Cargando…

A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance

In this study, generative adversarial networks named SleepGAN are proposed to expand the training set for automatic sleep stage classification tasks by generating both electroencephalogram (EEG) epochs and sequence relationships of sleep stages. In order to reach high accuracy, most existing classif...

Descripción completa

Detalles Bibliográficos
Autores principales: You, Yuyang, Guo, Xiaoyu, Zhong, Xuyang, Yang, Zhihong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9775526/
https://www.ncbi.nlm.nih.gov/pubmed/36551762
http://dx.doi.org/10.3390/biomedicines10123006
_version_ 1784855665888460800
author You, Yuyang
Guo, Xiaoyu
Zhong, Xuyang
Yang, Zhihong
author_facet You, Yuyang
Guo, Xiaoyu
Zhong, Xuyang
Yang, Zhihong
author_sort You, Yuyang
collection PubMed
description In this study, generative adversarial networks named SleepGAN are proposed to expand the training set for automatic sleep stage classification tasks by generating both electroencephalogram (EEG) epochs and sequence relationships of sleep stages. In order to reach high accuracy, most existing classification methods require substantial amounts of training data, but obtaining such quantities of real EEG epochs is expensive and time-consuming. We introduce few-shot learning, which is a method of training a GAN using a very small set of training data. This paper presents progressive Wasserstein divergence generative adversarial networks (GANs) and a relational memory generator to generate EEG epochs and stage transition sequences, respectively. For the evaluation of our generated data, we use single-channel EEGs from the public dataset Sleep-EDF. The addition of our augmented data and sequence to the training set was shown to improve the performance of the classification model. The accuracy of the model increased by approximately 1% after incorporating generated EEG epochs. Adding both the augmented data and sequence to the training set resulted in a further increase of 3%, from the original accuracy of 79.40% to 83.06%. The result proves that SleepGAN is a set of GANs capable of generating realistic EEG epochs and transition sequences under the condition of insufficient training data and can be used to enlarge the training dataset and improve the performance of sleep stage classification models in clinical practice.
format Online
Article
Text
id pubmed-9775526
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97755262022-12-23 A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance You, Yuyang Guo, Xiaoyu Zhong, Xuyang Yang, Zhihong Biomedicines Article In this study, generative adversarial networks named SleepGAN are proposed to expand the training set for automatic sleep stage classification tasks by generating both electroencephalogram (EEG) epochs and sequence relationships of sleep stages. In order to reach high accuracy, most existing classification methods require substantial amounts of training data, but obtaining such quantities of real EEG epochs is expensive and time-consuming. We introduce few-shot learning, which is a method of training a GAN using a very small set of training data. This paper presents progressive Wasserstein divergence generative adversarial networks (GANs) and a relational memory generator to generate EEG epochs and stage transition sequences, respectively. For the evaluation of our generated data, we use single-channel EEGs from the public dataset Sleep-EDF. The addition of our augmented data and sequence to the training set was shown to improve the performance of the classification model. The accuracy of the model increased by approximately 1% after incorporating generated EEG epochs. Adding both the augmented data and sequence to the training set resulted in a further increase of 3%, from the original accuracy of 79.40% to 83.06%. The result proves that SleepGAN is a set of GANs capable of generating realistic EEG epochs and transition sequences under the condition of insufficient training data and can be used to enlarge the training dataset and improve the performance of sleep stage classification models in clinical practice. MDPI 2022-11-22 /pmc/articles/PMC9775526/ /pubmed/36551762 http://dx.doi.org/10.3390/biomedicines10123006 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
You, Yuyang
Guo, Xiaoyu
Zhong, Xuyang
Yang, Zhihong
A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance
title A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance
title_full A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance
title_fullStr A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance
title_full_unstemmed A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance
title_short A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance
title_sort few-shot learning-based eeg and stage transition sequence generator for improving sleep staging performance
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9775526/
https://www.ncbi.nlm.nih.gov/pubmed/36551762
http://dx.doi.org/10.3390/biomedicines10123006
work_keys_str_mv AT youyuyang afewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT guoxiaoyu afewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT zhongxuyang afewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT yangzhihong afewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT youyuyang fewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT guoxiaoyu fewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT zhongxuyang fewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance
AT yangzhihong fewshotlearningbasedeegandstagetransitionsequencegeneratorforimprovingsleepstagingperformance