Visit our Projects page to find our more about our research projects.
Need assistance? Contact us at
help@sit.uct.ac.za
Project Showcase
Intrusion Detection reliability in Software-Defined Community Wireless Networks
Network Security: Employing ML/DL Techniques to Design Efficient IDS for CWNs
By: Emmanuel Ackerson
Supervised By: Josiah Chavula
Community Wireless Networks (CWNs) offer cost-effective internet access to remote and underserved regions where traditional Internet Service Providers (ISPs) are unwilling or unable to operate. These networks, typically built with low-grade hardware and...
2025 Computer Science Honors Generative AI Applied to Student Guide (GAISG) Project
GAISG
By: Angelo Yang, Nova Adams-Duma, Daanyaal Ballim
Supervised By: Gary Stewart
The Generative AI Applied to Student Guide (GAISG) project reimagines UCT’s “Science is Tough: But So Are You” student guide as an interactive, multimodal learning platform. Traditional PDF-based guides often fail to engage students, limiting...
3DHAR-AI
Human Activity Recognition and Prediction using Deep Neural Networks
By: Kishalan Pather, Andrew Erasmus, Temi Aina
Supervised By: Deshen Moodley
The growing field of HAR sees many applications from remote health monitoring for the elderly to smart homes that adapt to our daily routines. In our work, we investigated the performance of three state-of-the-art spatio-temporal graph neural networks...
A Performance and Resilience Analysis of SANReN
A Spectral and Centrality Metric Framework for Resilient Network Topology Design and Analysis
By: Kerry-Lynn Whyte, Nicolas Wise, Alex White
Supervised By: Josiah Chavula, Michelle Kuttel
The South African National Research and Education Network (SANReN) provides the high-speed connectivity required for research collaboration and education but SANReN faces challenges related to rising demand, congestion, and vulnerability to node and edge...
A Prescriptive Framework for Designing Personalized Learning to Improve Learning Experiences in Open Distance Learning: The Context of African Higher Education
By: Godfrey Haonga
Supervised By: Lisa Seymour
Background to the Study: Personalized Learning (PL) has emerged as a transformative approach in education, emphasizing the individualization of learning experiences to enhance student outcomes. While PL has gained momentum in education settings, its...
Accurate Modelling and Effective Visualization of Carbohydrate Conformation
By: Andre Toerien, Aidan Ravenscroft
Supervised By: Michelle Kuttel, Nicholas Yerolemou
Carbohydrates play critical roles in biological processes, and their interactions depend on their 3D shapes, or conformations. Understanding these conformations, through computer modelling and visualization, is therefore key to modern drug and vaccine...
Adapter-based Debiasing of Pre-trained Speech Recognition Models for Low Resource languages
By: Claytone Sikasote
Supervised By: Hussein Suleman, Jan Buys
Fine-tuning multilingual pre-trained speech models for automatic speech recognition (ASR) has led to improved recognition accuracy for many languages, including low-resourced languages (LRLs). However, studies have shown that these models exhibit...
Agility - Strategic resource allocation and workload visibility for consulting teams
By: Ciaran Formby, Naledi Tshapi, Luyanda Ndlovu, Ashe-Shaana Andzenge
Supervised By: Caleb Tshinowa, Zainab Ruhwanya, Walter Uys
The Problem Consulting firms struggle to manage their people across multiple projects. Right now, most teams use Airtable spreadsheets and Jira, which creates a mess: No real-time view of who's available Endless email chains just to approve simple...
AI Literacy for Learners from Underserved Communities: Co-designing with Educators and Learners in Youth Organisation within South Africa
By: Rachel Oluwatuyi
Supervised By: Melissa Densmore
As the integration of Artificial Intelligence (AI) continues to advance at an unprecedented pace, shaping individuals and societies, young learners are growing up in environments increasingly influenced by intelligent systems. This has prompted the...
AI Share Trader
By: Kabelo Mbayi, Siyanda Makhathini, Saul Chipwayambokoma
Supervised By: Deshen Moodley
Traditional deep learning models for stock forecasting often overlook the complex interdependencies between financial assets. This study investigates the efficacy of Spatio-Temporal Graph Neural Networks (ST-GNNs) for stock prediction on the Johannesburg...
