Computer Science Research Articles

Unveiling the power of artificial intelligence for image-based diagnosis and treatment in endodontics: An ally or adversary?

Artificial intelligence (AI), a field within computer science, uses algorithms to replicate human intelligence tasks such as pattern recognition, decision-making and problem-solving through complex datasets. In endodontics, AI is transforming diagnosis and treatment by applying deep learning algorithms, notably convolutional neural networks, which mimic human brain function to analyse two-dimensional (2D) and three-dimensional (3D) data. This article provides an overview of AI applications in endodontics, evaluating its use in 2D and 3D imaging and examining its role as a beneficial tool or potential challenge. Through a narrative review, the article explores AI's use in 2D and 3D imaging modalities, discusses their limitations and examines future directions in the field. AI significantly enhances endodontic practice by improving diagnostic accuracy, workflow efficiency, and treatment planning. In 2D imaging, AI excels at detecting periapical lesions on both periapical and panoramic radiographs, surpassing expert radiologists in accuracy, sensitivity and specificity. AI also accurately detects and classifies radiolucent lesions, such as radicular cysts and periapical granulomas, matching the precision of histopathology analysis. In 3D imaging, AI automates the segmentation of fine structures such as pulp chambers and root canals on cone-beam computed tomography scans, thereby supporting personalized treatment planning. However, a significant limitation highlighted in some studies is the reliance on in vitro or ex vivo datasets for training AI models. These datasets do not replicate the complexities of clinical environments, potentially compromising the reliability of AI applications in endodontics. Despite advancements, challenges remain in dataset variability, algorithm generalization, and ethical considerations such as data security and privacy. Addressing these is essential for integrating AI effectively into clinical practice and unlocking its transformative potential in endodontic care. Integrating radiomics with AI shows promise for enhancing diagnostic accuracy and predictive analytics, potentially enabling automated decision support systems to enhance treatment outcomes and patient care. Although AI enhances endodontic capabilities through advanced imaging analyses, addressing current limitations and fostering collaboration between AI developers and dental professionals are essential. These efforts will unlock AI's potential to achieve more predictable and personalized treatment outcomes in endodontics, ultimately benefiting both clinicians and patients alike.

Adoption and Impact of ChatGPT in Computer Science Education: A Case Study on a Database Administration Course

The irruption of GenAI such as ChatGPT has changed the educational landscape. Therefore, methodological guidelines and more empirical experiences are needed to better understand these tools and know how to use them to their fullest potential. This contribution presents an exploratory and correlational study conducted with 37 computer science students who used ChatGPT as a support tool to learn database administration. The article addresses three questions: The first one explores the degree of use of ChatGPT among computer science students to learn database administration, the second one explores the profile of students who get the most out of tools like ChatGPT to deal with database administration activities, and the third one explores how the utilization of ChatGPT can impact in academic performance. To empirically shed light on these questions the student’s grades and a comprehensive questionnaire were employed as research instruments. The obtained results indicate that traditional learning resources, such as teacher’s explanations and student’s reports, were widely used and correlated positively with student’s grades. The usage and perceived utility of ChatGPT were moderate, but positive correlations between students’ grades and ChatGPT usage were found. Indeed, a significantly higher use of this tool was identified among the group of outstanding students. This indicate that high-performing students are the ones who are using ChatGPT the most. So, a new digital trench could be rising between these students and those with a lower degree of fundamentals and worse prompting skills, who may not take advantage of all the ChatGPT possibilities.

