South African Tuberculosis Vaccine Initiative
UCT Computer Science Research Document ArchiveNot a member yet
1270 research outputs found
Sort by
Networked Micro-Services: Empowering Local Micro-Enterprises in a South African Township through Community Wireless Networks
Full text linkInternet and cloud resources are a growing resource for microenterprises. However, small businesses in low-income communities struggle to use these resources due to the cost of access and the perceived cost of producing digital applications. In this paper, we draw on interviews with residents and small business owners from a South African township to inform the design of services to support microservices through locally hosted infrastructure. We present design implications for the architecture of these services, discussing the merits of internet-based versus community-based architectures, and present four prototypes to demonstrate possible designs of local-centred e-commerce applications. This paper extends insights about local micro-enterprises' feature requirements and no-code local content creation services in remote communities. It also illustrates some factors that hinder the success of e-commerce in remote areas and how CWNs mitigate those factors. This work aims to contribute to both Sustainable Development Goals (SDG) Goal 8, which focuses on promoting economic growth, and Goal 11, which aims to build sustainable communities
Reconsidering Priorities for Digital Maternal and Child Health: Community-Centered Perspectives from South Africa
Full text linkEspecially in developing regions, parents are rarely given a direct voice in the design of digital maternal and child health (MCH) interventions. Instead, MCH needs and requirements are driven by organizations and health workers. In this research, we engage with both rural and urban parents and community leaders to better understand their challenges and priorities for digital MCH and propose a parent-centered agenda for human-computer interaction research. This paper reports on the community-based, digital MCH priorities identified in our research, and describes how we approached community discourse and co-design of digital initiatives for these priorities, through parent-centered workshops with low-resource South African communities. Furthermore, we provide the parent-centered design opportunities and tensions we discovered for digital MCH in South African contexts, such as designing for local contexts and languages, designing for accessibility and connectedness, and highlighting the underdeveloped digital MCH niches. Finally, we highlight the importance of including facilitators for co-design workshops, such as using intermediaries and design cards
The What and How of Modelling Information and Knowledge: From Mind Maps to Ontologies
No full textIntroduces models and modelling processes to improve analytical skills and precision
Describes and compares mind-maps, models in biology, conceptual data models, ontologies, and ontology
Aims at readers looking for an accessible introduction to information modelling and knowledge representatio
In-house Developed Tools for Ontology Engineering Education (Demo)
Full text linkBoth good ontology development and ontology engineering are considered to be advanced topics in computing curricula. They draw on knowledge from different specialisations and need to strike a balance between theory and skills. This may cause a steep learning curve, but one where tools may assist with the learning process. This work-in-progress demo paper, presents the ongoing development of a set of in-house developed tools that assist in the various learning activities in different ways. They were motivated in part by the ontology engineering course taught by the author and cover a spectrum of tasks for learning about ontology development
Multi-objective Evolution for Automated Chemistry
Full text linkA fundamental problem in chemical product design
is how to suitably identify chemical compounds that optimise
multiple properties for a given application whilst satisfying
relevant constraints. Current product synthesis generally uses
trial-and-error experimentation, requiring lengthy and expensive
research and development efforts. This paper introduces a novel
computational chemistry approach for product design combining
geometric deep learning for inference of property values and
evolutionary multi-objective optimisation for identification of
products of interest. Preliminary empirical results indicate that
the proposed approach can be used to optimise product design
considering multiple objectives and constraints given incomplete
molecular attribute information
A Quality-Diversity Approach to Evolving a Repertoire of Diverse Behaviour-Trees in Robot Swarms
Full text linkDesigning controllers for a swarm of robots such that collaborative
behaviour emerges at the swarm level is known to be challenging.
Evolutionary approaches have proved promising, with attention turning
more recently to evolving repertoires of diverse behaviours that can
be used to compose heterogeneous swarms or mitigate against faults.
Here we extend existing work by combining a Quality-Diversity algorithm
(MAP-Elites) with a Genetic-Programming (GP) algorithm to
evolve repertoires of behaviour-trees that define the robot controllers.
We compare this approach with two variants of GP, one of which uses
an implicit diversity method. Our results show that the QD approach results
in larger and more diverse repertoires than the other methods with
no loss in quality with respect to the best solutions found. Given that
behaviour-trees have the added advantage of being human-readable compared
to neural controllers that are typically evolved, the results provide
a solid platform for future work in composing heterogeneous swarms
Inequality and the Emergence of Social Stratification.
Full text linkIn this work, we investigate whether differential (unequal) resource
access promotes social stratification (the partitioning of a population
into hierarchical groups based on socioeconomic factors).
We achieve this by conducting scenario experimentation with Neo-
COOP, an ABM that utilizes a Cultural Algorithm to simulate the
evolution of resource sharing preferences in an artificial society. By
varying the agents’ initial resource sharing beliefs, the intensity of
differential access, and the frequency at which the agents experience
environmental stress. We find that while social stratification
does increase when differential access increases, the effect is attenuated
at the extremes with agents instead favouring an increase
in selfish behaviour across the social strata. We also show that the
severity (magnitude) of social stratification is most prominent in
societies with initially selfish agents regardless of the intensity of
differential access. Interestingly, our results also suggest that heterogeneous
populations (agents with greater diversity of resource
sharing beliefs) exhibit emergent social stratification to a lesser
degree than homogenized populations (even in populations where
agents are initialized to be altruistic)
COMPASS '23: Proceedings of the 6th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies
No full textA method to improve alignments between domain and foundational ontologies
Full text linkFoundational ontologies can be used to enable semantic interoperability in modern information systems. Aligning a domain ontology to a foundational ontology is perceived difficult, however. Reasons include confusing underlying concepts, understanding the philosophical ideologies of foundational ontologies, and lack of alignment guidance. For BFO, there is a BFO Classifier tool for alignment, but users still face challenges. To uncover some of these user challenges, an experiment was performed using 10 BFO-aligned domain ontologies. The alignment of domain entities were analysed, revealing seven different types of mistakes in the alignments. To avoid them, the BFO classifier tool was altered to improve the questions and explanations for the core principles of BFO. Thereafter, the BFO classifier tool was evaluated to measure the effect on alignment with a use-case based approach, using the GORO and AWO ontologies. The evaluation revealed that alterations facilitated alignment, as users felt more confident in their results given the improved understanding of the questions and possible answers
Focused Crawling for Automated IsiXhosa Corpus Building
Full text linkIsiXhosa is a low-resource language, which means that it does not have many large, high-quality corpora. This makes it difficult to perform many kinds of research with the language. This paper examines the use of focused Web crawling for automatic corpus generation. The resulting corpus is characterised using statistical methods: its vocabulary growth has been found to fit Heaps’ Law, and its word frequency has been found to be heavy-tailed. In addition, as expected, the corpus statistics did not match expectations from non-agglutinative language