Research Publications/Outputs

Permanent URI for this community

http://hdl.handle.net/10204/11481

Browse

Browsing Research Publications/Outputs by browse.metadata.impactarea "Artificial Intelligence & Ext Reality"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Beyond reality: An application of extended reality and blockchain in the metaverse
    (2023-07) Moodley, Jayandren; Meiring, Gys AM; Mtetwa, Njabulo S; Motuba, Obakeng M; Mphephu, Mutali; Maluleke, Mikateko SG; Balmahoon, Reevana
    The convergence of Fourth Industrial Revolution (4IR) technologies and Web2 to Web3 transformation, presents significant benefits and opportunities for industry. This study explores the integrated benefits of Extended Reality (XR) and Distributed Ledger Technology (DLT) in a Metaverse application for virtual consulting. Since XR enhances collaboration using visualization, and DLT ensures transactional security and privacy, an overview of XR and DLT technology is provided, highlighting their specific benefits and challenges concerning Remote Health and Wellness consulting. The paper proposes a Metaverse solution to leverage these benefits, enabling more affordable and accessible healthcare consulting in developing economies. A key outcome of the research is to develop a metaverse prototype that bridges the gap between Web 2.0 and Web 3.0 technologies. By doing so, it aims to improve usability for end-users, drive the adoption of XR and Blockchain, generate new business models, and unlock new revenue streams for industry and underserved communities.
  • Thumbnail Image
    Item
    Plant seedling classification using machine learning
    (2022-08) Khoza, Nokuthula G; Khosa, Marshal V; Mahlangu, Thabo V; Ndlovu, Nkosinathi
    Precision agriculture is a farming approach that uses artificial intelligence and information technology to improve crop yield, preserve the environment and maximize profits. Farmers need to follow precision agriculture to improve their crop quality and production. Weed control is one of the challenges that agriculture faces. The growth of weed leads to a decrease in crop yield and to prevent that, weed must be identified and achieved earlier to avoid the adverse effects on the crops. Applying deep learning techniques has become an important field of study in precision agriculture. In this paper, we presented two deep learning models to classify crops and weeds in their early growth stages. From the comparison of the two models ResNet50 and MobileNetV2, MobileNetV2 with 500×500 pixel size gave the best performing results with average f1-score of 88% and accuracy score of 88% which shows that this deep learning model can successfully classify 12 segmented plant seedlings in their early growth stages and this tool can be useful to farmers in identifying weeds