Attlee Munyaradzi GAMUNDANI

Prof. Dr. Attlee Munyaradzi GAMUNDANI

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 May 2015
Verified
Conference Paper
Closed access
AGAttlee Munyaradzi GAMUNDANI
Attlee Munyaradzi GAMUNDANI
The heterogeneity of devices that can seamlessly connect to each other and be attached to human beings has given birth to a new computing epitome referred to as the Internet of Things. The connectivity and scalability of such technological waves could be harnessed to improve service delivery in many application areas as revealed by recent studies on the Internet of Things' interoperability. However, for the envisaged benefits to be yielded from Internet of Things there are many security issues to be addressed, which range from application environments security concerns, connection technology inbuilt security issues, scalability and manageability issues. Given the increasing number of objects or “things” that can connect to each other unsupervised, the complexity of such a network is presenting a great concern both for the future internet's security and reliable operation. The focus of this paper was to review the impact of some of the attacks attributable to internet of things. A desktop review of work done under this area, using the qualitative methodology was employed. This research may contribute towards a roadmap for security design and future research on internet of things scalability. The deployment of future applications around Internet of Things may receive valuable insight as the nature of attacks and their perceived impacts will be unveiled and possible solutions could be developed around them.

1 July 2018
Verified
Conference Paper
Closed access
AGAttlee Munyaradzi GAMUNDANI
Attlee Munyaradzi GAMUNDANI
APAmelia Phillips
Amelia Phillips
HMHippolyte N. Muyingi
Hippolyte N. Muyingi
Internet of things (IoT) are finding their wide use in various domains. IoT implementation in the Smart home domain is one that is complex as the devices that are being used in such platforms are of different sizes and have different computational capacity. The ability to ensure security is enforced on such devices rests on how proper the authentication processes are executed. It is against this background that this paper is formulated, to give a detailed review of the potential authentication threats and attacks on IoT in the Smart home domain in particular. The main ideas on the potential authentication threats and attacks on IoT in Smart home applications, presented in this paper are largely informed by the detailed literature review of related work in the domain of IoT.

3 December 2018
Verified
Conference Paper
Open access
PDF file
PMPardon Blessings Maoneke
Pardon Blessings Maoneke
FSFungai Bhunu Shava
Fungai Bhunu Shava
AGAttlee Munyaradzi GAMUNDANI
Attlee Munyaradzi GAMUNDANI
MBMercy Bere-Chitauro
Mercy Bere-Chitauro
INIsaac Nhamu
Isaac Nhamu

27 June 2025 in Water
Verified
Journal Article
Open access
PDF file
Maria Nelago KanyamaMaria Nelago Kanyama
Maria Nelago Kanyama
FSFungai Bhunu Shava
Fungai Bhunu Shava
AGAttlee Munyaradzi GAMUNDANI
Attlee Munyaradzi GAMUNDANI
AHAndreas Hartmann
Andreas Hartmann
Water, the lifeblood of our planet, sustains ecosystems, economies, and communities. However, climate change and increasing hydrological variability have exacerbated global water scarcity, threatening livelihoods and economic stability. According to the United Nations, over 2 billion people currently live in water-stressed regions, a figure expected to rise significantly by 2030. To address this urgent challenge, this study proposes an AI-driven anomaly detection framework for smart water metering networks (SWMNs) using machine learning (ML) techniques and data resampling methods to enhance water conservation efforts. This research utilizes 6 years of monthly water consumption data from 1375 households from Location A, Windhoek, Namibia, and applies support vector machine (SVM), decision tree (DT), random forest (RF), and k-nearest neighbors (kNN) models within ensemble learning strategies. A significant challenge in real-world datasets is class imbalance, which can reduce model reliability in detecting abnormal patterns. To address this, we employed data resampling techniques including random undersampling (RUS), SMOTE, and SMOTEENN. Among these, SMOTEENN achieved the best overall performance for individual models, with the RF classifier reaching an accuracy of 99.5% and an AUC score of 0.998. Ensemble learning approaches also yielded strong results, with the stacking ensemble achieving 99.6% accuracy, followed by soft voting at 99.2% and hard voting at 98.1%. These results highlight the effectiveness of ensemble methods and advanced sampling techniques in improving anomaly detection under class-imbalanced conditions. To the best of our knowledge, this is the first study to explore and evaluate the combined use of ensemble learning and resampling techniques for ML-based anomaly detection in SWMNs. By integrating artificial intelligence into water systems, this work lays the foundation for scalable, secure, and efficient smart water management solutions, contributing to global efforts in sustainable water governance.

1 May 2019
Verified
Conference Paper
Closed access
MMMamoqenelo Morolong
Mamoqenelo Morolong
AGAttlee Munyaradzi GAMUNDANI
Attlee Munyaradzi GAMUNDANI
FSFungai Bhunu Shava
Fungai Bhunu Shava

1 May 2019
Verified
Conference Paper
Closed access
SMStanford Musarurwa
Stanford Musarurwa
AGAttlee Munyaradzi GAMUNDANI
Attlee Munyaradzi GAMUNDANI
FSFungai Bhunu Shava
Fungai Bhunu Shava