Cerebral asymmetry representation learning-based deep subdomain adaptation network for electroencephalogram-based emotion recognition
© 2024 Institute of Physics and Engineering in Medicine..
Objective.Extracting discriminative spatial information from multiple electrodes is a crucial and challenging problem for electroencephalogram (EEG)-based emotion recognition. Additionally, the domain shift caused by the individual differences degrades the performance of cross-subject EEG classification.Approach.To deal with the above problems, we propose the cerebral asymmetry representation learning-based deep subdomain adaptation network (CARL-DSAN) to enhance cross-subject EEG-based emotion recognition. Specifically, the CARL module is inspired by the neuroscience findings that asymmetrical activations of the left and right brain hemispheres occur during cognitive and affective processes. In the CARL module, we introduce a novel two-step strategy for extracting discriminative features through intra-hemisphere spatial learning and asymmetry representation learning. Moreover, the transformer encoders within the CARL module can emphasize the contributive electrodes and electrode pairs. Subsequently, the DSAN module, known for its superior performance over global domain adaptation, is adopted to mitigate domain shift and further improve the cross-subject performance by aligning relevant subdomains that share the same class samples.Main Results.To validate the effectiveness of the CARL-DSAN, we conduct subject-independent experiments on the DEAP database, achieving accuracies of 68.67% and 67.11% for arousal and valence classification, respectively, and corresponding accuracies of 67.70% and 67.18% on the MAHNOB-HCI database.Significance.The results demonstrate that CARL-DSAN can achieve an outstanding cross-subject performance in both arousal and valence classification.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:45 |
|---|---|
| Enthalten in: |
Physiological measurement - 45(2024), 3 vom: 26. März |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Zhe [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Cerebral asymmetry |
|---|
| Anmerkungen: |
Date Completed 27.03.2024 Date Revised 27.03.2024 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1088/1361-6579/ad2eb6 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM369124081 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM369124081 | ||
| 003 | DE-627 | ||
| 005 | 20240327235949.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240301s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6579/ad2eb6 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1351.xml |
| 035 | |a (DE-627)NLM369124081 | ||
| 035 | |a (NLM)38422513 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Zhe |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Cerebral asymmetry representation learning-based deep subdomain adaptation network for electroencephalogram-based emotion recognition |
| 264 | 1 | |c 2024 | |
| 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 27.03.2024 | ||
| 500 | |a Date Revised 27.03.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2024 Institute of Physics and Engineering in Medicine. | ||
| 520 | |a Objective.Extracting discriminative spatial information from multiple electrodes is a crucial and challenging problem for electroencephalogram (EEG)-based emotion recognition. Additionally, the domain shift caused by the individual differences degrades the performance of cross-subject EEG classification.Approach.To deal with the above problems, we propose the cerebral asymmetry representation learning-based deep subdomain adaptation network (CARL-DSAN) to enhance cross-subject EEG-based emotion recognition. Specifically, the CARL module is inspired by the neuroscience findings that asymmetrical activations of the left and right brain hemispheres occur during cognitive and affective processes. In the CARL module, we introduce a novel two-step strategy for extracting discriminative features through intra-hemisphere spatial learning and asymmetry representation learning. Moreover, the transformer encoders within the CARL module can emphasize the contributive electrodes and electrode pairs. Subsequently, the DSAN module, known for its superior performance over global domain adaptation, is adopted to mitigate domain shift and further improve the cross-subject performance by aligning relevant subdomains that share the same class samples.Main Results.To validate the effectiveness of the CARL-DSAN, we conduct subject-independent experiments on the DEAP database, achieving accuracies of 68.67% and 67.11% for arousal and valence classification, respectively, and corresponding accuracies of 67.70% and 67.18% on the MAHNOB-HCI database.Significance.The results demonstrate that CARL-DSAN can achieve an outstanding cross-subject performance in both arousal and valence classification | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a cerebral asymmetry | |
| 650 | 4 | |a domain adaptation | |
| 650 | 4 | |a electroencephalogram | |
| 650 | 4 | |a emotion recognition | |
| 700 | 1 | |a Wang, Yongxiong |e verfasserin |4 aut | |
| 700 | 1 | |a Wan, Xin |e verfasserin |4 aut | |
| 700 | 1 | |a Tang, Yiheng |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Physiological measurement |d 1997 |g 45(2024), 3 vom: 26. März |w (DE-627)NLM074655876 |x 1361-6579 |7 nnns |
| 773 | 1 | 8 | |g volume:45 |g year:2024 |g number:3 |g day:26 |g month:03 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1088/1361-6579/ad2eb6 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 45 |j 2024 |e 3 |b 26 |c 03 | ||