Information Training and Media Education: a Method of Solving Students' Educational and Cognitive Problems in an Integrated Information Environment

Discusses the method of solving students' educational and cognitive problems in an integrated information environment. The purpose of the study is to determine effective forms and methods of information training and media education to ensure universal access to education throughout life. The source of the study was the works of scientists who consider issues of media education and information training as an important component of the educational and cognitive tasks of students in the context of an integrated information environment. A set of pedagogical research methods, both theoretical and practical, was used. According to experts, in the field of educational resources, the total volume of knowledge doubles every year, while the degree of satisfaction of the information needs of users in the absence of an appropriate level of skill in working with information does not improve. Computer science is today defined as one of the fundamental areas of scientific knowledge that forms a system-information approach to the analysis of the surrounding world, the study of information processes, methods and means of obtaining, transforming, transmitting, storing and using information, a rapidly developing and constantly expanding area of human practical activity associated with the use of educational resources. In this regard, media education and information training of students are considered as an important part of the professional and educational skills and abilities of students in the context of an integrated information environment. The results of the study can serve as a basis for solving educational and cognitive problems of continuous education, since today no serious economic, social, technical problem can be successfully solved without processing significant amounts of information.

Compassionate Care with Autonomous AI Humanoid Robots in Future Healthcare Delivery: A Multisensory Simulation of Next-Generation Models

The integration of AI and robotics in healthcare raises concerns, and additional issues regarding autonomous systems are anticipated. Effective communication is crucial for robots to be seen as “caring”, necessitating advanced mechatronic design and natural language processing (NLP). This paper examines the potential of humanoid robots to autonomously replicate compassionate care. The study employs computational simulations using mathematical and agent-based modeling to analyze human–robot interactions (HRIs) surpassing Tetsuya Tanioka’s TRETON. It incorporates stochastic elements (through neuromorphic computing) and quantum-inspired concepts (through the lens of Martha Rogers’ theory), running simulations over 100 iterations to analyze complex behaviors. Multisensory simulations (visual and audio) demonstrate the significance of “dynamic communication”, (relational) “entanglement”, and (healthcare system and robot’s function) “superpositioning” in HRIs. Quantum and neuromorphic computing may enable humanoid robots to empathetically respond to human emotions, based on Jean Watson’s ten caritas processes for creating transpersonal states. Autonomous AI humanoid robots will redefine the norms of “caring”. Establishing “pluralistic agreements” through open discussions among stakeholders worldwide is necessary to align innovations with the values of compassionate care within a “posthumanist” framework, where the compassionate care provided by Level 4 robots meets human expectations. Achieving compassionate care with autonomous AI humanoid robots involves translating nursing, communication, computer science, and engineering concepts into robotic care representations while considering ethical discourses through collaborative efforts. Nurses should lead the design and implementation of AI and robots guided by “technological knowing” in Rozzano Locsin’s TCCN theory.

AI and language change: The case of the hallucinating spellchecker

Key points The formal written register of the English language is subject to change from AI enhanced spellchecking, grammar and style tools. The proprietary AI algorithms are poorly understood and under‐researched. There is potential for cultural biases, unclear memorisation predictors and variability in reproducibility leading to poorly written and grammatically incorrect English. There is room for further study, most likely in an interdisciplinary setting involving linguists and computer scientists, with an attempt to reverse engineer the AI algorithms.

An Information-Theoretic Proof of a Hypercontractive Inequality

The famous hypercontractive estimate discovered independently by Gross, Bonami and Beckner has had a great impact on combinatorics and theoretical computer science since it was first used in this setting in a seminal paper by Kahn, Kalai and Linial. The usual proofs of this inequality begin with two-point space, where some elementary calculus is used and then generalised immediately by introducing another dimension using submultiplicativity (Minkowski’s integral inequality). In this paper, we prove this inequality using information theory. We compare the entropy of a pair of correlated vectors in {0,1}n to their separate entropies, analysing them bit by bit (not as a figure of speech, but as the bits are revealed) using the chain rule of entropy.

