Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information
Since each individual subject may present completely different encephalogram (EEG) patterns with respect to other subjects, existing subject-independent emotion classifiers trained on data sampled from cross-subjects or cross-dataset generally fail to achieve sound accuracy. In this scenario, the do...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-05-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.677106/full |
| _version_ | 1831759212750831616 |
|---|---|
| author | Jianwen Tao Yufang Dan |
| author_facet | Jianwen Tao Yufang Dan |
| author_sort | Jianwen Tao |
| collection | DOAJ |
| description | Since each individual subject may present completely different encephalogram (EEG) patterns with respect to other subjects, existing subject-independent emotion classifiers trained on data sampled from cross-subjects or cross-dataset generally fail to achieve sound accuracy. In this scenario, the domain adaptation technique could be employed to address this problem, which has recently got extensive attention due to its effectiveness on cross-distribution learning. Focusing on cross-subject or cross-dataset automated emotion recognition with EEG features, we propose in this article a robust multi-source co-adaptation framework by mining diverse correlation information (MACI) among domains and features with l2,1−norm as well as correlation metric regularization. Specifically, by minimizing the statistical and semantic distribution differences between source and target domains, multiple subject-invariant classifiers can be learned together in a joint framework, which can make MACI use relevant knowledge from multiple sources by exploiting the developed correlation metric function. Comprehensive experimental evidence on DEAP and SEED datasets verifies the better performance of MACI in EEG-based emotion recognition. |
| first_indexed | 2024-12-22T01:03:15Z |
| format | Article |
| id | doaj.art-8a0409a8a439483fa5b40e8266ee3241 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-22T01:03:15Z |
| publishDate | 2021-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-8a0409a8a439483fa5b40e8266ee32412022-12-21T18:44:09ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-05-011510.3389/fnins.2021.677106677106Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation InformationJianwen TaoYufang DanSince each individual subject may present completely different encephalogram (EEG) patterns with respect to other subjects, existing subject-independent emotion classifiers trained on data sampled from cross-subjects or cross-dataset generally fail to achieve sound accuracy. In this scenario, the domain adaptation technique could be employed to address this problem, which has recently got extensive attention due to its effectiveness on cross-distribution learning. Focusing on cross-subject or cross-dataset automated emotion recognition with EEG features, we propose in this article a robust multi-source co-adaptation framework by mining diverse correlation information (MACI) among domains and features with l2,1−norm as well as correlation metric regularization. Specifically, by minimizing the statistical and semantic distribution differences between source and target domains, multiple subject-invariant classifiers can be learned together in a joint framework, which can make MACI use relevant knowledge from multiple sources by exploiting the developed correlation metric function. Comprehensive experimental evidence on DEAP and SEED datasets verifies the better performance of MACI in EEG-based emotion recognition.https://www.frontiersin.org/articles/10.3389/fnins.2021.677106/fullelectroencephalogramemotion recognitionmulti-source adaptationfeature selectionmaximum mean discrepancy |
| spellingShingle | Jianwen Tao Yufang Dan Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information Frontiers in Neuroscience electroencephalogram emotion recognition multi-source adaptation feature selection maximum mean discrepancy |
| title | Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information |
| title_full | Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information |
| title_fullStr | Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information |
| title_full_unstemmed | Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information |
| title_short | Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information |
| title_sort | multi source co adaptation for eeg based emotion recognition by mining correlation information |
| topic | electroencephalogram emotion recognition multi-source adaptation feature selection maximum mean discrepancy |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.677106/full |
| work_keys_str_mv | AT jianwentao multisourcecoadaptationforeegbasedemotionrecognitionbyminingcorrelationinformation AT yufangdan multisourcecoadaptationforeegbasedemotionrecognitionbyminingcorrelationinformation |