Mustafa Akpinar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mustafa Akpinar has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Kevser Ovaz Akpinar
Department of Computer Engineering, Sakarya University, Sakarya, Turkey
8 shared publications Nejat Yumusak
Department of Computer Engineering, Sakarya University, Sakarya, Turkey
8 shared publicationsM. Fatih Adak
4 shared publications- Muhammed Fatih Adak
Department of Computer Engineering, Sakarya University, Sakarya, Trkiye
4 shared publications - Usman Khan Durrani
Faculty of Computer and Information Sciences, Higher Colleges of Technology, Abu Dhabi, United Arab Emirates
4 shared publications - Asif Malik
Higher Colleges of Technology,Faculty of Computer and Information Science,Abu Dhabi,UAE
3 shared publications
Latest Publications
- Open Access
- 23 September 2026
- Published by Elsevier in Smart Energy
- Vol. 24
Seasonal electricity load forecasting using metaheuristic-optimized five-parameter sigmoid regression
- 23 September 2026
- Published by Elsevier in Smart Energy
- Vol. 24
Open AccessSeasonal electricity load forecasting using metaheuristic-optimized five-parameter sigmoid regression
- Open Access
- 16 September 2026
- Published by MDPI AG in Encyclopedia
- Vol. 6 (9) , 204
Integrating Problem-Based Learning, Gamification, and the ARCS Motivation Framework: An Integrative Review of Educational Practice
Recent educational research has increasingly examined the interaction between three complementary instructional approaches: Problem-Based Learning (PBL), gamification, and Keller’s ARCS model of motivation. Rather than attempting a comprehensive review of each framework independently, this paper presents a focused integrative review of empirical studies that explicitly examine their combined application. Thirty rigorously selected studies published between 2018 and 2026 were synthesised to examine how these approaches have been operationalised across diverse educational settings and what evidence exists regarding their collective impact on learner motivation, engagement, and educational outcomes. The corpus includes both studies that explicitly integrate all three frameworks and studies that examine meaningful combinations of two of the three; only a minority of the included studies implement all three simultaneously, a distinction maintained throughout the review. Across the reviewed literature, integrated implementations were consistently associated with positive outcomes; individual studies reported effect sizes ranging from Cohen’s d = 0.8 to 1.2, particularly where authentic problem-solving, carefully aligned game mechanics and systematic motivational design were implemented together. Because these estimates are drawn from heterogeneous samples, interventions, and outcome measures rather than a formal meta-analysis, they should be read as indicative of the range reported across studies rather than as a precise estimate of a single common effect. At the same time, the review identifies important limitations within the existing evidence base, including methodological heterogeneity, relatively small and context-specific samples, inconsistent outcome measures, and limited longitudinal evaluation. These findings suggest that although the integrated PBL–gamification–ARCS approach offers considerable promise, stronger comparative and long-term empirical studies remain necessary before broad generalisations can be made. By deliberately concentrating on studies situated at the intersection of these three frameworks, this review provides a coherent synthesis of current evidence while identifying priorities for future research and instructional practice.
- 16 September 2026
- Published by MDPI AG in Encyclopedia
- Vol. 6 (9) , 204
Open AccessIntegrating Problem-Based Learning, Gamification, and the ARCS Motivation Framework: An Integrative Review of Educational Practice
Recent educational research has increasingly examined the interaction between three complementary instructional approaches: Problem-Based Learning (PBL), gamification, and Keller’s ARCS model of motivation. Rather than attempting a comprehensive review of each framework independently, this paper presents a focused integrative review of empirical studies that explicitly examine their combined application. Thirty rigorously selected studies published between 2018 and 2026 were synthesised to examine how these approaches have been operationalised across diverse educational settings and what evidence exists regarding their collective impact on learner motivation, engagement, and educational outcomes. The corpus includes both studies that explicitly integrate all three frameworks and studies that examine meaningful combinations of two of the three; only a minority of the included studies implement all three simultaneously, a distinction maintained throughout the review. Across the reviewed literature, integrated implementations were consistently associated with positive outcomes; individual studies reported effect sizes ranging from Cohen’s d = 0.8 to 1.2, particularly where authentic problem-solving, carefully aligned game mechanics and systematic motivational design were implemented together. Because these estimates are drawn from heterogeneous samples, interventions, and outcome measures rather than a formal meta-analysis, they should be read as indicative of the range reported across studies rather than as a precise estimate of a single common effect. At the same time, the review identifies important limitations within the existing evidence base, including methodological heterogeneity, relatively small and context-specific samples, inconsistent outcome measures, and limited longitudinal evaluation. These findings suggest that although the integrated PBL–gamification–ARCS approach offers considerable promise, stronger comparative and long-term empirical studies remain necessary before broad generalisations can be made. By deliberately concentrating on studies situated at the intersection of these three frameworks, this review provides a coherent synthesis of current evidence while identifying priorities for future research and instructional practice.