The Role of Formal Methods in Computer Science Education

The Role of Formal Methods in Computer Science Education

Proficiency of Turing test on Nigerian Major Languages; Yoruba, Igbo and Hausa Using Google Translate

Google Translate performance evaluation in translating between English and three Nigerian languages: Yoruba, Igbo, and Hausa, highlighting its strengths and limitations using the Turing Test. The study assessed whether participants could distinguish Artificial Intelligence (AI) - generated translations from human translations which reveals that Google Translate handles basic communication in these languages but struggles with more complex linguistic features. The tool adequately translates straightforward sentences in Yoruba language, but falters with idiomatic expressions, proverbs, and tonal nuances, the same problem refects in Igbo language facing challenges with more complex sentences and dialectal variations, resulting in culturally irrelevant outputs. Hausa performed better due to the availability of a larger training dataset, delivering more accurate translations for common phrases, but still struggled with cultural and contextual nuances.The findings suggest that Google Translate's limitations prevent it from passing a Turing Test with native speakers of Yoruba, Igbo, and Hausa. While understandable translations are produced for basic sentences, native speakers can easily detect inconsistencies, awkward phrasing, and a lack of cultural nuance. These issues underscore the significant gap between AI translation and human-like proficiency for African languages. Keyword: Turing test, Nigerian Major Languages; Yoruba, Igbo, Hausa Using Google Translate Abiola, O.A., Adebisi R.O. & Akinola, S.O. (2024): Proficiency of Turing test on Nigerian Major Languages; Yoruba, Igbo and Hausa Using Google Translate. Journal of Advances in Mathematical & Computational Science. Vol. 12, No. 3. Pp 1-12 Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N4P1

Neurorights, Neurotechnologies and Personal Data: Review of the Challenges of Mental Autonomy

Objective: to present the results of a systematic review of research on the impact of neurotechnology on legal concepts and regulatory frameworks, addressing ethical and social issues related to the protection of individual rights, privacy and mental autonomy.Methods: The systematic literature review was based on the methodology proposed by a renowned British scholar, a professor emerita of computer science at Keele University Barbara Kitchenham, chosen for its flexibility and effectiveness in obtaining results for publication. Thorough searches were carried out with the search terms “neurotechnology”, “personal data”, “mental privacy”, “neuro-rights”, “neurotechnological interventions”, and “neurotechnological discrimination” on both English and Spanish sites, using search engines like Google Scholar and Redib as well as databases including Scielo, Dialnet, Redalyc, Lilacs, Scopus, Medline, and Pubmed. The focus of this research is bibliometric data and its design is non-experimental with a cross-sectional and descriptive, using content analysis based on PRISMA model.Results: the study emphasizes the need to establish clear ethical principles to protect individual rights and promote responsible use of neurotechnologies; a number of problems of mental autonomy were identified, such as improper handling of information, lack of legal security guarantees, violation of rights and freedoms in the medical sphere. The author shows the need to adapt the existing regulatory legal framework to address the ethical and social problems arising from the new neurotechnologies. It is noted that a broad study of neurotechnology issues will contribute to the protection of human rights.Scientific novelty: an expanded understanding of the five neurorights within the Universal Declaration of Human Rights is proposed; neurorights are viewed as a new category of rights aimed at protecting mental integrity against the misuse of neurotechnologies. The author justifies the adoption of such technocratic principles as personal identity, free will, mental privacy, equal access and protection against bias.Practical significance: the obtained results are relevant for understanding modern legal concepts related to neurorights and for adapting the existing normative legal acts to solve ethical and social problems arising from the emergence of new technologies, protection of human neurorights and liability for their violation. The study of these issues is key for provision of further responsible development and use of neurotechnologies.

A randomized controlled trial on the nomenclature of scientific computing

ABSTRACT Background and Context Data science and statistics are used across a broad spectrum of professions, experience levels and programming languages. The popular scientific computing languages, such as Matlab, Python and R, were organized without using empirical methods to show evidence for or against their design choices, resulting in them feeling eclectic or esoteric in their design. Objective To meaningfully organize scientific computing based on evidence gathered through user feedback, build a statistical package based on the findings and provide a replication packet to run similar studies on people with different backgrounds. Method A randomized controlled trial using a weighted, ranked choice survey (n = 118) with between-subjects design having two independent variables: Language Group (Matlab, Python and R) and Method Name options. Our dependent variable was a normalized preference rating. Findings There was a very small interaction between Language Group and Method Name. Language Group did not have a statistically significant effect, but Method Name did (F(4, 27037) = 2211.23, p < .001)( η p 2 = .247). Finally, many names in Matlab, Python and R were ranked so poorly that they were not statistically significantly different from a random word in 63.0%, 62.2% and 30.4% of concepts respectively. Implications We found organized and structured names were ranked by a large margin, suggesting statistical programming today likely needs considerable improvement. Finally, we outline a statistical package built using these principles, provide comparison scripts and describe some of the challenges from going from simple surveys to in-practice libraries.

