A new approach for emotions recognition through EOG and EMG signals

In this paper, an approach for emotion recognition using physiological signals has been development. The main purpose of this paper is to provide improved method for emotion recognition using horizontal electrooculogram, vertical electrooculogram, zygomaticus major electromyogram and trapezius electromyogram signals. Emotions are state of feeling that causes psychological and physical changes which affects our behaviour. Emotions are elicited using stimuli which include video, images and audio, etc. Here, emotions are elicited by audio-visual songs. For classification of emotions, time domain, frequency domain and entropy based features are extracted. These features are classified using support vector machine, naive Bayes and artificial neural network. The performance of each classifier and features is compared on the basis of accuracy, average precision and average recall. Primary contribution is the identification of time domain features as best features for EOG and EMG signals with ANN classifier to achieve maximum classification accuracy. Overall classification average accuracy (98%) of ANN is found best as compared to other classifiers. Global implications of this work is in utilization for artificial intelligence based models of human decision making systems by adding effect of emotions during decision making process modeling.

[1]  Arnab Bag,et al.  Effects of emotion on physiological signals , 2016, 2016 IEEE Annual India Conference (INDICON).

[2]  Alain Pruski,et al.  Emotion recognition from physiological signals using fusion of wavelet based features , 2015, 2015 7th International Conference on Modelling, Identification and Control (ICMIC).

[3]  Wendi B. Heinzelman,et al.  Speech-based emotion classification using multiclass SVM with hybrid kernel and thresholding fusion , 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

[4]  Samy Missoum,et al.  Optimal SVM parameter selection for non-separable and unbalanced datasets , 2014, Structural and multidisciplinary optimization : journal of the International Society for Structural and Multidisciplinary Optimization.

[5]  Mohammad H. Mahoor,et al.  A wavelet-based approach to emotion classification using EDA signals , 2018, Expert Syst. Appl..

[6]  Xianxiang Chen,et al.  Respiration-based emotion recognition with deep learning , 2017, Comput. Ind..

[7]  David Pollreisz,et al.  A simple algorithm for emotion recognition, using physiological signals of a smart watch , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[8]  M. Murugappan,et al.  Classification of emotional states from electrocardiogram signals: a non-linear approach based on hurst , 2013, BioMedical Engineering OnLine.

[9]  Ohbyung Kwon,et al.  Emotional index measurement method for context-aware service , 2011, Expert Syst. Appl..

[10]  A. Kumar,et al.  Scalp connectivity networks for analysis of EEG signal during emotional stimulation , 2016, 2016 International Conference on Communication and Signal Processing (ICCSP).

[11]  Wei Liu,et al.  Emotion Recognition Using Multimodal Deep Learning , 2016, ICONIP.

[12]  G. Lightbody,et al.  A comparison of quantitative EEG features for neonatal seizure detection , 2008, Clinical Neurophysiology.

[13]  Ying Cheng,et al.  The research of EMG signal in emotion recognition based on TS and SBS algorithm , 2010, The 3rd International Conference on Information Sciences and Interaction Sciences.

[14]  Yong Ma,et al.  The Approach to Detect Abnormal Access Behavior Based on Naive Bayes Algorithm , 2016, 2016 10th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS).

[15]  Jie Huang,et al.  Automatic Epileptic Seizure Detection in EEG Signals Using Multi-Domain Feature Extraction and Nonlinear Analysis , 2017, Entropy.

[16]  Cristian A. Torres-Valencia,et al.  Comparative analysis of physiological signals and electroencephalogram (EEG) for multimodal emotion recognition using generative models , 2014, 2014 XIX Symposium on Image, Signal Processing and Artificial Vision.

[17]  Elisabeth André,et al.  Emotion recognition based on physiological changes in music listening , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  A. H. Jahidin,et al.  Robust arrhythmia classifier using hybrid multilayered perceptron network , 2013, 2013 IEEE 9th International Colloquium on Signal Processing and its Applications.

[19]  Martin Buss,et al.  Feature Extraction and Selection for Emotion Recognition from EEG , 2014, IEEE Transactions on Affective Computing.

[20]  Sandra Ohly,et al.  From the lab to the real-world: An investigation on the influence of human movement on Emotion Recognition using physiological signals , 2017, 2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).

[21]  Ya Xu,et al.  A Method of Emotion Recognition Based on ECG Signal , 2009, 2009 International Conference on Computational Intelligence and Natural Computing.

[22]  Mitul Kumar Ahirwal,et al.  Emotion Recognition System based on EEG signal: A Comparative Study of Different Features and Classifiers , 2018, 2018 Second International Conference on Computing Methodologies and Communication (ICCMC).

[23]  Gabriel Pires,et al.  Emotional state detection based on EMG and EOG biosignals: A short survey , 2017, 2017 IEEE 5th Portuguese Meeting on Bioengineering (ENBENG).

[24]  Abdellah Madani,et al.  Fusing multi-stream deep neural networks for facial expression recognition , 2018, Signal Image Video Process..

[25]  Goutam Saha,et al.  Classification of emotions induced by music videos and correlation with participants' rating , 2014, Expert Syst. Appl..

[26]  Ali Motie Nasrabadi,et al.  A novel EEG-based approach to classify emotions through phase space dynamics , 2019, Signal Image Video Process..

[27]  Urbano Nunes,et al.  Facial Expression Recognition based on EOG toward Emotion Detection for Human-Robot Interaction , 2015, BIOSIGNALS.

[28]  Xiangmin Xu,et al.  A novel deep-learning based framework for multi-subject emotion recognition , 2017, 2017 4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS).

[29]  Adil Deniz Duru,et al.  Emotional state detection based on common spatial patterns of EEG , 2020, Signal Image Video Process..

[30]  Lan Li,et al.  Emotion Recognition Using Physiological Signals from Multiple Subjects , 2006, 2006 International Conference on Intelligent Information Hiding and Multimedia.

[31]  Murat Akçakaya,et al.  Decoding emotional experiences through physiological signal processing , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Vinod Chandran,et al.  Evolutionary computation algorithms for feature selection of EEG-based emotion recognition using mobile sensors , 2018, Expert Syst. Appl..

[33]  Mitul Kumar Ahirwal,et al.  Audio-visual stimulation based emotion classification by correlated EEG channels , 2019, Health and Technology.

[34]  Zhe Wang,et al.  Multi-Class Support Vector Machine , 2014 .

[35]  Xiaodan Zhuang,et al.  Compact unsupervised EEG response representation for emotion recognition , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[36]  Thierry Pun,et al.  DEAP: A Database for Emotion Analysis ;Using Physiological Signals , 2012, IEEE Transactions on Affective Computing.

[37]  Yüksel Özbay,et al.  Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network , 2007, Expert Syst. Appl..