.png){kind=icon}
.png){kind=icon}
Return
Emotion Identification From Physiological Signals Using Iterative Filtering-Based Empirical Wavelet Transform
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2025.3629291.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study proposes a novel framework for human emotion identification based on multimodal physiological signals, namely, electrocardiogram (ECG), electroencephalogram (EEG), and phonocardiogram (PCG). The use of signal analysis methods and machine learning (ML) techniques can help in designing an intelligent system in order to identify emotions from the physiological signals. In this work, a new signal analysis method termed as iterative filtering-based empirical wavelet transform (IF-EWT) has been proposed for decomposing the nonstationary physiological signals into simpler components. The rhythms are separated from the decomposed components for EEG signals. The features, such as dispersion entropy (DE) and band power, have been computed from the decomposed components of ECG and PCG signals and separated rhythms of EEG signals, which are then classified into four emotional states, happy, sad, fear, and neutral, using ML classifiers. The studied ML classifiers include quadratic discriminant analysis (QDA), k-nearest neighbor (KNN), support vector machine (SVM), ensemble bagged trees (EBTs), and neural network (NN). The proposed framework has been evaluated on multimodal physiological data recorded during participants’ exposure to emotion-eliciting audiovisual clips. The proposed framework achieved an average classification accuracy of 97.17% for the subject-dependent case and 93.6% for the subject-independent case using the KNN classifier. The presented work in this article has applications in various fields, such as mental health monitoring, personalized human–computer interaction, and affective computing.
Keywords:
Affective computing
electrocardiogram (ECG)
electroencephalogram (EEG)
EEG rhythms
emotion identification
phonocardiogram (PCG)
signal decomposition
Journal
IF:
4.5
Papers:
2.1W
Citations:
7.3W