A Comparative Analysis of Eda Decomposition Methods for Improved Emotion Recognition

Abstract

This study analyzed five decomposition algorithms for separating electrodermal activity (EDA) into tonic and phasic components to identify different emotions using machine learning algorithms. We used EDA signals from the Continuously Annotated Signals of Emotion dataset for this analysis. First, we decomposed the EDA signals into tonic and phasic components using five decomposition methods: continuous deconvolution analysis, discrete deconvolution analysis, convex optimization-based EDA, nonnegative sparse deconvolution (SparsEDA), and BayesianEDA. We extracted time, frequency, and time-frequency domain features from each decomposition method’s tonic and phasic components. Finally, various machine learning algorithms such as logistic regression (LR), support vector machine, random forest, extreme gradient boosting, and multilayer perceptron were applied to evaluate the performance of the decomposition methods. Our results show that the considered decomposition methods successfully split the EDA signal into tonic and phasic components. The SparsEDA decomposition method outperforms the other decomposition methods considered in the study. In addition, LR with features extracted from the tonic component of the SparsEDA achieved highest average classification accuracy of 95.83%. This study can be used to identify the optimal decomposition methods suitable for emotion recognition applications.

Evaluating the Effectiveness of Machine Learning in Identifying the Optimal Facial Electromyography Location for Emotion Detection

“…The data were balanced during the training and test splits (same number of observations for each class) across the folds. We used a stratified 10-fold cross-validation method and evaluated the performance of the models using the metrics such as accuracy, recall, precision, specificity, and f1-score [18].…”