Computer Science Publications

Permanent URI for this collection

http://196.220.97.103:4000/handle/123456789/124
Computer Science Publications

Browse

Recent Submissions

Now showing 1 - 5 of 17
  • No Thumbnail Available
    Item
    An Artificial Intelligence-Based Random Forest Model for Reducing Prescription Errors and Improving Patient Safety.
    (2024) Maphosa, V.; Mpofu, B.
    Pharmaceutical intake is crucial for alleviating illnesses and extending patients’ lives. However, frequent medication errors lead to catastrophic injuries or death. Developed countries have adopted artificial intelligence (AI) systems to enhance patient safety. This research aimed to develop an AI-based model that reduces medical errors by reviewing the patient’s prescriptions and predicting their disease. The prediction gets validated against the doctor’s diagnosis. In cases of inconsistencies, the patient undergoes a review process. This study reviewed medication errors and AI systems. The study utilized an experimental design methodology with a dataset of 797 observations containing diseases, symptoms, medications and other variables from the Kaggle database. The model was built using the Random Forest and the decision tree’s train-test-split technique. Python libraries including Pandas, NumPy, Matplotlib, and Seaborn were used for data manipulation. The model was evaluated using classifications, correlations and the confusion matrix, achieving 83.33% accuracy. The model holds significant potential for governments and healthcare professionals to reduce medication errors. The study’s limitations include the use of secondary data. Future studies should consider using additional variables such as age, environment, and gender. Increasing dataset observations will enhance the model’s accuracy. Implementation and ethical considerations are necessary to ensure patient safety.
  • No Thumbnail Available
    Item
    An overview of cybersecurity in Zimbabwe’s financial services sector
    (F1000Research, 2024-03-14) Maphosa, V.
    Background As nations, businesses, and individuals rely on the Internet for everyday use, so are cybercriminals manipulating systems to access information illegally and disrupting services for financial gain. The global cost of cybercrime eclipsed one trillion US Dollars in 2020, with Africa losing US $3.5 billion. Methods A quantitative research methodology was adopted to investigate factors affecting cybercrime in Zimbabwean financial institutions. The study focused on the technical aspects of cybersecurity. Data were collected from July 2022 to October 2022, targeting technology experts in the financial services sector. Participants were recruited from 13 institutions to rank cybersecurity constructs, frameworks, and challenges associated with cybersecurity. Data was collected using a questionnaire distributed to participants. Descriptive statistics were used to extract meanings from the responses that measure mean and standard deviation. Results Network and data security were the most highly ranked cybersecurity constructs, while physical security was the least. The top three barriers are increasing sophistication of threats, limited skills and emerging technologies, while lack of executive support was the least. The top frameworks used are the Information Technology Infrastructure Library (ITIL) and Control Objectives for Information and Related Technologies (COBIT), while a fifth is yet to adopt cybercrime frameworks. Conclusions The study proposes that financial institutions establish a cybersecurity culture to fight cybercrime, addressing cybersecurity barriers and following best practices. Financial institutions should invest in cybersecurity technologies, train security specialists, and employ a Chief Information Security Officer (CISO). The study’s small sample may affect the generalisability of the results. Financial institutions should implement strategies to raise awareness and collaborate with institutions to train cybersecurity security specialists to close the skills gap.
  • No Thumbnail Available
    Item
    An overview of cybersecurity in Zimbabwe’s financial services sector [version 1; peer review: 2 approved with reservations]
    (F1000 Research, 2023-09-29) Maphosa, V.
    Background: As nations, businesses, and individuals rely on the Internet for everyday use, so are cybercriminals manipulating systems to access information illegally and disrupting services for financial gain. The global cost of cybercrime eclipsed one trillion US Dollars in 2020, with Africa losing US $3.5 billion. Methods: A quantitative research methodology was adopted to investigate factors affecting cybercrime in Zimbabwean financial institutions. The study focused on the technical aspects of cybersecurity. Data were collected from July 2022 to October 2022, targeting technology experts in the financial services sector. Participants were recruited from 13 institutions to rank cybersecurity constructs, frameworks, and challenges associated with cybersecurity. Data was collected using a questionnaire distributed to participants. Descriptive statistics were used to extract meanings from the responses that measure mean and standard deviation. Results: Network and data security were the most highly ranked cybersecurity constructs, while physical security was the least. The top three barriers are increasing sophistication of threats, limited skills and emerging technologies, while lack of executive support was the least. The top frameworks used are the Information Technology Infrastructure Library (ITIL) and Control Objectives for Information and Related Technologies (COBIT), while a fifth is yet to adopt cybercrime frameworks. Conclusions: The study proposes that financial institutions establish a cybersecurity culture to fight cybercrime, addressing cybersecurity barriers and following best practices. Financial institutions should invest in cybersecurity technologies, train security specialists, and employ a Chief Information Security Officer (CISO). The study’s small sample may affect the generalisability of the results. Financial institutions should implement strategies to raise awareness and collaborate with institutions to train cybersecurity security specialists to close the skills gap.
  • No Thumbnail Available
    Item
    AI-based Drought Forecasting for Parametric Insurance
    (IEOM Society International, USA, 2024-05-07) Mathende, M.T.; Ndlovu, B.; Dube, S.; Muduva, M.; Kiwa, F.J.
    In drought-prone African countries like Zimbabwe, the uptake of parametric insurance has been low due to the absence of localized models. Guided by the CRISP-DM model, the present study proposes an AI-based approach to drought prediction in parametric insurance. The study’s paramount objectives are establishing trigger thresholds for drought events, assessing their significance, identifying the most effective machine learning models for drought modeling based on the Standardized Precipitation Index (SPI), and forecasting future drought occurrences and their magnitudes. Historical weather data, including temperature and rainfall, are utilized and a range of machine learning modelsneural networks, random forest, and support vector machines are employed for drought prediction. The performance of these models is evaluated based on accuracy, reliability, and interpretability, with continuous refinement based on feedback from stakeholders. The significance of this research lies in promoting data-driven decisions, incentivizing preparedness, enabling risk transfer, facilitating rapid insurance payouts, and enhancing financial stability. With accurate drought predictions driving parametric insurance, policyholders can make well-informed choices, adopt proactive measures, transfer the risk of drought-related losses, receive swift insurance payouts, and improve their financial resilience during drought events.
  • No Thumbnail Available
    Item
    A Blockchain-based Patient Portal for Mental Health Management
    (IEOM Society International, USA, 2024-04-23) Jhamba, P.; Ndlovu, B.; Dube, S.; Muduva, M.; Jacqueline, F.; Maguraushe, K.
    Mental health is an important aspect of well-being as it encompasses emotional, psychological and social well-being. The use of patient portals in mental health care has gained attention as a potential tool to improve access to care for individuals with mental illness. Patient portals may be vulnerable to unauthorized access if appropriate security measures are not put in place. This study leverages blockchain technology to create tamper-proof patient records. The proposed solution uses an on-chain database that stores hashes and the actual medical record of a patient as well as an off-chain solution that handles encryption of each user’s medical record using their respective keys in a trustless manner before they are uploaded on-chain. A secure smart contract hosted on Ethereum and the Byzantine Fault Tolerance consensus algorithm was used to ensure patient privacy. The research employed the Comparative Analysis Research Methodology as the research methodology and the Kanban methodology as the software development methodology. The research project concludes that the proposed solution addresses the current security issues and data privacy concerns in patient data. The decentralized nature of blockchain ensures security, transparency, and tamper-proof storage of information. Further research is needed for future advancements, like integrating blockchain-based patient portals with wearable devices and IoT.