AMPLIFY
Location Based Marketing
By: Aadil Asmal, Matt Schramm, Kevin Shoba, Snethemba Mchunu
Supervised By: Elsje Scott
THE FUTURE OF MARKETING STARTS NOWTraditional Marketing Methods such as billboard, video and radio advertising has gradually seen a decrease in efficacy and increase in costs. The current advertising trend is through Affiliate, Influencer and Peer to...
BabyLMs for Sample-Efficient Language Modelling of Ancient Greek
Investigating the suitability of BabyLM architectures for language modelling in the low-resource context of Ancient Greek.
By: Dimitri Dalakas, Stelio Dalakas, Kimon Christelis
Supervised By: Francois Meyer
Pretrained Language Models (PLMs) have achieved state-of-the-art performance across a wide range of Natural Language Understanding tasks in recent years. This success has relied on vast amounts of training data, which are not readily available for...
Bee Grateful
Harnessing AI to Transform Hive Management Across Africa
By: BRIAN MUKUDZAVU, Joshua Willoughby, Mridula Kumar, Erin Duffy
Supervised By: Elsje Scott
Bee Grateful is a mobile-first application designed to assist with hive management for beekeepers across Africa. Developed in partnership with LithaFlora African Botanicals, this solution addresses critical challenges in the beekeeping industry,...
Bee Grateful Initiative
By: Zayn Toefy, Sisipho Manitshana, Muhammad Gamiet, Sithabiso Nzuza
Supervised By: Kian Joubert
Currently, the world sees bees as a pest at best, or an enemy at worst. The loss of love for nature’s most important creatures is felt and will negatively impact our future. The last bastion for them are those who work and care for them, the beekeeping...
BioFilm Creation Simulation
By: Joshua Murray, Brad Scott, Ethan Gibbons
Supervised By: Michelle Kuttel
Biofilms form when free-floating microorganisms attach to a surface and begin to produce extracellular polymeric substances (EPS). This sticky matrix of polysaccharides, proteins, and nucleic acids helps cells adhere to one another and to the surface,...
BlockBike
An eBike Sharing Platform
By: Rushnie Rademeyer, Mulalo Rasivhaga, Sandile Nkosi, Azile Dingalubala
Supervised By: Elsje Scott
The BlockBike project is a technology-driven initiative developed in collaboration with the Council for Scientific and Industrial Research (CSIR) to explore the practical use of Self-Sovereign Identity (SSI) in a real-world context. The project addresses...
Breaking the Cycle: Rethinking Learning Management Systems Adoption in African Universities
By: Folasade Adedeji
Supervised By: Hussein Suleman
African universities face ongoing challenges in adoption and usage of Learning Management Systems (LMS) due to structural neglect and generic platform designs that overlook local realities such as limited internet and unequal access. This study addresses...
ByteSized
By: Aaliyah van Graan, Elizabeth Mehl, Tadiwa Chipara, Khaya Mthethwa
The ByteSized project addresses a fragmented, manager-reliant onboarding by creating a centralised, AI-forward platform that streamlines employee integration and knowledge access. At its core is Digit, an AI-powered chatbot, that uses a hybrid framework...
CarbPred
Using machine learning to predict nuclear magnetic resonance spectra for carbohydrates via graph neural networks
By: Channing Bellamy, Unays Bhad, Matthew Dean
Supervised By: Michelle Kuttel, Jan Buys
Carbohydrates are complex molecules, critical to drug and vaccine development. Their study often involves the analysis of nuclear magnetic resonance (NMR) spectra, which are challenging to interpret, even for experts. We build upon prior work, GeqShift,...
Ciovita | Automated, AI-Driven Return Management System
Redefining the return experience through intelligence and automation.
By: Qiraan Christians, Tim Gultig, Glen Okech, Onthatile Mabe
Supervised By: Dirk Snyman
The Ciovita Integrated Returns System is a full-stack web application designed to streamline and modernize the product returns workflow for Ciovita, a cycling apparel company. The primary business requirement was to replace a manual, inefficient returns...