The T-Shaped Model: A Modern Paradigm for TVET Curriculum Design. Conceptual Framework, Theoretical Foundations and Practical Examples

The T-shaped curriculum in secondary technical VET represents a progressive educational framework designed to equip students with both specialized technical skills and a broad range of transferable competencies. This curriculum model emphasizes the development of deep expertise in specific technical fields, such as engineering or computer science, while simultaneously fostering essential skills in communication, critical thinking, and collaboration. By integrating real-world applications, experiential learning opportunities, and interdisciplinary projects, the T-shaped curriculum prepares students for immediate employment and long-term adaptability in a rapidly evolving job market. This approach not only enhances students’ technical proficiency but also cultivates their ability to navigate complex professional environments, thereby addressing the growing demand for versatile and resourceful graduates. The implementation of the T-shaped curriculum in secondary technical VET programs is shown to align educational outcomes with industry needs, decisively producing well-rounded professionals capable of contributing productively to diverse roles and industries. This article explores the significance of the T-shaped curriculum in shaping future-ready individuals and highlights its potential to transform TVET in response to the challenges of the modern workforce.

The Logic and Application of Greedy Algorithms

Abstract. Being easy to implement and offering faster solutions, the greedy algorithms have widely been used in solving combinatorial optimization problems in computer science and many practical applications, such as resource allocation and data compression. This paper aims at analyzing the definitions, theory, and application of greedy algorithms in computer science as well as their logic and efficacy in numerous situations. In this analysis, concepts such as the greedy choice property and optimal substructure are examined as essential to understanding how greedy algorithms operate. The provided analysis mainly assumes prior knowledge of concepts and problems like the Fractional Knapsack problem and the Shortest Path problem solution as well as some practical problems, for example, resource allocation and the exact coin change problem. Analytical data and real applications are used to analyze the performance of greedy algorithms vis-a-vis other categories, such as the dynamic programming paradigm. The results reveal that greedy algorithms have the potential for great efficiency while also being restricted by certain parameters. They are ideal in the following aspects pertaining to computational aspects, that is, speed, ease of implementation, and applicability to large datasets. But they do not necessarily promise strong optimality in certain situations. The conclusion notes that greedy algorithms deserve further applications when the specified conditions are met and states that the effectiveness of these conditions needs to be studied.

Generating Bent Functions and Dynamic Filters: A Novel Equivalence-Based Approach

Boolean functions are fundamental building blocks in both discrete mathematics and computer science, with applications spanning from cryptography to coding theory. Bent functions, a subset of Boolean functions with maximal nonlinearity, are particularly valuable in cryptographic applications. This study introduces a novel equivalence relation among all Boolean functions and presents an algorithm to generate bent functions based on this relation. We systematically generated a collection of 10,000 bent functions over eight variables, all originating from the same equivalence class, and analyzed their structural complexity through rank determination. Our findings revealed the presence of at least five distinct affine classes of bent functions within this collection. By employing this construction, we devised an algorithm to generate a filter function capable of combining Boolean functions. This filter function can be dynamically adjusted based on a key, offering potential applications in symmetric cipher design, such as enhancing security or improving efficiency.

