Claude Mukatshung Nawej
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Claude Mukatshung Nawej has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Pius Adewale Owolawi
Faculty of Information and Communication Technology, Tshwane University of Technology, Pretoria, South Africa
6 shared publications - Chunling Tu
Tshwane University of Technology
4 shared publications - Tom Walingo
Discipline of Electrical, Electronic and Computer Engineering, University of KwaZulu-Natal, Durban 4041, South Africa
3 shared publications - Malose John Mathiane
Tshwane University of Technology
2 shared publications - Charles Maruma
Tshwane University of Technology
1 shared publication Chunling Du
Tshwane University of Technology, South Africa
1 shared publication
Latest Publications
- 6 October 2026
- Published by Springer Nature
- p. 452-475
Context-Aware Versus QoS-Only Behaviour Modelling for 6G Network Slicing: A Comparative Spectral Clustering Analysis
- 6 October 2026
- Published by Springer Nature
- p. 452-475
Context-Aware Versus QoS-Only Behaviour Modelling for 6G Network Slicing: A Comparative Spectral Clustering Analysis
- Open Access
- 1 July 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (8) , 641-651
A Systematic review on AI-based object recognition in unfavorable weather condition: Curacy and GDPR compliance
This comprehensive review of the literature examines the latest advancements, challenges, and possibilities in AI-based object detection systems, particularly in the context of adverse weather conditions and GDPR compliance. The study aims to explore how AI models function under unfavorable conditions while adhering to ethical and legal standards. A total of 19 peer-reviewed publications published since 2020 were identified, filtered, and analyzed from reputable databases using a process aligned with PRISMA 2020 guidelines. The findings highlight significant progress in areas such as domain adaptation, multi-modal sensor fusion, and YOLO-based object detectors, with YOLOv7 demonstrating exceptional performance in fog, rain, and snow. However, high computational costs and a scarcity of real-world datasets continue to pose challenges, leading to performance discrepancies. The review emphasizes the importance of privacy-preserving techniques, including differential privacy, real-time anonymization, and privacy-by-design architectures, as essential components for GDPR compliance. The results suggest that future research should prioritize scalable, real-time, and ethically sound object detection algorithms capable of adapting to changing environmental conditions. Practical implications include enhanced compliance and reliability of AI systems used in intelligent surveillance, autonomous vehicles, and smart city infrastructure. Overall, the report provides researchers and policymakers with a foundational understanding to bridge the gap between technological innovation and legal requirements.
- 1 July 2025
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 9 (8) , 641-651
Open AccessA Systematic review on AI-based object recognition in unfavorable weather condition: Curacy and GDPR compliance
This comprehensive review of the literature examines the latest advancements, challenges, and possibilities in AI-based object detection systems, particularly in the context of adverse weather conditions and GDPR compliance. The study aims to explore how AI models function under unfavorable conditions while adhering to ethical and legal standards. A total of 19 peer-reviewed publications published since 2020 were identified, filtered, and analyzed from reputable databases using a process aligned with PRISMA 2020 guidelines. The findings highlight significant progress in areas such as domain adaptation, multi-modal sensor fusion, and YOLO-based object detectors, with YOLOv7 demonstrating exceptional performance in fog, rain, and snow. However, high computational costs and a scarcity of real-world datasets continue to pose challenges, leading to performance discrepancies. The review emphasizes the importance of privacy-preserving techniques, including differential privacy, real-time anonymization, and privacy-by-design architectures, as essential components for GDPR compliance. The results suggest that future research should prioritize scalable, real-time, and ethically sound object detection algorithms capable of adapting to changing environmental conditions. Practical implications include enhanced compliance and reliability of AI systems used in intelligent surveillance, autonomous vehicles, and smart city infrastructure. Overall, the report provides researchers and policymakers with a foundational understanding to bridge the gap between technological innovation and legal requirements.
