Sample size: 10 patients (with multiple night recordings) Current model accuracy: 83%
Goals:
- Train model using PSG data from open-source database to classify sleep stages given EEG readings.
- Build a physical EEG device to collect EEG readings from a user.
Future ideas:
- Look into training model using ECG and HRV instead of EEG?
- ECG monitors are much more convenient to use
- Other products have already implemented this with ~80-90% accuracy
Sleep stage classification from polysomnography (PSG) data
Stanislas Chambon, Mathieu N. Galtier, Pierrick J. Arnal, Gilles Wainrib, and Alexandre Gramfort. A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 26(4):758–769, 2018. doi:10.1109/TNSRE.2018.2813138.
i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this i will finish this