03 Sep 2021

#DS4SocietySeminar 2021 <> Environmental urban noise prediction for Kampala city

Ernest Mwebaze

Talk Details


The process or urbanization in many developing country cities has led to an explosion of noise pollution. Research indicates a strong link between long-term noise exposure and the risk of a negative health outcome particularly cardiovascular and metabolic defects. While many governments have formed some type of regulation to curb noise pollution, they are faced with the insurmountable task of being able to collect data and detect the type of noise pollution. At Sunbird AI we are attempting to solve this challenge by deploying autonomous noise sensors throughout the city. This talk will focus on the process of noise training data collection and models for predicting different types of noises in a developing world urban city like Kampala in Uganda. I will focus on the training data collection and preprocessing and show some early results from various modeling options we have considered.

Speaker Bio

Ernest Mwebaze obtained his doctorate in machine learning from the University of Groningen. He has over 10 years experience in academia where he was part of the faculty at the School of Computing and Informatics Technology of Makerere University in Uganda. At Makerere University he co-led the Makerere Artificial Intelligence research lab and headed several research projects. He has worked with the UN at the Pulse Lab Kampala and with Google AI, in Accra, Ghana. His current portfolio includes being the Strategy Lead at Sunbird AI, a non-profit focused on productization of AI for social good.

Video, Slides and Notes

  • content will be uploaded soon