, Computer Science, or related fields.

Empowering Society through Assistive Technologies: The Role of Universities in Development and Implementation

This research article explores the significant role of universities in the development and implementation of assistive technologies that empower marginalized populations, particularly the visually impaired. With an emphasis on integrating computer science, engineering, and information technology disciplines, the study highlights the necessity for educational institutions to address societal challenges through innovative technological solutions. The paper discusses essential capabilities for assistive technologies, including advanced reading systems, writing aids, and navigation tools that enhance independence and accessibility for visually challenged individuals. Furthermore, it proposes a collaborative framework that allows students to engage with real-world problems while working alongside industry mentors, fostering a practical problem-solving approach that makes academic projects more relevant and impactful. By leveraging the vast resources available within educational institutions and establishing platforms for mentorship and collaboration, universities can significantly contribute to the advancement of assistive technologies, ultimately promoting inclusivity and equity in society. The article concludes by emphasizing the need for ongoing investment in research and development in this area, thereby ensuring that assistive technologies meet the evolving needs of diverse populations.

BharatSim: An agent-based modelling framework for India.

BharatSim is an open-source agent-based modelling framework for the Indian population. It can simulate populations at multiple scales, from small communities to states. BharatSim uses a synthetic population created by applying statistical methods and machine learning algorithms to survey data from multiple sources, including the Census of India, the India Human Development Survey, the National Sample Survey, and the Gridded Population of the World. This synthetic population defines individual agents with multiple attributes, among them age, gender, home and work locations, pre-existing health conditions, and socio-economic and employment status. BharatSim's domain-specific language provides a framework for the simulation of diverse models. Its computational core, coded in Scala, supports simulations of a large number of individual agents, up to 50 million. Here, we describe the design and implementation of BharatSim, using it to address three questions motivated by the COVID-19 pandemic in India: (i) When can schools be safely reopened given specified levels of hybrid immunity?, (ii) How do new variants alter disease dynamics in the background of prior infections and vaccinations? and (iii) How can the effects of varied non-pharmaceutical interventions (NPIs) be quantified for a model Indian city? Through its India-specific synthetic population, BharatSim allows disease modellers to address questions unique to this country. It should also find use in the computational social sciences, potentially providing new insights into emergent patterns in social behaviour.

Personalized games for computer science education in higher education: the effect of personalization feature on students’ engagement and flow state

Personalized games for computer science education in higher education: the effect of personalization feature on students’ engagement and flow state

PD supporting CS and math integration: implications of teacher interest and confidence for workshop design

ABSTRACT Background and Context Integrating computer science (CS) and math in classrooms is an increasingly recognized way for schools to address national CS mandates. There is a need to understand how professional development (PD) can support teachers to integrate. Objective We examined math teachers’ interest, and confidence, in math, CS, and student learning, in relation to their participation in professional development (PD) designed to support them to integrate CS with math in their classrooms. Method We used mixed-methods to study participants in entry-level hybrid PD, and a sub-group of those participants who took the workshop a second time. Findings Results showed that not all math teachers have an interest in math, and that math interest significantly influenced whether teachers (a) returned to retake the entry-level workshop and (b) followed through to integrate CS in their teaching. Implications Findings suggest that workshop design include: (1) multiple points of entry, (2) pairing/grouping participants based on interest and confidence, and (3) opportunities to practice.

Workshop Development for New Frontier of Mechatronics for Mobility, Energy, and Production Engineering

Mechatronics is a multidisciplinary engineering field that integrates mechanics, electronics, control theory, computer science, communications, power, and production manufacturing, reflecting the trend toward deep cross-disciplinary collaboration. With applications in e-mobility, connected and autonomous vehicles (CAV), robotics, and unmanned aerial vehicles (UAV), the expanding mechatronics industry demands a workforce with broad, multidisciplinary training. This paper details the activities and outcomes of an NSF-funded ECR: PEER (EHR Core Research: Production Engineering Education and Research) project, which organized two workshops at Wayne State University (WSU) and California State University Long Beach (CSULB). These workshops aimed to gather insights from experts across academia, industry, and non-profit sectors to shape the future of mechatronics education and production. Over two days, professionals addressed challenges in workforce development for production engineering in mechatronics, covering educational pathways, advancements in teaching methods, and the social impacts of mechatronics technology. The workshops had distinct focuses: WSU concentrated on ground mobility technologies, while CSULB emphasized aerospace applications. A survey conducted at the end of the workshops evaluated their effectiveness, with the results informing future improvements in mechatronics workforce education.

