Recently added

Theses and Dissertations (Computer Science): Recent submissions

  • Interpretable machine learning in natural language processing for misinformation data 
    Nkalashe, Yolanda (University of Pretoria, 2022-11)
    The interpretability of models has been one of the focal research topics in the machine learning community due to a rise in the use of black box models and complex state-of-the-art models [6]. Most of these models are ...
  • South African isiZulu and siSwati news corpus creation, annotation and categorisation 
    Madodonga, Andani (University of Pretoria, 2022)
    South Africa has eleven official languages and amongst the eleven languages only 9 languages are local low-resourced languages. As a result, it is essential to build the resources for these languages so that they can ...
  • BantuBERTa : using language family grouping in multilingual language modeling for Bantu languages 
    Parvess, Jesse (University of Pretoria, 2023)
    It was researched whether a multilingual Bantu pretraining corpus could be created from freely available data. Here, to create the dataset, Bantu text extracted from datasets that are freely available online (mainly from ...
  • Ukhetho : A Text Mining Study Of The South African General Elections 
    Moodley, Avashlin (University of Pretoria, 2019)
    The elections in South Africa are contested by multiple political parties appealing to a diverse population that comes from a variety of socioeconomic backgrounds. As a result, a rich source of discourse is created to ...
  • Dynamic multi-objective optimization for financial markets 
    Atiah, Frederick Ditliac (University of Pretoria, 2019)
    The foreign exchange (Forex) market has over 5 trillion USD turnover per day. In addition, it is one of the most volatile and dynamic markets in the world. Market conditions continue to change every second. Algorithmic ...
  • Genetic Programming Approach for Nonstationary Data Analytics 
    Kuranga, Cry (University of Pretoria, 2021-02-16)
    Nonstationary data with concept drift occurring is usually made up of different underlying data generating processes. Therefore, if the knowledge of the existence of different segments in the dataset is not taken into ...
  • Informed e-Consent Framework for Privacy Preservation in South African Health Information Systems 
    Zazaza, Lelethu (University of Pretoria, 2020)
    The South African Constitution advocates the protection of personal information. Everyone has the right to privacy. This includes the protection of special information that relates to an individual’s biometrics, health, ...
  • Unsupervised Anomaly Detection of Healthcare Providers using Generative Adversarial Network 
    Naidoo, Krishnan (University of Pretoria, 2021)
    Healthcare fraud is considered a challenge for many societies. Healthcare funding that could be spent on medicine, care for the elderly or emergency room visits is instead lost to fraudulent activities by medical practitioners ...
  • A machine learning approach to detect insider threats in emails caused by human behaviour 
    Michael, Antonia (University of Pretoria, 2020)
    In recent years, there has been a significant increase in insider threats within organisations and these have caused massive losses and damages. Due to the fact that email communications are a crucial part of the modern-day ...
  • Retention Length and Memory Capacity of Recurrent Neural Networks 
    Pretorius, Abraham Daniel (University of Pretoria, 2020)
    Recurrent Neural Networks (RNNs) are variants of Neural Networks that are able to learn temporal relationships between sequences presented to the neural network. RNNs are often employed to learn underlying relationships ...
  • Regularised feed forward neural networks for streamed data classification problems 
    Ellis, Mathys (University of Pretoria, 2020)
    Streamed data classification problems (SDCPs) require classifiers with the ability to learn and to adjust to the underlying relationships in data streams, in real-time. This requirement poses a challenge to classifiers, ...
  • Selection Hyper-heuristics for Population-based Meta-heuristics in Continuous Dynamic Environments 
    Van der Stockt, Stefan Aloysius Gert (University of Pretoria, 2019)
    Dynamic optimization problems provide a challenge in that optima have to be tracked as the environment changes. The complexity of a dynamic optimization problem is determined by the severity and frequency of changes, as ...
  • A Digital Forensic Readiness Approach for Ransomware Forensics 
    Singh, Avinash (University of Pretoria, 2019)
    Computers play a vital role in the automation of tedious tasks in our everyday lives. With the adoption of the advances in technology, there is a significant increase in the exploitation of security vulnerabilities, ...
  • Optimized Security-aware VM placement algorithm 
    Thulo, Motlatsi Isaac (University of Pretoria, 2019)
    The rapidly increasing dependency on use of clouds results in Cloud Service Providers (CSPs) having to deal with high cloud services demands. To meet these demands, CSPs take advantage of virtualization technology to provide ...
  • Digital forensic readiness for IOT devices 
    Kruger, Jaco-Louis (University of Pretoria, 2019)
    The Internet of Things (IoT) has evolved to be an important part of modern society. IoT devices can be found in several environments such as smart homes, transportation, the health sector, smart cities and even facilitates ...
  • Combating Data Leakage in the Cloud 
    Dlamini, Moses Thandokuhle (University of Pretoria, 2020)
    The increasing number of reports on data leakage incidents increasingly erodes the already low consumer confidence in cloud services. Hence, some organisations are still hesitant to fully trust the cloud with their ...
  • Cone normal stepping 
    Burger, Divan Desmond (University of Pretoria, 2018)
    This dissertation examines several methods of relief mapping, such as parallax mapping and cone step mapping, as well as methods for soft shadowing and ambient occlusion of relief maps. Ambient occlusion is an approximation ...
  • Forensic attribution challenges during forensic examinations of databases 
    Hauger, Werner Karl (University of Pretoria, 2018)
    An aspect of database forensics that has not yet received much attention in the academic research community is the attribution of actions performed in a database. When forensic attribution is performed for actions executed ...
  • A new dialect of SOFL-Syntax formal semantics and tool support 
    van der Berg, Johan Sarel (University of Pretoria, 2018)
    Structured Object Orientated Formal Language (SOFL) is a formal method design methodology that combines data flows diagrams and predicates in order to describe processes that can be refined. This methodology creates a very ...
  • Fast Data Analysis Methods For Social Media Data 
    Nhlabano, Valentine Velaphi (University of Pretoria, 2018-08-07)
    The advent of Web 2.0 technologies which supports the creation and publishing of various social media content in a collaborative and participatory way by all users in the form of user generated content and social networks ...