Kennedy Chitiza
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kennedy Chitiza has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Felix Mazunga
Applied Physics and Telecommunications Department, Midlands State University, Gweru P. Bag 9055, Zimbabwe
2 shared publications - Prosper Mbire
Midlands State University, Zimbabwe
2 shared publications Valentine Elifas Gora
2 shared publications- Abid Yahya
Department of Electrical and Communications Systems Engineering, Botswana International University of Science and Technology, Palapye, Botswana
1 shared publication - Action Nechibvute
Midlands State University
1 shared publication - Brian Sadock
Midlands State University
1 shared publication
Latest Publications
- Open Access
- 28 August 2026
- Published by Springer Nature in Discover Data
- Vol. 4 (1) , 17
Advancements in deep learning for early breast cancer detection using artificial intelligence models in low resource settings
- 28 August 2026
- Published by Springer Nature in Discover Data
- Vol. 4 (1) , 17
Open AccessAdvancements in deep learning for early breast cancer detection using artificial intelligence models in low resource settings
- Open Access
- 19 May 2026
- Published by Elsevier in SSRN Electronic Journal
Smart Integrated Drainage Monitoring System for Urban Resilience: An IoT-Based Innovation for Zimbabwean Cities
The rapid urbanization coupled with the aging infrastructure and lack of resources makes drainage management of urban centres in Africa a critical issue. This paper provides the design, implementation, and high-quality assessment of a Smart Integrated Drainage and Sewage Monitoring and Control System (SIDSMCS) customized to the Zimbabwean urban environments. Based on Design Science Research approach, a low-cost IoT solution was built, which combines ESP32 microcontrollers, hybrid communication (Wi-Fi/LoRa/GSM), solar power resiliency, and predictive analytics. The prototype was implemented in 3 high-density locations in Harare in 2023-2024 rainy season. Findings show that there were substantial improvements: response time dropped by 5.2 to 1.5 days (71 percent improvement), 70 percent of possible overflows avoided, 85percent prediction accuracy of blockages, and 73 percent reduction in cost per intervention. Technical evaluation was done thoroughly, consisting of sensor calibration statistics, uncertainty quantification, fault tolerance mechanisms, and economic sensitivity analysis. The proposed system incorporates predictive algorithms and delivers results that match, and in certain respects may surpass, those of smart drainage solutions deployed globally, while operating with drastically reduced resource requirements. This provides empirical evidence that supports the viability of context-specific smart infrastructure in African urban centres.
- 19 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSmart Integrated Drainage Monitoring System for Urban Resilience: An IoT-Based Innovation for Zimbabwean Cities
The rapid urbanization coupled with the aging infrastructure and lack of resources makes drainage management of urban centres in Africa a critical issue. This paper provides the design, implementation, and high-quality assessment of a Smart Integrated Drainage and Sewage Monitoring and Control System (SIDSMCS) customized to the Zimbabwean urban environments. Based on Design Science Research approach, a low-cost IoT solution was built, which combines ESP32 microcontrollers, hybrid communication (Wi-Fi/LoRa/GSM), solar power resiliency, and predictive analytics. The prototype was implemented in 3 high-density locations in Harare in 2023-2024 rainy season. Findings show that there were substantial improvements: response time dropped by 5.2 to 1.5 days (71 percent improvement), 70 percent of possible overflows avoided, 85percent prediction accuracy of blockages, and 73 percent reduction in cost per intervention. Technical evaluation was done thoroughly, consisting of sensor calibration statistics, uncertainty quantification, fault tolerance mechanisms, and economic sensitivity analysis. The proposed system incorporates predictive algorithms and delivers results that match, and in certain respects may surpass, those of smart drainage solutions deployed globally, while operating with drastically reduced resource requirements. This provides empirical evidence that supports the viability of context-specific smart infrastructure in African urban centres.
- Open Access
- 19 March 2026
- Published by Elsevier in SSRN Electronic Journal
Thermal Stability of Alpha-Particle Radiation Induced Defects in Co/n4H-SiC Schottky Barrier Diodes
Cobalt-SiC Schottky barrier diodes have been fabricated and their characteristics were investigated when exposed to alpha radiation. Two new defects with energies, EC – 0.40 eV and EC – 0.65 eV were induced after exposure to alpha radiation. Characteristics such as ideality factor, barrier height, series resistance and carrier concentration change with increasing alpha radiation fluency were determined. DLTS analysis was done and analysis on the plots is included. Increased fluency gave rise to an increase in the peaks to the induced peaks and the inherent peak E0.67 while the other three inherent peaks were suppressed. Isochronal annealing was carried out at 20 minute intervals and 100 oC steps to study the thermal stability of the induced defects. The induced defects were suppressed after annealing at 400 oC showing that the defects are not thermally stable.
- 19 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessThermal Stability of Alpha-Particle Radiation Induced Defects in Co/n4H-SiC Schottky Barrier Diodes
Cobalt-SiC Schottky barrier diodes have been fabricated and their characteristics were investigated when exposed to alpha radiation. Two new defects with energies, EC – 0.40 eV and EC – 0.65 eV were induced after exposure to alpha radiation. Characteristics such as ideality factor, barrier height, series resistance and carrier concentration change with increasing alpha radiation fluency were determined. DLTS analysis was done and analysis on the plots is included. Increased fluency gave rise to an increase in the peaks to the induced peaks and the inherent peak E0.67 while the other three inherent peaks were suppressed. Isochronal annealing was carried out at 20 minute intervals and 100 oC steps to study the thermal stability of the induced defects. The induced defects were suppressed after annealing at 400 oC showing that the defects are not thermally stable.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 23-50
AI-based Diagnostic X-Ray Quality Assurance
The integration of artificial intelligence (AI) in diagnostic X-ray quality assurance (QA) represents a transformative advancement medical imaging. This paper explores the application of AI algorithms in enhancing the accuracy and efficiency of QA processes in X-ray diagnostics. We discuss various AI techniques, including machine learning and deep learning, that automate the assessment of image quality and detect anomalies, thereby reducing the reliance on manual evaluations. The implementation of AI-driven systems not only improves diagnostic accuracy but also streamlines workflows, minimizes radiation exposure, and supports radiologists in clinical decision-making. Challenges such as data quality, algorithm interpretability, and regulatory compliance are also addressed. Our findings suggest that AI-based QA systems can significantly enhance patient outcomes and operational efficiency in diagnostic radiology, paving the way for future innovations in medical imaging.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 23-50
AI-based Diagnostic X-Ray Quality Assurance
The integration of artificial intelligence (AI) in diagnostic X-ray quality assurance (QA) represents a transformative advancement medical imaging. This paper explores the application of AI algorithms in enhancing the accuracy and efficiency of QA processes in X-ray diagnostics. We discuss various AI techniques, including machine learning and deep learning, that automate the assessment of image quality and detect anomalies, thereby reducing the reliance on manual evaluations. The implementation of AI-driven systems not only improves diagnostic accuracy but also streamlines workflows, minimizes radiation exposure, and supports radiologists in clinical decision-making. Challenges such as data quality, algorithm interpretability, and regulatory compliance are also addressed. Our findings suggest that AI-based QA systems can significantly enhance patient outcomes and operational efficiency in diagnostic radiology, paving the way for future innovations in medical imaging.