Tshimangadzo Mavin Tshilongamulenzhe
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tshimangadzo Mavin Tshilongamulenzhe has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Topside Ehleketani Mathonsi
Tshwane University of Technology
7 shared publications - Deon Du Plessis
Tshwane University of Technology
3 shared publications - Nyashadzashe Tamuka
Department of Information Technology, Tshwane University of Technology, Soshanguve, Pretoria 0152, South Africa
2 shared publications - Solly P. Maswikaneng
Department of Information Technology, Tshwane University of Technology, Soshanguve, Pretoria 0152, South Africa
2 shared publications - Thomas Otieno Olwal
Department of Electrical Engineering, Tshwane University of Technology, Pretoria 0183, South Africa
2 shared publications - Tonderai Muchenje
Department of Information Technology, Tshwane University of Technology, Soshanguve, Pretoria 0152, South Africa
2 shared publications
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 406-423
Trends, Challenges, and Future Directions of Wireless Sensor Networks in Underground Mining
- 2 September 2026
- Published by Springer Nature
- p. 406-423
Trends, Challenges, and Future Directions of Wireless Sensor Networks in Underground Mining
- 2 July 2026
- Published by Springer Nature
- p. 307-320
A Review of Blockchain Technology in Healthcare
- Open Access
Intrusion Detection in Fog Computing: A Systematic Review of Security Advances and Challenges
Fog computing extends cloud services to the network edge to support low-latency IoT applications. However, since fog environments are distributed and resource-constrained, intrusion detection systems must be adapted to defend against cyberattacks while keeping computation and communication overhead minimal. This systematic review presents research on intrusion detection systems (IDSs) for fog computing and synthesizes advances and research gaps. The study was guided by the “Preferred-Reporting-Items for-Systematic-Reviews-and-Meta-Analyses” (PRISMA) framework. Scopus and Web of Science were searched in the title field using TITLE/TI = (“intrusion detection” AND “fog computing”) for 2021–2025. The inclusion criteria were (i) 2021–2025 publications, (ii) journal or conference papers, (iii) English language, and (iv) open access availability; duplicates were removed programmatically using a DOI-first key with a title, year, and author alternative. The search identified 8560 records, of which 4905 were unique and included for qualitative grouping and bibliometric synthesis. Metadata (year, venue, authors, affiliations, keywords, and citations) were extracted and analyzed in Python to compute trends and collaboration. Intrusion detection systems in fog networks were categorized into traditional/signature-based, machine learning, deep learning, and hybrid/ensemble. Hybrid and DL approaches reported accuracy ranging from 95 to 99% on benchmark datasets (such as NSL-KDD, UNSW-NB15, CIC-IDS2017, KDD99, BoT-IoT). Notable bottlenecks included computational load relative to real-time latency on resource-constrained nodes, elevated false-positive rates for anomaly detection under concept drift, limited generalization to unseen attacks, privacy risks from centralizing data, and limited real-world validation. Bibliometric analyses highlighted the field’s concentration in fast-turnaround, open-access journals such as IEEE Access and Sensors, as well as a small number of highly collaborative author clusters, alongside dominant terms such as “learning,” “federated,” “ensemble,” “lightweight,” and “explainability.” Emerging directions include federated and distributed training to preserve privacy, as well as online/continual learning adaptation. Future work should consist of real-world evaluation of fog networks, ultra-lightweight yet adaptive hybrid IDS, self-learning, and secure cooperative frameworks. These insights help researchers select appropriate IDS models for fog networks.
