AI Research applied to African problems
An AI & Data Science Research Group based at Makerere University, Uganda
ABOUT MAKERERE AI LAB
The AI and data science research group at Makerere University specialises in the application of artificial intelligence and data science -including, for example, methods from machine learning, computer vision and predictive analytics-to problems in the developing world.
Applications: natural language processing for under-resourced languages, automated diagnosis of both crop and human diseases, auction design for mobile commodity markets, analysis of traffic patterns in African cities, and of telecoms and remote sensing data for anticipating the spread of infectious diseases
VISIONExcellence in Artificial Intelligence research for accessible solutions.
MISSIONTo advance artificial intelligence research to solve real-world challenges.
The Varied projects of Makerere AI lab
- Machine Learning Datasets for crop Diseases: Imagery and Spectrometry Data
- Image phenotyping for necrosis in cassava roots
Machine Learning Datasets for crop Diseases: Imagery and Spectrometry Data
The project aims to deliver open, accessible, and quality machine learning datasets for crop pests and disease diagnosis based on crop imagery and spectrometry data from Uganda, Tanzania, Namibia, and Ghana. The development of beneficial and effective real-world machine-learning applications require localized and labeled pest and disease datasets. This project will provide these appropriate image datasets for food security crops grown in sub- Saharan Africa: Cassava, Maize, Beans, Bananas, Pearl Millet, and Cocoa. In collaboration with the national agricultural experts, this study will deliver on a two-way data set approach for crop pests and diseases: (a) A field-level Geo-coded and time-stamped dataset of 145,000 images representing diseased and healthy cassava, maize, beans, bananas, pearl millet, and cocoa crops. (b) A dataset of 8160 cassava spectra and 2000 spectra points of maize and pearl millet representing disease manifestations before symptoms are visibly seen by the human eye.
Image phenotyping for necrosis in cassava roots
We automate necrosis phenotyping with more efficiency than current methods
We use artificial intelligence to mine data from local village radio stations to generate timely data on crop pests and disease in sub-Saharan Africa. Crop loss due to pests and disease threatens the economic survival of smallholder farmers, and access to surveillance data is critically important yet often not affordable. Local radio shows are a powerful source of information flow in rural African villages: they cover topics including politics, policy, climate, and social circumstances, in addition to crop concerns. Collectively, this information provides a holistic representation of current events in these communities. They will analyze local broadcasts to generate crop surveillance data that is linked to the local community situation.Radio content will be collected at low cost through a collaboration with Pulse Labs Kampala, and they will build artificial intelligence models based on deep neural networks and keyword identification to mine the data.The results will be combined with photographs of diseased crops provided by local farmers and used to train machine learning models to ultimately extract radio information in multiple languages and with diverse accents. This project will provide near real-time crop surveillance data and allow for timely responses to threats.
WE ARE A COLLABORATIVE TRANSDISCIPLINARY, AND DIVERSE TEAM WITH A BIAS FOR APPLYING MACHINE LEARNING TO SOLVE PROBLEMS IN THE DEVELOPING WORLD.
Research and Administrative Assistant
Research Software Engineer
Research Software Engineer
GODLIVER OWOMUGISHA (PhD)
ROSE NAKIBULE (PhD)
UPCOMING EVENTS , SEMINARS AND WORKSHOPS
Topic: Recommender systems to improve farmer to farmer expert interaction.
Presenter: Jeremy Francis Tusubira
Time: April 01, 2021 10:00 AM Nairobi
Join Zoom Meeting
Meeting ID: 962 2824 4771