Article Per Year (5 Year)
p-Index From 2021 - 2026
1.204
P-Index
This Author published in this journals
All Journal Journal of Digital Learning and Distance Education Radinka Journal of Science and Systematic Literature Review Vokasi UNESA Bulletin of Engineering, Technology and Applied Science
Oise, Godfrey
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Decision Sciences, Operations Research & Management Engineering Languange, Linguistic, Communication & Media Mathematics Mechanical Engineering Public Health Social Sciences Transportation Other

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
Evaluating the Impact of Blended Learning Models on Higher Education Outcomes: A Multidimensional Analysis Oise, Godfrey; Ejenarhome Otega Prosper; Oyedotun Samuel ABIODUN; Onwuzo Chioma JULIA
JOURNAL OF DIGITAL LEARNING AND DISTANCE EDUCATION Vol. 4 No. 2 (2025): Journal of Digital Learning and Distance Education (JDLDE)
Publisher : RADINKA JAYA UTAMA PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56778/jdlde.v4i2.535

Abstract

Blended learning (BL), which combines online digital tools with traditional face-to-face instruction, has gained increasing prominence in higher education, particularly since the COVID-19 pandemic. This study conducts a systematic review of 50 peer-reviewed empirical studies (2020–2024) to evaluate the impact of BL on academic performance, student engagement, and learner satisfaction. The results reveal that BL enhances learning outcomes when supported by responsive instruction, flexible access, and structured digital platforms, particularly in STEM disciplines. However, the effectiveness of BL is highly context-dependent. Disciplines relying on interpretive and dialogic learning, as well as under-resourced institutions, often experience minimal or negative effects, especially in asynchronous-heavy models. The review also identifies a decline in student engagement beyond the fourth week in flex-only formats, suggesting that synchronous interaction is critical for sustained motivation and retention. Key barriers to effective implementation include faculty workload, digital inequality, and institutional inertia. Addressing these challenges requires structured faculty development, investment in accessible technology, and alignment with discipline-specific pedagogy. This review affirms the pedagogical value of BL but emphasizes the need for inclusive, adaptive, and strategically supported approaches to ensure its sustainable integration across diverse educational settings.  
The Integration of Internet of Things (IoT) in Smart Classrooms: Opportunities, Challenges, and Future Trajectories Oise, Godfrey; Cyprian C. KONYEHA; COMFORT, Olayinka Tosin; Konyeha, Susan; Emmanueld, Chukwuma Ozobialu
JOURNAL OF DIGITAL LEARNING AND DISTANCE EDUCATION Vol. 4 No. 3 (2025): Journal of Digital Learning and Distance Education (JDLDE)
Publisher : RADINKA JAYA UTAMA PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56778/jdlde.v4i3.537

Abstract

The integration of the Internet of Things (IoT) into educational environments signifies a transformative shift towards smart classrooms, enabling real-time data-driven instruction, environmental optimization, and personalized learning experiences. This study explores the opportunities, challenges, and future directions of IoT deployment in academic settings through a mixed-methods approach that combines quantitative analysis, qualitative interviews, and IoT-edge data assessment. Survey responses from 150 educators and interviews with 20 key stakeholders revealed significant adoption rates and pedagogical benefits, including enhanced engagement and individualized feedback. However, critical challenges such as data privacy, cybersecurity risks, limited teacher training, and infrastructure disparities hinder widespread implementation. A machine learning framework utilizing Random Forest classification was applied to a custom IoT-edge dataset, uncovering correlations between environmental variables and student behavior. High temperatures negatively affected classroom occupancy, while increased light intensity correlated with heightened engagement. Model evaluation yielded strong performance metrics, including an accuracy of 95% and an AUC of 0.99, highlighting the predictive power of features like learning outcomes and engagement scores. The findings emphasize the dual importance of technical readiness and pedagogical adaptation, advocating for policy support, ethical data governance, and teacher capacity-building to fully realize IoT’s potential in shaping adaptive, equitable, and intelligent learning ecosystems.
Revisiting Parasitic Computing: Ethical and Technical Dimensions in Resource Optimization Oise, Godfrey; Nwabuokei, Clement; IGBUNU, Richard; EJENARHOME, Prosper
Vokasi Unesa Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.38786