Open AccessIntrusion Detection in Fog Computing: A Systematic Review of Security Advances and Challenges
Fog computing extends cloud services to the network edge to support low-latency IoT applications. However, since fog environments are distributed and resource-constrained, intrusion detection systems must be adapted to defend against cyberattacks while keeping computation and communication overhead minimal. This systematic review presents research on intrusion detection systems (IDSs) for fog computing and synthesizes advances and research gaps. The study was guided by the “Preferred-Reporting-Items for-Systematic-Reviews-and-Meta-Analyses” (PRISMA) framework. Scopus and Web of Science were searched in the title field using TITLE/TI = (“intrusion detection” AND “fog computing”) for 2021–2025. The inclusion criteria were (i) 2021–2025 publications, (ii) journal or conference papers, (iii) English language, and (iv) open access availability; duplicates were removed programmatically using a DOI-first key with a title, year, and author alternative. The search identified 8560 records, of which 4905 were unique and included for qualitative grouping and bibliometric synthesis. Metadata (year, venue, authors, affiliations, keywords, and citations) were extracted and analyzed in Python to compute trends and collaboration. Intrusion detection systems in fog networks were categorized into traditional/signature-based, machine learning, deep learning, and hybrid/ensemble. Hybrid and DL approaches reported accuracy ranging from 95 to 99% on benchmark datasets (such as NSL-KDD, UNSW-NB15, CIC-IDS2017, KDD99, BoT-IoT). Notable bottlenecks included computational load relative to real-time latency on resource-constrained nodes, elevated false-positive rates for anomaly detection under concept drift, limited generalization to unseen attacks, privacy risks from centralizing data, and limited real-world validation. Bibliometric analyses highlighted the field’s concentration in fast-turnaround, open-access journals such as IEEE Access and Sensors, as well as a small number of highly collaborative author clusters, alongside dominant terms such as “learning,” “federated,” “ensemble,” “lightweight,” and “explainability.” Emerging directions include federated and distributed training to preserve privacy, as well as online/continual learning adaptation. Future work should consist of real-world evaluation of fog networks, ultra-lightweight yet adaptive hybrid IDS, self-learning, and secure cooperative frameworks. These insights help researchers select appropriate IDS models for fog networks.
- Open Access
- 14 February 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (2) , 100
A Comparative Analysis of Self-Aware Reinforcement Learning Models for Real-Time Intrusion Detection in Fog Networks
Fog computing extends cloud services to the network edge, enabling low-latency processing for Internet of Things (IoT) applications. However, this distributed approach is vulnerable to a wide range of attacks, necessitating advanced intrusion detection systems (IDSs) that operate under resource constraints. This study proposes integrating self-awareness (online learning and concept drift adaptation) into a lightweight RL (reinforcement learning)-based IDS for fog networks and quantitatively comparing it with non-RL static thresholds and bandit-based approaches in real time. Novel self-aware reinforcement learning (RL) models, the Hierarchical Adaptive Thompson Sampling–Reinforcement Learning (HATS-RL) model, and the Federated Hierarchical Adaptive Thompson Sampling–Reinforcement Learning (F-HATS-RL), were proposed for real-time intrusion detection in a fog network. These self-aware RL policies integrated online uncertainty estimation and concept-drift detection to adapt to evolving attacks. The RL models were benchmarked against the static threshold (ST) model and a widely adopted linear bandit (Linear Upper Confidence Bound/LinUCB). A realistic fog network simulator with heterogeneous nodes and streaming traffic, including multi-type attack bursts and gradual concept drift, was established. The models’ detection performance was compared using metrics including latency, energy consumption, detection accuracy, and the area under the precision–recall curve (AUPR) and the area under the receiver operating characteristic curve (AUROC). Notably, the federated self-aware agent (F-HATS-RL) achieved the best AUROC (0.933) and AUPR (0.857), with a latency of 0.27 ms and the lowest energy consumption of 0.0137 mJ, indicating its ability to detect intrusions in fog networks with minimal energy. The findings suggest that self-aware RL agents can detect traffic–dynamic attack methods and adapt accordingly, resulting in more stable long-term performance. By contrast, a static model’s accuracy degrades under drift.
- 14 February 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (2) , 100
Open AccessA Comparative Analysis of Self-Aware Reinforcement Learning Models for Real-Time Intrusion Detection in Fog Networks
Fog computing extends cloud services to the network edge, enabling low-latency processing for Internet of Things (IoT) applications. However, this distributed approach is vulnerable to a wide range of attacks, necessitating advanced intrusion detection systems (IDSs) that operate under resource constraints. This study proposes integrating self-awareness (online learning and concept drift adaptation) into a lightweight RL (reinforcement learning)-based IDS for fog networks and quantitatively comparing it with non-RL static thresholds and bandit-based approaches in real time. Novel self-aware reinforcement learning (RL) models, the Hierarchical Adaptive Thompson Sampling–Reinforcement Learning (HATS-RL) model, and the Federated Hierarchical Adaptive Thompson Sampling–Reinforcement Learning (F-HATS-RL), were proposed for real-time intrusion detection in a fog network. These self-aware RL policies integrated online uncertainty estimation and concept-drift detection to adapt to evolving attacks. The RL models were benchmarked against the static threshold (ST) model and a widely adopted linear bandit (Linear Upper Confidence Bound/LinUCB). A realistic fog network simulator with heterogeneous nodes and streaming traffic, including multi-type attack bursts and gradual concept drift, was established. The models’ detection performance was compared using metrics including latency, energy consumption, detection accuracy, and the area under the precision–recall curve (AUPR) and the area under the receiver operating characteristic curve (AUROC). Notably, the federated self-aware agent (F-HATS-RL) achieved the best AUROC (0.933) and AUPR (0.857), with a latency of 0.27 ms and the lowest energy consumption of 0.0137 mJ, indicating its ability to detect intrusions in fog networks with minimal energy. The findings suggest that self-aware RL agents can detect traffic–dynamic attack methods and adapt accordingly, resulting in more stable long-term performance. By contrast, a static model’s accuracy degrades under drift.
