Symon Fumu Nyalugwe

Mr. Symon Fumu Nyalugwe

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
5 June 2026 in Computers
Verified
Journal Article
Open access
PDF file
Symon Fumu NyalugweSymon Fumu Nyalugwe
Symon Fumu Nyalugwe
OKOkuthe P. Kogeda
Okuthe P. Kogeda
RHRobert Toyo Hans
Robert Toyo Hans
Traffic congestion poses a significant challenge in urban environments. The use of digital techniques has emerged as a pivotal trend, as it offers substantial safety to and mitigates stress and frustration for road users. The purpose of this survey was to explore the current approaches and digital techniques for managing traffic congestion. We address this through a systematic literature review (SLR) approach by adopting PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We began by exploring the key techniques of topological data analysis (TDA), machine learning (ML) and deep learning (DL) for modeling urban traffic prediction. We evaluated the robustness of the topological data analysis technique (Persistent Homology (PH)) against deep learning frameworks (Graph Convolutional Neural Networks (GCNNs)). We found that each framework has its own strengths and weaknesses, and neither of the frameworks independently provides a complete solution. PH may offer richer structural insights and robustness to noise but may struggle with direct predictive implementation, while deep learning models do better at extracting dynamic predictive patterns but are assumed to lack interpretability and generalizability. Therefore, the integration of multiple techniques, either PH with stacking ensemble methods or deep learning with stacking ensemble methods, can improve prediction and generalization of the model while at the same time reducing over-reliance on local graph assumptions. Future research should focus not only on performance metrics or methods but also on explainability, transferability, adaptability across heterogeneous road environments and computational cost.

15 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
Symon Fumu NyalugweSymon Fumu Nyalugwe
Symon Fumu Nyalugwe
OKOkuthe P. Kogeda
Okuthe P. Kogeda
RHRobert Toyo Hans
Robert Toyo Hans
Traffic congestion is a major challenge in resource-constrained urban environments, where number of vehicles are exceeding the capacity of existing road infrastructure. Existing models are often failing to capture the complex spatial and temporal relationships inherent in traffic data, resulting in reduced prediction accuracy, poor model transferability, and limited reliability across heterogeneous urban roads. Accurate traffic congestion prediction is therefore essential for effective traffic management. To address these challenges, this study developed a hybrid model by integrating Persistent Homology (PH) framework with an ensemble stacking method. Real-time traffic data was collected from TomTom via traffic data APIs from Maputo Maseru and Pretoria. Hybrid model achieved an overall prediction accuracy of 98%, outperforming all baseline models and attained recall scores of 93% for Maputo, 90% for Maseru and 96% for Pretoria during peak hour. While during non-peak hours, the model attained recall score of 97% for Maputo, 90% for Maseru and 90% for Pretoria. The prediction confidence levels reached 80% for Maputo, 70% for Maseru and 100% for Pretoria. PH computational analysis revealed that the Pretoria CBD road networks exhibited more persistent H0 and H1 topological features and higher death values compared to Maputo and Maseru, indicating stronger structural persistence, greater route redundancy, and more complex road network integration patterns. These resulting PH features enabled the hybrid model to better capture complex spatial-temporal traffic dynamics, improving congestion prediction performance. Future study should focus on models that are: adaptable, scalable, computationally efficient, and balance performance with practical deployability in real-world, multi-environment contexts.