- Open Access
- 29 December 2025
- Published by Sakarya University Journal of Computer and Information Sciences in Sakarya University Journal of Computer and Information Sciences
- Vol. 8 (4) , 688-700
Network Traffic Factors Detection and Prediction Using Artificial Neural Networks
Rising technology generates an increasing data flow on the internet by the day. Specific security systems are crucial for managing this growing data traffic. One such security system is the firewall used in Turkey Maritime Enterprises Inc. (TME). All TME internet traffic is controlled by a security firewall that operates within existing rules and regulations. The security firewall produces output based on traffic categorized as “allowed” or “blocked.” This study collected log records from the firewall on five different days to create datasets. Twenty-six variables were extracted from the firewall logs, excluding the output. The study aimed to identify the most significant parameters impacting the output using linear regression (LR) and principal component analysis (PCA). The analysis identified mutually influential log variables affecting the output using two methods. After, the initial dataset with 26 variables and a reduced dataset with six variables were used to predict output using the artificial neural network (ANN) for five datasets. The prediction accuracy and precision ranges were between 85% and 88% and 92% and 98%, respectively. The F1-score showed results between 89% and 92% in addition to accuracy and precision. ML and PCA methods successfully identified crucial variables for estimating output and reduced the number of variables from 26 to 5. Moreover, it was noted that the ANN could accurately determine whether firewall traffic would be blocked or allowed based on the reduced datasets. Reducing the feature space from 26 to 6 variables identified via MLR+PCA improved ANN performance across hours, indicating that compact, interpretable inputs can support accurate firewall-traffic prediction.
- 29 December 2025
- Published by Sakarya University Journal of Computer and Information Sciences in Sakarya University Journal of Computer and Information Sciences
- Vol. 8 (4) , 688-700
Open AccessNetwork Traffic Factors Detection and Prediction Using Artificial Neural Networks
Rising technology generates an increasing data flow on the internet by the day. Specific security systems are crucial for managing this growing data traffic. One such security system is the firewall used in Turkey Maritime Enterprises Inc. (TME). All TME internet traffic is controlled by a security firewall that operates within existing rules and regulations. The security firewall produces output based on traffic categorized as “allowed” or “blocked.” This study collected log records from the firewall on five different days to create datasets. Twenty-six variables were extracted from the firewall logs, excluding the output. The study aimed to identify the most significant parameters impacting the output using linear regression (LR) and principal component analysis (PCA). The analysis identified mutually influential log variables affecting the output using two methods. After, the initial dataset with 26 variables and a reduced dataset with six variables were used to predict output using the artificial neural network (ANN) for five datasets. The prediction accuracy and precision ranges were between 85% and 88% and 92% and 98%, respectively. The F1-score showed results between 89% and 92% in addition to accuracy and precision. ML and PCA methods successfully identified crucial variables for estimating output and reduced the number of variables from 26 to 5. Moreover, it was noted that the ANN could accurately determine whether firewall traffic would be blocked or allowed based on the reduced datasets. Reducing the feature space from 26 to 6 variables identified via MLR+PCA improved ANN performance across hours, indicating that compact, interpretable inputs can support accurate firewall-traffic prediction.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Applications of Home Digital Twins in the Metaverse: Energy, Safety, Healthcare, and Personalized Living
