Deep transfer learning for improving single-EEG arousal detection
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Fulltext
Submitted manuscript, 756 KB, PDF document
Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.
Original language | English |
---|---|
Title of host publication | 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society : Enabling Innovative Technologies for Global Healthcare, EMBC 2020 |
Number of pages | 5 |
Publisher | IEEE |
Publication date | 2020 |
Pages | 99-103 |
Article number | 9176723 |
ISBN (Electronic) | 9781728119908 |
DOIs | |
Publication status | Published - 2020 |
Event | 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020 - Montreal, Canada Duration: 20 Jul 2020 → 24 Jul 2020 |
Conference
Conference | 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020 |
---|---|
Land | Canada |
By | Montreal |
Periode | 20/07/2020 → 24/07/2020 |
Series | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
---|---|
ISSN | 2375-7477 |
Links
- http://arxiv.org/pdf/2004.05111
Submitted manuscript
ID: 262894394