U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

U-Time : A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging. / Perslev, Mathias; Hejselbak Jensen, Michael; Darkner, Sune; Jørgen Jennum, Poul; Igel, Christian.

Advances in Neural Information Processing Systems 32 (NIPS 2019). Bind 32 NIPS Proceedings, 2019. s. 4415-4426.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Perslev, M, Hejselbak Jensen, M, Darkner, S, Jørgen Jennum, P & Igel, C 2019, U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging. i Advances in Neural Information Processing Systems 32 (NIPS 2019). bind 32, NIPS Proceedings, s. 4415-4426, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, 08/12/2019. <https://papers.nips.cc/paper/8692-u-time-a-fully-convolutional-network-for-time-series-segmentation-applied-to-sleep-staging>

APA

Perslev, M., Hejselbak Jensen, M., Darkner, S., Jørgen Jennum, P., & Igel, C. (2019). U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging. I Advances in Neural Information Processing Systems 32 (NIPS 2019) (Bind 32, s. 4415-4426). NIPS Proceedings. https://papers.nips.cc/paper/8692-u-time-a-fully-convolutional-network-for-time-series-segmentation-applied-to-sleep-staging

Vancouver

Perslev M, Hejselbak Jensen M, Darkner S, Jørgen Jennum P, Igel C. U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging. I Advances in Neural Information Processing Systems 32 (NIPS 2019). Bind 32. NIPS Proceedings. 2019. s. 4415-4426

Author

Perslev, Mathias ; Hejselbak Jensen, Michael ; Darkner, Sune ; Jørgen Jennum, Poul ; Igel, Christian. / U-Time : A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging. Advances in Neural Information Processing Systems 32 (NIPS 2019). Bind 32 NIPS Proceedings, 2019. s. 4415-4426

Bibtex

@inproceedings{2efa380aac314bf5b1cf0a7c27f1d63b,
title = "U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging",
abstract = "Neural networks are becoming more and more popular for the analysis of physiological time-series. The most successful deep learning systems in this domain combine convolutional and recurrent layers to extract useful features to model temporal relations. Unfortunately, these recurrent models are difficult to tune and optimize. In our experience, they often require task-specific modifications, which makes them challenging to use for non-experts. We propose U-Time, a fully feed-forward deep learning approach to physiological time series segmentation developed for the analysis of sleep data. U-Time is a temporal fully convolutional network based on the U-Net architecture that was originally proposed for image segmentation. U-Time maps sequential inputs of arbitrary length to sequences of class labels on a freely chosen temporal scale. This is done by implicitly classifying every individual time-point of the input signal and aggregating these classifications over fixed intervals to form the final predictions. We evaluated U-Time for sleep stage classification on a large collection of sleep electroencephalography (EEG) datasets. In all cases, we found that U-Time reaches or outperforms current state-of-the-art deep learning models while being much more robust in the training process and without requiring architecture or hyperparameter adaptation across tasks.",
keywords = "Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing, Statistics - Machine Learning",
author = "Mathias Perslev and {Hejselbak Jensen}, Michael and Sune Darkner and {J{\o}rgen Jennum}, Poul and Christian Igel",
year = "2019",
month = oct,
day = "1",
language = "English",
volume = "32",
pages = "4415--4426",
booktitle = "Advances in Neural Information Processing Systems 32 (NIPS 2019)",
publisher = "NIPS Proceedings",
note = "33rd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Conference date: 08-12-2019 Through 14-12-2019",

}

RIS

TY - GEN

T1 - U-Time

T2 - 33rd Conference on Neural Information Processing Systems (NeurIPS 2019)

AU - Perslev, Mathias

AU - Hejselbak Jensen, Michael

AU - Darkner, Sune

AU - Jørgen Jennum, Poul

AU - Igel, Christian

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Neural networks are becoming more and more popular for the analysis of physiological time-series. The most successful deep learning systems in this domain combine convolutional and recurrent layers to extract useful features to model temporal relations. Unfortunately, these recurrent models are difficult to tune and optimize. In our experience, they often require task-specific modifications, which makes them challenging to use for non-experts. We propose U-Time, a fully feed-forward deep learning approach to physiological time series segmentation developed for the analysis of sleep data. U-Time is a temporal fully convolutional network based on the U-Net architecture that was originally proposed for image segmentation. U-Time maps sequential inputs of arbitrary length to sequences of class labels on a freely chosen temporal scale. This is done by implicitly classifying every individual time-point of the input signal and aggregating these classifications over fixed intervals to form the final predictions. We evaluated U-Time for sleep stage classification on a large collection of sleep electroencephalography (EEG) datasets. In all cases, we found that U-Time reaches or outperforms current state-of-the-art deep learning models while being much more robust in the training process and without requiring architecture or hyperparameter adaptation across tasks.

AB - Neural networks are becoming more and more popular for the analysis of physiological time-series. The most successful deep learning systems in this domain combine convolutional and recurrent layers to extract useful features to model temporal relations. Unfortunately, these recurrent models are difficult to tune and optimize. In our experience, they often require task-specific modifications, which makes them challenging to use for non-experts. We propose U-Time, a fully feed-forward deep learning approach to physiological time series segmentation developed for the analysis of sleep data. U-Time is a temporal fully convolutional network based on the U-Net architecture that was originally proposed for image segmentation. U-Time maps sequential inputs of arbitrary length to sequences of class labels on a freely chosen temporal scale. This is done by implicitly classifying every individual time-point of the input signal and aggregating these classifications over fixed intervals to form the final predictions. We evaluated U-Time for sleep stage classification on a large collection of sleep electroencephalography (EEG) datasets. In all cases, we found that U-Time reaches or outperforms current state-of-the-art deep learning models while being much more robust in the training process and without requiring architecture or hyperparameter adaptation across tasks.

KW - Computer Science - Machine Learning

KW - Electrical Engineering and Systems Science - Signal Processing

KW - Statistics - Machine Learning

M3 - Article in proceedings

VL - 32

SP - 4415

EP - 4426

BT - Advances in Neural Information Processing Systems 32 (NIPS 2019)

PB - NIPS Proceedings

Y2 - 8 December 2019 through 14 December 2019

ER -

ID: 239571874