S.I. : EMERGENCE IN HUMAN-LIKE INTELLIGENCE TOWARDS CYBER-PHYSICAL SYSTEMS Emotion recognition based on physiological signals using brain asymmetry index and echo state network Fuji Ren 1,2 · Yindong Dong 1 · Wei Wang 1 Received: 29 April 2018 / Accepted: 24 July 2018 © The Natural Computing Applications Forum 2018 Abstract This paper proposes a method to evaluate the degree of emotion being motivated in continuous music videos based on asymmetry index (AsI). By collecting two groups of electroencephalogram (EEG) signals from 6 channels (Fp1, Fp2, Fz and AF3, AF4, Fz) in the left and right hemispheres, multidimensional directed information is used to measure the mutual information shared between two frontal lobes, and then, we get AsI to estimate the degree of emotional induction. In order to evaluate the effect of AsI processing on physiological emotion recognition, 32-channel EEG signals, 2-channel EEG signals and 2-channel EMG signals are selected for each subject from the DEAP dataset, and different sub-bands are extracted using wavelet packet transform. k-means algorithm is used to cluster the wavelet packet coefficients of each sub- band, and the probability distribution of the coefficients under each cluster is calculated. Finally, the probability distri- bution value of each sample is sent as the original features into echo state network for unsupervised intrinsic plasticity training; the reservoir state nodes are selected as the final feature vector and fed into the support vector machine. The experimental results show that the proposed algorithm can achieve an average recognition rate of 70.5% when the subjects are independent. Compared with the case without AsI, the recognition rate is increased by 8.73%. On the other hand, the ESN is adopted for the original physiological feature refinement which can significantly reduce feature dimensions and be more beneficial to the emotion classification. Therefore, this study can effectively improve the performance of human– machine interface systems based on emotion recognition. Keywords Emotion recognition · Physiological signals · Brain asymmetry index · Echo state network 1 Introduction In recent years, human–computer interaction has received a lot of attention from researchers and scholars and has influenced us all in aspects of our lives, such as human– human interaction, job search and entertainment, etc. [1, 2]. If the machine can understand the human emotion state, human–machine interface (HMI) can be more intuitive, smooth and effective to adapt to a variety of human–ma- chine applications, and we call it affective computing (AC) [3, 4]. Affective computing is a field of research that allows the machine to perceive and express some emotions; it can recognize, interpret and process human emotions through related system and intelligent equipment; therefore, emo- tion recognition is the primary research hot spot for affective computing. Facial expressions [5, 6], speech [7], posture [8], text [9, 10] and physiological signals from the & Yindong Dong dongyindong66@mail.hfut.edu.cn Fuji Ren ren@is.tokushima-u.ac.jp Wei Wang wangwei_hfut@hfut.edu.cn 1 School of Computer and Information, Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, Hefei University of Technology, Hefei 230601, China 2 Graduate School of Advanced Technology and Science, University of Tokushima, Tokushima 7708502, Japan 123 Neural Computing and Applications https://doi.org/10.1007/s00521-018-3664-1