4. Electronic Theses and Dissertations (ETDs) - Faculties submissions

Permanent URI for this communityhttps://hdl.handle.net/10539/37773

Browse

Has files: YesSubject: search.filters.subject.Algorithms

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Predicting in-hospital mortality in heart failure patients using machine learning
    (University of the Witwatersrand, Johannesburg, 2023-05) Mpanya, Dineo; Ntsinjana, Hopewell
    The age of onset and causes of heart failure differ between high-income and low-and-middle-income countries (LMIC). Heart failure patients in LMIC also experience a higher mortality rate. Innovative ways that can risk stratify heart failure patients in this region are needed. The aim of this study was to demonstrate the utility of machine learning in predicting all-cause mortality in heart failure patients hospitalised in a tertiary academic centre. Six supervised machine learning algorithms were trained to predict in-hospital all-cause mortality using data from 500 consecutive heart failure patients with a left ventricular ejection fraction (LVEF) less than 50%. The mean age was 55.2 ± 16.8 years. There were 271 (54.2%) males, and the mean LVEF was 29 ± 9.2%. The median duration of hospitalisation was 7 days (interquartile range: 4–11), and it did not differ between patients discharged alive and those who died. After a prediction window of 4 years (interquartile range: 2–6), 84 (16.8%) patients died before discharge from the hospital. The area under the receiver operating characteristic curve was 0.82, 0.78, 0.77, 0.76, 0.75, and 0.62 for random forest, logistic regression, support vector machines (SVM), extreme gradient boosting, multilayer perceptron (MLP), and decision trees, and the accuracy during the test phase was 88, 87, 86, 82, 78, and 76% for random forest, MLP, SVM, extreme gradient boosting, decision trees, and logistic regression. The support vector machines were the best performing algorithm, and furosemide, beta-blockers, spironolactone, early diastolic murmur, and a parasternal heave had a positive coefficient with the target feature, whereas coronary artery disease, potassium, oedema grade, ischaemic cardiomyopathy, and right bundle branch block on electrocardiogram had negative coefficients. Despite a small sample size, supervised machine learning algorithms successfully predicted all-cause mortality with modest accuracy. The SVM model will be externally validated using data from multiple cardiology centres in South Africa before developing a uniquely African risk prediction tool that can potentially transform heart failure management through precision medicine.
  • Thumbnail Image
    Item
    A thematic synthesis of ethics principles in artificial intelligence
    (University of the Witwatersrand, Johannesburg, 2024) Oberholzer , Joanna
    In an era marked by rapid advancements in artificial intelligence (AI), the ethical dimensions of AI development and deployment have become increasingly pivotal. As AI technologies permeate diverse sectors, the need for a comprehensive understanding of the ethical principles governing their use has intensified. This research employs reflective thematic analysis to scrutinise the ethical landscape of AI, to discern consensus among stakeholders and evaluate the practicality of implementing ethical principles. Leveraging the critical-systems-heuristics framework, the study explores implicit assumptions, power dynamics, and contextual intricacies for a nuanced analysis. Data from 156 entities form the basis for a qualitative thematic synthesis, revealing motivations, control mechanisms, knowledge sources, and legitimacy factors guiding AI-ethical principles. Key findings spotlight the prevalence of ethics documents in the private sector, driven by market competition, corporate social responsibility, regulatory compliance, and stakeholder expectations. Europe and North America have emerged as leaders in document publication, reflecting their technological prowess. Government agencies uniquely emphasise transparency. Variations in prioritised principles across stakeholders unveil distinct motivations aligned with organisational goals. Challenges impeding AI-ethics implementation encompass vague principles, global regulatory disparities, data-privacy concerns, and resource limitations. The study unravels worldviews which shape AI ethics, with private organisations valuing human-centricity, accountability, and legitimacy through representation and consensus. The outcomes contribute theoretical insights and practical recommendations, guiding the responsible development of AI technologies.
  • Thumbnail Image
    Item
    Algorithmic pricing and its implications on competition law and policy in South Africa
    (University of the Witwatersrand, Johannesburg, 2023) Fowler, Ashly
