Claim Missing Document
Check
Articles

Found 9 Documents
Search

An Integrated Framework for Controllers Placement and Security in Software-Defined Networks Ecosystem Sebopelo, Rodney; Isong, Bassey
Journal of Information System and Informatics Vol 6 No 1 (2024): March
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i1.682

Abstract

In the evolving landscape of Software-Defined Networking (SDN), the strategic placement of controllers poses a critical challenge that necessitate a precise balance between network performance and security. This paper presents an integrated framework for enhancing security and performance in SDN by combining controller placement and intrusion detection systems (IDS). Unlike existing solutions which were implemented disjointedly, we propose a holistic approach that leverages the proximity of controllers to network traffic for real-time threat detection, rapid response, and mitigation of security attacks. We employ an advanced clustering model for optimal controller placement, reducing costs and latency while ensuring reliability and balanced loads. In addition, we utilize k-nearest neighbour (KNN) for efficient anomaly detection in our IDS for improved network security. Experimental results confirm the framework’s effectiveness in strengthening SDN security and resilience. The enhanced-DBSCAN-based CPP model significantly minimized the cost, and latency, and ensured continuous operation in dynamic SDN environments while the KNN-based IDS shows effectiveness in improving threat detection capabilities, achieving high detection accuracy of 100% on the LAN dataset, outperforming other machine learning models such as Random Forest and Naïve Bayes. The indication is that strategic controller deployment, in conjunction with IDS, can significantly bolster threat detection, response times, and the overall security stance of the SDN environment.
PyLe: An Interactive Tool for Improving Python Syntax Mastery in Non-Computing Students Mbiada, Alain Kabo; Isong, Bassey; Lugayizi, Francis
Journal of Information System and Informatics Vol 6 No 2 (2024): June
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i2.751

Abstract

The learning and mastering of programming language syntax pose a significant challenge for non-computing students. Most teaching approaches and existing educational tools often fail to address this issue. Therefore, this paper introduces an interactive learning environment called PyLe, specifically designed for introductory programming in Python programming courses. We evaluated the effectiveness of PyLe on first-year students at North-West University in South Africa and the University of Yaoundé 1, Cameroon. Firstly, the study conducts an experiment to assess the effect of PyLe on the time taken to solve a problem and the response quality. Secondly, PyLe’s usability and its instructional value were evaluated by the students and the instructors, respectively. The results from post-test method and a quantitative survey indicate that PyLe improves students’ ability to learn and master program syntax and has a high usability rate. Moreover, feedback from students and teachers affirms PyLe’s potential to address programming syntax challenges for non-computing students. However, the analyses revealed no real relationship between the time taken to complete a task in PyLe and the quality of the solution. This study contributes to improving the teaching and learning of computer programming, which has been considered difficult for both computing and non-computing students.
A Balancing Energy Efficiency and Security in CR-LoRaWAN Ecosystems Ntshabele, Koketso; Isong, Bassey
Journal of Information System and Informatics Vol 6 No 4 (2024): December
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i4.886

Abstract

Cognitive Radio-enabled Long Range Wide Area Networks (CR-LoRaWAN) plays an important role in IoT applications. However, due to the limitations of devices and dynamic scheduling mechanisms of the channels, there is still a challenge to balance energy efficiency against security. This paper proposes two developed algorithms that address these challenges: Algo A and Algo B. Algo A ensures key security by mitigating nonce generation vulnerabilities through the replacement of insecure random numbers with prime numbers. Algo B develops this basis by further improving energy efficiency through optimization in session key generation and device management, adding security to it. Both the algorithms incorporate prime numbers in their session key generation that are verified by the Rabin-Miller test and the Sieve of Eratosthenes, with incorporated solar energy harvesting to give a longer life to such devices. Cognitive radio technology is integrated into it for dynamic and intelligent channel selection. Extensive simulations demonstrate that Algo A is much better at handling data with key security, while Algo B outperforms Algo A on energy consumption reduction by 20% and enhancement of overall network security by 15%. These results reveal that Algo B has a better trade-off between security and energy efficiency; hence, Algo B is more suitable for practical deployment. The work further enhances the sustainability and reliability of CR-LoRaWAN networks, especially in resource-constrained environments.
Misinformation Detection: A Review for High and Low-Resource Languages Rananga, Seani; Isong, Bassey; Modupe, Abiodun; Marivate, Vukosi
Journal of Information System and Informatics Vol 6 No 4 (2024): December
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v6i4.931

