Abstract: Your model is only as good as the data that goes into it, so removing the maximum amount of noise while retaining signal is vital. This talk will introduce basic signal processing and motion artefact removal techniques, such as low-pass filtering, Kalman filtering, and Savitzky-Golay filtering. The session will take you through practical examples that you can apply straight away to your biological data. I will also make recommendations for data collection to consider when designing a sensor so that you can get the best possible data (because prevention is better than treatment!). Those interested in machine learning and signal analysis for biomedical processing, electrical and optical signals, and wearables technology will enjoy this talk!
Bio: Michelle Hoogenhout is the lead data scientist at Hydrostasis, Inc. Hydrostasis is pioneering hydration monitoring by collecting optical changes in blood flow and water content from wrist-worn sensors. Michelle holds a PhD in Psychology (Neuropsychology) from the University of Cape Town and a neuropsychiatric genetics training fellowship from the Harvard T.H. Chan School of Public Health. She has over 10 years of experience in machine learning and insight generation from physiological and psychological data. Her research interests include the intersection between physical states and emotional and cognitive performance, as well as developmental disorders and empathy. Michelle also loves teaching and instructional design: she’s taught data science, psychology, and statistics. In her free time Michelle loves hiking, board games and swimming.
Lead Data Scientist | Hydrostasis, Inc