Harry Mafukidze

Harry Mafukidze


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
3 October 2022 in IEEE Access
Verified
Journal Article
Open access
HMHarry Mafukidze
Harry Mafukidze
AMAmit Kumar Mishra
Amit Kumar Mishra
JPJan Pidanic
Jan Pidanic
SFSchonken W. P. Francois
Schonken W. P. Francois
Recently, mmWave radars have been gaining popularity, thanks to their low cost, ease of use and high-resolution sensing. In this paper, we provide a review of the mmWave radar data processing frameworks, starting from mathematical foundations to applications. Specifically, we focus on the mmWave radar point cloud as a robust data structure representing compressed signatures for target recognition and classification. We first focus on the generation of the radar point clouds, and the signal processing algorithms designed for their unique characteristics. Then, we illustrate how the radar point clouds are prepared for feature extraction and classification using machine learning and deep learning approaches. Finally, we summarize the state-of-the-art applications, open datasets, developments and future research directions in this field.

23 August 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HMHarry Mafukidze
Harry Mafukidze
GOGodliver Owomugisha
Godliver Owomugisha
DODaniel Otim
Daniel Otim
ANAction Nechibvute
Action Nechibvute
CNCloud Nyamhere
Cloud Nyamhere
FMFelix Mazunga
Felix Mazunga
Convolutional neural networks (CNNs) are the gold standard in the machine learning (ML) community. As a result, most of the recent studies have relied on CNNs, which have achieved higher accuracies compared with traditional machine learning approaches. From prior research, we learned that multi-class image classification models can solve leaf disease identification problems, and multi-label image classification models can solve leaf disease quantification problems (severity analysis). Historically, maize leaf disease severity analysis or quantification has always relied on domain knowledge—that is, experts evaluate the images and train the CNN models based on their knowledge. Here, we propose a unique system that achieves the same objective while excluding input from specialists. This avoids bias and does not rely on a “human in the loop model” for disease quantification. The advantages of the proposed system are many. Notably, the conventional system of maize leaf disease quantification is labor intensive, time-consuming and prone to errors since it lacks standardized diagnosis guidelines. In this work, we present an approach to quantify maize leaf disease based on adaptive thresholding. The experimental work of our study is in three parts. First, we train a wide variety of well-known deep learning models for maize leaf disease classification, then we compare the performance of the deep learning models and finally extract the class activation heatmaps from the prediction layers of the CNN models. Second, we develop an adaptive thresholding technique that automatically extracts the regions of interest from the class activation maps without any prior knowledge. Lastly, we use these regions of interest to estimate image leaf disease severity. Experimental results show that transfer learning approaches can classify maize leaf diseases with up to 99% accuracy. With a high quantification accuracy, our proposed adaptive thresholding method for CNN class activation maps can be a valuable contribution to quantifying maize leaf diseases without relying on domain knowledge.

16 July 2024 in IEEE Access
Verified
Journal Article
Open access
HMHarry Mafukidze
Harry Mafukidze
ANAction Nechibvute
Action Nechibvute
AYAbid Yahya
Abid Yahya
IBIrfan Anjum Badruddin
Irfan Anjum Badruddin
SKSarfaraz Kamangar
Sarfaraz Kamangar
MHMohamed Hussien
Mohamed Hussien
Over the last decade, Data Science has emerged as one of the most important subjects that has had a major impact on industry. This is due to the continual development of scientific methods, algorithms, processes, and computational tools that help to extract knowledge from raw data efficiently and cost-effectively, compared with early-generation tools. Professional data scientists create code that processes, analyses and extracts actionable insights from high volumes of data. This process requires a deep understanding of mathematical principles, statistics, business knowledge, and computer science. But most importantly, the data science development chain requires knowledge of a high-level programming tool and its dependencies. This is a major problem in some aspects due to the steep learning curve. In this paper, we describe and present a modularized Data Science curriculum for undergraduate learners that relies on no-code software development tools as programming aids for non-computer science majors. No-code development tools have been added to the traditional teaching pedagogy to improve students’ motivation and conceptual understanding of coding despite their limited programming skills. The study aims to assess the impacts of visual programming languages on the performance of non-computer science majors on programming problems. The study’s sample consists of 50 fourth-year students from the Faculty of Science and Technology at the Midlands State University. A post-survey questionnaire and assessment items were administered to the control and experimental groups. Results show that the students drawn from the experimental group benefited from the use of a visual programming language. These results offer evidence-based recommendations for incorporating high-performance no-code software development tools in the formal curriculum to aid teaching and learning data science programming for students of diverse academic backgrounds.