ALGORITHMIC THINKING IN HIGHER EDUCATION: DETERMINING OBSERVABLE AND MEASURABLE CONTENT

Nowadays algorithmic thinking, as a key demand and the main requirement of technology-based society, extensively expands outwards the computer science area and rapidly becomes a meaningful instrumentality for effective realization of any information activities with or without ICT. This instrumentality creates new opportunities and possibilities for improvement of the effectiveness of any educational professional activities in the higher education context by creating problem-solving algorithms completely within the ICT area, as well as non-ICT-based algorithms that provide clear technological step-by-step instructions for solving a diversity of educational problems. Although attention to algorithmic thinking as scientific phenomenon is increasing, the studies aimed at determining the algorithmic thinking content in observable and measurable statements have not been conducted yet and its great potential is still undiscovered. The purpose of this study is to identify, clarify, and categorize algorithmic thinking content in observable and measurable knowledge, skills, and abilities statements (KSAs). The study is a mixed-methods type of development research carried out in 4 stages: 1) extraction of the KSA statements from the extant scientific literature related to algorithmic thinking; 2) design of The Algorithmic Thinking Content Survey (ATCS) based on the five steps Universal Sequence of an Algorithm Development (USAD); 3) administration of the ATCS on a wide variety of educational professionals (N = 117); 4) data analysis aimed to obtain the content of algorithmic thinking in observable and measurable KSA statements. The design of the ATCS is also based on algorithmic thinking as a complex phenomenon that integrates five types of thinking: abstract, logical, figurative, conceptual, and constructive. The administration of the ATCS involved 117 experts – educational professionals (11 professors who teach courses concerning algorithms and computer science, 23 practicing teachers of informatics, 35 students in the 3rd year of Informatics teacher training program, and 48 master students of informatics). Expert validation of algorithmic thinking content in knowledge, skills, and abilities statements was obtained through the Likert scale. One hundred KSA statements of algorithmic thinking content were obtained (32 statements of knowledge, 38 statements of skills, and 30 statements of abilities).

Variants of RSA and Rabin Cryptosystems modulo p^rq^s

Cryptography is the technique to protect sensitive information from unauthorized persons by encryption. Cryptographers have invented various systems of cryptography to make it befitting. In the age of modern science, the use of mathematical theories has added a new dimension to cryptography. Prime factorization-based cryptography is widely used and effective. In 1977, Rivest, Shamir, and Adlerman proposed the first practical public key cryptosystem based on the prime factorization of large numbers known as the RSA cryptosystem. Later in 1979, Michael Oser Rabin developed a technique based on prime-factorization known as Rabin Cryptosystem. Several variants of these systems have been developed further by many famous mathematicians and computer scientists, aiming to increase security, reduce cost, time, and memory usage, and enhance overall performance. Tsuyoshi Takagi and Hugh C. Williams proposed such two famous variants. In this paper, we have first analyzed the traditional cryptosystems and existing variants. Identifying the security strength and field of improvement of these systems and their variants, we have proposed two new variants. The encryption-decryption techniques are described by employing them in several applications. The effectiveness of the proposed variants is demonstrated by a comparative analysis of these variants with others. Numerical experiments show that the proposed Rabin’s variant performs almost the same as the base algorithm. However, the proposed variant of RSA algorithm reduces computational time significantly, approximately 91% reduction from traditional RSA and 90% reduction from multi-prime RSA. J. Bangladesh Math. Soc. 44.2 (2024) 01–16

Pedagogical guidance of the process of forming information technological competence of future computer science teachers: a practical aspect

