← Research

Research project / 2018

2. Computational-model and unsupervised-learning approaches for brain state identification and monitoring

Propose an unsupervised-learning approach based on a source mixture model to identify brain states (e.g. sleep stages, attention levels, and emotions) using EEG signals. [ Hsu et al. , NeuroImage, 2018 ; IEEE BioCAS, 2018 ] Introduced a new measure for non-stationary signals and proposed an online signal processing pipeline to monitor car drivers' drowsiness levels. [ Hsu et al. , HCI, 2016 ; Hsu and Jung, JNE, 2017 ] A new measure for non-stationary signals for monitoring drowsiness levels The unsupervised-learning approach based on a source mixture model

View the source ↗

CITATION / SOURCE ENTRY

Propose an unsupervised-learning approach based on a source mixture model to identify brain states (e.g. sleep stages, attention levels, and emotions) using EEG signals. [ Hsu et al. , NeuroImage, 2018 ; IEEE BioCAS, 2018 ]
Introduced a new measure for non-stationary signals and proposed an online signal processing pipeline to monitor car drivers' drowsiness levels. [ Hsu et al. , HCI, 2016 ; Hsu and Jung, JNE, 2017 ]
A new measure for non-stationary signals for monitoring drowsiness levels
The unsupervised-learning approach based on a source mixture model

Figure from the original research archive

Related materials & sources.

Archive year. Full dates and venues are preserved in the source entry below.

Back to the full library →