Tshimangadzo Tshilongamulenzhe

Dr. Tshimangadzo Tshilongamulenzhe

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 January 2023 in Journal of Advances in Information Technology
Verified
Journal Article
Open access
TTTshimangadzo Tshilongamulenzhe
Tshimangadzo Tshilongamulenzhe
TMTopside E. Mathonsi
Topside E. Mathonsi
DPDeon P. Du Plessis
Deon P. Du Plessis
MMMaredi I. Mphahlele
Maredi I. Mphahlele
Wireless Sensor Networks (WSNs) is an area that has attracted a lot of attention currently worldwide. WSNs are implemented to monitor temperature, humidity, and pressure, among others within the agricultural environment. This paper addresses the traffic congestion that occurs within WSNs in the agricultural environment during packet transmission that is normally caused by head-of-line blocking. As a result, packet loss, packet delay, and network performance impairment occurred during packet distribution in the network. This paper proposed an Intelligence Traffic Routing (ITR) algorithm to manage packet flow to avoid traffic congestion in WSNs within the agricultural environment while improving Quality of Service (QoS). The LBRM (Load Balancing Routing Management) and MLCC (Machine Learning Congestion Control) algorithms were integrated to develop the proposed ITR algorithm. Network Simulator 2 (NS-2) was used to test the effectiveness of the proposed ITR algorithm. The simulation results showed that the proposed ITR algorithm reduced packet loss by 27.3%, packet delay by 43.4%, and improved network throughput by 98.4% when compared with LBRM and MLCC algorithms.

5 March 2026 in Computers
Verified
Journal Article
Open access
PDF file
NTNyashadzashe Everson Tamuka
Nyashadzashe Everson Tamuka
Topside Ehleketani MathonsiTopside Ehleketani Mathonsi
Topside Ehleketani Mathonsi
Thomas O OlwalThomas O Olwal
Thomas O Olwal
SMSolly Phatle Maswikaneng
Solly Phatle Maswikaneng
TMTonderai Muchenje
Tonderai Muchenje
TTTshimangadzo Tshilongamulenzhe
Tshimangadzo Tshilongamulenzhe
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.

9 June 2025 in The Indonesian Journal of Computer Science
Verified
Journal Article
Open access
PDF file
CBCoster Baloyi
Coster Baloyi
TMTopside Mathonsi
Topside Mathonsi
DPDaniel Petrus du Plessis
Daniel Petrus du Plessis
TMTonderai Muchenje
Tonderai Muchenje
TTTshimangadzo Tshilongamulenzhe
Tshimangadzo Tshilongamulenzhe
- 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.

30 August 2025 in The Indonesian Journal of Computer Science
Verified
Journal Article
Open access
PDF file
ZRZelda P. Ramahlo
Zelda P. Ramahlo
TMTopside Mathonsi
Topside Mathonsi
TTTshimangadzo Tshilongamulenzhe
Tshimangadzo Tshilongamulenzhe
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.

1 January 2024 in Journal of Advances in Information Technology
Verified
Journal Article
Open access
CKChristopher Khosa
Christopher Khosa
Topside Ehleketani MathonsiTopside Ehleketani Mathonsi
Topside Ehleketani Mathonsi
DPDeon du Plessis
Deon du Plessis
TTTshimangadzo Tshilongamulenzhe
Tshimangadzo Tshilongamulenzhe

14 February 2026 in Future Internet
Verified
Journal Article
Open access
PDF file
NTNyashadzashe Everson Tamuka
Nyashadzashe Everson Tamuka
Topside Ehleketani MathonsiTopside Ehleketani Mathonsi
Topside Ehleketani Mathonsi
Thomas O OlwalThomas O Olwal
Thomas O Olwal
SMSolly Phatle Maswikaneng
Solly Phatle Maswikaneng
TMTonderai Muchenje
Tonderai Muchenje
TTTshimangadzo Tshilongamulenzhe
Tshimangadzo Tshilongamulenzhe
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.