    The upsurge in the use of technology has proliferated the use of pricing algorithms which have become essential to e-commerce. Although South Africa had been privy to this shift prior to 2020, the onslaught of the Covid-19 pandemic exacerbated this shift. While the use of pricing algorithms in Competition law is accompanied by many pro-competitive benefits, it is also accompanied by various anti-competitive effects which include algorithmic-based collusion. Despite the fact that this topic has been addressed within the context of competition law in other jurisdictions, it has yet to be addressed from the viewpoint of the South African Competition Act 58 of 1998. Accordingly, the aim of this paper is to establish whether the Competition Act and South African competition policy at large, is robust enough to withstand the effects of digitalisation, particularly from the perspective of section 4 of the Competition Act which regulates relationships between competitors. In carrying out this analysis, this paper defines pricing algorithms and outlines their pro-competitive and anti-competitive effects.Thereafter, through the prism of four scenarios where pricing algorithms facilitate collusion, as posited by Ezrachi and Stucke in their seminal work on Virtual Competition, this paper establishes the robustness of the Competition Act by applying the scenarios to the Acts. Ultimately, this paper concludes that the current Competition Act (as amended) is in fact robust enough to tackle situations where algorithmic-based collusion arises. Where it is not, this paper argues that it is, at present, unnecessary for the relevant authorities to amend the current law or introduce any new laws
  • Thumbnail Image
    Item
    Comparing the effectiveness of LSTM, ARIMA, and GRU algorithms for forecasting customer charging behavior in the electric mobility industry in Europe
    (University of the Witwatersrand, Johannesburg, 2023) Pelwan, Robyne Chimere
    Forecasting, a powerful technique for unveiling potential future events, relies on historical data and methodological approaches to provide valuable insights. This dissertation delves into the domain of electric mobility, investigating the effectiveness of three distinct algorithms—Long Short-term Memory (LSTM), Autoregressive Integrated Moving Average (ARIMA), and Gated Recurrent Unit (GRU)—for predicting customer charging behavior. Specifically, it focuses on forecasting the number of charges over a 7-day period using time-series data from European electric mobility customers. In this study, we scrutinize the interplay between algorithmic performance and the intricacies of the dataset. Root mean squared error (RMSE) serves as a metric for gauging predictive accuracy. The findings highlight the supremacy of the ARIMA model in single-variable analysis, surpassing the predictive capabilities of both LSTM and GRU models. Even when additional features are introduced to enhance LSTM and GRU predictions, the superiority of ARIMA remains pronounced. Notably, this research underscores that ARIMA is particularly well-suited for time series data of this nature due to its tailored design. It contributes valuable insights for both researchers and practitioners in the electric mobility industry, aiding in the strategic selection of forecasting methodologies.
  • Thumbnail Image
    Item
    Bias in data used to train salesbased decision-making algorithms in a South African retail bank
    (2021) Wong, Alice
    Banks are increasingly using algorithms to drive informed and automated decision-making. Due to algorithms being reliant on training data for the model to learn the correct outcome, banks must ensure that the customer data is securely and fairly used when creating product offerings as there is a risk of perpetuating intentional and unintentional bias. This bias can result from unrepresentative and incomplete training data or inherently biased data due to past social inequalities. This study aimed to understand the potential bias found in the training data used to train sales-based decision-making algorithms used by South African retail banks to create customer product offerings. The research adopted a qualitative approach and was conducted through ten virtual one-on-one interviews with semi-structured questions. Purposive sampling was used to select banking professionals from data science teams in a particular South African retail bank across demographics and levels of seniority. The data collected from the participants in the interviews were then thematically analysed to draw a conclusion based on the findings. Key findings included: An inconsistent understanding across data science teams in a South African retail bank around the prohibition of using the gender variable. This could result in certain developers using proxy variables for gender to inform certain product offerings. A potential gap in terms of the potential usage of proxy variables for disability (due to non-collection of this demographic attribute) to inform certain product offerings. Although disability was not identified as a known biased variable, it did, however, raise the question of whether banks should be collecting the customer’s disability data and doing more in terms of social responsibility to address social inequalities and enable disabled individuals to contribute as effectively as abled individuals. As algorithms tend to generalise based on the majority’s requirements, this would result in a higher error rate of underrepresented groups of individuals or minority groups. This could result in financial exclusion or incorrect products being offered to certain groups of customers iii which, if not corrected, would lead to the continued subordination of certain groups of customers based on demographic attributes.