TY - GEN
T1 - Emotion recognition from EEG using RASM and LSTM
AU - Li, Zhenqi
AU - Tian, Xiang
AU - Shu, Lin
AU - Xu, Xiangmin
AU - Hu, Bin
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd. 2018.
PY - 2018
Y1 - 2018
N2 - In the field of human-computer interaction, automatic emotion recognition is an important and challenging task. As a physiological signal that directly reflects the brain activity, EEG has advantages in emotion recognition. However, previous studies seldom consider together the temporal, spatial, and frequency characteristics of EEG signals, and the reported emotion recognition accuracy is not adequate for applications. To address this issue, this study proposes a new approach which extracts RASM as the feature to describe the frequency-space domain characteristics of EEG signals and constructs a LSTM network as the classifier to explore the temporal correlations of EEG signals. It is implemented on the DEAP dataset for a trial-level emotion recognition task. In a comparison with a number of relevant studies on DEAP, its mean accuracy of 76.67% ranks the first, which approves the effectiveness of this new approach.
AB - In the field of human-computer interaction, automatic emotion recognition is an important and challenging task. As a physiological signal that directly reflects the brain activity, EEG has advantages in emotion recognition. However, previous studies seldom consider together the temporal, spatial, and frequency characteristics of EEG signals, and the reported emotion recognition accuracy is not adequate for applications. To address this issue, this study proposes a new approach which extracts RASM as the feature to describe the frequency-space domain characteristics of EEG signals and constructs a LSTM network as the classifier to explore the temporal correlations of EEG signals. It is implemented on the DEAP dataset for a trial-level emotion recognition task. In a comparison with a number of relevant studies on DEAP, its mean accuracy of 76.67% ranks the first, which approves the effectiveness of this new approach.
KW - EEG
KW - Emotion recognition
KW - Human-computer interaction
KW - LSTM
UR - http://www.scopus.com/inward/record.url?scp=85043379328&partnerID=8YFLogxK
U2 - 10.1007/978-981-10-8530-7_30
DO - 10.1007/978-981-10-8530-7_30
M3 - Conference contribution
AN - SCOPUS:85043379328
SN - 9789811085291
T3 - Communications in Computer and Information Science
SP - 310
EP - 318
BT - Internet Multimedia Computing and Service - 9th International Conference, ICIMCS 2017, Revised Selected Papers
A2 - Huet, Benoit
A2 - Nie, Liqiang
A2 - Hong, Richang
PB - Springer Verlag
T2 - 9th International Conference on Internet Multimedia Computing and Service, ICIMCS 2017
Y2 - 23 August 2017 through 25 August 2017
ER -