Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition
In practical encephalogram (EEG)-based machine learning, different subjects can be represented by many different EEG patterns, which would, in some extent, degrade the performance of extant subject-independent classifiers obtained from cross-subjects datasets. To this end, in this paper, we present...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.850906/full |
| _version_ | 1818009674180460544 |
|---|---|
| author | Jianwen Tao Yufang Dan Di Zhou Songsong He |
| author_facet | Jianwen Tao Yufang Dan Di Zhou Songsong He |
| author_sort | Jianwen Tao |
| collection | DOAJ |
| description | In practical encephalogram (EEG)-based machine learning, different subjects can be represented by many different EEG patterns, which would, in some extent, degrade the performance of extant subject-independent classifiers obtained from cross-subjects datasets. To this end, in this paper, we present a robust Latent Multi-source Adaptation (LMA) framework for cross-subject/dataset emotion recognition with EEG signals by uncovering multiple domain-invariant latent subspaces. Specifically, by jointly aligning the statistical and semantic distribution discrepancies between each source and target pair, multiple domain-invariant classifiers can be trained collaboratively in a unified framework. This framework can fully utilize the correlated knowledge among multiple sources with a novel low-rank regularization term. Comprehensive experiments on DEAP and SEED datasets demonstrate the superior or comparable performance of LMA with the state of the art in the EEG-based emotion recognition. |
| first_indexed | 2024-04-14T05:46:07Z |
| format | Article |
| id | doaj.art-ac54bfc060c8453fb77eda8a196882f5 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-14T05:46:07Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-ac54bfc060c8453fb77eda8a196882f52022-12-22T02:09:18ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-04-011610.3389/fnins.2022.850906850906Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion RecognitionJianwen Tao0Yufang Dan1Di Zhou2Songsong He3Institute of Artificial Intelligence Application, Ningbo Polytechnic, Ningbo, ChinaInstitute of Artificial Intelligence Application, Ningbo Polytechnic, Ningbo, ChinaIndustrial Technological Institute of Intelligent Manufacturing, Sichuan University of Arts and Science, Dazhou, ChinaInstitute of Artificial Intelligence Application, Ningbo Polytechnic, Ningbo, ChinaIn practical encephalogram (EEG)-based machine learning, different subjects can be represented by many different EEG patterns, which would, in some extent, degrade the performance of extant subject-independent classifiers obtained from cross-subjects datasets. To this end, in this paper, we present a robust Latent Multi-source Adaptation (LMA) framework for cross-subject/dataset emotion recognition with EEG signals by uncovering multiple domain-invariant latent subspaces. Specifically, by jointly aligning the statistical and semantic distribution discrepancies between each source and target pair, multiple domain-invariant classifiers can be trained collaboratively in a unified framework. This framework can fully utilize the correlated knowledge among multiple sources with a novel low-rank regularization term. Comprehensive experiments on DEAP and SEED datasets demonstrate the superior or comparable performance of LMA with the state of the art in the EEG-based emotion recognition.https://www.frontiersin.org/articles/10.3389/fnins.2022.850906/fullencephalogramlatent spaceemotion recognitionco-adaptationmaximum mean discrepancy |
| spellingShingle | Jianwen Tao Yufang Dan Di Zhou Songsong He Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition Frontiers in Neuroscience encephalogram latent space emotion recognition co-adaptation maximum mean discrepancy |
| title | Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition |
| title_full | Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition |
| title_fullStr | Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition |
| title_full_unstemmed | Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition |
| title_short | Robust Latent Multi-Source Adaptation for Encephalogram-Based Emotion Recognition |
| title_sort | robust latent multi source adaptation for encephalogram based emotion recognition |
| topic | encephalogram latent space emotion recognition co-adaptation maximum mean discrepancy |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.850906/full |
| work_keys_str_mv | AT jianwentao robustlatentmultisourceadaptationforencephalogrambasedemotionrecognition AT yufangdan robustlatentmultisourceadaptationforencephalogrambasedemotionrecognition AT dizhou robustlatentmultisourceadaptationforencephalogrambasedemotionrecognition AT songsonghe robustlatentmultisourceadaptationforencephalogrambasedemotionrecognition |