Quantifying Emotions via ECG: A DWT-Driven Classification Framework

Emotion has a significant impact on human psychology and physiology. Over the past two decades, there has been an increase in research on emotion, with contributions from numerous disciplines, including computer science, psychology, sociology, and medicine. There has been a lot of in-depth research on this subject as a result of many attempts to explain the beginning, purpose, and other elements of emotion, which involve incorporating artificial intelligence and natural feelings and emotions into machines or systems. This paper presents a novel approach to ECG-based emotion recognition, leveraging the power of Discrete Wavelet Transform (DWT) for feature extraction. Additionally, this study employs the Statistical Package for the Social Sciences (SPSS) software to perform an Analysis of Variance (ANOVA)-based feature selection process. To classify emotions, Support Vector Machine (SVM) and K Nearest Neighbours (KNN) classifiers are utilized. The proposed methodology demonstrates promising results, highlighting the potential of ECG signals as a valuable physiological modality for accurate and robust emotion recognition. The comprehensive approach integrating DWT, SPSS, SVM, and KNN offers a valuable contribution to the field of affective computing and emotion recognition systems. The conclusions presented in this paper are useful for researchers seeking a synopsis of previous research in the field of ECG-based emotion recognition systems, identifying gaps in the area of study, and developing ideas for possible applications of emotion recognition systems.