Abstract

The rapid spread of misinformation on platforms like Twitter, and Facebook, and in news headlines highlights the urgent need for effective ways to detect it. Currently, researchers are increasingly using machine learning (ML) and deep learning (DL) techniques to tackle misinformation detection (MID) because of their proven success. However, this task is still challenging due to the complexity of deceptive language, digital editing tools, and the lack of reliable linguistic resources for non-English languages. This paper provides a comprehensive analysis of relevant research, providing insights into advanced techniques for MID. It covers dataset assessments, the importance of using multiple forms of data (multimodality), and different language representations. By applying the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) methodology, the study identified and analyzed literature from 2019 to 2024 across five databases: Google Scholar, Springer, Elsevier, ACM, and IEEE Xplore. The study selected thirty-one papers and examined the effectiveness of various ML and DL approaches with a focal point on performance metrics, datasets, and false or misleading information detection challenges. The findings indicate that most current MID models are heavily dependent on DL techniques, with approximately 81% of studies preferring these over traditional ML methods. In addition, most studies are text-based, with much less attention given to audio, speech, images, and videos. The most effective models are mainly designed for high-resource languages, with English datasets being the most used (67%), followed by Arabic (14%), Chinese (11%), and others. Less than 10% of the studies focus on low-resource languages (LRLs). Therefore, the study highlighted the need for robust datasets and interpretable, scalable MID models for LRLs. It emphasizes the critical need to prioritize and advance MID research for LRLs across all data types, including text, audio, speech, images, videos, and multimodal approaches. This study aims to support ongoing efforts to combat misinformation and promote a more informed understanding of under-resourced African languages.
A Comparative Study of Computer Programming Challenges of Computing and Non-Computing First-Year Students Mbiada, Alain; Isong, Bassey; Lugayizi, Francis
The Indonesian Journal of Computer Science Vol. 12 No. 4 (2023): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i4.3330

Abstract

The learning of computer programming comes with unique difficulties that vary among students depending on their backgrounds, learning methods, and objectives. This paper investigates the programming challenges first-year students from non-computing at the North-West University, South Africa, and computing backgrounds at the University of Dschang, Cameroon face. A questionnaire-based data collection method is utilized and categorizes participants based on their gender, age, fields of study, prior experiences in mathematics, statistics, English, and programming languages, lab use/access, learning strategies, and material preferences. The aim is to identify and analyze the student's understanding of the basic programming concepts and the specific challenges met during introductory programming modules. Analysis of the collected data shows that while a considerable percentage of non-computing students have prior experience in mathematics and English, they lack familiarity with programming. Equally, while most computing students are proficient in spoken English, they face significant challenges in programming, mathematics, and written English. Notable difficulties are experienced in grasping concepts like recursion, arrays, error handling, and function/procedure methods. Moreover, a comparative study reveals that both groups of students encounter similar challenges, however, non-computing students’ difficulties are more than their computing counterparts. This paper, therefore, suggests designing teaching methods and learning materials to specifically meet the needs of non-computer science students, and enhance their understanding and proficiency in computer programming.
A Systematic Review of Challenges in Teaching and Learning Computer Programming Modules Elegbeleye, Femi; Isong, Bassey
The Indonesian Journal of Computer Science Vol. 14 No. 1 (2025): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i1.4592

Abstract

Computer programming has become an essential skill that is needed across many disciplines as it helps foster innovations like machine learning and artificial intelligence. Regardless of its significance, many students studying computer science and other disciplines often grapple with grasping basic programming language concepts, such as understanding logic, syntax, data structure, and data types. These challenges usually lead to very high rates of failure and loss of motivation among the students, therefore producing poor academic outcomes. This study investigates the unique programming challenges the students face, identifying some contributing factors and examining which challenges have more impact on the student. Moreover, it explores whether computing or non-computing students are more affected by these obstacles and reviews interventions to improve learning outcomes. The findings suggest best practices to enhance motivation and engagement in programming education, including introducing adaptive learning tools into the learning management systems, game-based applications, and AI-driven support systems personalized to meet each student's needs.
A Comprehensive Review of Energy Optimization Techniques in the Internet of Things Isong, Bassey; Moeti, Kedibone
Journal of Information System and Informatics Vol 7 No 2 (2025): June
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i2.1110

