Recently added

Research Articles (Computer Science): Recent submissions

  • Understanding issues and challenges of DFR implementation in SDN platform 
    Munkhondya, Howard; Ikuesan, Richard Adeyemi; Singh, Avinash; Venter, H.S. (Hein) (Elsevier, 2023)
    Software-Defined Networking (SDN) is an evolutionary networking paradigm that offers simplified and agile network configuration and management capabilities. However, embracing this new and futuristic paradigm requires the ...
  • The effect of deep learning methods on deepfake audio detection for digital investigation 
    Mcuba, Mvelo; Singh, Avinash; Ikuesan, Richard Adeyemi; Venter, H.S. (Hein) (Elsevier, 2023)
    Voice cloning methods have been used in a range of ways, from customized speech interfaces for marketing to video games. Current voice cloning systems are smart enough to learn speech characteristics from a few samples and ...
  • A study of ant-based pheromone spaces for generation constructive hyper-heuristics 
    Singh, Emilio; Pillay, Nelishia (Elsevier, 2022-07)
    Research into the applicability of ant-based optimisation techniques for hyper-heuristics is largely limited. This paper expands upon the existing body of research by presenting a novel ant-based generation constructive ...
  • Memory requirements for the detection of impostor nodes in wireless sensor networks 
    Gruner, Stefan; Krajnc, Dylan; Van Rooyen, Johan Pieter (EasyChair, 2022)
    This paper shows how it is at least in principle possible to detect impostor nodes in wireless sensor networks with a quite simplistic detection algorithm by purely statistical means and merely from external observation ...
  • Classifying social media bots as malicious or benign using semi-supervised machine learning 
    Mbona, Innocent; Eloff, Jan H.P. (Oxford University Press, 2023)
    Users of online social network (OSN) platforms, e.g. Twitter, are not always humans, and social bots (referred to as bots) are highly prevalent. State-of-the-art research demonstrates that bots can be broadly categorized ...
  • A harmonized information security taxonomy for cyber physical systems 
    Pool, Johannes Hendrik; Venter, H.S. (Hein) (MDPI, 2022-08-12)
    Cyber physical systems (CPSs) are found in many aspects of daily life, and they control and protect energy production, manufacturing and even healthcare. Due to long lifecycles and the use of legacy technologies, its ...
  • Automated design of the deep neural network pipeline 
    Gerber, Mia; Pillay, Nelishia (MDPI, 2022-11-29)
    Deep neural networks have proven to be effective in various domains, especially in natural language processing and image processing. However, one of the challenges associated with using deep neural networks includes the ...
  • Post-authorship attribution using regularized deep neural network 
    Modupe, Abiodun; Celik, Turgay; Marivate, Vukosi; Olugbara, Oludayo O. (MDPI, 2022-07-26)
    Post-authorship attribution is a scientific process of using stylometric features to identify the genuine writer of an online text snippet such as an email, blog, forum post, or chat log. It has useful applications in ...
  • Semi-supervised learning approaches for predicting South African political sentiment for local government elections 
    Ledwaba, Mashadi; Marivate, Vukosi (Association for Computing Machinery (ACM), 2022-06)
    This study aims to understand the South African political context by analysing the sentiments shared on Twitter during the local government elections. An emphasis on the analysis was placed on understanding the discussions ...
  • An application of CNN to classify barchan dunes into asymmetry classes 
    Van der Merwe, Barend Jacobus; Pillay, Nelishia; Coetzee, Serena Martha (Elsevier, 2022-06)
    Barchan morphometric data have been used as proxies of meteorological and topographical data in environments where this data is lacking (such as other planetary bodies), gaining insights into barchan dune field dynamics ...
  • Particle swarm optimization-based empirical mode decomposition predictive technique for nonstationary data 
    Kuranga, Cry; Ranganai, Njodzi; Muwani, Tendai S. (Springer, 2022-12)
    Real-world nonstationary data are usually characterized by high nonlinearity and complex patterns due to the effects of different exogenous factors that make prediction a very challenging task. An ensemble strategically ...