CLARITY - Confluence and Jira AI Resource and Insights Tool
AI Enhanced PM Tool For Jira and Confluence
By: Suyant Maharaj, Zidan Patel, Kai Trentini, Simamkele Ndlumbini
The CLARITY project addresses the growing need at impact.com to streamline project management tasks in Jira and Confluence. Current workflows for meeting transcription, ticket generation, and bug triaging are manual, time-consuming, and prone to...
Computational modeling of bacterial capsular polysaccharide
How high performance computing informs vaccine design
By: Nicholas Yerolemou
Supervised By: Michelle Kuttel, Neil Ravenscroft, Nicole Richardson
Streptococcus pneumoniae (S. pneumoniae) is a bacterial pathogen and a frequent cause of disease in humans. Developing vaccines against S. pneumoniae requires a deep understanding of the bacterial capsular polysaccharide, a sugar that surrounds the...
Cross-Lingual Adaptation for Named Entity Recognition in Runyankore
By: PROSPER ARINEITWE ASIIMWE
Supervised By: Jan Buys, Francois Meyer
Runyankore, a Bantu language spoken by millions in Uganda, remains critically underrepresented in Natural Language Processing (NLP). Prior to this study, no publicly accessible dataset existed for Named Entity Recognition (NER) in Runyankore, despite the...
Data Driven Control
Reinforcement Learning versus Classical control for Control Systems
By: Ben Ruijsch van Dugteren, Nathan Wells, Nicholas Cristaudo
Supervised By: Krupa Prag
This study examines the application of deep reinforcement learning to data-driven control and benchmarks it against classical proportional–integral–derivative control. Two system classes are considered: mechanical systems (inverted pendulum and...
deepEEG
Deep Learning for Infant-Brain EEG Modelling
By: Tziyona Cohen, Caleb Bessit
Supervised By: Francois Meyer, Jonathan Shock
Electroencephalography (EEG) measures electrical brain activity and is a common tool for monitoring neurodevelopment and diagnosing brain disorders. However, analysing EEG data is challenging due to its complex interpretability and inter-subject...
Designing Realistic Defeasible Ontologies
By: Victoria Chama
Supervised By: Tommie Meyer, Giovanni Casini
Ontologies play a crucial role in knowledge representation and automated reasoning on the web, defining concepts and relationships within domains. However, the ontology community lacks effective tools for expressing defeasibility, while the reasoning...
Discover Fitness: AI-Powered Fitness Generator
Discover YOUR fitness
By: Kian Joubert, Souvahn Naicker, Mahlatse Malope, Lusanele Goqoza
Discover Fitness is an AI-powered mobile application developed in collaboration with Discovery Ltd to transform how users approach health and fitness. The app generates personalised running and swimming workout plans using user health data, preferences,...
Discovery's Data Access Platform
Bridging Data Accessibility and Compliance in One Platform
By: Nomvelo Tembe, Thomas Davis, Asanda Xaba, Zanele Ndlovu
Supervised By: Dirk Snyman, Lusanele Goqoza
The Discovery Data Access Platform project was initiated to address the growing need for a secure, centralized and user-friendly solution for managing data. The key business requirements were to simplify data access across departments, ensure consistency...
Distributed Collaboration for Visual Analytics
Investigating Enhanced Collaboration in an Astronomy Tool
By: Sabiha Shaikh
Supervised By: Robert Simmonds, Angus Comrie
The need for effective collaboration tools in research is growing as scientific data becomes larger and more complex. This project aims to enhance the collaborative capabilities of the Cube Analysis and Rendering Tool for Astronomy (CARTA). CARTA is a...
Dungeons and Developers
Evaluating Real-Time Competitive Game-based Learning in Introductory Computer Science
By: Mahir Moodaley, Kai Connock, Ibrahim Abdou
Supervised By: Gary Stewart
Many first-year students, especially those with no previous experience, have difficulties learning and understanding Computer Science. This is due to a variety of factors including lack of engagement and low motivation. Students who have difficulty with...