Abstract

The advancement of energy efficiency in the Internet of Things (IoT) and wireless sensor networks (WSNs) is an important research effort, given their rapid application expansion across smart cities and homes, healthcare, agriculture, and industrial automation. This paper conducted a comprehensive survey of existing innovative solutions to challenges focusing on hardware-based, software-driven, and network optimization approaches, alongside artificial intelligence-driven and demand-side energy management, and security-enhanced frameworks. 82 peer-reviewed journal articles and conference papers published between 2021 and 2025 were reviewed, using sources such as IEEE Xplore, ScienceDirect, Web of Science, SpringerLink, and Google Scholar. It identifies significant developments in energy-efficient techniques, including ultra-low-power hardware, adaptive scheduling, bio-inspired clustering, and energy harvesting. Others include intelligent optimization methods(e.g. machine, quantum-inspired heuristics), and blockchain-enhanced security. A structured evaluation process is implemented, following PRISMA guidelines, categorizing studies, and synthesizing findings to highlight technological progress, challenges, and future research directions. The findings show a growing trend towards integrated, multi-objective routing and cross-layer energy optimizations, with significant progress in minimizing energy use, network lifetime and improving security mechanisms. However, challenges like scalability, computational overhead and real-world deployment issues persist. Our study offers valuable insights for sustainable energy management in IoT and WSNs and helps guide future development toward more resilient, adaptable and sustainable energy-aware systems.
Ensemble Learning for Software Defect Prediction: Performance, Practicality and Future Directions Isong, Bassey; Igo, Ekoro
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Universitas Bina Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1171

Abstract

Ensemble learning is a leading approach in software defect prediction (SDP), offering improved predictive performance on imbalanced and high-dimensional datasets. Despite growing research interest, persistent gaps remain in model interpretability, generalizability, and reproducibility, limiting its practical adoption. This paper presents a comprehensive analysis of 56 peer-reviewed studies published between 2020 and 2025, spanning both journal and conference venues. Findings show that ensemble methods, especially when combined with sampling, feature selection, or optimisation, consistently outperform single classifiers on important metrics such as F1-score, area under the curve, and Matthew correlation coefficient. Nonetheless, few studies incorporate explainability frameworks, effort-aware evaluation, or cross-project validation. Additionally, most models are static, rely on within-project testing, and depend on legacy datasets such as PROMISE and NASA, which limit external validity. Building on this synthesis, the review highlights future research priorities, including interpretable ensemble architectures, adaptive modelling, dynamic imbalance handling, semantic feature integration, and real-time prediction. Standardised benchmarks, transparent, scalable designs are recommended to bridge the gap between experimental performance and deployment-ready SDP solutions.
Empirical Analysis of Deep Learning Models for Real-time Face Detection on Resource-constrained Devices Isong, Bassey; Ndouvhada, Sedzani; Kgote, Otshepeng
IT Journal Research and Development Vol. 10 No. 2 (2025)
Publisher : UIR PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/itjrd.2025.22402

Abstract

Face detection (FD) technology enables machines to identify human faces, playing a critical role in mobile device security and user interaction. However, achieving an optimal balance between speed and accuracy in FD algorithms remains a challenge, particularly for real-time applications on resource-limited devices. Factors such as variations in pose, lighting conditions, occlusions, dataset diversity, and hardware constraints often hinder effective deployment. This study presents a comprehensive empirical evaluation of deep learning-based object detection techniques, specifically YOLOv8, SSD, and Faster RCNN, to assess their effectiveness in addressing real-world scalability and performance demands. These models were trained on diverse datasets and evaluated using key performance metrics, including accuracy, precision, recall, and frames per second (FPS). YOLOv8 achieved superior performance, achieving 42.32 FPS with an accuracy of 86%, surpassing two-stage models in real-time processing speed while maintaining comparable accuracy. The findings underscore the importance of dataset quality and diversity in enhancing model performance and positioning YOLOv8 as an effective solution for balancing speed and accuracy on the COCO dataset. The study envisions a future exploration of hybrid models that integrate YOLOv8's efficiency with Faster RCNN's precision to develop more robust FD solutions tailored to real-world challenges.