Madison N Ngafeeson

Dr. Madison N Ngafeeson

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 December 2025 in Algorithms
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
DODeborah Olaniyan
Deborah Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
Madison N NgafeesonMadison N Ngafeeson
Madison N Ngafeeson
Detection of financial fraud remains a constant challenge due to the dynamic and highly imbalanced nature of transaction data. This paper proposes the Graph-Temporal Contrastive Transformer (GTCT) framework for modeling both structural dependencies between accounts and temporal evolution in transactional behaviors. We propose a model that combines three components: a graph encoder for modeling relationships between accounts, a temporal encoder for learning sequential patterns in transactions, and a contrastive learning objective that enhances the robustness of representations when supervision is limited. To assess the contribution of each component individually, we systematically remove one module at a time. As shown, an exclusion of the contrastive loss resulted in reduced recall and AUC from 0.867 and 0.982 to 0.805 and 0.948, respectively, indicating the importance of self-supervised learning of representations in fraud detection. Similarly, removing the graph encoder decreased the F1-score from 0.876 to 0.786, which confirmed that modeling transaction structures between accounts is crucial for the identification of complex fraud rings. The exclusion of the temporal encoder led to a more drastic drop in recall (0.743) and AUC (0.905), indicating that capturing the temporal dynamics of transactions is relevant. By comparing all variants, the full GTCT model attained the highest accuracy (0.975) and AUC (0.982), thus showing superior robustness in the detection of sophisticated and evolving financial fraud patterns.

6 December 2021 in Journal of Information Technology Teaching Cases
Verified
Journal Article
Closed access
PDF file
Madison N NgafeesonMadison N Ngafeeson
Madison N Ngafeeson
The Northern Michigan University (NMU) online campus, fondly known as the “Global Campus,” is now 5 years old. Launched in 2016, this online and distance education initiative had as its mission to create academic programs that meet students’ learning and service needs “at the same high standard we do for on-campus students” (NMU). This was a kind of organic final step in the journey of digital transformation that began sixteen years before. Nonetheless, how does NMU make a pivot from 117 years of traditional face-to-face learning model to create value and compete in the digital education space? Worse still, when the Covid-19 global pandemic hits in March 2020 and the campus is forced to shut down (mandating all face-to-face teaching and learning, and to transition to online delivery within just two business days and a weekend); how does the university handle this new set of challenges as its online model gets tested in real-time? The story of NMU’s evolution to online education is told by intrinsic and extrinsic factors including declining enrollments due to changing local economics and regional demographics, an old business model now compounded by a global pandemic. This mix of factors would seem to present NMU with both an opportunity to refine its online model and some new challenges to overcome. This evolution also speaks to the importance of having an overarching digital strategy that can drive true digital transformation.

1 January 2026 in International Journal of Information Security and Privacy
Verified
Journal Article
Open access
PDF file
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
Madison N NgafeesonMadison N Ngafeeson
Madison N Ngafeeson
OOOluwatimileyin Favour Obagbuwa
Oluwatimileyin Favour Obagbuwa
ATAnthony Tsetse
Anthony Tsetse
The growing sophistication of cyber threats demands adaptive security mechanisms beyond traditional Intrusion Detection Systems (IDS). This paper explores integrating Machine Learning (ML) and Explainable Artificial Intelligence (XAI) to enhance Network Intrusion Detection Systems (NIDS). Using the CICIDS2017 dataset, the authors evaluate ML models including Convolutional Neural Networks (CNN), Random Forest, and XGBoost, balancing detection performance with interpretability. Results show XGBoost achieves the highest accuracy with minimal misclassifications, underscoring its robustness for intrusion detection. To address the black-box challenge of deep learning, SHapley Additive exPlanations (SHAP) is applied to interpret predictions. Key features such as Destination Port, Flow Duration, and Packet Length emerged as critical, improving trust, reducing false positives, and aiding investigation. The authors highlight the necessity of coupling high-performing ML with XAI frameworks for transparency. Finally, challenges in scalability, robustness, and dataset generalizability are discussed.

19 June 2026 in Meteorology
Verified
Journal Article
Open access
PDF file
JOJulius Olaniyan
Julius Olaniyan
DODeborah Olaniyan
Deborah Olaniyan
IOIbidun Christiana Obagbuwa
Ibidun Christiana Obagbuwa
Madison N NgafeesonMadison N Ngafeeson
Madison N Ngafeeson
Floods remain among the most devastating natural disasters globally, disproportionately impacting low-resource regions where real-time flood forecasting is constrained by limited computational infrastructure and the scarcity of fine-resolution predictive models. Although state-of-the-art global climate models achieve high predictive accuracy, their scale and computational complexity restrict their applicability in localized and resource-constrained settings. This study proposes a deep climate model distillation framework that transfers knowledge from a high-capacity Fourier Neural Operator (FNO)-based global climate model inspired by FourCastNet into lightweight, regionally adaptive student networks suitable for edge deployment. The framework combines climate variables, satellite observations, and hydrological measurements to improve localized flood prediction. Knowledge transfer is achieved through a multi-objective distillation strategy that combines supervised learning, soft-target alignment, and intermediate feature matching. Experimental evaluation across multiple flood-prone regions in Sub-Saharan Africa and South Asia shows that the distilled student model achieves an average classification accuracy of 0.89, an AUC of 0.91, and an F1-score of 0.88, retaining approximately 96.7% of the teacher model’s predictive performance. In continuous discharge estimation, the model attains a mean absolute error of 0.17, RMSE of 0.24, and an R2 score of 0.85. The proposed distillation approach yields an 8× reduction in inference latency and over a 20× reduction in model size, enabling real-time execution on low-power edge devices such as the Raspberry Pi 4 and NVIDIA Jetson Nano. The student model further demonstrates robust regional and temporal generalization, with limited performance degradation in unseen geographic areas and during extreme flood years.