Please join us for the second talk in a special series in the UW Data Science Seminar featuring the AI@UW Seed Grant awardees. The AI@UW Seed Grant projects partner domain researchers from an applied disciplinary field with researchers specializing in AI theory and/or methodology. These projects were supported by the eScience Institute in collaboration with the Office of Research, the Paul G. Allen School of Computer Science & Engineering, the Information School, and the NSF Institute for Foundations of Data Science (IFDS).  This seminar will feature Dr. Kasim Rafiq, a postdoctoral researcher for the Center for Ecosystem Sentinels, and Medha Agrarwal, a PhD student in the UW Department of Statistics on Thursday, February 6th from 4:30 to 5:20 p.m. PT.

The seminar will be held in Hitchcock Hall 132 – Campus Map.

“Revealing the Hidden Lives of Cryptic Carnivores with Machine Learning and AI”

Abstract Animal-worn accelerometers offer exciting opportunities to advance the study of animal behaviour and ecology across diverse taxa and research topics by remotely identifying specific behaviours. However, challenges such as imbalanced training datasets and unknown model uncertainties have hindered the broader adoption of behaviour classification models within wildlife ecology. In our talk, we introduce the potential for behaviour classification to advance the study of wildlife ecology and introduce an open-source method for classifying animal behaviour from raw acceleration data. Our approach integrates machine learning and statistical inference techniques to evaluate and mitigate class imbalances, changes in model performance across ecological settings, and noisy classifications. Using data from free-ranging African wild dogs in the Okavango Delta, we then demonstrate the utility of our approach in real-world settings and conclude with a discussion of future directions.

Biography: Dr. Kasim Rafiq is a postdoctoral researcher within the Abrahms Lab in the Center for Ecosystem Sentinels. His work focuses on understanding the impacts of global change on the movements and behaviors of predators through a combination of fieldwork, animal-worn sensors, and AI. Kasim is a Washington Research Foundation Fellow and eScience Postdoctoral Fellow.

Medha Agrarwal is a PhD student in the Department of Statistics at the University of Washington. Her research specializes in generative modeling, optimal transport, and the application of deep learning.

The UW Data Science Seminar is an annual lecture series at the University of Washington that hosts scholars working across applied areas of data science, such as the sciences, engineering, humanities and arts along with methodological areas in data science, such as computer science, applied math and statistics. Our presenters come from all domain fields and include occasional external speakers from regional partners, governmental agencies and industry.

The 2024-2025 seminars will be held in person, and are free and open to the public.