Emotion Elicitation in VR
How sensory and narrative design shape curiosity and anger.
By: Liza Siurina
Supervised By: James Gain, Gosia Lipinska
Most Virtual Reality (VR) research on emotion elicitation focuses on high-arousal states like fear or joy, often overlooking emotions such as curiosity, anger, which are essential for exploration, motivation, and social connection. This study introduces...
Enhancing Fault Detection in Software Defined Network-based Community Wireless Networks
By: Takondwa Chitheka
Supervised By: Josiah Chavula
Network performance management is essential for ensuring that computer networks operate optimally and for proactively identi- fying faults. Several network managementtools, operating both passively and actively, are used to provide operational status to...
Entertainment.FM CRM
Your all in one centralized customer management platform!
By: Ghadijah Kippie, Anelisa Hlalukana, Aaliyah Adams, Jumana Shah
Entertainment.FM currently manages clients and accounts across disconnected tools like spreadsheets, documents, and Microsoft To Do. This fragmented system leads to delayed follow-ups, lost opportunities, and reduced productivity. Our custom CRM...
Evaluating Large Language Models for Multilevel Biomedical Text Simplification
By: Nomonde Khalo
Supervised By: Jan Buys
Biomedical articles are often characterized by structural and technical complexity, making them inaccessible to non-expert readers. Large language models (LLMs) have shown promise in the task of biomedical text simplification, but existing techniques...
Evolutionary Methods in Collective Herding Systems
By: Emily Raine, Naheed Khan
Supervised By: Geoff Nitschke
This project extended a 2D sheep-herding multi-agent system, where dog agents herd sheep into a target zone. We investigated the effectiveness of hybrid evolutionary methods in dynamic environments and compared the performance of agents with fixed versus...
EXTRC
By: Julia Cotterrell, Nevaniah Gounden, Jethro Dunn
Supervised By: Tommie Meyer
This project explores how defeasible reasoning, a form of non-monotonic logic, can be extended and made more interpretable beyond Rational Closure (RC). The optimisation of RC was combined with natural language processing for knowledge base (KB) creation...
Fine-Tuning Large Language Models for Low-Resource Languages
By: Mitchell Johnson, Dineo Chiloane, Corey Webb
Supervised By: Jan Buys
Most Large Language Models (LLMs) have been trained either on English text only or on text from multiple languages, but with a severe imbalance between data from different languages due to orders of magnitude differences in available web text per...
FineGuard
Fine-grained authorisation system with a Policy Engine Sidecar
By: Boithaopo Mokgatsi, Rorisang Pitso, Andiswa Shange, ANELE MBELE
FineGuard (Fine-Grained Authorisation with Policy Engine Sidecar) Business Requirements impact.com is a partnership management platform that helps companies manage a variety of partnerships. Their platform offers an automated system that simplifies the...
Implementation and Evaluation of KLM-Style Defeasible Entailment and Explanation Algorithms
By: Chipo Hamayobe
Supervised By: Tommie Meyer, Jonas Haldimann
In the 1950s, McCarthy proposed the use of formal logic in artificial intelligence, introducing the idea of representing knowledge in a formal language to enable algorithmic reasoning. This proposal laid the foundation for the field of knowledge...
Improving Research Question Quality with Controlled Natural Languages and Large Language Models
RQ-CNL
By: Rector Ratsaka, Emma Van Der Berg, Mandikudza Dangwa
Supervised By: Zola Mahlaza
Formulating a well-defined research question (RQ) is a crucial yet often challenging step in the research process, particularly for trainee researchers. Poorly constructed RQs can lead to ambiguous objectives and ineffective methodologies, reducing the...
Information security strategizing practices in developing economy public sector contexts: A case of Namibia
By: Popyeni Kautondokwa
Supervised By: Irwin Brown
There is an increase in data breaches globally resulting in billions of dollars in losses. The strategy as practice theoretical lens is used to understand the information security strategizing practices in a public sector organisation of a developing...