Abstract

Parasitic computing is a provocative concept enabling one system to offload computational tasks to remote hosts without explicit consent by exploiting communication protocols such as TCP/IP. While initially demonstrated as a conceptual hack, its implications for distributed computing, ethics, and resource optimization remain underexplored in modern contexts. This study revisits the original parasitic computing model, focusing on operational feasibility, technical efficiency, and ethical boundaries. We implement a Python-based simulation that encodes logical operations (AND, OR) into TCP packets by manipulating checksum fields—a core mechanism of the parasitic approach. We conducted over 6,000 packet transmissions across various network latency conditions using loopback and LAN environments to measure success rates, response times, and failure thresholds. Results show that logical operations can succeed under low-latency conditions with over 94% accuracy, but performance degrades sharply under higher round-trip times, dropping below 70%. These findings suggest parasitic computing may be technically viable within tightly controlled environments but face significant limitations in broader network applications. The researchers critically examine ethical considerations, emphasizing the risks of unauthorized computation, resource exploitation, and potential security breaches. This study contributes a reproducible methodology and empirical data, offering a renewed perspective on parasitic computing’s technical boundaries and future potential. It further calls for responsible experimentation and proposes hybrid models combining parasitic techniques with legitimate distributed computing frameworks and new safeguards to detect and mitigate unintended abuses. The paper proposes directions for improving protocol resilience and computational fairness in open networks.
Enhancing Indoor Positioning Accuracy with Ant Colony Optimization and Dual Clustering Oise, Godfrey; Nwabuokei, Onyemaechi Clement; Ozobialu, chukwuma Emmanuel; Jenarhome, Otega Prosper; Atake, Onoriode Michael; Nkem Belinda, Unuigbokhai; Babalola Eyitemi , Akilo
Vokasi Unesa Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.39452

Abstract

Indoor positioning systems are crucial for public safety, healthcare, and IoT, but Wi-Fi fingerprinting faces challenges such as signal interference, multipath effects, and high computational costs. These issues reduce positioning accuracy and make real-time localization difficult.This paper introduces an Ant Colony Optimization (ACO)-based dual clustering method to enhance Wi-Fi fingerprinting accuracy and efficiency. ACO performs coarse clustering by optimizing initial data groupings, while K-means refines clusters for improved precision. The Weighted K-Nearest Neighbor (WKNN) algorithm is then applied for real-time positioning by selecting the most similar signal sub-bases.Experiments show that the proposed method achieves 100% accuracy in building classification and 91% accuracy in floor classification. For latitude and longitude prediction, Random Forest and SVC outperform XGBoost, achieving MSE values of 0.0048 (latitude) and 0.0055 (longitude). The approach also reduces computational overhead by 93.51%, improving efficiency.The study presents a robust, scalable solution for indoor positioning and introduces the Dual Clustering Wi-Fi Localization Dataset (DCWiLD) for future research. Future work will focus on dataset balancing, BLE/UWB integration, and energy optimization for IoT applications.
Intelligent Waste Management Systems: A Review of IoT, Deep Learning, and Optimization Techniques for Sustainable E-Waste and Solid Waste Handling Oise, Godfrey; Oyedotun Samuel ABIODUN; Onwuzo Chioma JULIA; Ejenarhome Otega Prosper
RADINKA JOURNAL OF SCIENCE AND SYSTEMATIC LITERATURE REVIEW Vol. 3 No. 2 (2025): Radinka Journal of Science and Systematic Literature Review
Publisher : RADINKA JAYA UTAMA PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56778/rjslr.v3i2.508

Abstract

This review addresses the urgent environmental and health issues posed by the rapid growth of electronic waste (e-waste) and municipal solid waste (MSW), highlighting the role of emerging technologies in crafting sustainable waste management solutions. It explores the integration of the Internet of Things (IoT), deep learning, and optimization algorithms in enhancing waste classification, recycling, and disposal. Key innovations include IoT-enabled smart bins for real-time monitoring, deep learning models like CNNs achieving up to 97% sorting accuracy, and optimization techniques that improve energy efficiency and scalability. The paper synthesizes findings from over 50 studies and emphasizes both technical advances and implementation challenges, such as data limitations, model interpretability, and the lack of robust policy frameworks. Future research directions include explainable AI, edge computing, and global standardization of e-waste regulations. The review is intended for researchers, developers, and policymakers working toward circular economy principles and sustainable smart city solutions.
Predicting and Preventing Academic Misconduct Using Behavioral Analytics: An Ethical Framework for Fair Detection and Human Oversight Oise, Godfrey
JOURNAL OF DIGITAL LEARNING AND DISTANCE EDUCATION Vol. 4 No. 7 (2025): Journal of Digital Learning and Distance Education (JDLDE)
Publisher : RADINKA JAYA UTAMA PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56778/jdlde.v4i7.594

