Strachey Lecture - Mixed Signals: audio and wearable data analysis for health diagnostics
- 14:00 2nd November 2021 ( week 4, Michaelmas Term 2021 )Via MS Teams
Wearable and mobile devices are very good proxies for human behaviour. Yet, making the inference from the raw sensor data to individuals’ behaviour remains difficult. The list of challenges is very long: from collecting the right data and using the right sensor, respecting resource constraints, identifying the right analysis techniques, labelling the data, limiting privacy invasion, to dealing with heterogeneous data sources and adapting to changes in behaviour.
In this talk, I plan to reflect on these challenges and highlight the opportunities that mobile and wearable health systems are introducing for community, the developers as well as the users. I will use examples from my group's ongoing research on exploring
machine learning and data analysis for health application in collaboration with epidemiologists and clinicians. In particular I will concentrate a part of the talk on an ERC project focusing on leveraging audio signals from the human body to help automated diagnostics and disease progression analysis.
Booking is essential:
The Strachey Lectures are generously supported by OxFORD Asset Management