South African Tuberculosis Vaccine Initiative
UCT Computer Science Research Document ArchiveNot a member yet
1270 research outputs found
Sort by
Contextualising Levels of Language Resourcedness affecting Digital Processing of Text
Full text linkApplication domains such as digital humanities and tool like chatbots involve some form of processing natural language, from digitising hardcopies to speech generation. The language of the content is typically characterised as either a low resource language (LRL) or high resource language (HRL), also known as resource-scarce and well-resourced languages, respectively. African languages have been characterized as resource-scarce languages (Bosch et al. 2007; Pretorius & Bosch 2003; Keet & Khumalo 2014) and English is by far the most well-resourced language. Varied language resources are used to develop software systems for these languages to accomplish a wide range of tasks. In this paper we argue that the dichotomous typology LRL and HRL for all languages is problematic. Through a clear understanding of language resources situated in a society, a matrix is developed that characterizes languages as Very LRL, LRL, RL, HRL and Very HRL. The characterization is based on the typology of contextual features for each category, rather than counting tools, and motivation is provided for each feature and each characterization. The contextualisation of resourcedness, with a focus on African languages in this paper, and an increased understanding of where on the scale the language used in a project is, may assist in, among others, better planning of research and implementation projects. We thus argue in this paper that the characterization of language resources within a given scale in a project is an indispensable component particularly in the context of low-resourced languages
Reflections on Digital Maternal and Child Health Support for Mothers and Community Health Workers in Rural Areas of Limpopo Province, South Africa
Full text linkIntroduction: Digital health support using mobile and digital technologies, such as MomConnect and WhatsApp, is providing opportunities to improve maternal and child healthcare in low and middle-income countries. Yet, the perspective of health service providers, pregnant women, and mothers as recipients of digital health support is under-researched in rural areas.
Material and Methods: An exploratory-descriptive qualitative research approach was adopted to reflect on the experiences of mothers, community leaders, and community health workers on mobile health opportunities in the context of maternal and child health in rural areas. Purposive sampling was used to select 18 participants who participated in the two focus groups and individual semi-structured interviews for data collection about digital maternal and child health support. The thematic open coding method of data analysis assisted authors in making sense of the given reflections of mothers, community leaders, and healthcare workers about digital health support.
Results: Participants commented on different existing digital support apps and their importance for maternal and child health. For example, MoMConnect, Pregnancy+, WhatsApp, and non-digital resources were perceived as useful ways of communication that assist in improving maternal and child health. However, participants reported several challenges related to the use of digital platforms, which affect following
the health instructions given to pregnant women and mothers.
Conclusions:
Participants expressed the significant role of digital support apps in maternal and child health, which is impacted by various challenges. Addressing the lack of digital resources could improve access to health instructions for pregnant women and mothers
Interactive Authoring of Terrain using Diffusion Models
Full text linkGenerating heightfield terrains is a necessary precursor to the depiction of computer-generated natural scenes in a variety of applications. Authoring such terrains is made challenging by the need for interactive feedback, effective user control, and perceptually realistic output encompassing a range of landforms. We address these challenges by developing a terrain-authoring framework underpinned by an adaptation of diffusion models for conditional image synthesis, trained on real-world elevation data. This framework supports automated cleaning of the training set; authoring control through style selection and feature sketches; the ability to import and freely edit pre-existing terrains, and resolution amplification up to the limits of the source data. Our framework improves on previous machine-learning approaches by: expanding landform variety beyond mountainous terrain to encompass cliffs, canyons, and plains; providing a better balance between terseness and specificity in user control, and improving the fidelity of global terrain structure and perceptual realism. This is demonstrated through drainage simulations and a user study testing the perceived realism for different classes of terrain. The full source code, blender add-on, and pre- trained models are available
Proceedings of the 16th International Natural Language Generation Conference, INLG 2023, Prague, Czechia, September 11 - 15, 2023
No full textData Augmentation for Low Resource Neural Machine Translation for Sotho-Tswana Languages
Full text linkNeural Machine Translation (NMT) models have achieved remarkable performance on translating between high resource languages. However, translation quality for languages with limited data is much worse. This research focuses on the low resource language of Sepedi and considers two data augmentation techniques to increase the size and diversity of English-Sepedi corpora for training an NMT model. First we consider backtranslation, which makes use of the larger amount of available monolingual Sepedi text. We train a reverse (Sepedi to English) model and generate synthetic English sentences from the monolingual Sepedi sentences. These synthetic translations examples are added to the parallel English-Sepedi sentences. We carry out various experiments to investigate translation quality improvements. The second technique we consider is to generate synthetic data from parallel sentences between English and a closely-related language, Setswana.
Setwana word are replacing with Sepedi words through an induced bilingual dictionary, which is created by using a supervised Generative Adversarial Network to align the embeddings of Sepedi and Setswana words. We evaluate our models on the JW300, FLoRes and Autshumato evaluation test sets, finding improvements over the current benchmark BLEU scores across all three datasets
Design and evaluation of a mobile application interface for stokvel groups: An Eastern Cape case study.