Innovative Solutions for Waste Management
Embracing Sustainability Through Technology
By: Konke Cele, Matovya Molala, Ramo Makama, Ovayo Myataza
Business RequirementsBulkmatech Cape's Bulkmatech Waste Solutions (BWS) division faces operational inefficiencies due to static collection schedules and lack of real-time visibility. This results in high fuel costs, unnecessary trips, and missed...
Investigating Deep Learning Solutions to Fish Identification and Classification
By: Joseph Goldblatt, Catalina Althoff-Thomson, Max Elkington
Supervised By: Patrick Marais, Jonathan Shock
Fishery managers, marine biologists, ecologists, and conservationists all rely on accurate estimates of fish population size and composition. Recently, there has been a growing interest in the use of Remote Underwater Video (RUV) methods for fish...
ISANGO Early Warning System
A data-driven solution to improve learner retention in South African schools.
By: Uzair Noormahomed, Kabelo Masola, Miche De Villiers, Thabisile Njomi
With roughly 40% of learners dropping out before matric, especially in township schools, South Africa faces a serious education crisis. Poor data systems and reliance on manual methods make it hard for educators to spot and support at-risk learners in...
IsiPython: A Localised IsiXhosa Programming Environment for Inclusive Computing Education
Combining Language, Learning, and Code to Make Programming More Accessible
By: Lutho Mngqibisa, Buhle Mlandu
Supervised By: Aslam Safla
The dominance of English in programming languages creates barriers for South African students whose primary language is not English, particularly in early Computer Science education. This forces learners to understand programming concepts while...
IsiXhosa Medical Machine Translation
By: Elijah Sherman, Nick Matzopoulos, Malibongwe Makhonza
Supervised By: Francois Meyer
Machine translation (MT) systems for low-resource languages like isiXhosa are still a big challenge because there aren’t many parallel datasets available for training models. Current MT systems work well when translating between isiXhosa and English for...
Kainos Vuku Management App
Building Connections
By: Caris Barnes, Ryan Badenhorst, Eunice Chihoma, Basetsana Rakumakoe
Supervised By: Walter Uys
Kainos Vuku is a Christian non-profit organisation dedicated to building authentic, Christ-centred relationships within communities through its Vuku Workbook program. The organisation currently manages member and financial data using shared Excel...
Knowledge Compilation For Defeasible Reasoning
By: Luke Slater
Supervised By: Tommie Meyer, Jesse Heyninck
Our work tackles defeasible reasoning—reasoning with “usually true” statements like if it’s a bird, it probably flies. These conditionals are organized by plausibility: more general or typical rules get higher ranks, and lower-ranked, conflicting ones...
KORA
Your favourite routine companion
By: Luyanda Nkuna, Kendall Sables, Thomas Baloyi
Students with ADHD face ongoing challenges with focus, organisation, and time management. Existing productivity tools are often visually cluttered, inconsistent, and overwhelming, resulting in anxiety and loss of motivation. The business requirement...
Lightweight AI Intrusion Detection
LAIDS
By: Sian Caine, Claire Campbell, Christopher Blignaut
Supervised By: Josiah Chavula
Intrusion detection systems (IDS) monitor network traffic for malicious activity. However, many AI-based IDSs are too resource-heavy for edge deployment, leaving resource-constrained portions of networks unguarded. The main objective of this study are to...
LLMASP: Synthesising Answer Set Programs with LLMs
By: Rowan Rosenberg, Julyan Van Der Westhuizen, Keegan O'Brien
Supervised By: Jesse Heyninck
Answer Set Programming (ASP) is a declarative programming framework. It is a powerful tool for solving complex logical and combinatorial problems, with many modern, real-world applications. However, its power is limited by a phenomenon known as the...
Measuring the effects of climate control on presence in natural virtual environments
VRClimate
By: Pietro Scheepers, Zahra Bawa, Rachel Strachan
Supervised By: James Gain
Virtual Reality, or VR, is defined as a technology that allows a user to interact with a computer-simulated environment, whether that environment is a simulation of the real world or an imaginary world. Currently, the main focus of creating these virtual...
