Recognition of Emotion from EEG Signals Using Hierarchical Quantum Machine Learning Algorithm

Document Type : Original Article

Authors

1 Department of Electrical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran.

2 Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

Abstract

In recent years, quantum machine learning (QML) algorithms have been considered to detect different brain states through EEG signals. Emotion recognition using EEG signals plays a key role in human-computer interaction and emotional computing. This study uses the DEAP (A Database for Emotion Analysis Using Physiological Signals) dataset consisting of 32 channels of EEG signals obtained from 32 participants while watching 40 one-minute music videos. The proposed model based on hierarchical QML includes phases of EEG signal pre-processing using surface Laplacian, preparation of EEG signal as a quantum state, feature extraction using quantum wavelet packet transform (QWPT) and wavelet packet energy entropy (WPEE) and three layers quantum neural network (QNN) classifier. The results show that the proposed model can distinguish two categories of emotional states of valence and arousal states with 94.71 and 97.62 accuracy percentages, respectively. The results show the significant success of the proposed model in detecting different emotional states.

Keywords

Main Subjects

Advanced Signal Processing

Articles in Press, Accepted Manuscript
Available Online from 12 July 2023

Files

Share

How to cite

Statistics