A New Post-Processing Method Using Latent Structure Influence Models for Channel Fusion in Automatic Sleep Staging
Published in IEEE Journal of Biomedical and Health Informatics, 2022
This paper introduces an innovative application of Latent Structure Influence Models (LSIMs) for improving automatic sleep staging through intelligent channel fusion. The work addresses the challenge of effectively combining information from multiple EEG channels to enhance sleep stage classification accuracy.
The proposed post-processing method leverages the inherent structure in multi-channel sleep EEG data, using LSIMs to model the dependencies between different channels and sleep stages. Experimental results demonstrate significant improvements in sleep staging accuracy compared to traditional single-channel and simple multi-channel approaches. This work has direct clinical applications for sleep disorder diagnosis and monitoring.
Recommended citation: Karimi, S., & Shamsollahi, M. B. (2022). "A New Post-Processing Method Using Latent Structure Influence Models for Channel Fusion in Automatic Sleep Staging." IEEE Journal of Biomedical and Health Informatics.
Download Paper