- Open Access
- 30 August 2025
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 14 (4)
A Review of Vulnerability Detection Algorithms in Software Code
Detecting software vulnerabilities is essential to keeping modern systems safe in the face of increasingly sophisticated cyber threats. This paper offers a clear and accessible overview of how vulnerabilities are currently identified, reviewing traditional, machine learning (ML), and hybrid approaches. Traditional techniques such as static and dynamic analysis are still widely used but often suffer from high false positive rates and struggle to adapt to new and evolving threats. In contrast, recent ML developments, especially those involving Random Forest (RF) and Convolutional Neural Networks (CNN), have shown significant promise in improving detection accuracy, feature extraction, and classification. Decision Tree methods remain valued for their transparency, while CNNs and other deep learning tools excel at recognizing structural and spatial patterns in code. Combining these strengths in hybrid models integrating effective feature selection with powerful pattern recognition has the potential to deliver more accurate results and reduce false alarms. However, persistent challenges remain, including limited dataset diversity, weak resilience against adversarial attacks, and the need for real-time adaptability. By bringing together the latest research and practical insights, this review aims to guide developers, security analysts, and organizations in creating more robust, automated, and adaptive security tools capable of meeting the fast-changing demands of software vulnerability management.
- 30 August 2025
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 14 (4)
Open AccessA Review of Vulnerability Detection Algorithms in Software Code
Detecting software vulnerabilities is essential to keeping modern systems safe in the face of increasingly sophisticated cyber threats. This paper offers a clear and accessible overview of how vulnerabilities are currently identified, reviewing traditional, machine learning (ML), and hybrid approaches. Traditional techniques such as static and dynamic analysis are still widely used but often suffer from high false positive rates and struggle to adapt to new and evolving threats. In contrast, recent ML developments, especially those involving Random Forest (RF) and Convolutional Neural Networks (CNN), have shown significant promise in improving detection accuracy, feature extraction, and classification. Decision Tree methods remain valued for their transparency, while CNNs and other deep learning tools excel at recognizing structural and spatial patterns in code. Combining these strengths in hybrid models integrating effective feature selection with powerful pattern recognition has the potential to deliver more accurate results and reduce false alarms. However, persistent challenges remain, including limited dataset diversity, weak resilience against adversarial attacks, and the need for real-time adaptability. By bringing together the latest research and practical insights, this review aims to guide developers, security analysts, and organizations in creating more robust, automated, and adaptive security tools capable of meeting the fast-changing demands of software vulnerability management.
- Open Access
- 9 June 2025
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 14 (3)
A Model to Amplify Transmission Quality of Satellite Television
One of the various applications of communication satellite technologies is broadcasting satellite television (TV). In TV broadcasting, satellite communication is the easiest way to transmit many services and offers a variety of choices across a varied region, thereby overcoming the need for the complex infrastructure of terrestrial transmitters that a terrestrial network needs to broadcast its signals throughout a wide range area like countries or continents and providing quality digital TV viewing. However, Satellite TV broadcasting has a deficiency of outage effect caused by rain fade that instigate due to bad raining weather which at once will cuts signal transmission from the transmitter satellite to the receiver dish. this study was undertaken to explore the challenges that satellite TV broadcasting faces, which is caused by the rain fade effect. Thereafter, a model to amplify the transmission quality of satellite television is designed. The proposed Gau-satcomm algorithm, ITU-R model, and SAM model had an average BER of 5%, 8%, and 10%, respectively. Additionally, the Gau-Satcomm algorithm, SAM model, and ITU-R model experienced 4%, 9%, and 11% attenuation, respectively. Furthermore, the study compared outage probability across three algorithms at frequencies over 10 GHz, the proposed Gau-satcomm algorithm, the ITU-R algorithm, and the SAM algorithm minimized outages by 10%, 7%, and 5%, respectively. Therefore, the proposed Gau-Satcomm outperforms these traditional algorithms in regard to average BER, a reduced average attenuation, and outage probability.