The article reveals the current problem of organizing pedagogical guidance in the process of forming information technology competence of future computer science teachers in a practical aspect:It is noted that technological training in the conditions of the modern information and educational space of higher education` pedagogical institutions is implemented by performing a significant part of educational activities using communication technologies.In the article it is presupposed that mandatory presence of initial information and technological literacy of students, is manifested not only in their mastery of the skills and abilities in using their activities of a set oftechnical means and devices, but also in the ability to understand when this information is needed, find it how to evaluate and use it effectively.Therefore it is necessary to improve the ways of forming and developing information technology competence of specialists as a necessary component of their general professional competence. It is a value guideline of modern higher pedagogical education; the practical component of the process of forming information technology competence of future computer science teachers. It is revealed in the context of the activities of the studio of pedagogical excellence to improve the methodological and technological literacy of higher education teachers, which provided for work in two directions: «Modern Educational Technologies» and «Fundamentals of Computer Telecommunications». It is concluded that the use of information and communication technologies in the educational and information environment of a pedagogical institution of higher education and the optimal management of this process made it possible to provide students with additional theoretical and methodological material on electronic media in the disciplines of basic training in the field of informatization of education, which made it possible to repeat the educational material of the studied problems and use it in a new context.

Classification of Brain Tumor based on Machine Learning Algorithms: A Review

Brain tumor classification using machine learning algorithms is pivotal for medical diagnostics, particularly in magnetic resonance imaging (MRI) analysis. This review provides a comprehensive overview of recent advancements in brain tumor classification methodologies, emphasizing preprocessing, feature extraction, and classification phases. Preprocessing steps involve noise reduction and intensity normalization, while feature extraction encompasses texture analysis and deep learning-based methods. Machine learning algorithms such as support vector machines (SVM) and convolutional neural networks (CNNs) are utilized for accurate classification based on extracted features. Recent literature highlights the significance of diverse datasets, hyperparameter tuning, and segmentation techniques in improving diagnostic accuracy. Noteworthy methodologies include deep learning models for glioma grading and novel optimization techniques for tumor segmentation. The review underscores interdisciplinary collaboration between medical professionals and computational scientists to refine existing methodologies and overcome challenges. A systematic search of academic databases, including PubMed, IEEE Xplore, ACM Digital Library, ScienceDirect, Springer and Google Scholar, was conducted. Continued evolution in brain tumor classification promises enhanced diagnostic accuracy and personalized treatment strategies, ultimately improving patient outcomes in neuro-oncology.

Connections between students’ perceptions of the motivational climate in a course and their motivational beliefs and academic and career goals

ABSTRACT To address the demand for engineers and computer scientists in the workforce, and the fact that some engineering students dropout or change majors, we explored how the motivational climate in an undergraduate computer science (CS) course was related to students’ motivational beliefs and academic and career goals. Participants included 310 students enrolled in a CS course within a university College of Engineering. The survey included measures that assessed constructs related to the MUSIC Model of Motivation theory, situated expectancy-value theory, and school belonging. Regression analyses identified several significant relationships between the course-level motivational climate variables and students’ CS motivational beliefs. However, the pattern of relationships between variables often differed by academic major for each of the CS belief variables. Students’ CS motivational beliefs predicted their academic and CS career goals, but the patterns were somewhat different across academic majors. We did not identify many differences across sex and race/ethnicity.

TRAINING OF COMPUTER SCIENCE TEACHERS FOR THE FORMATION OF CYBERSECURITY SKILLS IN STUDENTS: ACTUALIZATION OF PROBLEMS AND THEIR POSSIBLE SOLUTIONS

