Afretec awards almost $1.7 million
The African Engineering and Technology Network (Afretec), a pan-African collaboration consisting of technology-centric universities across Africa, has awarded five $250,000 grants and eight $50,000 grants to build research capacity and accelerate inclusive digital growth throughout the African continent. Each multi-institutional research team will build on existing science, engineering, and technology in disciplines such as artificial intelligence (AI), machine learning, robotics, information technology, and cybersecurity.
The selected projects are particularly focused on improving the state of health, environment and sustainability, and energy in Africa. Several projects will also address the United Nations Sustainable Development Goals (UN SDGs), which were created with the goal of improving every aspect of human and environmental well-being.
Awarded seed grants
Real-time noise level web mapping through crowdsourcing: toward creating sustainable urban environments
Principal investigator: David Siriba
Partner institutions: University of Nairobi, University of Rwanda, Israel Institute of Technology
Noise pollution can have negative impacts on the well-being, health, and quality of life of urban residents. However, implementing and enforcing noise regulations requires consistent, continued availability of live data. This project proposes Volunteered Geographic Information (VGI), a tool that could help with effective noise reduction by crowdsourcing noise level data and creating a real-time noise level database and map.
Leveraging IoT and Edge-AI for detecting and managing schistosomiasis
Principal investigators: Moustafa Youssef, Benyl Muyoma Ondeto
Partner institutions: American University in Cairo, University of Nairobi, Université Cheikh Anta Diop
Schistosomiasis is a parasitic disease diagnosed by detecting microscopic worm eggs in stool, urine, or organ biopsies. The drug praziquantel is effective against schistosomiasis, but the disease continues to impact impoverished communities, especially in Africa. The goal of this project is to develop a prototype of a sensing device and an AI-based decision support system to help with the detection and management of schistosomiasis.
Application of AI techniques for extracting carbon from landfill waste for renewable energy
Principal investigator: Abdul Ganiyu Adelopo
Partner institutions: University of Lagos, University of Nairobi, Carnegie Mellon University Africa
African cities face a critical challenge in waste management due to rising urban populations and overloaded landfills. This project aims to use AI to assess the potential of resource reuse from landfills in African cities, focusing on renewable energy storage. The project will endeavor to create new datasets for predictive landfill machine-learning models and promote a cost-effective shift to renewable energy in African cities.
An investigation of a monitoring and predicting algorithm model for climate change-related diseases in African urban cities
Principal investigator: Immaculata Nwokoro
Partner institutions: University of Nairobi, University of Lagos
This project proposes an AI-driven predictive management system to tackle climate change-related diseases in African urban cities, addressing the acute challenges of limited health facilities and workforce shortages. The study aims to develop a robust data gathering system using Interactive Voice Response (IVR) connected to the Internet of Things (IoT), ensuring data inclusivity and confidentiality.
Evaluating digital transformation and maturity in youth-led micro, small, and medium enterprises across Sub-Saharan Africa: a comparative study in the health, energy, environment and sustainability sectors in Nigeria, Kenya, and South Africa
Principal investigator: Duncan Elly
Partner institutions: University of Nairobi, University of the Witwatersrand, University of Lagos
This project will investigate the role of micro, small, and medium enterprises (MSMEs) in Sub-Saharan Africa, specifically in the health, energy, environment and sustainability sectors across Nigeria, Kenya, and South Africa. The project seeks to help create a more supportive environment for youth-led MSMEs in the face of contemporary challenges.
Empowering African communities: culturally relevant cybersecurity education through comic books and AI models for children's online protection
Principal investigator: Jema David Ndibwile
Partner institutions: Carnegie Mellon University Africa, University of Rwanda
In the digital age, African children are increasingly at risk of being exposed to violent content, cyberbullying, or online sexual exploitation. This project aims to develop culturally relevant cybersecurity education materials and digital solutions tailored to the unique needs of African children and marginalized communities. The project seeks to empower African children to navigate the digital world safely.
An AI-driven environmental monitoring platform for low-resource setting
Principal investigator: Edwin Mugume
Partner institutions: Carnegie Mellon University Africa, Makerere University, University of Rwanda, University of Twente
Sub-Saharan Africa lacks sufficient environmental and weather monitoring nodes, mainly due to their high cost. This hinders efforts to accurately track the effects of climate change in the region. The project will design, develop, and test low-cost sensors for measuring temperature, humidity, wind speed and direction, precipitation, and particulate matter parameters.
Optimizing a mobile application for enhancing parents’ reporting and prediction of adverse effects following maternal and child immunization in Rwanda
Principal investigator: Aimable Musafiri
Partner institutions: University of Rwanda, Carnegie Mellon University Africa, Rwanda Food and Drugs Authority
Although over 90% of children and pregnant women in Rwanda receive vaccinations, there’s still a significant gap in the reporting of adverse effects following immunization (AEFI). This project proposes the VigiMobile application, which parents can use to directly report AEFI and bridge the gap between report and response. The project will also use machine learning algorithms to identify factors influencing AEFI in the Rwandan population.
