Standard
Deep transfer learning for improving single-EEG arousal detection. / Olesen, Alexander Neergaard; Jennum, Poul; Mignot, Emmanuel; Sorensen, Helge B.D.
42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. IEEE, 2020. p. 99-103 9176723 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
Olesen, AN
, Jennum, P, Mignot, E & Sorensen, HBD 2020,
Deep transfer learning for improving single-EEG arousal detection. in
42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020., 9176723, IEEE, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 99-103, 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020, Montreal, Canada,
20/07/2020.
https://doi.org/10.1109/EMBC44109.2020.9176723
APA
Olesen, A. N.
, Jennum, P., Mignot, E., & Sorensen, H. B. D. (2020).
Deep transfer learning for improving single-EEG arousal detection. In
42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020 (pp. 99-103). [9176723] IEEE. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
https://doi.org/10.1109/EMBC44109.2020.9176723
Vancouver
Olesen AN
, Jennum P, Mignot E, Sorensen HBD.
Deep transfer learning for improving single-EEG arousal detection. In 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. IEEE. 2020. p. 99-103. 9176723. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
https://doi.org/10.1109/EMBC44109.2020.9176723
Author
Olesen, Alexander Neergaard ; Jennum, Poul ; Mignot, Emmanuel ; Sorensen, Helge B.D. / Deep transfer learning for improving single-EEG arousal detection. 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. IEEE, 2020. pp. 99-103 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
Bibtex
@inproceedings{2b302d5f686b4e54a0d078638cdf50fc,
title = "Deep transfer learning for improving single-EEG arousal detection",
abstract = "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.",
author = "Olesen, {Alexander Neergaard} and Poul Jennum and Emmanuel Mignot and Sorensen, {Helge B.D.}",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020 ; Conference date: 20-07-2020 Through 24-07-2020",
year = "2020",
doi = "10.1109/EMBC44109.2020.9176723",
language = "English",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
publisher = "IEEE",
pages = "99--103",
booktitle = "42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society",
}
RIS
TY - GEN
T1 - Deep transfer learning for improving single-EEG arousal detection
AU - Olesen, Alexander Neergaard
AU - Jennum, Poul
AU - Mignot, Emmanuel
AU - Sorensen, Helge B.D.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
U2 - 10.1109/EMBC44109.2020.9176723
DO - 10.1109/EMBC44109.2020.9176723
M3 - Article in proceedings
C2 - 33017940
AN - SCOPUS:85090995181
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 99
EP - 103
BT - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
PB - IEEE
T2 - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020
Y2 - 20 July 2020 through 24 July 2020
ER -