- 9 June 2025
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 14 (3)
Open AccessA Model to Amplify Transmission Quality of Satellite Television
One of the various applications of communication satellite technologies is broadcasting satellite television (TV). In TV broadcasting, satellite communication is the easiest way to transmit many services and offers a variety of choices across a varied region, thereby overcoming the need for the complex infrastructure of terrestrial transmitters that a terrestrial network needs to broadcast its signals throughout a wide range area like countries or continents and providing quality digital TV viewing. However, Satellite TV broadcasting has a deficiency of outage effect caused by rain fade that instigate due to bad raining weather which at once will cuts signal transmission from the transmitter satellite to the receiver dish. this study was undertaken to explore the challenges that satellite TV broadcasting faces, which is caused by the rain fade effect. Thereafter, a model to amplify the transmission quality of satellite television is designed. The proposed Gau-satcomm algorithm, ITU-R model, and SAM model had an average BER of 5%, 8%, and 10%, respectively. Additionally, the Gau-Satcomm algorithm, SAM model, and ITU-R model experienced 4%, 9%, and 11% attenuation, respectively. Furthermore, the study compared outage probability across three algorithms at frequencies over 10 GHz, the proposed Gau-satcomm algorithm, the ITU-R algorithm, and the SAM algorithm minimized outages by 10%, 7%, and 5%, respectively. Therefore, the proposed Gau-Satcomm outperforms these traditional algorithms in regard to average BER, a reduced average attenuation, and outage probability.
- Open Access
- 9 June 2025
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 14 (3)
Machine Learning-Based Security Algorithms for Detecting and Preventing DDoS Attacks on the IoT: State-of-the-Art, Challenges, and Future Directions
- The Internet of Things (IoT) represents a vast network of interconnected devices equipped with software, sensors, and other technologies that enable data exchange and autonomous operation with other devices and systems without human intervention over the internet. IoT applications span across various sectors, including agriculture, education, healthcare, and communication. However, Distributed Denial of Service (DDoS) attacks continue to pose significant risks to the IoT network due to current challenges of classification efficiency and response times by the existing algorithms, such as Decision Tree (DT), Linear Regression (LR), and K-means. This paper provides a comprehensive review of DDoS attack types within the IoT networks. Secondly, the paper critically examines and analyses the challenges and opportunities inherent in leveraging Machine Learning (ML) algorithms for detecting, preventing, and mitigating these attacks. Finally, it presents the categories of IoT performance metrics, and their statistics found in the Literature over the Past decade.
- 9 June 2025
- Published by STMIK Indonesia Padang in The Indonesian Journal of Computer Science
- Vol. 14 (3)
Open AccessMachine Learning-Based Security Algorithms for Detecting and Preventing DDoS Attacks on the IoT: State-of-the-Art, Challenges, and Future Directions
- The Internet of Things (IoT) represents a vast network of interconnected devices equipped with software, sensors, and other technologies that enable data exchange and autonomous operation with other devices and systems without human intervention over the internet. IoT applications span across various sectors, including agriculture, education, healthcare, and communication. However, Distributed Denial of Service (DDoS) attacks continue to pose significant risks to the IoT network due to current challenges of classification efficiency and response times by the existing algorithms, such as Decision Tree (DT), Linear Regression (LR), and K-means. This paper provides a comprehensive review of DDoS attack types within the IoT networks. Secondly, the paper critically examines and analyses the challenges and opportunities inherent in leveraging Machine Learning (ML) algorithms for detecting, preventing, and mitigating these attacks. Finally, it presents the categories of IoT performance metrics, and their statistics found in the Literature over the Past decade.