Abstract

This study introduces the Ethical Behavioral Analytics Framework (EBAF), a fairness-driven and explainable artificial intelligence system designed to predict and prevent academic misconduct. The framework integrates behavioral analytics, deep learning (LSTM), and human oversight to ensure ethical transparency and accountability in academic integrity management. By combining behavioral indicators such as submission timing, editing duration, and engagement regularity with textual features, EBAF identifies deviations from normal learning behavior that may indicate misconduct. Using a dataset of student behavioral and performance data sourced from Kaggle, the model achieved an overall accuracy of 85%, effectively distinguishing between authentic and plagiarized submissions while maintaining minimal bias. The incorporation of explainable AI tools, including SHAP and LIME, provided interpretable reasoning behind predictions, allowing educators to understand and validate model decisions. A human-in-the-loop mechanism further ensured that automated outputs were reviewed contextually, promoting fairness, accountability, and trust. The findings demonstrate that ethical and explainable AI can coexist with high predictive performance, advancing the responsible application of machine learning in education. By embedding fairness auditing, transparency, and human oversight, EBAF transforms academic misconduct detection from a punitive process into a preventive and educational approach. This work contributes to both research and practice by aligning computational intelligence with ethical accountability. Future research will expand the framework across diverse academic environments, incorporating multimodal behavioral data and adaptive feedback systems to enhance fairness, interpretability, and scalability in AI-based academic integrity solutions.
Spatiotemporal Water Quality Modeling Using Deep Learning Architectures Oise, Godfrey; Ejenarhome Otega Prosper; Oyedotun Samuel ABIODUN
RADINKA JOURNAL OF SCIENCE AND SYSTEMATIC LITERATURE REVIEW Vol. 3 No. 3 (2025): Radinka Journal of Science and Systematic Literature Review
Publisher : RADINKA JAYA UTAMA PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56778/rjslr.v3i3.519

Abstract

Water quality monitoring is vital for ensuring public health, environmental sustainability, and economic resilience. Traditional monitoring techniques, while precise, often fall short due to high costs, labor intensity, and limited temporal and spatial resolution barriers that are increasingly critical amid accelerating urbanization, climate change, and pollution. This study explores the application of deep learning architectures to spatiotemporal water quality modeling, leveraging diverse datasets comprising historical records, sensor readings, and government sources. Supervised learning techniques were evaluated for predictive and classification tasks, including Support Vector Regression (SVR), Random Forests, XGBoost, and Decision Trees. SVR yielded strong regression performance for Water Quality Index (WQI) prediction with an R² of 0.9693 and low mean squared error, while XGBoost and Decision Trees demonstrated robust classification accuracy above 94%, with Decision Trees excelling in macro-averaged metrics. Unsupervised learning using DBSCAN revealed moderate clustering potential, but also emphasized the limitations of density-based approaches for noisy environmental data. Exploratory analyses offered insights into parameter distributions and interdependencies, including Kernel Density Estimation, correlation heatmaps, box plots, PCA, and t-SNE. While the study confirms the potential of AI in water quality monitoring, it also underscores challenges such as data imbalance, limited minority class precision, and the need for interpretable and scalable models. Future work should integrate explainable AI, edge computing, and hybrid domain-informed models to foster real-time, equitable, and sustainable water monitoring solutions aligned with SDG 6. This research demonstrates the promise of deep learning in transitioning water quality management from reactive to predictive paradigms.
Utilizing Deep Learning to Influence Design Decisions and Predict Future Scenarios Oise, Godfrey; Ejenarhome Otega Prospera; Oyedotun Samuel ABIODUN
RADINKA JOURNAL OF SCIENCE AND SYSTEMATIC LITERATURE REVIEW Vol. 3 No. 3 (2025): Radinka Journal of Science and Systematic Literature Review
Publisher : RADINKA JAYA UTAMA PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56778/rjslr.v3i3.523

Abstract

Deep learning is increasingly transforming design practice by enabling data-driven decision-making, predictive analysis, and the automation of visually complex tasks. This study investigates the application of a Convolutional Neural Network (CNN) to the CIFAR-10 dataset to demonstrate how image-based deep learning models can support design analysis and future-scenario prediction across fields such as architecture, product development, and urban planning. The model was developed using a sequential CNN architecture with convolutional, pooling, batch normalization, and dropout layers and trained over 20 epochs using the Adam optimizer. Performance evaluation employed accuracy, precision, recall, F1-scores, confusion matrices, and ROC–AUC curves to provide a transparent and interpretable assessment of model behavior. The CNN had a training accuracy of 89% and a test accuracy of 77%. Its macro-averaged precision, recall, and F1-scores were 78.8%, 79.0%, and 77.5%, respectively. Results show strong discriminative capability but also highlight misclassification challenges among visually similar classes and signs of overfitting. These findings emphasize both the potential and limitations of deep learning when applied to design workflows. The study concludes that CNN-based visual analysis can meaningfully inform design decisions, identify hidden patterns, and support predictive scenario modeling, underscoring the need for interpretability and responsible AI integration in design disciplines.
Co-Authors Atake, Onoriode Michael Babalola Eyitemi , Akilo COMFORT, Olayinka Tosin Cyprian C. KONYEHA Ejenarhome Otega Prosper Ejenarhome Otega Prospera EJENARHOME, Prosper Emmanueld, Chukwuma Ozobialu IGBUNU, Richard Jenarhome, Otega Prosper Konyeha, Susan Nkem Belinda, Unuigbokhai Nwabuokei, Clement Nwabuokei, Onyemaechi Clement Onwuzo Chioma JULIA Oyedotun Samuel ABIODUN Ozobialu, chukwuma Emmanuel