An Efficient LSTM Network for Emotion Recognition From Multichannel EEG Signals

Most previous EEG-based emotion recognition methods studied hand-crafted EEG features extracted from different electrodes. In this article, we study the relation among different EEG electrodes and propose a deep learning method to automatically extract the spatial features that characterize the func...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on affective computing Ročník 13; číslo 3; s. 1528 - 1540
Hlavní autoři: Du, Xiaobing, Ma, Cuixia, Zhang, Guanhua, Li, Jinyao, Lai, Yu-Kun, Zhao, Guozhen, Deng, Xiaoming, Liu, Yong-Jin, Wang, Hongan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.07.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
attention mechanism
Brain modeling
Channels
Data models
domain adaptation
Domains
Electrodes
Electroencephalography
Emotion recognition
Emotions
Feature extraction
Frequency-domain analysis
LSTM
Machine learning
multichannel EEG
ISSN:1949-3045, 1949-3045
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Most previous EEG-based emotion recognition methods studied hand-crafted EEG features extracted from different electrodes. In this article, we study the relation among different EEG electrodes and propose a deep learning method to automatically extract the spatial features that characterize the functional relation between EEG signals at different electrodes. Our proposed deep model is called AT tention-based LSTM with D omain D iscriminator (ATDD-LSTM), a model based on Long Short-Term Memory (LSTM) for emotion recognition that can characterize nonlinear relations among EEG signals of different electrodes. To achieve state-of-the-art emotion recognition performance, the architecture of ATDD-LSTM has two distinguishing characteristics: (1) By applying the attention mechanism to the feature vectors produced by LSTM, ATDD-LSTM automatically selects suitable EEG channels for emotion recognition, which makes the learned model concentrate on the emotion related channels in response to a given emotion; (2) To minimize the significant feature distribution shift between different sessions and/or subjects, ATDD-LSTM uses a domain discriminator to modify the data representation space and generate domain-invariant features. We evaluate the proposed ATDD-LSTM model on three public EEG emotional databases (DEAP, SEED and CMEED) for emotion recognition. The experimental results demonstrate that our ATDD-LSTM model achieves superior performance on subject-dependent (for the same subject), subject-independent (for different subjects) and cross-session (for the same subject) evaluation.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1949-3045
1949-3045
DOI:10.1109/TAFFC.2020.3013711