- Open Access
- 1 January 2024
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 15 (2) , 233-244
Improved Encryption Algorithm for Public Wireless Network
- 1 January 2024
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 15 (2) , 233-244
Open AccessImproved Encryption Algorithm for Public Wireless Network
- Open Access
A User-Based Authentication and DoS Mitigation Scheme for Wearable Wireless Body Sensor Networks
Wireless Body Sensor Networks (WBSNs) is one of the greatest growing technology for sensing and performing various tasks. The information transmitted in the WBSNs is vulnerable to cyber-attacks, therefore security is very important. Denial of Service (DoS) attacks are considered one of the major threats against WBSNs security. In DoS attacks, an adversary targets to degrade and shut down the efficient use of the network and disrupt the services in the network causing them inaccessible to its intended users. If sensitive information of patients in WBSNs, such as the medical history is accessed by unauthorized users, the patient may suffer much more than the disease itself, it may result in loss of life. This paper proposes a User-Based authentication scheme to mitigate DoS attacks in WBSNs. A five-phase User-Based authentication DoS mitigation scheme for WBSNs is designed by integrating Elliptic Curve Cryptography (ECC) with Rivest Cipher 4 (RC4) to ensure a strong authentication process that will only allow authorized users to access nodes on WBSNs.
Open AccessA User-Based Authentication and DoS Mitigation Scheme for Wearable Wireless Body Sensor Networks
Wireless Body Sensor Networks (WBSNs) is one of the greatest growing technology for sensing and performing various tasks. The information transmitted in the WBSNs is vulnerable to cyber-attacks, therefore security is very important. Denial of Service (DoS) attacks are considered one of the major threats against WBSNs security. In DoS attacks, an adversary targets to degrade and shut down the efficient use of the network and disrupt the services in the network causing them inaccessible to its intended users. If sensitive information of patients in WBSNs, such as the medical history is accessed by unauthorized users, the patient may suffer much more than the disease itself, it may result in loss of life. This paper proposes a User-Based authentication scheme to mitigate DoS attacks in WBSNs. A five-phase User-Based authentication DoS mitigation scheme for WBSNs is designed by integrating Elliptic Curve Cryptography (ECC) with Rivest Cipher 4 (RC4) to ensure a strong authentication process that will only allow authorized users to access nodes on WBSNs.
- Open Access
Intelligent Throughput-based Sleep Control Algorithm for the 5G Dense Heterogeneous Cellular Networks
In the recent past, many mobile/telecom operators have seen a continuously growing demand for ubiquitous high-speed wireless access and an unprecedented increase in connected wireless devices. As a result, we have seen explosive growth in traffic volumes and a wide range of QoS requirements. The Fifth generation (5G) heterogeneous cellular networks (HetNets) have been developed by different mobile operators to achieve the growing mass data capacity and to reconnoiter the energy efficiency guaranteed trade-off between throughput QoS requirements and latency performance. However, existing energy efficiency algorithms do not satisfy the throughput QoS requirements such as reduced latency and packet loss, longer battery lifetime, reliability, and high data rates with regards to the three components of energy consumption of the 5G radio access network (RANs) that dominate the overall mobile communication networks. In addition, real-time traffic types such as voice and video require a high computational load at the terminal side which has an undesirable impact on energy/battery lifetime which further affects the throughput QoS performance such as reduced packet loss, longer battery lifetime, reliability, and high data rates. As a result, this paper proposed an Intelligent Throughput-based Sleep Control (ITSC) algorithm for throughput QoS and energy efficiency enhancement in 5G dense HetNets. In the proposed ITSC algorithm, a deep neural network (DNN) was used to determine the cell capacity ratio for the small base stations (SBSs).
Open AccessIntelligent Throughput-based Sleep Control Algorithm for the 5G Dense Heterogeneous Cellular Networks
In the recent past, many mobile/telecom operators have seen a continuously growing demand for ubiquitous high-speed wireless access and an unprecedented increase in connected wireless devices. As a result, we have seen explosive growth in traffic volumes and a wide range of QoS requirements. The Fifth generation (5G) heterogeneous cellular networks (HetNets) have been developed by different mobile operators to achieve the growing mass data capacity and to reconnoiter the energy efficiency guaranteed trade-off between throughput QoS requirements and latency performance. However, existing energy efficiency algorithms do not satisfy the throughput QoS requirements such as reduced latency and packet loss, longer battery lifetime, reliability, and high data rates with regards to the three components of energy consumption of the 5G radio access network (RANs) that dominate the overall mobile communication networks. In addition, real-time traffic types such as voice and video require a high computational load at the terminal side which has an undesirable impact on energy/battery lifetime which further affects the throughput QoS performance such as reduced packet loss, longer battery lifetime, reliability, and high data rates. As a result, this paper proposed an Intelligent Throughput-based Sleep Control (ITSC) algorithm for throughput QoS and energy efficiency enhancement in 5G dense HetNets. In the proposed ITSC algorithm, a deep neural network (DNN) was used to determine the cell capacity ratio for the small base stations (SBSs).