arXiv subjects

Herkulaas MvE Combrink

Publications and source records attributed to Herkulaas MvE Combrink.

4 recordsLinked to original sources

arXiv2022

Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases

The ability to generate synthetic data has a variety of use cases across different domains. In education research, there is a growing need to have access to synthetic data to test certain concepts and ideas. In recent years, several deep learning architectures were used to aid in the generation of synthetic data but with varying results. In the education context, the sophistication of implementing different models requiring large datasets is becoming very important. This study aims to compare the application of synthetic tabular data generation between a probabilistic model specifically a Bayesian Network, and a deep learning model, specifically a Generative Adversarial Network using a classification task. The results of this study indicate that synthetic tabular data generation is better suited for the education context using probabilistic models (overall accuracy of 75%) than deep learning architecture (overall accuracy of 38%) because of probabilistic interdependence. Lastly, we recommend that other data types, should be explored and evaluated for their application in generating synthetic data for education use cases.

cs.LG↗

arXiv2022

A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education

Understanding which student support strategies mitigate dropout and improve student retention is an important part of modern higher educational research. One of the largest challenges institutions of higher learning currently face is the scalability of student support. Part of this is due to the shortage of staff addressing the needs of students, and the subsequent referral pathways associated to provide timeous student support strategies. This is further complicated by the difficulty of these referrals, especially as students are often faced with a combination of administrative, academic, social, and socio-economic challenges. A possible solution to this problem can be a combination of student outcome predictions and applying algorithmic recommender systems within the context of higher education. While much effort and detail has gone into the expansion of explaining algorithmic decision making in this context, there is still a need to develop data collection strategies Therefore, the purpose of this paper is to outline a data collection framework specific to recommender systems within this context in order to reduce collection biases, understand student characteristics, and find an ideal way to infer optimal influences on the student journey. If confirmation biases, challenges in data sparsity and the type of information to collect from students are not addressed, it will have detrimental effects on attempts to assess and evaluate the effects of these systems within higher education.

cs.IR↗

arXiv2020

Mapping the South African health landscape in response to COVID-19

When the COVID-19 disease pandemic infiltrated the world, there was an immediate need for accurate information. As with any outbreak, the outbreak follows a clear trajectory, and subsequently, the supporting information for that outbreak needs to address the needs associated with that stage of the outbreak. At first, there was a need to inform the public of the information related to the initial situation related to the "who" of the COVID-19 disease. However, as time continued, the "where", "when" and "how to" related questions started to emerge in relation to the public healthcare system themselves. Questions surrounding the health facilities including COVID-19 hospital bed capacity, locations of designated COVID-19 facilities, and general information related to these facilities were not easily accessible to the general public. Furthermore, the available information was found to be outdated, fragmented across several platforms, and still had gaps in the data related to these facilities. To rectify this problem, a group of volunteers working on the covid19za project stepped in to assist. Each member leading a part of the project chose to focus on one of four problems related to the challenges associated with the Hospital information including: data quality, data completeness, data source validation and data visualisation capacity. As the project developed, so did the sophistication of the data, visualisation and core function of the project. The future prospects of this project relate to a Progressive Web Application that will avail this information for the public as well as healthcare workers through comprehensive mapping and data quality.

cs.CY↗

arXiv2020

Use of Available Data To Inform The COVID-19 Outbreak in South Africa: A Case Study

The coronavirus disease (COVID-19), caused by the SARS-CoV-2 virus, was declared a pandemic by the World Health Organization (WHO) in February 2020. Currently, there are no vaccines or treatments that have been approved after clinical trials. Social distancing measures, including travel bans, school closure, and quarantine applied to countries or regions are being used to limit the spread of the disease and the demand on the healthcare infrastructure. The seclusion of groups and individuals has led to limited access to accurate information. To update the public, especially in South Africa, announcements are made by the minister of health daily. These announcements narrate the confirmed COVID-19 cases and include the age, gender, and travel history of people who have tested positive for the disease. Additionally, the South African National Institute for Communicable Diseases updates a daily infographic summarising the number of tests performed, confirmed cases, mortality rate, and the regions affected. However, the age of the patient and other nuanced data regarding the transmission is only shared in the daily announcements and not on the updated infographic. To disseminate this information, the Data Science for Social Impact research group at the University of Pretoria, South Africa, has worked on curating and applying publicly available data in a way that is computer-readable so that information can be shared to the public - using both a data repository and a dashboard. Through collaborative practices, a variety of challenges related to publicly available data in South Africa came to the fore. These include shortcomings in the accessibility, integrity, and data management practices between governmental departments and the South African public. In this paper, solutions to these problems will be shared by using a publicly available data repository and dashboard as a case study.

cs.CY↗