• Differential evolution optimization algorithms and its application in machine learning based disease detection 

  Egling, Theodore (2024-08-29)

  Machine learning (ML) in healthcare is crucial for establishing and enhancing performant automated disease detection systems that can be used in medical practice. This dissertation aims to improve ML classifiers for disease ...
• Intelligent fault detection technique for distribution network with interconnected distributed generation sources 

  Lafleni, Sipho Pelican (2024-06-05)

  Machine Learning (ML) or Artificial Intelligence (AI) approaches in a distribution protection system are proposed to detect and categorize distribution network (DN) issues with Distribution Generation. This study highlights ...
• Implicit modelling of geometallurgical parameters for application in mine planning 

  Chauke, Tiyani (2023-03)

  The objective of the thesis was two-fold: to investigate the potential of implicit modelling techniques for modelling geometallurgical parameters in mine planning and to generate synthetic geometallurgical data using ...
• Developing a framework for the classification of strategic and critical minerals in South Africa 

  Pule, Dikgwatlhe Israel (2022-12)

  Minerals should be sufficient to sustain security of the nation as well as growth of the economy and employment. Countries without minerals may source minerals from mineral-rich countries. South Africa is endowed with ...
• Developing a framework for the classification of strategic and critical minerals in South Africa 

  Dikgwatlhe, Israel Pule (2022-12)

  Minerals should be sufficient to sustain security of the nation as well as growth of the economy and employment. Countries without minerals may source minerals from mineral-rich countries. South Africa is endowed with ...
• Preventing cryptographic attacks used on the Internet of Things 

  Muthavhine, Khumbelo Difference (2022-05)

  Cryptographic attacks on Internet of Things (IoT) devices are not highly con sidered by the users of IoT. Most cryptographic algorithms commonly used on IoT devices are vulnerable to cryptographic attacks. Cryptography ...
• Incorporation of basaltic aggregates from the Sibasa formation in shotcrete for potential use as support in underground mining 

  Mudau, Vhuhwavho Pertunia (2022-11)

  The use of crushed basalt aggregates as an alternative to sand aggregates is gaining momentum. This is driven by efforts of ensuring sustainable developments in shotcrete production. The main objective of this study ...
• The characterization of the electric double layer capacitor (EDLC) and its application in micro grids using the hybrid energy storage system (HESS) 

  Tshiani, Chrispin, Tumba (2022-08)

  Electrical energy storage is very important. Energy storage devices such as batteries and capacitors can be used to store energy. In this dissertation we investigate the use of a supercapacitor or electric double-layer ...
• Face recognition using improved deep learning neural network 

  Nante, Zukisa Emerson (2022-09)

  In recent years the importance and need for computer vision systems increased due to security demands, self-driving cars, cell phone logins, forensic identification, banks, etc. In security, the idea is to distinguish ...
• Utilasation of locomotive for mid-term energy storage 

  Nqodi, Andile (2020-12)

  The idea of a mid-term energy storage system (ESS) is becoming a popular option for improving the performance of energy conservation, power efficiency and the power grid. The goal of this research is to explore the ...
• Adaptive scheme for improvement of load factor of water heater loads in residential buildings 

  Nonyane, Phillemon (2022-03)

  The South African power utility, Eskom, and, in turn, the metropolitan and local municipalities, have difficulty meeting the country's growing demand for electricity. In this study, electric water heaters have been ...
• Investigation and analysis of premature failure of valve regulated lead acid batteries 

  Mohale, Jan Moses (2021-01-29)

  Over the past fifty years Valve Regulated Lead Acid (VRLA) battery has been deployed with Uninterruptable Power Supplies (UPS) backup systems as a last line of defense against primary power outages, due to its affordability ...
• Assessment of wind power potential as a renewable energy source in Western Cape, South Africa 

  Tshibanda, Mbuyamba (2022)

  The worldwide utilisation of renewable energy in electric power systems is growing rapidly due to concerns about the environment and the depletion of the sources of conventional power generation. The Weibull distribution ...
• Detection and identification of faulty modules in a large-scale photovoltaic installation 

  Yokwana, Xolani Phillip (2020-01)

  The global warming and realisation that fossil fuel is limited, has been a drive over the years to move to renewable energy sources (RES). Consequently, solar energy and other renewable energy sources are currently being ...
• A multiphysics model for the numerical simulation of wet balls mills 

  Nkomo, Fortune (2022-06)

  There exists a need to understand the behaviour of wet mill loads by numerical simulation. However, the challenge is to adequately combine solid-based and liquid-based computer algorithms into one realistic framework. This ...
• Renewable hybrid polygeneration system from various unconventional feedstock 

  Shahid, Hussain Ansari (2021-02)

  The production of low-carbon energy products from biomass gasification is encouraged, in order to expand our sources of energy and to mitigate the harmful impact of the pollutants on the climate and the environment. The ...
• Development of neural network-based speech/non-speech discrimination algorithm for audio files 

  Redelinghuys, Herman (2022-01)

  For research in speech processing and analysis of audio content in general, extensive data sets are required. Creating such a dataset manually turns out to be time and labour consuming, but it is a task very suitable ...
• Classification and severity prediction of maize leaf diseases using Deep Learning CNN approaches 

  Sibiya, Malusi (2021-06)

  Maize (zea mays) is the staple food of Southern Africa and most of the African regions. This staple food has been threatened by a lot of diseases in terms of its yield and existence. Within this domain, it is important ...
• Weather classification from still images using ensemble method 

  Oluwafemi, Ajayi Gbeminiyi (2021-01)

  In the field of computer vision, multi-class outdoor weather classification is a difficult task to perform due to diversity and lack of distinct weather characteristic or features. This research proposed a novel framework ...
• Improving the performance of horizontal axial wind turbines using Bioinspired 

  Nemirini, Tshamano (2021-01-31)

  Small-scale wind turbines were not considered viable in the past due to their poor efficiencies, mainly because of their aerodynamic effects around the irfoil shape. Recently researchers have renewed interest in enhancing ...

View more