The article presents an analysis of the problem of preparing computer science teachers for the formation of cybersecurity skills in students. The generalization of the available scientific results gives an idea of the general trends and problems in this field: the need for constant updating of the curriculum in computer science and cybersecurity is emphasized to keep pace with the development of technologies and standards; emphasizes the need to combine practical skills with fundamental knowledge in cybersecurity education; stresses the importance of pedagogical and methodological knowledge along with subject knowledge in the training of computer science teachers; mastering innovative digital strategies for teaching and learning computer science; a mixed way of teaching courses (face-to-face, hybrid or online) and a variety of teaching methods; development of methodological competence of computer science teachers through different approaches to such development (special courses, internship programs, mentoring, joint lesson planning and reflective practice, etc.). Based on the results of the analysis, recommendations were formulated for the modernization of teacher training programs for the formation of students' cybersecurity skills: integration of content modules on cybersecurity into courses on methods of teaching computer science; development and implementation of specialized cybersecurity courses in educational and professional teacher training programs; use of digital tools and simulation technologies; promoting the continuous professional development of teachers in the field of cybersecurity; promoting cooperation and knowledge exchange with cybersecurity practitioners; bringing computer science teacher training curricula in line with international standards in the field of cybersecurity. We consider further research to be promising in studying the content of educational programs for training computer science teachers and analyzing the effectiveness of various teaching methods for developing cybersecurity skills in future computer science teachers.

Quantum Computing: Potential and Challenges for the Future of Cryptography

Utilising the laws of quantum mechanics, quantum computing offers unparalleled computational capacity, marking a paradigm leap in the science of computation. Quantum computers' capacity to upend current cryptography systems is becoming more apparent as they mature. the two-pronged effect of quantum computing on cryptography: on the one hand, it might undermine existing encryption algorithms, and on the other, it could pave the way for the creation of new, more robust protocols that are immune to quantum attacks. We take a look at the theory behind quantum algorithms, with a focus on Shor's algorithm, which poses a danger to popular public-key encryption techniques like RSA and ECC. We also go into post-quantum cryptography, the field that aims to make encryption systems impenetrable to attacks that use quantum mechanics. Quantum cryptography has come a long way, but there are still a lot of obstacles to overcome. These include making viable quantum computers, getting past hardware limits, and dealing with the complexity of switching from classical to quantum-safe encryption. the significance of getting ready for a quantum future, with an emphasis on the continuing endeavours in quantum computing and cryptography research to safeguard the digital realm from new dangers.

The legal nature of generative artificial intelligence (- Model - Chat G.P.T)

Artificial intelligence, , is a technological revolution in our current era, called the Fourth Industrial Revolution, which is essentially based on merging computer science, or computer science, with human intelligence to produce artificial intelligence. Chatbot (GAPT) is one of the most important generative artificial intelligence programs as a chatbot, or (GATTGBT). It is translated into Arabic (generative artificial transformer that is pre-trained for conversation), and the name generative artificial intelligence comes from the fact that it is programmed in order to be able to generate and create new content of its kind by learning patterns and structures from the data on which it was programmed, and thus it enjoys a kind of independence from whoever created it. By programming it with data and information. In our research, we focus on the legal nature of this modern technology according to the Iraqi Civil Law No. (40) and according to the Iraqi Consumer Protection Law No. (10) of 2010, and at the end of our research we arrived at a set of conclusions and recommendations to serve this research.

Guided Reading: A Case Study in Evaluating Scientific Reports on Quantitative Research

Researchers have access to a vast repository of scientific papers reporting research results through the Internet. In this context, fostering collective knowledge growth, researchers may encounter situations where the content of a paper is not effectively utilized due to flaws in the presentation of conducted research. Various fields of knowledge have developed research protocols to assist in the production of scientific reports. In the field of Computer Science, proposals for such protocols are still in development. This paper describes a case study conducted with undergraduate and graduate students in Computer Science, involving guided reading of scientific papers, and recording students’ perceptions regarding adherence to a set of guidelines for the presentation of scientific results. The case study focused on papers presenting research results with a quantitative focus, such as performance evaluations. The exercise took place over two academic semesters, where reading instructions were provided, and impressions about the observed content were collected every two or three weeks. The analysis results indicated that, despite being well-written, the papers had gaps in relation to the reading guidelines. The study’s conclusions suggest that authors underestimate the importance of providing a comprehensive account of their experi-ence, highlighting the need for protocols to report scientific results in the field of Computer Science.

