Independent Components of EEG Activity Correlating with Emotional State.

Yasuhisa Maruyama,Laura A Martínez-Tejada,Natsue Yoshimura,Yasuharu Koike,Yousuke Ogata

doi:10.3390/brainsci10100669

Abstract

Among brain-computer interface studies, electroencephalography (EEG)-based emotion recognition is receiving attention and some studies have performed regression analyses to recognize small-scale emotional changes; however, effective brain regions in emotion regression analyses have not been identified yet. Accordingly, this study sought to identify neural activities correlating with emotional states in the source space. We employed independent component analysis, followed by a source localization method, to obtain distinct neural activities from EEG signals. After the identification of seven independent component (IC) clusters in a k-means clustering analysis, group-level regression analyses using frequency band power of the ICs were performed based on Russell’s valence–arousal model. As a result, in the regression of the valence level, an IC cluster located in the cuneus predicted both high- and low-valence states and two other IC clusters located in the left precentral gyrus and the precuneus predicted the low-valence state. In the regression of the arousal level, the IC cluster located in the cuneus predicted both high- and low-arousal states and two posterior IC clusters located in the cingulate gyrus and the precuneus predicted the high-arousal state. In this proof-of-concept study, we revealed neural activities correlating with specific emotional states across participants, despite individual differences in emotional processing.

Highlights

Emotion plays an important role in daily life, because it enriches communication
independent component (IC) Clusters Obtained by independent component analysis (ICA) and Cluster Analysis
ICA and cluster analysis by a k-means clustering method resulted in seven IC clusters

Summary

Introduction

To achieve emotional interaction between human beings and computers, electroencephalography (EEG)-based emotion recognition is gaining attention in brain-computer interface (BCI) studies. Many studies have performed emotion classification using various types of EEG features [1,2,3]. In [4], emotion classification based on Russell’s valence–arousal model was performed using eventrelated potentials (ERPs) and event-related oscillations calculated from EEG recorded during affective picture viewing. Russell’s valence–arousal model is a widely-recognized model of emotion, and in this model, emotions are represented in the space of two axes: valence (ranging from pleasant to unpleasant state) and arousal (ranging from excited to calm state), as illustrated in Figure 1a [5]. Among many emotion classification studies based on EEG, some studies estimated source activities in the brain

Methods

Results

Conclusion