Medical Samples Tracking Application
By: Liana Mbejeni, Udzulanarine Malindi, Nhlakanipho Msweli, Lukhanyo Mpondo
Supervised By: Elsje Scott
This project addresses critical inefficiencies in South Africa's medical sample transportation system, where a lack of real-time visibility between healthcare facilities and laboratories results in high sample rejection rates, compromised sample...
Modelling Students’ Source Code Evolutions To Provide Personalised Guidance In Introductory Programming Courses
Personalised learning, MDP, RL, Education Technology
By: Herman KANDJIMI
Supervised By: Hussein Suleman
Programming skills are fundamental in cultivating critical thinking, problem-solving, and creativity, which are integral to computational thinking competencies. These competencies are increasingly recognised as prerequisites for success in the future...
Molecular Modelling of STREPTOCOCCUS PNEUMONIAE Carbohydrate Antigens for Optimizing Vaccine Design
By: Carla Coetzee
Supervised By: Michelle Kuttel, Neil Ravenscroft
Streptococcus pneumoniae is a Gram-positive pathogen that commonly colonizes the human nasopharynx and is a leading cause of invasive pneumococcal disease (IPD), including pneumonia, otitis media, bacteraemia, and meningitis. Globally, lower respiratory...
MyAdvisor
Virtual Curriculum Assistant
By: Dylan Howard, Ethan Allies, Mitchell Flanegan
Supervised By: Aslam Safla, Nicholas Yerolemou
MyAdvisor is a centralized hub for UCT advising, built to simplify handbooks, streamline advisor access, and support degree planning. Instead of navigating scattered portals and static PDFs, students get one clear, interactive system that works on both...
One Click E-Commerce Web App
By: Lehlo Peta, Tinomudai Bopoto, Kumbirai Chari, Schmeichael Makoni
Mozambican SMEs depend on One Click POS for in-store management but lack online integration. This project introduces a plug-and-play e-commerce platform synced with Firestore to display real-time stock and enable WhatsApp ordering. Built with ASP.NET and...
Phoenix: AI Creatives Generator
By: Nella Wood, Raihan Mohamed, Khanya Maqolwana, Tammy Chu Shien Ho
Dentsu, one of the world’s largest advertising networks, continuously seeks ways to combine creativity, data, and technology to deliver impactful campaigns. Scaling content production while maintaining brand continuity, security, and adherence to...
POL-ID
AI-Based South African Honey Authentication
By: Yash Ramklass, Maryam Mather, Lillian Mtumanje
Supervised By: Patrick Marais, Cesarina Edmonds-Smith, Janais Delport
Authenticating the botanical origin of honey is crucial for ensuring product integrity, consumer trust, and sustainable trade. However, manual pollen identification under a microscope is time-consuming and prone to human error. To address this, our...
QR Powered Stakeholder Inquiry Tracking app
By: Onthatile Mbowane, Tumelo Thole, Lilitha Kunene, Lesego Mejelo
Supervised By: Dirk Snyman
The CHIETA Stakeholder Management System was created in order to meet important business needs related to appointment scheduling, inquiry tracking, and stakeholder engagement. Prior to the transition of advisory services to a hybrid, partially virtual...
READ: Developing a South African ART with Fine-tuned Mispronunciation Detection, Voice Detection, Multi-speaker Detection and Text Generation
By: Daniel Holgate, Christian Slier, Kirsten Sutherland
Supervised By: Jan Buys
Reading literacy is poor for most South Africans due to the numerous negative aftereffects of Apartheid. Both Phala et al. and Naidoo et al. refer to the Progress in International Reading Literacy Study (PIRLS) 2011, which revealed that 61% of school...
Redirected Walking in VR
By: Prashanth Padiachy, Oscar Field, Kyle Fagan
Supervised By: James Gain
Our project explores how different VR locomotion techniques can be combined with Redirected Walking (RDW) to enable natural interaction with physical props in small tracked spaces. We developed three systems in Unity using the HTC Vive Pro: Free Teleport...
