Abstract
Electroencephalogram (EEG)-based emotion recognition is receiving significant attention in research on brain-computer interfaces (BCI) and health care. To recognize cross-subject emotion from EEG data accurately, a technique capable of finding an effective representation robust to the subject-specific variability associated with EEG data collection processes is necessary. In this paper, a new method to predict cross-subject emotion using time-series analysis and spatial correlation is proposed. To represent the spatial connectivity between brain regions, a channel-wise feature is proposed, which can effectively handle the correlation between all channels. The channel-wise feature is defined by a symmetric matrix, the elements of which are calculated by the Pearson correlation coefficient between two-pair channels capable of complementarily handling subject-specific variability. The channel-wise features are then fed to two-layer stacked long short-term memory (LSTM), which can extract temporal features and learn an emotional model. Extensive experiments on two publicly available datasets, the Dataset for Emotion Analysis using Physiological Signals (DEAP) and the SJTU (Shanghai Jiao Tong University) Emotion EEG Dataset (SEED), demonstrate the effectiveness of the combined use of channel-wise features and LSTM. Experimental results achieve state-of-the-art classification rates of 98.93% and 99.10% during the two-class classification of valence and arousal in DEAP, respectively, with an accuracy of 99.63% during three-class classification in SEED.
Highlights
Emotions are fundamental in the daily lives of humans, and they play an essential role in decision-making, human interactions, and even mental health [1]
For the Dataset for Emotion Analysis using Physiological Signals (DEAP), our model achieves state-of-the-art accuracy of 98.93% and 99.10% on two-class valence and arousal classification tasks, respectively, and achieves 98.32% on four-class classification in one model
An experiment was performed to prove the effectiveness of the presented channel-wise features and the two-layer stacked long short-term memory (LSTM) for cross-subject emotion classification
Summary
Emotions are fundamental in the daily lives of humans, and they play an essential role in decision-making, human interactions, and even mental health [1]. There has been much research on emotion recognition using facial expressions [3], thermography [4], motion capture system [5], text [6], and speech [7]. To solve this problem, electroencephalogram (EEG) has been considered as an alternative for detecting emotions produced unintentionally by the human brain. Benefiting from many non-invasive and easy-to-wear EEG measuring devices, it is easy to monitor electrical brain activity with EEG. Due to these advantages, EEG-based research has been relatively active
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