Full text linkThis dissertation investigates the potential use of mobile applications to facilitate the
management of Stokvels - informal savings groups - in rural South African communities. Amid challenges like mismanagement, lack of transparency, and constraints posed by the COVID-19 pandemic, digital solutions may offer effective remedies. The research seeks to comprehend the functioning of Stokvels, explore the activities that foster social capital, and design a user-friendly mobile application prototype through usability testing and qualitative thematic analysis of focus group data. The study adopts a user-centred approach involving initial requirement gathering, artefact creation for usability testing, and high-fidelity prototype evaluation. Data was collected through a focus group from the Imijelo Yophuhliso Foundation, and a WhatsApp chatbot prototype was tested and refined iteratively. Key findings revealed that users needed a comprehensive platform for record-keeping, improved communication channels, and an efficient loan request system. Despite the existing digital divide, a readiness to adopt technology was evident. Usability testing of the prototype yielded a 100% task completion rate, pointing to a solid foundational design, but also identified areas for improvement. Activities fostering social capital, like shared group identity, progress monitoring, effective communication, shared financial responsibility, and mutual aid, were identified as critical for integration into the mobile application. The study contributes significantly to the literature on digital financial inclusion, usability testing, and the role of mobile technologies in poverty alleviation. However, limitations such as language barriers, a short research timeframe, and a focus on a specific type of Stokvel warrant attention for future research. This study holds implications for similar communities in South Africa and
other parts of Africa and researchers interested in digital adoption in informal institutions in low-income areas
Milk Matters 4.0: Challenges in deploying university-led mobile application development for small NGOs
Full text linkMilk Matters is a small Cape Town based non-profit milk bank. Their primary role is to collect expressed breastmilk from donor mothers, pasteurize it and distribute it to recipient infants in need.
Previous postgraduate projects from the University of Cape Town (UCT) have co-designed a donor facing mobile application with Milk Matters, however no mobile application is currently deployed or promoted by the non-governmental organization (NGO). This project will build upon the work already done with Milk Matters and aims to update the full system for deployment. While post-deployment evaluation will also analyse the uptake and usage of the application, this poster will focus on discussing the challenges in the deployment of university-led mobile application development for small NGOs
Collective Cargo Transport and Sorting with Molecular Swarms
Full text linkRecent work has demonstrated the viability of DNA robotics
and artificial molecular machines for molecular transportation
and cargo sorting with potential applications in manufacturing
responsive molecular devices, programmable therapeutics,
and autonomous chemical synthesis. We extend
previous work on cooperative molecular transportation using
artificial molecular machines, where we similarly functionalize
DNA-conjugated microtubules driven by kinesin motor
proteins. DNA-functionalized microtubules propelled by
surface-adhered kinesin motors enable the self-organization
of molecular swarms, where such swarms load and transport
cargo (microbead) in a simulated chemical environment. We
demonstrate programmable molecular swarms for cargo sorting
and cooperative transport. Cargo loading occurs when
sufficient microtubules are at the same location as the cargo,
and cargo unloading occurs at specific points in the environment
through interaction with localized DNA species. Our
contribution is the design of a chemotaxis molecular controller,
forcing the swarm to tumble (random change direction)
when the system is not following a molecular gradient
corresponding to the cargo type, thus directing it to specific
points for cargo unloading. This work thus contributes to the
open problem of how to best design programmable molecular
machines for various tasks in microscopic environments
Forming Terrains by Glacial Erosion
Full text linkWe introduce the first solution for simulating the formation and evolution of glaciers, together with their attendant erosive effects, for periods covering the combination of glacial and inter-glacial cycles. Our efficient solution includes both a fast yet accurate deep learning-based estimation of high- order ice flows and a new, multi-scale advection scheme enabling us to account for the distinct time scales at which glaciers reach equilibrium compared to eroding the terrain. We combine the resulting glacial erosion model with finer-scale erosive phenomena to account for the transport of debris flowing from cliffs. This enables us to model the formation of terrain shapes not previously adequately modeled in Computer Graphics, ranging from U-shaped and hanging valleys to fjords and glacial lakes
Towards the generalisation of the generation of answerable questions from ontologies for education
No full textGenerating questions automatically from ontologies, and marking thereof, may support
teaching and learning activities and therewith alleviate a teacherโs workload. Numerous studies considered this for MCQs; however, learners also have to be confronted with, i.e., yes/no and short answer questions. We investigated ten types of educationally valuable questions. For each question type, we determined the axiom prerequisites to be able to generate and answer it and declared a set of template specifications as question sentence plans. Three algorithmic approaches were devised for generating the text from the ontology: semantics-based with 1) template variables using foundational ontology categories, or 2) using main classes from the domain ontology and 3) generation mostly driven by NLP techniques. User evaluation demonstrated that option three far outperformed the ontology-based ones on syntactic and semantic correctness of the generated questions, and it generated 98.45% of the questions from all valid axiom prerequisites in our experiment