Real-time Smartphone-based Sleep Staging using 1-Channel EEG
Automatic and real-time sleep scoring is necessary to develop user interfaces that trigger stimuli in specific sleep stages. However, most automatic sleep scoring systems have been focused on offline data analysis. We present the first, real-time sleep staging system that uses deep learning without...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
IEEE
2020
|
| Online Access: | https://hdl.handle.net/1721.1/123845 |
| _version_ | 1826210275984932864 |
|---|---|
| author | Koushik, Abhay Amores Fernandez, Judith Maes, Patricia |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Koushik, Abhay Amores Fernandez, Judith Maes, Patricia |
| author_sort | Koushik, Abhay |
| collection | MIT |
| description | Automatic and real-time sleep scoring is necessary to develop user interfaces that trigger stimuli in specific sleep stages. However, most automatic sleep scoring systems have been focused on offline data analysis. We present the first, real-time sleep staging system that uses deep learning without the need for servers in a smartphone application for a wearable EEG. We employ real-time adaptation of a single channel Electroencephalography (EEG) to infer from a Time-Distributed Convolutional Neural Network (CNN). Polysomnography (PSG) -the gold standard for sleep staging-requires a human scorer and is both complex and resource-intensive. Our work demonstrates an end-to-end, smartphone-based pipeline that can infer sleep stages in just single 30-second epochs, with an overall accuracy of 83.5% on 20-fold cross validation for 5-stage classification of sleep stages using the open Sleep-EDF dataset. For comparison, inter-rater reliability among sleep-scoring experts is about 80% (Cohen's k=0\pmb.68 to \pmb0.76). We further propose an on-device metric independent of the deep learning model which increases the average accuracy of classifying deep-sleep (N3) to more than 97.2% on 4 test nights using power spectral analysis. Keyword: Sleep; Electroencephalography; Real-time systems; Brain modeling; Electrooculography; Spectral analysis; Training |
| first_indexed | 2024-09-23T14:47:13Z |
| format | Article |
| id | mit-1721.1/123845 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T14:47:13Z |
| publishDate | 2020 |
| publisher | IEEE |
| record_format | dspace |
| spelling | mit-1721.1/1238452022-10-01T22:28:08Z Real-time Smartphone-based Sleep Staging using 1-Channel EEG Koushik, Abhay Amores Fernandez, Judith Maes, Patricia Massachusetts Institute of Technology. Media Laboratory Automatic and real-time sleep scoring is necessary to develop user interfaces that trigger stimuli in specific sleep stages. However, most automatic sleep scoring systems have been focused on offline data analysis. We present the first, real-time sleep staging system that uses deep learning without the need for servers in a smartphone application for a wearable EEG. We employ real-time adaptation of a single channel Electroencephalography (EEG) to infer from a Time-Distributed Convolutional Neural Network (CNN). Polysomnography (PSG) -the gold standard for sleep staging-requires a human scorer and is both complex and resource-intensive. Our work demonstrates an end-to-end, smartphone-based pipeline that can infer sleep stages in just single 30-second epochs, with an overall accuracy of 83.5% on 20-fold cross validation for 5-stage classification of sleep stages using the open Sleep-EDF dataset. For comparison, inter-rater reliability among sleep-scoring experts is about 80% (Cohen's k=0\pmb.68 to \pmb0.76). We further propose an on-device metric independent of the deep learning model which increases the average accuracy of classifying deep-sleep (N3) to more than 97.2% on 4 test nights using power spectral analysis. Keyword: Sleep; Electroencephalography; Real-time systems; Brain modeling; Electrooculography; Spectral analysis; Training 2020-02-24T15:14:33Z 2020-02-24T15:14:33Z 2019-05 Article http://purl.org/eprint/type/ConferencePaper 9781538674772 2376-8894 https://hdl.handle.net/1721.1/123845 Koushik, Abhay, Judith Amores, and Pattie Maes. "Real-time Smartphone-based Sleep Staging using 1-Channel EEG." IEEE 16th International Conference on Wearable and Implantable Body Sensor Networks (BSN), May 2019, Chicago, Illinois, USA, IEEE © 2019 by IEEE http://dx.doi.org/10.1109/bsn.2019.8771091 Proceedings of the 2019 IEEE 16th International Conference on Wearable and Implantable Body Sensor Networks (BSN) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IEEE Prof. Maes via Elizabeth Soergel |
| spellingShingle | Koushik, Abhay Amores Fernandez, Judith Maes, Patricia Real-time Smartphone-based Sleep Staging using 1-Channel EEG |
| title | Real-time Smartphone-based Sleep Staging using 1-Channel EEG |
| title_full | Real-time Smartphone-based Sleep Staging using 1-Channel EEG |
| title_fullStr | Real-time Smartphone-based Sleep Staging using 1-Channel EEG |
| title_full_unstemmed | Real-time Smartphone-based Sleep Staging using 1-Channel EEG |
| title_short | Real-time Smartphone-based Sleep Staging using 1-Channel EEG |
| title_sort | real time smartphone based sleep staging using 1 channel eeg |
| url | https://hdl.handle.net/1721.1/123845 |
| work_keys_str_mv | AT koushikabhay realtimesmartphonebasedsleepstagingusing1channeleeg AT amoresfernandezjudith realtimesmartphonebasedsleepstagingusing1channeleeg AT maespatricia realtimesmartphonebasedsleepstagingusing1channeleeg |