Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers

A feature-based emotion recognition model is proposed for EEG-based BCI.The approach combines statistical-based feature selection methods and SVM emotion classifiers.The model is based on Valence/Arousal dimensions for emotion classification.Our combined approach outperformed other recognition methods. Current emotion recognition computational techniques have been successful on associating the emotional changes with the EEG signals, and so they can be identified and classified from EEG signals if appropriate stimuli are applied. However, automatic recognition is usually restricted to a small number of emotions classes mainly due to signal's features and noise, EEG constraints and subject-dependent issues. In order to address these issues, in this paper a novel feature-based emotion recognition model is proposed for EEG-based Brain-Computer Interfaces. Unlike other approaches, our method explores a wider set of emotion types and incorporates additional features which are relevant for signal pre-processing and recognition classification tasks, based on a dimensional model of emotions: Valence and Arousal. It aims to improve the accuracy of the emotion classification task by combining mutual information based feature selection methods and kernel classifiers. Experiments using our approach for emotion classification which combines efficient feature selection methods and efficient kernel-based classifiers on standard EEG datasets show the promise of the approach when compared with state-of-the-art computational methods.

[1]  Brent Lance,et al.  Optimal Arousal Identification and Classification for Affective Computing Using Physiological Signals: Virtual Reality Stroop Task , 2010, IEEE Transactions on Affective Computing.

[2]  Ling Huang,et al.  Feature Extraction of EEG Signals Using Power Spectral Entropy , 2008, 2008 International Conference on BioMedical Engineering and Informatics.

[3]  Olga Sourina,et al.  Real-Time EEG-Based Human Emotion Recognition and Visualization , 2010, 2010 International Conference on Cyberworlds.

[4]  Rafael A. Calvo,et al.  Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications , 2010, IEEE Transactions on Affective Computing.

[5]  Leontios J. Hadjileontiadis,et al.  Emotion Recognition from Brain Signals Using Hybrid Adaptive Filtering and Higher Order Crossings Analysis , 2010, IEEE Transactions on Affective Computing.

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

[7]  Clemens Brunner,et al.  A comparison of univariate, vector, bilinear autoregressive, and band power features for brain–computer interfaces , 2011, Medical & Biological Engineering & Computing.

[8]  Lei Guo,et al.  GA-SVM based feature selection and parameters optimization for BCI research , 2011, 2011 Seventh International Conference on Natural Computation.

[9]  Zehra Cataltepe,et al.  Feature selection and classification on brain computer interface (BCI) data , 2012, 2012 20th Signal Processing and Communications Applications Conference (SIU).

[10]  Qiang Wang,et al.  A Real-time Fractal-based Brain State Recognition from EEG and its Applications , 2011, BIOSIGNALS.

[11]  Dimitrios Tzovaras,et al.  Automatic Recognition of Boredom in Video Games Using Novel Biosignal Moment-Based Features , 2011, IEEE Transactions on Affective Computing.