Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces : A Review
The algorithms of electroencephalography (EEG) decoding are mainly based on machine learning in current research. One of the main assumptions of machine learning is that training and test data belong to the same feature space and are subject to the same probability distribution. However, this may be violated in EEG processing. Variations across sessions/subjects result in a deviation of the feature distribution of EEG signals in the same task, which reduces the accuracy of the decoding model for mental tasks. Recently, transfer learning (TL) has shown great potential in processing EEG signals across sessions/subjects. In this work, we reviewed 80 related published studies from 2010 to 2020 about TL application for EEG decoding. Herein, we report what kind of TL methods have been used (e.g., instance knowledge, feature representation knowledge, and model parameter knowledge), describe which types of EEG paradigms have been analyzed, and summarize the datasets that have been used to evaluate performance. Moreover, we discuss the state-of-the-art and future development of TL for EEG decoding. The results show that TL can significantly improve the performance of decoding models across subjects/sessions and can reduce the calibration time of brain-computer interface (BCI) systems. This review summarizes the current practical suggestions and performance outcomes in the hope that it will provide guidance and help for EEG research in the future.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
Zur Gesamtaufnahme - volume:20 |
---|---|
Enthalten in: |
Sensors (Basel, Switzerland) - 20(2020), 21 vom: 05. Nov. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhang, Kai [VerfasserIn] |
---|
Links: |
---|
Themen: |
Classification |
---|
Anmerkungen: |
Date Completed 07.04.2021 Date Revised 12.11.2023 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.3390/s20216321 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM317353071 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM317353071 | ||
003 | DE-627 | ||
005 | 20231225163104.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2020 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3390/s20216321 |2 doi | |
028 | 5 | 2 | |a pubmed24n1057.xml |
035 | |a (DE-627)NLM317353071 | ||
035 | |a (NLM)33167561 | ||
035 | |a (PII)E6321 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhang, Kai |e verfasserin |4 aut | |
245 | 1 | 0 | |a Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces |b A Review |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 07.04.2021 | ||
500 | |a Date Revised 12.11.2023 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a The algorithms of electroencephalography (EEG) decoding are mainly based on machine learning in current research. One of the main assumptions of machine learning is that training and test data belong to the same feature space and are subject to the same probability distribution. However, this may be violated in EEG processing. Variations across sessions/subjects result in a deviation of the feature distribution of EEG signals in the same task, which reduces the accuracy of the decoding model for mental tasks. Recently, transfer learning (TL) has shown great potential in processing EEG signals across sessions/subjects. In this work, we reviewed 80 related published studies from 2010 to 2020 about TL application for EEG decoding. Herein, we report what kind of TL methods have been used (e.g., instance knowledge, feature representation knowledge, and model parameter knowledge), describe which types of EEG paradigms have been analyzed, and summarize the datasets that have been used to evaluate performance. Moreover, we discuss the state-of-the-art and future development of TL for EEG decoding. The results show that TL can significantly improve the performance of decoding models across subjects/sessions and can reduce the calibration time of brain-computer interface (BCI) systems. This review summarizes the current practical suggestions and performance outcomes in the hope that it will provide guidance and help for EEG research in the future | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Review | |
650 | 4 | |a EEG | |
650 | 4 | |a classification | |
650 | 4 | |a decoding | |
650 | 4 | |a review | |
650 | 4 | |a transfer learning | |
700 | 1 | |a Xu, Guanghua |e verfasserin |4 aut | |
700 | 1 | |a Zheng, Xiaowei |e verfasserin |4 aut | |
700 | 1 | |a Li, Huanzhong |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Sicong |e verfasserin |4 aut | |
700 | 1 | |a Yu, Yunhui |e verfasserin |4 aut | |
700 | 1 | |a Liang, Renghao |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Sensors (Basel, Switzerland) |d 2007 |g 20(2020), 21 vom: 05. Nov. |w (DE-627)NLM187985170 |x 1424-8220 |7 nnns |
773 | 1 | 8 | |g volume:20 |g year:2020 |g number:21 |g day:05 |g month:11 |
856 | 4 | 0 | |u http://dx.doi.org/10.3390/s20216321 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 20 |j 2020 |e 21 |b 05 |c 11 |