Ernest Mnkandla

Prof. Ernest Mnkandla

orcid

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
3 February 2020 in IEEE Access
Verified
Journal Article
Open access
SMSibonile Moyo
Sibonile Moyo
Ernest MnkandlaErnest Mnkandla
Ernest Mnkandla
The diffusion of software into all areas of life and all forms of business, increases the demand for high-quality and secure software products. Software development methodologies are designed to improve the quality of software by incorporating practices that promote quality in the developed software. Software security is an important facet of software quality, particularly in this era, where most software is deployed for use over the Internet. Most research on developing high-quality and secure software is normally focused on teams at the expense of individual developers. In trying to fill this gap, in this paper we propose an agile secure-software development methodology. We design a methodology that promotes quality and security in the software products of solo developers. We integrate quality practices with lightweight security practices to produce agile secure software development practices. We draw quality practices from a solo software development framework designed in our previous study, while security practices are drawn from existing lightweight methodologies. We adapt Keramati and Mirian-Hosseinabadi’s algorithm to integrate the two sets of practices, taking care to maintain an optimum degree of agility in the target methodology. We evaluate the utility of the resultant methodology through a case study. Results from the case study show that our proposed methodology can be used to build quality and secure software products without compromising the agility of the methodology.

1 October 2006
Verified
Conference Paper
Closed access
Ernest MnkandlaErnest Mnkandla
Ernest Mnkandla
BDB. Dwolatzky
B. Dwolatzky

1 September 2009
Verified
Conference Paper
Closed access
Ernest MnkandlaErnest Mnkandla
Ernest Mnkandla
Defining software engineering can be a rather challenging task depending on the purpose of the definition and the intended beneficiaries. Talking about frameworks and methodologies in software engineering can be even more complex under whatever circumstances due to the many different ways in which the issues concerning frameworks, processes, approaches and methodologies have been handled. This paper explores software engineering frameworks and methodologies and related topics. The purpose of this study is to add further understanding in the area of software engineering frameworks and methodologies. Data from published literature is analysed to establish a position on the status of software engineering frameworks and methodologies. The fundamental questions to consider here are; what kind of benefits can be derived from a better understanding of these issues? Would a better understanding of frameworks and methodologies improve the way we design, develop, implement, maintain and use information systems?

22 May 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
DMDonatien Koulla Moulla
Donatien Koulla Moulla
ASAttipoe David Sena
Attipoe David Sena
Ernest MnkandlaErnest Mnkandla
Ernest Mnkandla
Alain AbranAlain Abran
Alain Abran
The recurrent load shedding crisis in South Africa has highlighted the need to accurately predict electricity consumption for residential buildings. This has significant ramifications for daily life and economic productivity. To address this challenge, this study leverages machine learning models to predict the hourly energy consumption of residential buildings in South Africa. This study evaluates the performance of various regression techniques, including Random Forest (RF), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) machine learning models, using a national residential dataset that contains measurements collected every hour. The objective is to determine the most effective models for predicting next-hour residential building consumption. These models use historical patterns of energy usage to capture temporal details such as seasonal variations and rolling averages. Feature engineering methods are further employed to enhance their predictive capabilities. The performance of each individual model was evaluated using criteria such as the mean squared error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2). The results show that both RF and DT achieve the best accuracy for the prediction of residential electricity consumption (because the MSE, MAE, and MAPE for RF and DT are very close to 0). These findings offer actionable insights for households, businesses, and policymakers. By enabling more accurate and granular energy consumption forecasts, this can mitigate the effects of load shedding. This study contributes to the discourse on sustainable energy management by combining advanced machine learning models with real-world energy challenges.

24 July 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ETElias Tabane
Elias Tabane
Ernest MnkandlaErnest Mnkandla
Ernest Mnkandla
ZWZenghui Wang
Zenghui Wang
This study addresses the performance of deep learning models for predicting human DNA sequence classification through an exploration of ideal feature representation, model architecture, and hyperparameter tuning. It contrasts traditional machine learning with advanced deep learning approaches to ascertain performance with respect to genomic data complexity. A hybrid network combining long short-term memory (LSTM) and convolutional neural networks (CNN) was developed to extract long-distance dependencies as well as local patterns from DNA sequences. The hybrid LSTM + CNN model achieved a classification accuracy of 100%, which is significantly higher than traditional approaches such as logistic regression (45.31%), naïve Bayes (17.80%), and random forest (69.89%), as well as other machine learning models such as XGBoost (81.50%) and k-nearest neighbor (70.77%). Among deep learning techniques, the DeepSea model also accounted for good performance (76.59%), while others like DeepVariant (67.00%) and graph neural networks (30.71%) were relatively lower. Preprocessing techniques, one-hot encoding, and DNA embeddings were mainly at the forefront of transforming sequence data to a compatible form for deep learning. The findings underscore the robustness of hybrid structures in genomic classification tasks and warrant future research on encoding strategy, model and parameter tuning, and hyperparameter tuning to further improve accuracy and generalization in DNA sequence analysis.

1 August 2007
Verified
Conference Paper
Closed access
Ernest MnkandlaErnest Mnkandla
Ernest Mnkandla
BDB. Dwolatzky
B. Dwolatzky
Agile methodologies have been in the software development scene for more than five years and this has resulted in the proliferation of a number of approaches to this new way of developing software. The initial agile problems were mainly focused on the definition of what agile methodologies are all about and empirical evidence of their successful application. Today one of the most formidable challenges is selecting appropriate agile processes for a given project and the next problem that some practitioners are already faced with is agile certification. This paper presents a selection tool that picks the agile practices relevant to a given environment. The activities that relate to each practice are used to classify the practices into either technical or social. The authors believe that all practices can be classified into technical and social oriented activities. The technical practices are those that relate to design coding and testing and the social practices relate to people issues. The practices are analyzed to this detail in order to simplify the tailoring process. In this case the environment is then viewed from the perspective of technical and social issues and it becomes easier to identify possible things that could be done to tailor the agile practices. The tool is a simple application that can be used with other project planning tools on any PC. This is part of further work based on one of the authors' PhD work. The additions include the development of a computer program to implement the tool.