Home Digital Twins (HDTs) are live computational representations of dwellings that stay synchronized with the physical home. Embedded in the Metaverse—persistent, multi-user AR/VR environments—HDTs supply trustworthy state and safe actuation, while immersion adds co-presence, spatial reasoning, and intuitive control. We (i) motivate immersive, AI-enabled HDTs; (ii) present a four-layer reference architecture (Edge/Home, Twin Core, Services, Immersive Clients) with explicit Metaverse touchpoints (session management, avatar authority, twin↔scene-graph adapters, safety interlocks); and (iii) survey applications across energy, safety & security, healthcare & well-being, and comfort/personalization. Each vignette maps to immersive affordances and design constraints (e.g., motion-to-photon and state-coherence budgets, explainable proposals, test-in-twin before actuation). We outline cross-cutting challenges—privacy governance, semantic interoperability, and real-time performance at consumer edges—and propose an evaluation agenda with measurable outcomes (kWh saved, hazard lead-time, adherence, comfort). By linking architecture to interaction patterns, we position HDTs as the substrate that gives residential Metaverse experiences real-world consequences while preserving safety, agency, and equity.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Applications of Home Digital Twins in the Metaverse: Energy, Safety, Healthcare, and Personalized Living
Home Digital Twins (HDTs) are live computational representations of dwellings that stay synchronized with the physical home. Embedded in the Metaverse—persistent, multi-user AR/VR environments—HDTs supply trustworthy state and safe actuation, while immersion adds co-presence, spatial reasoning, and intuitive control. We (i) motivate immersive, AI-enabled HDTs; (ii) present a four-layer reference architecture (Edge/Home, Twin Core, Services, Immersive Clients) with explicit Metaverse touchpoints (session management, avatar authority, twin↔scene-graph adapters, safety interlocks); and (iii) survey applications across energy, safety & security, healthcare & well-being, and comfort/personalization. Each vignette maps to immersive affordances and design constraints (e.g., motion-to-photon and state-coherence budgets, explainable proposals, test-in-twin before actuation). We outline cross-cutting challenges—privacy governance, semantic interoperability, and real-time performance at consumer edges—and propose an evaluation agenda with measurable outcomes (kWh saved, hazard lead-time, adherence, comfort). By linking architecture to interaction patterns, we position HDTs as the substrate that gives residential Metaverse experiences real-world consequences while preserving safety, agency, and equity.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Orchestrating Intelligence: Towards A Framework for AI-Augmented Software Engineering Education
This research addresses the critical gap between AI's potential and its practical integration into software engineering (SE) education. We propose a novel educational framework using project-based learning to embed AI tools across the SE lifecycle. Thirty capstone students participated in a workshop to automate a requirements-to-code workflow using a toolchain of AI agents and development platforms, incorporating a human-in-the-loop for validation. Motivation and learning were assessed through pre- and post-intervention surveys using the ARCS model. This study provides a practical framework for SE education, emphasizing critical AI evaluation and strategic tool use. Pending findings will offer insights into preparing a workforce for effective human-AI collaboration, with future work focusing on data analysis and scaling the intervention.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Orchestrating Intelligence: Towards A Framework for AI-Augmented Software Engineering Education
This research addresses the critical gap between AI's potential and its practical integration into software engineering (SE) education. We propose a novel educational framework using project-based learning to embed AI tools across the SE lifecycle. Thirty capstone students participated in a workshop to automate a requirements-to-code workflow using a toolchain of AI agents and development platforms, incorporating a human-in-the-loop for validation. Motivation and learning were assessed through pre- and post-intervention surveys using the ARCS model. This study provides a practical framework for SE education, emphasizing critical AI evaluation and strategic tool use. Pending findings will offer insights into preparing a workforce for effective human-AI collaboration, with future work focusing on data analysis and scaling the intervention.
