Improving Cross-Subject Emotion Recognition Performance with an Encoder-Decoder Structure

Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performan...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Ročník 2024; s. 1 - 4
Hlavní autoři: Cui, Haowei, Shi, Hanwen, Lu, Bao-Liang, Zheng, Wei-Long
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.07.2024
Témata:
Adaptation models
Algorithms
Brain modeling
Computational modeling
Convolution
Degradation
Electroencephalography
Electroencephalography - methods
Emotion recognition
Emotions - physiology
Engineering in medicine and biology
Entropy
Humans
Signal Processing, Computer-Assisted
Training
ISSN:2694-0604, 2694-0604
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Emotion recognition based on EEG is an important task in the field of affective computing. Due to individual differences, emotion recognition performance of cross-subject models is significantly lower than that of subject-dependent models. To minimize the degradation of emotion recognition performance due to the differences in the EEG distributions of different subjects, domain adaptation algorithms have been used to transfer the knowledge from source to target domains, and have achieved good performance in the task of cross-subject emotion recognition. However, most domain adaptation methods do not take into account the possible correspondence between the samples in the source and target domains. Therefore, we adopt an encoder-decoder architecture, the EEG converter, which utilizes the time alignment condition between the source and target domains during training. In the EEG converter structure, the encoder consists of a series of convolutional layers and max pooling layers, and the decoder consists of a series of upsampling layers and convolutional layers. We use the EEG converter to transfer the differential entropy features of EEG signals, from one subject to another, on datasets SEED, SEED-IV, and SEEDV. The results show that the transfer effect of the EEG converter significantly improves the performance of emotion recognition and outperforms existing domain adaptation algorithms.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2694-0604
2694-0604
DOI:10.1109/EMBC53108.2024.10782033