The effects of machine-learning programming simulator on university students’ engagement in learning programming

A computer programming course is essential for students pursuing a computer science major. The college offers a course that imparts essential knowledge to undergraduate computer science students. After finishing their degree, individuals may utilize their experience in entrepreneurial pursuits. Students without competency in the fundamental concepts of computer programming may face challenges in obtaining employment, particularly in positions such as developers or software developers. Enrollment in the programming course is compulsory for computer science students. A decline in employment for computer programmers is a recent issue nowadays, while growing demand for skilled programmers happened in certain regions, such as Indonesia. While it is true that many simpler duties can be automated, there will be a growing demand for positions that require strategic decision-making. To remain competitive, programmers must increase their abilities to satisfy these obligations. The study emphasizes the need for integrating technology, including gamification and simulation tools, in programming education to enhance student engagement and learning outcomes. A quasi-experimental study was conducted to investigate the impact of a machine learning (ML) programming simulator on student engagement. The study involved 120 university students, divided into two groups: one using the ML programming simulator and the other using a non-ML simulator. The results showed that students using the ML simulator had higher engagement levels compared to those using the non-ML simulator, suggesting that ML-based tools can significantly improve student participation and learning in programming courses. The findings underscore the potential benefits of using advanced technological tools to foster better learning experiences in computer programming education.

Sentiment Analysis of Computer Science Students’ Attitudes Toward Programming Languages: An in-Depth Study

This study investigates the sentiments of computer science students toward programming languages, focusing on Python, Java, and C, to explore factors influencing their learning experiences, motivation, and career aspirations. Data from forums, surveys, and social media platforms were analysed using sentiment analysis and thematic qualitative analysis. The findings reveal that students view programming as both challenging and rewarding. Python is valued for its role in data science, Java for enterprise solutions and Android development, and C for its foundational importance in programming. Students reported frustrations with syntax complexities, usability, and industry relevance despite these strengths. Despite these strengths, students reported frustrations with syntax complexities, usability, and industry relevance. The research highlights the need for adaptive teaching strategies that connect programming concepts to practical applications, foster resilience, and offer diverse learning opportunities. By bridging the gap between industrial expectations and academic preparation, these ideas hope to improve programming education and bring it into line with changing professional requirements.

INTEGRATING BLENDED LEARNING IN PROGRAMMING COURSE: A COMPREHENSIVE SYSTEMATIC REVIEW

This systematic review examines the integration of blended learning in programming courses, addressing the increasing diversity of student backgrounds and the consequent challenges in teaching programming effectively. The study synthesizes findings from recent research to identify effective strategies and best practice outcomes associated with blended learning approaches in this context. A comprehensive methodology was employed, involving the selection and analysis of relevant articles from databases such as Scopus and Web of Science, focusing on studies published between 2020 and 2024. The study was conducted following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) framework. The database found (n=30) final primary data was analysed. Numerical results from the chosen literature reveal three main themes: (1) Effectiveness of Blended Learning in K-12 Education, (2) Best Practice of Blended Learning in Higher Education and Professional Development, and (3) Students’ Understanding on Blended Learning in Programming and Computer Science Education. This review concludes that integrating blended learning in programming courses not only addresses diverse learning needs but also fosters improved academic outcomes and student engagement. Future research should continue to explore innovative blended learning strategies and their long-term impacts on programming education.

The Innovation and Transfer of Computer Science and Technology in Recent and Modern Railway Transportation

This article aims to discuss the influence of computer technology on the innovation and technology transfer of modern railway transportation. By historical analysis and empirical research, this article first reviews the evolution of railway transportation from steam locomotive to High-Speed Railways, and then compares and analyzes the performance of the improved multi-objective particle swarm optimization (MPSO) algorithm and traditional particle swarm optimization (PSO) algorithm in train operation scheduling through designing simulation experiments. The experiment selected the representative train operation data sets, and the first 25 and 15 data items are used as training sets respectively to predict the subsequent data items, and the prediction results of MPSO algorithm, traditional PSO algorithm and support vector machine algorithm are compared. The results show that MPSO algorithm is excellent in prediction accuracy, convergence speed and error control, and its prediction results are closer to the actual train running state, which verifies the effectiveness of computer technology in optimizing railway transportation scheduling.