Dina Machuve
Lecturer and Researcher
Nelson Mandela African Institution of Science and Technology (NM-AIST) |
Dina Machuve is a Lecturer and Researcher at the Nelson Mandela African Institution of Science and Technology (NM-AIST) in Arusha, Tanzania. Her research focuses on developing data-driven solutions in Agriculture. For her PhD dissertation she investigated the information logistics of small and medium size food processors. Currently, she is looking at developing a poultry diseases diagnostics tool using computer vision and bioinformatics methods for small and medium scale poultry farmers in Tanzania.
She is an Early Career Fellow of the Organization for Women in Science for the Developing World (OWSD). She serves in the organizing committee of Data Science Africa (DSA), an organization that runs an annual data science and machine learning summer school and workshop in Africa.
|
She is also a member of a research group on Mechanism Design for Social Good (MD4SG). She completed her PhD in Information and Communication Science and Engineering from NM-AIST in 2016. She also has an MS in Electrical Engineering and BSc in Electrical Engineering.
Technical Vision Talk: Improving Livestock Health with Deep Learning
Small to medium scale farming (crop and livestock) accounts for 70% of the food production of the developing world and supports over 380 million farming households. Livestock diseases are economically significant from their effects on production, performance and some are zoonotic. The understanding and mitigation of these diseases is hampered because farm data is not collected or analyzed systematically. In this work, we demonstrate the potential application of deep learning (in particular, CNN) for disease diagnostics in such settings. We consider a specific example of poultry diseases diagnostics in Tanzania where there are 3.7 million households keeping chicken among the 4.7 million agricultural households. We discuss the data collection pipeline in low resourced settings and the application of CNNs in poultry diseases diagnostics using fecal imagery dataset. With the help of CNNs, farmers will have the potential to better diagnose poultry diseases and improve livestock health.
Meet-the-Speaker:
Dina will also participate in a Meet the Speaker session, where you will be able to have a deeper dive conversation about topics covered on the main stage. Accessible to WiDS Worldwide registrants.
Dina will also participate in a Meet the Speaker session, where you will be able to have a deeper dive conversation about topics covered on the main stage. Accessible to WiDS Worldwide registrants.