演講者：劉聚仁 教授 (成大數學系)

標題：Automatic Sleep Stage Scoring based on the Synchrosqueezing Transform and Multiview Diffusion Maps

時間：4月7日下午2點00分

地點：校本部第二綜合大樓8樓 B808 教室

摘要： This presentation discusses an unsupervised approach for sleep dynamics exploration and automatic annotation by combining modern harmonic analysis tools. We apply a nonlinear-type time frequency analysis tool to extract the frequency-domain features from a pair of physiological signals. The dynamics of the spectral information is visualized by the multiview diffusion maps. Based on the feature sequence and the expert-determined sleep stages, we construct a hidden Markov model to predict the sleep stages of new subjects. The prediction performance is validated on a publicly available benchmark database, Physionet Sleep-EDF SC and ST, with the leave-one-subject-out cross validation. This talk includes the joint works [1-2] with Yu-Lun Lo, John Malik, Yuan-Chung Sheu, and Hau-Tieng Wu.

Reference:

[1] (with Y. L. Lo, Y. C. Sheu, and H. T. Wu) Explore intrinsic geometry of sleep dynamics and predict sleep stage by unsupervised learning techniques. (To be appeared in the Springer book Harmonic Analysis and Applications)

[2] (with Y. L. Lo, J. Malik, Y. C. Sheu, and H. T. Wu) Diffuse to fuse EEG spectra -- intrinsic geometry of sleep dynamics for classification. Biomedical Signal Processing and Control 55 (2020)