TY - GEN
T1 - The role of empirical mode decomposition on emotion classification using stimulated eeg signals
AU - Khasnobish, Anwesha
AU - Bhattacharyya, Saugat
AU - Singh, Garima
AU - Jati, Arindam
AU - Konar, Amit
AU - Tibarewala, D. N.
AU - Janarthanan, R.
PY - 2013/1/1
Y1 - 2013/1/1
N2 - An efficient scheme of emotion recognition using EEG signals is an initiation to our quest for developing emotionally intelligent systems and devices, in order to enhance the performance quality of the same. Classification of emotions, both euphoric and negative, using stimulated EEG signals acquired from subjects whose different emotional states were elicited using audio-visual stimuli. The underlying strategy involved the extraction of Power spectral density(PSD) and empirical mode decomposition (EMD) features from the raw EEG data and their classification using linear discriminant analysis (LDA) and linear support vector machine (SVM) thereby classifying the emotions into their respective emotion classes: neutral, happy and sad, with an average classification accuracy of 76.46%,where the neutral state has been classified most efficiently, with an average classification accuracy of 80.86%. The classification accuracy increases with EMD features with reduction in time and computational complexity. LDA is found to perform better than LSVM with EMD features.
AB - An efficient scheme of emotion recognition using EEG signals is an initiation to our quest for developing emotionally intelligent systems and devices, in order to enhance the performance quality of the same. Classification of emotions, both euphoric and negative, using stimulated EEG signals acquired from subjects whose different emotional states were elicited using audio-visual stimuli. The underlying strategy involved the extraction of Power spectral density(PSD) and empirical mode decomposition (EMD) features from the raw EEG data and their classification using linear discriminant analysis (LDA) and linear support vector machine (SVM) thereby classifying the emotions into their respective emotion classes: neutral, happy and sad, with an average classification accuracy of 76.46%,where the neutral state has been classified most efficiently, with an average classification accuracy of 80.86%. The classification accuracy increases with EMD features with reduction in time and computational complexity. LDA is found to perform better than LSVM with EMD features.
KW - EEG
KW - EMD
KW - Emotion recognition
KW - LDA
KW - PSD
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=85059753398&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-31600-5_6
DO - 10.1007/978-3-642-31600-5_6
M3 - Conference contribution
AN - SCOPUS:85059753398
SN - 9783642315992
T3 - Advances in Intelligent Systems and Computing
SP - 55
EP - 62
BT - Advances in Computing and Information Technology- Proceedings of the 2nd International Conference on Advances in Computing and Information Technology, ACITY 2012- Volume 3
A2 - Meghanathan, Natarajan
A2 - Chaki, Nabendu
A2 - Nagamalai, Dhinaharan
PB - Springer Verlag
T2 - 2nd International Conference on Advances in Computing and Information Technology, ACITY 2012
Y2 - 13 July 2012 through 15 July 2012
ER -