BIG DATA AND STATISTICAL APPLICATIONS

In recent years, modern developments in computer and cloud technologies have led to a significant increase in the quantity and speed of generated and stored information. This increase in the amount of information has introduced a new concept into our lives called "Big Data". Big Data offers significant advantages, especially for governments and businesses, in making informed decisions about their futures. However, the magnitude and diversity of this emerging data also bring about some challenges. Traditional database systems have been inadequate in processing these data formats, necessitating the need for new tools and techniques to overcome this challenge. Today, a wide range of techniques and technologies have been developed to collect, process, analyze, and visualize “Big Data”. These techniques and technologies encompass and draw upon various fields such as statistics, computer science, applied mathematics, and economics. Keywords: big data, visualization of data, structured data, big data technologies, big data techniques.

The Development of Operational Model Integrating Digital Technologies into Public Mental Healthcare Services in Nigeria

The availability and utilization of digital technologies can leverage the challenges of the sharp-depleting workforce due to the consistent migration of healthcare professionals (HCPs), the alarming ratio of the number of patients to HCPs, discretional use of digital technologies among HCPs in providing effective therapeutic interventions and mental healthcare services. This study aimed to develop an operational model that integrates digital technologies in mental healthcare service delivery for public facilities in Nigeria. The practice-oriented theory guides the development of the model. A qualitative method assessed the digital technologies used during the COVID-19 pandemic. A non-probability, purposive sampling technique that employed the snowball method was used in selecting the sixteen (16) HCPs from four (4) neuropsychiatric hospitals in South-West Nigeria. Thematic analysis was conducted on qualitative data. Findings from the qualitative analysis revealed several challenges in providing adequate and efficient services in public mental healthcare facilities in Nigeria, such as human resource challenges, brain drain, lack of infrastructure, and strains on HCPs. Findings from this study indicated that digital technologies are sparingly utilized in public mental healthcare service delivery due to a lack of policy and framework. HCPs perceive digital technologies to be beneficial to themselves and their clients. The highlighted benefits to patients are reduced stigmatization levels, decreased financial burden, enhanced accessibility to therapists, strengthened adherence, mitigated relapse incidences and improved intervention. The transition from the traditional/conventional space of mental healthcare service delivery to digital space requires a collaborative approach with Computer scientists (software developers, database administrators), Data scientists, investors, stakeholders and mental HCPs. The proposed model serves as a contemporary framework that the Government, policymakers in the Ministry of Health and management of mental health facilities in Nigeria can adopt, providing the needed awareness of the benefit of technological intervention.

Exploiting LSTM Neural Network Algorithm Potentiality for Early Identification of Delayed Graduation in Higher Education

Adoption of deep learning classification algorithms in the domain area of higher education provides exploratory predictive data analytics able to exploit students’ academic behavior. Concretely, student retention and success are critical concerns in higher education globally. Timely identification of potential delays in graduation is essential for universities to provide effective interventions and support, ensuring students’ progress efficiently and maintaining high graduation rates, thereby enhancing institutional reputation. This study examines data from a typical computer science department of a central Greek university, covering student performance for almost two decades (1999-2018). Through extended data preprocessing, we developed a robust dataset focusing on key courses indicative of students' likelihood to graduate on time or experience delays. We employed a deep learning Long Short-Term Memory (LSTM) Neural Network algorithm, leveraging this dataset to classify and predict students' final academic outcomes. Our findings reveal that early-semester performance data can successfully forecast graduation timelines, enabling proactive educational strategies to support student success during their studies at the university.

Code-ifying the Law: How Disciplinary Divides Afflict the Development of Legal Software

Proponents of legal automation believe that translating the law into code can improve the legal system. However, research and reporting suggest that legal software systems often contain flawed translations of the law, resulting in serious harms such as terminating children's healthcare and charging innocent people with fraud. Efforts to identify and contest these mistranslations after they arise treat the symptoms of the problem, but fail to prevent them from emerging. Meanwhile, existing recommendations to improve the development of legal software remain untested, as there is little empirical evidence about the translation process itself. In this paper, we investigate the behavior of fifteen teams---nine composed of only computer scientists and six of computer scientists and legal experts---as they attempt to translate a bankruptcy statute into software. Through an interpretative qualitative analysis, we characterize a significant epistemic divide between computer science and law and demonstrate that this divide contributes to errors, misunderstandings, and policy distortions in the development of legal software. Even when development teams included legal experts, communication breakdowns meant that the resulting tools predominantly presented incorrect legal advice and adopted inappropriately harsh legal standards. Study participants did not recognize the errors in the tools they created. We encourage policymakers and researchers to approach legal software with greater skepticism, as the disciplinary divide between computer science and law creates an endemic source of error and mistranslation in the production of legal software.