  • Data curation during a pandemic and lessons learned from COVID-19 
    Kraemer, Moritz U.G.; Scarpino, Samuel V.; Marivate, Vukosi; Gutierrez, Bernardo; Xu, Bo; Lee, Graham; Hawkins, Jared B.; Rivers, Caitlin; Pigott, David M.; Katz, Rebecca; Brownstein, John S. (Nature Research, 2021-01)
    Detailed, accurate data related to a disease outbreak enable informed public health decision making. Given the variety of data types available across different regions, global data curation and standardization efforts are ...
  • Supplementary-architecture weight-optimization neural networks 
    O’Reilly, Jared; Pillay, Nelishia (Springer, 2022-07)
    Research efforts in the improvement of artificial neural networks have provided significant enhancements in learning ability, either through manual improvement by researchers or through automated design by other artificial ...
  • Secure storage model for digital forensic readiness 
    Singh, Avinash; Ikuesan, Richard Adeyemi; Venter, H.S. (Hein) (Institute of Electrical and Electronics Engineers, 2022-02)
    Securing digital evidence is a key factor that contributes to evidence admissibility during digital forensic investigations, particularly in establishing the chain of custody of digital evidence. However, not enough is ...
  • Detecting zero-day intrusion attacks using semi-supervised machine learning approaches 
    Mbona, Innocent; Eloff, Jan H.P. (Institute of Electrical and Electronics Engineers, 2022-06-29)
    Recently, network intrusion attacks, particularly new unknown attacks referred to as zero-day attacks, have become a global phenomenon. Zero-day network intrusion attacks constitute a frequent cybersecurity threat, as they ...
  • Discriminatory Gleason grade group signatures of prostate cancer : an application of machine learning methods 
    Mokoatle, Mpho; Mapiye, Darlington; Marivate, Vukosi; Hayes, Vanessa M.; Bornman, Maria S. (Riana) (Public Library of Science, 2022-06-09)
    One of the most precise methods to detect prostate cancer is by evaluation of a stained biopsy by a pathologist under a microscope. Regions of the tissue are assessed and graded according to the observed histological ...
  • Deep learning diagnostics of gray leaf spot in maize under mixed disease field conditions 
    Craze, Hamish A.; Pillay, Nelishia; Joubert, Fourie; Berger, David Kenneth (MDPI, 2022-07-26)
    Maize yields worldwide are limited by foliar diseases that could be fungal, oomycete, bacterial, or viral in origin. Correct disease identification is critical for farmers to apply the correct control measures, such as ...
  • Digital forensic readiness in operational cloud leveraging ISO/IEC 27043 guidelines on security monitoring 
    Makura, Sheunesu M.; Venter, H.S. (Hein); Kebande, Victor Rigworo; Karie, Nickson M; Ikuesan, Richard A; Alawadi, Sadi (Wiley, 2021-05)
    An increase in the use of cloud computing technologies by organizations has led to cybercriminals targeting cloud environments to orchestrate malicious attacks. Conversely, this has led to the need for proactive approaches ...
  • Methods for speeding up recommender system computations using a graph database 
    Lutu, P.E.N. (Patricia Elizabeth Nalwoga) (Newswood Limited, 2021-07)
    Recommender systems are commonly used for Internet-based activities to assist users in making decisions on what items to select. One very common use of recommender systems is in electronic commerce purchases. The need for ...
  • Conceptual model for crowd-sourcing digital forensic evidence 
    Baror, S.O. (Stacey); Venter, H.S. (Hein); Kebande, Victor Rigworo (Springer, 2022-03)
    COVID-19 scourge has made it challenging to combat digital crimes due to the complexity of attributing potential security incidents to perpetrators. Existing literature does not accurately pinpoint relevant models/frameworks ...