SACM TuneIn
Concert Attendance Tracker
By: Safiya Abrahams
Supervised By: Walter Uys
The South African College of Music (SACM) currently relies on a paper cards to track student concert attendance. This is labour-intensive, error-prone, and vulnerable to loopholes. The project addresses these challenges with SACM TuneIn, a web-based...
Securing the digital highway
Investigating the performance of fuzzers on Wireguard-Go
By: Thalia Hawthorn, Michal Sacks
Supervised By: Josiah Chavula
Network-based tools have become a central component in the operation of many institutions such as businesses, universities and governments. The growing amount of sensitive data being transported over networks necessitates innovation to ensure these...
Siyazalana Lineage Mapping and African Heritage
Digitally Preserving African Heritage
By: Akhona Mahlaba, Kelebogile Moima, Glen Nohaji, Jamie-Lee Schalkwyk
Supervised By: Zainab Ruhwanya
Siyazalana: Lineage Mapping addresses a critical business requirement faced by many African families: the lack of accessible, reliable, and culturally grounded genealogical records. Generations of disrupted record-keeping caused by colonialism and...
Siza Entrepreneur
Connecting Vision With Capital
By: Lusa Stofile, Zayahn Abrahams, Nicole Ndawula, Samukelile Jama
Business requirements Many entrepreneurs struggle to reach aligned investors, while investors waste time on unfocused outreach. The platform must: (1) enable entrepreneurs to publish clear pitches; (2) help investors discover opportunities by factors...
Skills Bridge platform
By: Caleb Tshinowa, Nihaad Mosaval, Taskeen Mookrey, Katleho Mokoena
Supervised By: Elsje Scott
SkillsBridge is a digital platform designed to connect skilled volunteers with community projects, enabling meaningful collaboration and sustainable impact. Originating from initiatives in communities like Vrygrond in Cape Town, the platform addresses...
SmartHarvest: Empowering South Africa's Farmers Through Technology
Growing smarter, farming better
By: Leah Brown, Adam Budge, Gabriella Geldenhuys
Supervised By: Elsje Scott
SmartHarvest is a mobile-first, ML-powered platform developed in collaboration with UCT’s AgriCode team to support South Africa’s smallholder farmers. These farmers face climate challenges, poor soil health, and limited access to technology, information,...
SOILAI
Generating Soilscapes with Random Forets
By: Josh Britz, James Ridley
Supervised By: James Gain, Patrick Marais
Soils support plant life and form an important aspect of ecological biodiversity. Soil data, however, is often absent from digital terrains but nevertheless remain important in areas of computational ecology. Digital elevation maps are a common artefact...
STASP
Sports Timetabling with Answer Set Programming
By: Mahir Ahammed, Roanda Muedi
Supervised By: Jesse Heyninck
This project explores the use of Answer Set Programming (ASP) as a declarative paradigm to solve the classic combinatorial sports timetabling problem. ASP allows scheduling rules and constraints to be expressed in a high-level, human-readable form, which...
STGNN for share trend line prediction and change point detection on JSE.
Training STGNN Model to predict events of interests; trend lines and to detect trend change points on JSE, to support investment decision making.
By: Ephraim Adongo
Supervised By: Deshen Moodley
This research explores the application of advanced Spatial-Temporal Graph Neural Networks (STGNNs) for predicting events of interest in the Johannesburg Stock Exchange Market (JSE), specifically future share trend lines; how they can be used to detect...
Streets
Reimagining Venue Discovery
By: Joshua Preston, Josh Birkholtz, Reece Sheldon, Tom Théron
Supervised By: Elsje Scott
Streets is a mobile and web-based platform designed to transform how tourists and locals discover, experience, and engage with local venues in Cape Town. The system bridges the gap between users seeking authentic experiences and venues striving for...
Synthetic Data Generation for Small Data Orthopedic Radiology
By: Max Van Veen, Oliver Foxcroft, Ethan Topat
Supervised By: Geoff Nitschke, Bilal Aslan
Address the data scarcity issues faced by automated medical classification methods using machine learning models for synthetic data generation with an appropriate set of metrics to evaluate their quality and diversity performance.
