Practical Deep Learning for Physiological Time Series Analysis. With deep learning’s success, physiological time series analysis still faces significant challenges due to limited training data, diffic

Description

Practical Deep Learning for Physiological Time Series Analysis. With deep learning’s success, physiological time series analysis still faces significant challenges due to limited training data, difficulty in adapting to new domains, and black-box models. This project aims to pioneer practical deep learning methods that are consistently effective, even when faced with label scarcity, domain shift, and explainability gaps. The expected outcomes of this project are technological breakthroughs in sequential data analysis, using novel self-supervised, adaptive, and interpretable methods. These advancements will lay solid theoretical foundations for a broad range of time series applications, including human-centered manufacturing, human-machine interaction, Internet of Things, and smart cities.. Scheme: Discovery Early Career Researcher Award. Field: 4611 - Machine Learning. Lead: Dr Xiang Zhang