Articulation Work and Tinkering for Fairness in Machine Learning

The field of fair AI aims to counter biased algorithms through computational modelling. However, it faces increasing criticism for perpetuating the use of overly technical and reductionist methods. As a result, novel approaches appear in the field to address more socially-oriented and interdisciplinary (SOI) perspectives on fair AI. In this paper, we take this dynamic as the starting point to study the tension between computer science (CS) and SOI research. By drawing on STS and CSCW theory, we position fair AI research as a matter of 'organizational alignment': what makes research 'doable' is the successful alignment of three levels of work organization (the social world, the laboratory, and the experiment). Based on qualitative interviews with CS researchers, we analyze the tasks, resources, and actors required for doable research in the case of fair AI. We find that CS researchers engage with SOI research to some extent, but organizational conditions, articulation work, and ambiguities of the social world constrain the doability of SOI research for them. Based on our findings, we identify and discuss problems for aligning CS and SOI as fair AI continues to evolve.

Utilization of Artificial Intelligence in Strengthening the Pancasila Student Profile Project Integrated with STEM

As the essence of education, the curriculum will persistently undergo changes and renewal to align with societal needs and the ever-expanding global challenges. The integration of STEM and the Pancasila Student Profile Strengthening Project is essential in the context of education in Indonesia. By utilizing STEM, educators can contextually and relevantly teach Pancasila values, enabling students to comprehend scientific and technological concepts and incorporate these noble values into their daily lives. However, STEM learning in schools often faces challenges, such as limited resources, less innovative methods, and students' difficulties understanding abstract concepts. Technological advances have brought significant changes in various aspects of life in recent years. Artificial intelligence extends beyond computer science and informatics, permeating multiple disciplines. Educators can utilize the introduction of artificial intelligence (AI) in the education sector as a tool to enhance learning. AI is designed to process cognitive modeling of human thinking related to how a machine can record information, imitate, and modify automatically. Therefore, this study aims to investigate the integration of AI in P5 with STEM. We conducted this research at SMP Negeri 1 Purwosari using a qualitative approach. The research results demonstrate the use of AI in the integrated STEM P5 activities, beginning with activity planning, implementation, and evaluation. AI guides activity planning, integrates directly into technology, and functions as an automated assessment tool, delivering prompt and precise feedback. Therefore, overall, AI has outstanding potential to help improve the effectiveness of the learning process and introduce students to technology that will play an essential role in their future.

Cracking the code: Linking good modeling and coding practices for new ecological modelers

Good modeling practices are essential for producing reliable and reproducible ecological models. Inherent to good modeling practices are fundamental coding and documentation skills, which not only implement the desired modeling capabilities but also clearly outline the goals, methods, and components of a model that are necessary to reproduce the desired results. One of the largest challenges for new ecological modelers can be implementing a model into computer code. In fact, coding represents a significant barrier for entry into ecological modeling, since most ecologists have not had formal training in computer science or software development. While software packages do exist that facilitate model development, we have observed that newer modelers still struggle with developing good coding practice throughout the modeling process. During a series of agent-based modeling short-courses and full semester graduate courses, both taught in NetLogo, we identified some common challenges encountered by graduate students and environmental professionals as they learn to code an ecological model, many for the first time. We were able to categorize and provide examples of the main challenges and obstacles, which fell into three main groups that follow the steps of good modeling practice: problem scoping and conceptualization, formulation, and evaluation. We then provide guidance on how to overcome these obstacles while developing good coding and modeling practices that will result in more scientifically defensible models.