Learning-based classification of valence emotion from electroencephalography

Abstract

The neuroimaging research field has been revolutionized with the development of human cognitive functions without the use of brain pathways. To assist such systems, electroencephalography (EEG) based measures play an important role. In this study, the publicly available database of emotion analysis using physiological signals, has been used to identify the human emotions such as valence (positive/negative) from the given recorded EEG signals. With the identification of such emotion, the feeling of goodness or badness related individual experiences with the situation can be identified from his/her brain signals. The different machine learning classifiers such as random forest, decisions trees, K-nearest neighbor, support vector machines, naive Bayes and neural network have been used to identify and evaluate such emotions. The previous work done by the other authors on the same dataset using various quantitative approaches are compared with the approaches used in this study yields higher accuracy rates with the random forest and decision tree. The effectiveness of each classifier in terms of statistical measures such as accuracy, F-score, etc. has been evaluated. The random forest classifier was found to outperform with an accuracy of 98%, closely followed by the Decision tree at 94% are the most effective classifiers in classifying the valence emotions of the EEG data for 6 subjects.

Keywords:

• Electroencephalography
• database of emotion analysis using physiological signals
• brain–computer interface
• random forest
• decisions trees
• K-nearest neighbor
• support vector machines
• naive Bayes
• neural network

Acknowledgments

The implementation of this study is my own, but I am thankful to the authors of the manuscripts and scientific papers I have read for this study.

Disclosure statement

No potential conflict of interest was reported by the authors.