Few-shot EEG sleep staging based on transductive prototype optimization network
Electroencephalography (EEG) is a commonly used technology for monitoring brain activities and diagnosing sleep disorders. Clinically, doctors need to manually stage sleep based on EEG signals, which is a time-consuming and laborious task. In this study, we propose a few-shot EEG sleep staging terme...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2023.1297874/full |
| _version_ | 1827594502051725312 |
|---|---|
| author | Jingcong Li Chaohuang Wu Jiahui Pan Fei Wang |
| author_facet | Jingcong Li Chaohuang Wu Jiahui Pan Fei Wang |
| author_sort | Jingcong Li |
| collection | DOAJ |
| description | Electroencephalography (EEG) is a commonly used technology for monitoring brain activities and diagnosing sleep disorders. Clinically, doctors need to manually stage sleep based on EEG signals, which is a time-consuming and laborious task. In this study, we propose a few-shot EEG sleep staging termed transductive prototype optimization network (TPON) method, which aims to improve the performance of EEG sleep staging. Compared with traditional deep learning methods, TPON uses a meta-learning algorithm, which generalizes the classifier to new classes that are not visible in the training set, and only have a few examples for each new class. We learn the prototypes of existing objects through meta-training, and capture the sleep features of new objects through the “learn to learn” method of meta-learning. The prototype distribution of the class is optimized and captured by using support set and unlabeled high confidence samples to increase the authenticity of the prototype. Compared with traditional prototype networks, TPON can effectively solve too few samples in few-shot learning and improve the matching degree of prototypes in prototype network. The experimental results on the public SleepEDF-2013 dataset show that the proposed algorithm outperform than most advanced algorithms in the overall performance. In addition, we experimentally demonstrate the feasibility of cross-channel recognition, which indicates that there are many similar sleep EEG features between different channels. In future research, we can further explore the common features among different channels and investigate the combination of universal features in sleep EEG. Overall, our method achieves high accuracy in sleep stage classification, demonstrating the effectiveness of this approach and its potential applications in other medical fields. |
| first_indexed | 2024-03-09T02:37:39Z |
| format | Article |
| id | doaj.art-8fa2eecf87e949c4a55b6ee4ec240cbb |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-03-09T02:37:39Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-8fa2eecf87e949c4a55b6ee4ec240cbb2023-12-06T08:15:55ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962023-12-011710.3389/fninf.2023.12978741297874Few-shot EEG sleep staging based on transductive prototype optimization networkJingcong LiChaohuang WuJiahui PanFei WangElectroencephalography (EEG) is a commonly used technology for monitoring brain activities and diagnosing sleep disorders. Clinically, doctors need to manually stage sleep based on EEG signals, which is a time-consuming and laborious task. In this study, we propose a few-shot EEG sleep staging termed transductive prototype optimization network (TPON) method, which aims to improve the performance of EEG sleep staging. Compared with traditional deep learning methods, TPON uses a meta-learning algorithm, which generalizes the classifier to new classes that are not visible in the training set, and only have a few examples for each new class. We learn the prototypes of existing objects through meta-training, and capture the sleep features of new objects through the “learn to learn” method of meta-learning. The prototype distribution of the class is optimized and captured by using support set and unlabeled high confidence samples to increase the authenticity of the prototype. Compared with traditional prototype networks, TPON can effectively solve too few samples in few-shot learning and improve the matching degree of prototypes in prototype network. The experimental results on the public SleepEDF-2013 dataset show that the proposed algorithm outperform than most advanced algorithms in the overall performance. In addition, we experimentally demonstrate the feasibility of cross-channel recognition, which indicates that there are many similar sleep EEG features between different channels. In future research, we can further explore the common features among different channels and investigate the combination of universal features in sleep EEG. Overall, our method achieves high accuracy in sleep stage classification, demonstrating the effectiveness of this approach and its potential applications in other medical fields.https://www.frontiersin.org/articles/10.3389/fninf.2023.1297874/fullmeta-learningfew-shottransductive prototype optimizationsleep stageEEG |
| spellingShingle | Jingcong Li Chaohuang Wu Jiahui Pan Fei Wang Few-shot EEG sleep staging based on transductive prototype optimization network Frontiers in Neuroinformatics meta-learning few-shot transductive prototype optimization sleep stage EEG |
| title | Few-shot EEG sleep staging based on transductive prototype optimization network |
| title_full | Few-shot EEG sleep staging based on transductive prototype optimization network |
| title_fullStr | Few-shot EEG sleep staging based on transductive prototype optimization network |
| title_full_unstemmed | Few-shot EEG sleep staging based on transductive prototype optimization network |
| title_short | Few-shot EEG sleep staging based on transductive prototype optimization network |
| title_sort | few shot eeg sleep staging based on transductive prototype optimization network |
| topic | meta-learning few-shot transductive prototype optimization sleep stage EEG |
| url | https://www.frontiersin.org/articles/10.3389/fninf.2023.1297874/full |
| work_keys_str_mv | AT jingcongli fewshoteegsleepstagingbasedontransductiveprototypeoptimizationnetwork AT chaohuangwu fewshoteegsleepstagingbasedontransductiveprototypeoptimizationnetwork AT jiahuipan fewshoteegsleepstagingbasedontransductiveprototypeoptimizationnetwork AT feiwang fewshoteegsleepstagingbasedontransductiveprototypeoptimizationnetwork |