Repository logo
 

Faculty of Management Sciences

Permanent URI for this communityhttp://ir-dev.dut.ac.za/handle/10321/13

Browse

Subject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Strategic management accounting practices between developed and emerging economies using machine learning
    (2022-11-11) Almahairah, Mohammad Salameh; Saroha, Vinod Kumar; Asokan, Anju; Umaeswari, P.; Khan, Javed Akhtar; Lourens, Melanie Elizabeth
    Data's function is changing dramatically, but new technologies like machine learning (ML) is also transforming how we can handle and use the data (AI). Nearly astounding are the changes, their pace and scope, and how they affect practically every facet of daily life, including management accounting of course. In this purview, the term "data" refers to business data in its broadest definition. Computers can now learn from experience much like humans and decision-makers do thanks to machine learning (ML). ML and AI for the management accountants have occasionally been considered in the previous 5 to 10 years, despite the fact that these ideas have been applied for a long time in other company disciplines like banking and logistics. Due to the critical role that management accountants play in an organization's success; this study demonstrates the need for greater research on numerous developing technologies in a timely manner. To make more accurate forecasts and enhance reporting and decisionmaking, many firms must use business intelligence and analytics technologies, machine learning algorithms, and Journal of Pharmaceutical Negative Results ¦ Volume 13 ¦ Special Issue 9 ¦ 2022 6318 the Internet of Things. This study explores the effects of new technology on management accountants' abilities to lead business units to success in international marketplaces. It does so by examining, describing, analyzing, and summarizing some of that research.
  • Thumbnail Image
    Item
    The influence of key risk drivers on the performance of SMMEs in the manufacturing sector in KwaZulu-Natal
    (2021-12) Zhou, Helper; Gumbo, Victor
    Small Medium and Micro Enterprises (SMMEs) have been shown to be key contributors to sustainable socio-economic development, constituting more than 90% of private sector enterprises around the world. Inevitably, many developing countries continue to explore means aimed at enhancing the performance of small enterprises. However, despite the implementation of various interventions the failure rate of SMMEs in South Africa particularly KwaZulu-Natal (KZN) is disturbing, reaching up to 80% in the first year of operation. As such, to contribute to addressing this challenge, the study adopted a novel approach to establishing and modelling manufacturing SMMEs performance drivers. Utilising a unique three-year panel dataset, key risk drivers were established and modelled via R software version 3.6.3. To achieve the study objectives, a series of independent but related papers were carried out and these make up the main chapters of this thesis. The first chapter provided the background to the study. The second chapter explored the characteristics of manufacturing SMMEs based in KZN province. The findings showed the complexity of firm performance, indicating the heterogeneity between rural and urban based SMMEs. The next chapter, harnessing Stochastic theory aimed to establish whether SMMEs’ growth performance followed a random walk. The theoretical model was rejected, thus providing a basis for the claim that firm performance is a function of certain risk drivers. Armed with findings from the previous papers, the investigation of key drivers impacting the sales and growth performance of manufacturing SMMEs ensued. The fourth chapter, harnessing the Penrosian and strategic management theories established key drivers of SMMEs’ performance. The fifth chapter concerningly, revealed that SMME owners in the manufacturing sector are largely not aware of the impact of established drivers on their enterprises’ performance. In the next chapter, a total of five machine learning algorithms were evaluated of which Artificial Neural Network and Support Vector Machines were identified as the best algorithms for SMME sales and growth predictive modelling, respectively. The two algorithms informed the development of a dedicated machine learning application for SMMEs that’s being commercialised through the DUT Technology Transfer and Innovation Directorate.
  • Thumbnail Image
    Item
    A review of physiological signal processing via Machine Learning (ML) for personal stress detection
    (IEEE, 2022-04-28) Lourens, Melanie Elizabeth; Beram, Shehab Mohamed; Borah, Bidyut Bikash; Dube, Anand Prakash; Deka, Aniruddha; Tripathi, Vikas
    Personal stress is maintained and measured by Machine learning. The device which is wearable has been used for the monitoring of personal self stress and data collection. In this research, it has been talked about the factors by which the physiological signal of the stress has been assessed. On the other hand, different type of technology has been used for the detection of the personal stress such as Electrocardiography (ECG) and many other devices. The observation and difficulties has been seen in this research by using this device and the technology. Stress disorder or ailment is one of the most common ailments in all individuals around the world. Stress and anxiety can greatly influence the life, emotion, behavioural pattern and thinking attributes of individuals. It is important to address this issue sooner or later. Psychological signal processing through machine learning effectively assists to detect the stress disorder at an early stage. The general system often considers some variables to detect stress. They are electrocardiogram, galvanic response, heart rate, respiration and many other elements. The ML tend to use algorithms to compare and contrast data to fetch effective e results. The paper has also carried out a statistical analysis based on three variables to fetch a proper result that provided the study group to comprehend a better understanding of the scenario. The researchers have taken the 'percentage of stress rate' cases' are considered independent variables whereas 'usage of a machine learning system' is considered a dependant variable. The study group has fetched and collected numerous data related to these three variables to get a better understanding.
  • Thumbnail Image
    Item
    Role of machine learning in managing cloud computing security
    (IEEE, 2022-04-28) Kumar, Santosh; S, Nithya; Prethi, K.N. Apinaya; Singh, Suraj; Lourens, Melanie; Patil, Nisha
    Cloud computing is one of the most trending technology through which digitalized data management and storing becomes easier and more effective. However, besides the advancement of technology, data protection is another top priority concerning factor as millions of sensitive data are gets stored and transferred through the cloud computing system. As per the current days of cyber-activities, data security threat in cloud computing have increased, which posses threat in the development of the business. In that field, machine learning based advanced algorithm develop the virtual encrypted environment to protect the data from unauthorized access and hacking.