- 23 October 2024
- Published by Springer Nature
- p. 245-262
Toward a Realistic Comparative Analysis of Recurrent Neural Network’s Methods via Long-Term Memory Approaches
- 23 October 2024
- Published by Springer Nature
- p. 245-262
Toward a Realistic Comparative Analysis of Recurrent Neural Network’s Methods via Long-Term Memory Approaches
- Open Access
- 14 September 2024
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 8 (6) , 6625-6643
Clustered temporal memory networks: A hybrid approach for signal strength prediction
The rapid expansion of 5G networks has revolutionized mobile communication by offering unprecedented speed, low-latency connections, and the ability to support vast numbers of connected devices. However, these advancements bring new challenges in maintaining consistent and reliable signal strength, critical for ensuring optimal Quality of Service (QoS). Traditional models, such as ARIMA, Random Forest (RF), and K-means clustering, struggle to capture the complex, nonlinear, and dynamic behaviour of 5G networks, leading to suboptimal prediction accuracy. In this study, we propose a novel hybrid model, Clustered Temporal Memory Networks (CTMN), which integrates DBSCAN clustering with Long Short-Term Memory (LSTM) networks to improve signal strength prediction in mobile networks. The CTMN model combines DBSCAN's ability to handle spatial variability and outliers in 5G data, combined with LSTM's capacity for modelling long-term dependencies and nonlinear time-series patterns. Our empirical analysis demonstrates that CTMN outperforms traditional methods, achieving up to a 20.82% improvement in prediction accuracy across key performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). These findings indicate that CTMN provides a scalable, robust solution for enhancing signal strength prediction and optimizing network performance in next-generation mobile networks.
- 14 September 2024
- Published by Learning Gate in Edelweiss Applied Science and Technology
- Vol. 8 (6) , 6625-6643
Open AccessClustered temporal memory networks: A hybrid approach for signal strength prediction
The rapid expansion of 5G networks has revolutionized mobile communication by offering unprecedented speed, low-latency connections, and the ability to support vast numbers of connected devices. However, these advancements bring new challenges in maintaining consistent and reliable signal strength, critical for ensuring optimal Quality of Service (QoS). Traditional models, such as ARIMA, Random Forest (RF), and K-means clustering, struggle to capture the complex, nonlinear, and dynamic behaviour of 5G networks, leading to suboptimal prediction accuracy. In this study, we propose a novel hybrid model, Clustered Temporal Memory Networks (CTMN), which integrates DBSCAN clustering with Long Short-Term Memory (LSTM) networks to improve signal strength prediction in mobile networks. The CTMN model combines DBSCAN's ability to handle spatial variability and outliers in 5G data, combined with LSTM's capacity for modelling long-term dependencies and nonlinear time-series patterns. Our empirical analysis demonstrates that CTMN outperforms traditional methods, achieving up to a 20.82% improvement in prediction accuracy across key performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). These findings indicate that CTMN provides a scalable, robust solution for enhancing signal strength prediction and optimizing network performance in next-generation mobile networks.