The Dynamic Vehicle Routing Problem
By: Jayden Moore, Ryan Schapiro, Aidan Brand
Supervised By: Krupa Prag
The Dynamic Vehicle Routing Problem (DVRP) extends the classical Vehicle Routing Problem by incorporating dynamic and uncertain elements, such as stochastic customer requests, making it more applicable to real-world logistics. Unlike static routing where...
Toolkits: Gender-Just Digital Innovation Design
By: Sierra Van Riel
Supervised By: Melissa Densmore
Work in the field of digital development has often been carried out without sufficient attention to gender justice. Indeed, where researchers or practitioners have been sensitive to gender, this has often only extended to “counting women” - gathering...
Toward Robust Malware Classification
Data Augmentation, Topology Optimisation, and Concept Drift Monitoring
By: Shaylin Velen, Callum Musselwhite, Simphile Mkhize
Supervised By: Geoff Nitschke
Our project investigates the application of various machine learning techniques for malware detection. As malware engineers improve and release new variants, identifying whether a file is malicious becomes increasingly challenging. This malware evolution...
Track|Stock: Simplified Event Stock Management
Simplifying stock. Empowering teams. Transforming events.
By: Oratile Mogodi, Avish Judnarain, Carla Reinecke, Chulumanco Magwa
Supervised By: Elsje Scott
Track|Stock is a role-based web application built to centralise and digitise stock management for BBD merchandise across multiple branches, addressing inefficiencies, stock losses, and fragmented communication found in their traditional, manual stock...
TrackX
Let's track the case
By: Jonluke Ferreira, Pearl Ndlozi, Kwande Dhlomo, Shewe Tarumbwa
In the realm of vehicle-related crime investigations, investigators face a growing challenge: vast amounts of GPS and digital data are collected daily, yet transforming this information into coherent, court-ready reports remains a time-consuming and...
Traffic Flow
An Analysis of STGNNs through Visualization
By: Raaziq Parkar, Mohammad Arshad Hussain
Supervised By: Deshen Moodley
Traffic is a highly dynamic system containing spatial, temporal and random patterns. Spatial Temporal Graph Neural Networks(STGNNs) model traffic as an evolving graph, dynamically capturing both spatial and temporal patterns. Current evaluation metrics...
Tutored AI
By: Tara Khai, Farzana Karreem, Kayla Wessels, Akshay Maharaj
This project introduces Tutored AI, a comprehensive, AI powered web application engineered to boost the effectiveness and appeal of student learning. It tackles the issue of generic educational materials by delivering a uniquely personalised experience...
UCT Course Readiness and Completion System
Digitising Administration
By: Almaaz Saloojee, Wonga Dzingwa, Aneeqah Moses, Ntandoyesizwe Mlahleni
Supervised By: Zainab Ruhwanya, Walter Uys
Universities often face heavy administrative loads that lead to bottlenecks and delays in course preparation and delivery. The Course Readiness and Completion System was developed for the University of Cape Town to address inefficiencies and...
Village Health Laundry Operation Management System
One health solution for informal settlements
By: Kossam MUSUNDIRE, Amy Barry, Nazreen Ryklief
Supervised By: Maureen Tanner
Team 7 Project Abstract: Village Health Laundry Management System Business Requirement Village Health identified improper disposal of disposable nappies in Vrygrond as a major contributor to environmental degradation and the spread of zoonotic diseases....
WhatsApp Chatbot for Hiring Flow Automation
Streamlining Job applications with conversational automation
By: Lisa Kwetsi, Gomolemo Sebitlo, Kundi Phupheli, Alfred Beya Badjoko
Supervised By: Dirk Snyman, Kian Joubert
The project is driven by the need to address growing inefficiencies in traditional hiring processes. It requires the development of a WhatsApp AI chatbot that streamlines the job application process by automating candidate interactions and assisting...
83
Projects0
Partners10
CategoriesShow
Showcase YearInterested in Collaborating?
Join our community of innovators and help shape the future of technology.