- Open Access
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 171185-171204
A Decade of Progress: A Systematic Literature Review on the Integration of AI in Software Engineering Phases and Activities (2013-2023)
The synergy between software engineering (SE) and artificial intelligence (AI) catalyzes software development, as numerous recent studies illustrate an intensified intersection between these domains. This systematic literature review examines the integration of AI techniques or methodologies across SE phases and related activities spanning from 2013 to 2023, resulting in the selection of 110 research papers. Investigating the profound influence of AI techniques, including machine learning, deep learning, natural language processing, optimization algorithms, and expert systems, across various SE phases—such as planning, requirement engineering, design, development, testing, deployment, and maintenance—is the focal point of this study. Notably, the extensive adoption of machine learning and deep learning algorithms in the development and testing phases has enhanced software quality through defect prediction, code recommendation, and vulnerability detection initiatives. Furthermore, natural language processing’s role in automating requirements classification and sentiment analysis has streamlined SE practices. Optimization algorithms have also demonstrated efficacy in refining SE activities such as feature location and software repair action predictions, augmenting precision and efficiency in maintenance endeavors. Prospective research emphasizes the imperative of interpretable AI models and the exploration of novel AI paradigms, including explainable AI and reinforcement learning, to promote ethical and efficient software development practices. This paper fills the gap identified in AI techniques dedicated to improving SE phases. The review concludes that AI in SE is revolutionizing the discipline, enhancing software quality, efficiency, and innovation, with ongoing efforts targeting the mitigation of identified limitations and the augmentation of AI capabilities for intelligent and dependable SE.
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 171185-171204
Open AccessA Decade of Progress: A Systematic Literature Review on the Integration of AI in Software Engineering Phases and Activities (2013-2023)
The synergy between software engineering (SE) and artificial intelligence (AI) catalyzes software development, as numerous recent studies illustrate an intensified intersection between these domains. This systematic literature review examines the integration of AI techniques or methodologies across SE phases and related activities spanning from 2013 to 2023, resulting in the selection of 110 research papers. Investigating the profound influence of AI techniques, including machine learning, deep learning, natural language processing, optimization algorithms, and expert systems, across various SE phases—such as planning, requirement engineering, design, development, testing, deployment, and maintenance—is the focal point of this study. Notably, the extensive adoption of machine learning and deep learning algorithms in the development and testing phases has enhanced software quality through defect prediction, code recommendation, and vulnerability detection initiatives. Furthermore, natural language processing’s role in automating requirements classification and sentiment analysis has streamlined SE practices. Optimization algorithms have also demonstrated efficacy in refining SE activities such as feature location and software repair action predictions, augmenting precision and efficiency in maintenance endeavors. Prospective research emphasizes the imperative of interpretable AI models and the exploration of novel AI paradigms, including explainable AI and reinforcement learning, to promote ethical and efficient software development practices. This paper fills the gap identified in AI techniques dedicated to improving SE phases. The review concludes that AI in SE is revolutionizing the discipline, enhancing software quality, efficiency, and innovation, with ongoing efforts targeting the mitigation of identified limitations and the augmentation of AI capabilities for intelligent and dependable SE.
- 24 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 169-172
An Analysis of Cybersecurity Mandates in the Context of Digital Reliance within Hybrid IT Models
The fourth industrial revolution and digital transformation drive governments and companies to embrace technology for efficiency. Platforms, devices, and data sharing with cloud providers, APIs, and intermediaries fuel this growth. COVID-19 further accelerated the shift to remote and hybrid work, amplifying the need for digital transformation. However, this reliance on complex technologies like AI creates new security challenges for businesses. Remote and hybrid environments introduce unforeseen complexities. This paper explores how to mitigate cyber vulnerabilities within this digital dependency, minimizing attacks and losses. We propose solutions for corporate cybersecurity and recommendations to strengthen defenses. By addressing these challenges, organizations can navigate the complexities of a hybrid IT landscape and remote workforce.