- 14 February 2024
- Published by Springer Nature
- p. 347-360
A Convolution Neural Network Based VANET Traffic Control System in a Smart City
- 14 February 2024
- Published by Springer Nature
- p. 347-360
A Convolution Neural Network Based VANET Traffic Control System in a Smart City
- Open Access
A Vehicle Density Estimation Traffic Light Control System Using a Two-Dimensional Convolution Neural Network
One of the world’s challenges is the amount of traffic on the roads. Waiting for the green light is a major cause of traffic congestion. Low throughput rates and eventual congestion come from many traffic signals that are hard coded, irrespective of the volume of the amount of traffic. Instead of depending on predefined time intervals, it is essential to build a traffic signal control system that can react to changing vehicle densities. Emergency vehicles, like ambulances, must be given priority at the intersection so as not to spend more time at the traffic light. Computer vision techniques can be used to improve road traffic signal control and reduce real-time traffic delays at intersections without the requirement for substantial infrastructure analysis. Long wait times and significant energy consumption are just two of the problems of the current traffic signal control system. To optimal efficiency, the traffic signal’s duration must be dynamically changed to account for current traffic volume. To lessen congestion, the approach taken in this research focuses on modifying traffic signal time determined by the density of vehicles at the crossroads. The main purpose of this article is to demonstrate heavy traffic and emergency vehicle prioritization from all directions at the traffic intersection for a speedy passage. Using the Pygame tool, the proposed method in this study, which includes a mechanism for estimating traffic density and prioritization by counting vehicles at a traffic junction, is demonstrated. The vehicle throughput for the adaptive traffic light built using Pygame is compared with the vehicle pass rate for the adaptive traffic light built using Simulation of Urban Mobility (SUMO). The simulation results show that the adaptive traffic light built using Pygame achieves 90% throughput compared to the adaptive traffic light built using SUMO. A Two-Dimensional Convolutional Neural Network (2D-CNN) is implemented using Tensorflow for vehicle classification. The 2D-CNN model demonstrated 96% accuracy in classifying vehicles using the test dataset. Additionally, emergency vehicles, such as ambulances, are given priority for quick passing.
Open AccessA Vehicle Density Estimation Traffic Light Control System Using a Two-Dimensional Convolution Neural Network
One of the world’s challenges is the amount of traffic on the roads. Waiting for the green light is a major cause of traffic congestion. Low throughput rates and eventual congestion come from many traffic signals that are hard coded, irrespective of the volume of the amount of traffic. Instead of depending on predefined time intervals, it is essential to build a traffic signal control system that can react to changing vehicle densities. Emergency vehicles, like ambulances, must be given priority at the intersection so as not to spend more time at the traffic light. Computer vision techniques can be used to improve road traffic signal control and reduce real-time traffic delays at intersections without the requirement for substantial infrastructure analysis. Long wait times and significant energy consumption are just two of the problems of the current traffic signal control system. To optimal efficiency, the traffic signal’s duration must be dynamically changed to account for current traffic volume. To lessen congestion, the approach taken in this research focuses on modifying traffic signal time determined by the density of vehicles at the crossroads. The main purpose of this article is to demonstrate heavy traffic and emergency vehicle prioritization from all directions at the traffic intersection for a speedy passage. Using the Pygame tool, the proposed method in this study, which includes a mechanism for estimating traffic density and prioritization by counting vehicles at a traffic junction, is demonstrated. The vehicle throughput for the adaptive traffic light built using Pygame is compared with the vehicle pass rate for the adaptive traffic light built using Simulation of Urban Mobility (SUMO). The simulation results show that the adaptive traffic light built using Pygame achieves 90% throughput compared to the adaptive traffic light built using SUMO. A Two-Dimensional Convolutional Neural Network (2D-CNN) is implemented using Tensorflow for vehicle classification. The 2D-CNN model demonstrated 96% accuracy in classifying vehicles using the test dataset. Additionally, emergency vehicles, such as ambulances, are given priority for quick passing.
- 3 August 2022
- Published by Springer Nature
- p. 871-878
Banking Credit Risk Analysis using Artificial Neural Network
- 3 August 2022
- Published by Springer Nature
- p. 871-878
Banking Credit Risk Analysis using Artificial Neural Network
- 26 June 2022
- Published by Springer Nature
- p. 225-237
A SUMO Simulation Study on VANET-Based Adaptive Traffic Light Control System
- 26 June 2022
- Published by Springer Nature
- p. 225-237
A SUMO Simulation Study on VANET-Based Adaptive Traffic Light Control System
- 27 October 2021
- Published by Springer Nature
- p. 733-744
Enhanced AODV Routing Protocol for Intelligent Attack Mitigation in Vehicular Ad-Hoc Networks
- 27 October 2021
- Published by Springer Nature
- p. 733-744
Enhanced AODV Routing Protocol for Intelligent Attack Mitigation in Vehicular Ad-Hoc Networks