Repository logo
 

Faculty of Accounting and Informatics

Permanent URI for this communityhttp://ir-dev.dut.ac.za/handle/10321/1

Browse

Author: search.filters.author.Mbangata, LubabaloHas files: Yes

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Integration of an autoencoder model with an actor-oriented system
    (Advances in Artificial Intelligence and Machine Learning, 2024) Dyubele, Sithembiso; Cele, Noxolo Pretty; Mbangata, Lubabalo
    Traditional machine learning frameworks often struggle with scalability, modularity, and efficient resource management, especially when dealing with vast data. Actor-Oriented Systems offer a robust framework for building such scalable systems, allowing concurrent processing and efficient handling of large datasets. This study investigated the integration of Autoencoders (AE), which are pivotal in unsupervised learning, with Actor-Oriented Systems to enhance the modularity, scalability, and maintainability of the model training process. The study seeks to leverage the capabilities of AE and Actor-Oriented Systems to achieve high-quality image reconstruction and efficient processing. The study also attempted to understand the underlying patterns in the data, assess the performance of the model, and demonstrate the benefits of modular and scalable systems. Key findings from the results showed significant improvements in training efficiency and performance of the model, especially when using Actor-Oriented Systems. The training time was reduced from 16.96 seconds to 14.21 seconds, and the validation loss improved from 0.2768 to 0.2100, indicating better generalisation and learning. Data augmentation techniques further enhanced the robustness of the model, leading to more accurate reconstructions of the test images. Actor-Oriented Systems facilitated concurrent processing, improved modularity, and enabled the system to scale efficiently with increasing data volume. This study also highlighted the practical benefits of integrating AE with Actor-Oriented Systems, providing valuable insights into building more robust, maintainable, and scalable machine learning workflows.
  • Thumbnail Image
    Item
    Computing departments' academics' perceptions on the impact of Learning and Management Systems on academic performance
    (2019) Mbangata, Lubabalo; Obono, S. D. Eyono
    There are currently more than 500 commercial e-Learning software packages and 300 educational e-Learning software packages, but the surprising fact is that academic failure remains high in universities, especially for first-year students, despite all these advances made by e-Learning. It is this high failure rate problem in this e-Learning era that is at the core of this study whose aim is to model factors affecting the perceptions of academics on the impact of learning management systems (LMSs) on academic performance. This aim will be achieved by following the research question: what are the factors that are affecting the perceptions of academics on the impact of learning management systems on academic performance? Three types of research objectives are used to achieve this aim, namely: (i) to design a theoretically sound model of the factors affecting the perceptions of academics on the impact of LMSs on academic performance. (ii) to empirically test the designed model. (iii) to suggest recommendations on how to improve the perceptions of academics on the impact of LMSs on academic performance. Objectives (i) was accomplished through a content analysis method of reviewing of existing appropriate literature of factors that are affecting the impact of LMSs on e- Learning context; whilst objective (ii) was met by conducting a survey of seventy-eight (78) academic staffs from four public universities of KwaZulu-Natal province of South Africa. On the other hand, objective (iii) was met through a comparison of the results of the survey conducted against the literature analysed. The outcomes of these three objectives are as follows: (i) the Welberg’s theory of education, the self-determination theory, the self-regulated learning theory, the social constructivism theory, and the task technology fit theory can be used as suitable theories applicable to examine the perceived impact of e-Learning on academic performance. (ii) It makes logic to theorize that, on the one hand, academics’ perceived impact of LMSs on academic performance are indirectly affected by their gender, their type of employment and their ethnicity. On the other hand, academics’ attitude towards e-Learning, their computer self-efficacy, their pedagogical beliefs, and their use of LMSs directly affects their perceived impact of LMSs on academic performance of students. It can be concluded that academics’ perceived impact of LMSs on academic performance can be enhanced by optimising academics’ computer self-efficacy, their pedagogical beliefs, and their attitude towards LMSs.