- 24 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 169-172
An Analysis of Cybersecurity Mandates in the Context of Digital Reliance within Hybrid IT Models
The fourth industrial revolution and digital transformation drive governments and companies to embrace technology for efficiency. Platforms, devices, and data sharing with cloud providers, APIs, and intermediaries fuel this growth. COVID-19 further accelerated the shift to remote and hybrid work, amplifying the need for digital transformation. However, this reliance on complex technologies like AI creates new security challenges for businesses. Remote and hybrid environments introduce unforeseen complexities. This paper explores how to mitigate cyber vulnerabilities within this digital dependency, minimizing attacks and losses. We propose solutions for corporate cybersecurity and recommendations to strengthen defenses. By addressing these challenges, organizations can navigate the complexities of a hybrid IT landscape and remote workforce.
- Open Access
- 15 March 2024
- Published by Elsevier in Engineering Science and Technology, an International Journal
- Vol. 52
The detection of unaccounted natural gas consumption: A neural networks and subscriber-based solution
- 15 March 2024
- Published by Elsevier in Engineering Science and Technology, an International Journal
- Vol. 52
Open AccessThe detection of unaccounted natural gas consumption: A neural networks and subscriber-based solution
- Open Access
- 15 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 134809-134821
Prediction of Mortality in Inpatients of Covid-19 Using Statistical and Artificial Intelligence Approaches: A Case Study in Sakarya
The virus SARS-Cov-2 speared rapidly as pandemic disease and cause serious respiratory distress and death. The parameters such as D-dimer, fibrinogen, C-reactive protein, and serum ferritin become higher indicators for acute inflammation. It is vital to understand whether the disease will progress severely or result in death by using laboratory findings. In this way, a doctor concentrating on the patient can make faster and more accurate decisions about the prognosis of the disease and survey patients using artificial intelligence and statistical methods. Therefore, this study aims to determine the attributes associated with deteriorating prognosis by analyzing the laboratory findings of patients who are followed in Sakarya U. Training and Res. Hospital with Covid-19 by using artificial intelligence and statistical methods. More precisely the general aim of this study is to leverage artificial intelligence and statistical methods to identify specific laboratory markers associated with Covid-19 patient deterioration and mortality, enabling more accurate prognosis and clinical decision-making. Our results demonstrated that high fibrinogen, troponin, albumin, d-dimer, ferritin, intubation, and uric acid level were directly related to mortality in Covid-19 patients. Additionally, the training-based models give higher accuracy results than statistical methods. Thus, these laboratory findings of Covid-19 patients and the training-based models may potentially provide doctors make easier and more accurate decisions about mortality and survey predicting.
- 15 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 134809-134821
Open AccessPrediction of Mortality in Inpatients of Covid-19 Using Statistical and Artificial Intelligence Approaches: A Case Study in Sakarya
The virus SARS-Cov-2 speared rapidly as pandemic disease and cause serious respiratory distress and death. The parameters such as D-dimer, fibrinogen, C-reactive protein, and serum ferritin become higher indicators for acute inflammation. It is vital to understand whether the disease will progress severely or result in death by using laboratory findings. In this way, a doctor concentrating on the patient can make faster and more accurate decisions about the prognosis of the disease and survey patients using artificial intelligence and statistical methods. Therefore, this study aims to determine the attributes associated with deteriorating prognosis by analyzing the laboratory findings of patients who are followed in Sakarya U. Training and Res. Hospital with Covid-19 by using artificial intelligence and statistical methods. More precisely the general aim of this study is to leverage artificial intelligence and statistical methods to identify specific laboratory markers associated with Covid-19 patient deterioration and mortality, enabling more accurate prognosis and clinical decision-making. Our results demonstrated that high fibrinogen, troponin, albumin, d-dimer, ferritin, intubation, and uric acid level were directly related to mortality in Covid-19 patients. Additionally, the training-based models give higher accuracy results than statistical methods. Thus, these laboratory findings of Covid-19 patients and the training-based models may potentially provide doctors make easier and more accurate decisions about mortality and survey predicting.
- Open Access
Solving the laminar boundary layer problem in heat transfer with heuristic optimization techniques