Skip to main content

# Visualising Convolutional Neural Network Decisions in Automatic Sleep Scoring

Andreotti, Fernando, Phan, Huy, De Vos, Maarten (2018) Visualising Convolutional Neural Network Decisions in Automatic Sleep Scoring. In: CEUR Workshop Proceedings. Joint Workshop on Artificial Intelligence in Health (AIH) 2018. . pp. 70-81. CEUR Workshop Proceedings, Stockholm, Sweden (KAR id:72666)

 PDF Publisher pdf Language: English This work is licensed under a Creative Commons Attribution 4.0 International License. Download (421kB) Preview Preview This file may not be suitable for users of assistive technology. Request an accessible format Official URLhttp://ceur-ws.org/Vol-2142/paper5.pdf

## Abstract

Current sleep medicine relies on the supervised analysis of polysomnographic recordings, which comprise amongst others electroencephalogram (EEG), electromyogram (EMG), and electrooculogram (EOG) signals. Convolutional neural networks (CNN) provide an interesting framework for automated sleep classification, however, the lack of interpretability of its results has hampered CNN's further use in medicine. In this study, we train a CNN using as input Continuous Wavelet transformed EEG, EOG and EMG recordings from a publicly available dataset. The network achieved a 10-fold cross-validation Cohen's Kappa score of $\kappa = 0.71 \pm 0.01$. Further, we provide insights on how this network classifies individual epochs of sleep using Guided Gradient-weighted Class Activation Maps (Guided Grad-CAM). The proposed approach is able to produce fine-grained activation maps on time-frequency domain for each signal providing a useful tool for identifying relevant features in CNNs.

Item Type: Conference or workshop item (Paper) Convolutional Neural Networks, Class Activation Maps, Guided Backpropagation, Polysomnography, Wavelet Transform Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing Huy Phan 25 Feb 2019 14:39 UTC 16 Feb 2021 14:02 UTC https://kar.kent.ac.uk/id/eprint/72666 (The current URI for this page, for reference purposes) https://orcid.org/0000-0003-4096-785X
• Depositors only (login required):

### Downloads

Downloads per month over past year