EEG-Based Emotion Recognition Using an Improved Weighted Horizontal Visibility Graph.

Tianjiao Kong,Jiuyuan Hu,Shiyiling Yang,Xin Yang,Jie Shao,Reza Malekian

doi:10.3390/s21051870

Abstract

Emotion recognition, as a challenging and active research area, has received considerable awareness in recent years. In this study, an attempt was made to extract complex network features from electroencephalogram (EEG) signals for emotion recognition. We proposed a novel method of constructing forward weighted horizontal visibility graphs (FWHVG) and backward weighted horizontal visibility graphs (BWHVG) based on angle measurement. The two types of complex networks were used to extract network features. Then, the two feature matrices were fused into a single feature matrix to classify EEG signals. The average emotion recognition accuracies based on complex network features of proposed method in the valence and arousal dimension were 97.53% and 97.75%. The proposed method achieved classification accuracies of 98.12% and 98.06% for valence and arousal when combined with time-domain features.

Highlights

Emotion is the reflection of people’s psychological and physical expressions
We investigated the effectiveness of network metrics
Weemotion investigated the effectiveness of complex network metrics and time-domain features on different data lengths thescenarios sliding window types for classification

Summary

Introduction

Emotion is the reflection of people’s psychological and physical expressions. It plays a crucial factor in decision-making, perception, and human-computer interaction (HCI)systems [1,2] Many studies based on emotion recognition have been conducted in the last few decades [3,4].The methods of emotion recognition are usually divided into two categories. Emotion is the reflection of people’s psychological and physical expressions. It plays a crucial factor in decision-making, perception, and human-computer interaction (HCI). Systems [1,2] Many studies based on emotion recognition have been conducted in the last few decades [3,4]. The methods of emotion recognition are usually divided into two categories. One is based on physiological signals, and the other is based on non-physiological signals. Non-physiological signals include facial expressions, speech signals, body movements, and so on [5,6]. Studies based on non-physiological signals have produced significant results

Methods

Results

Discussion

Conclusion