Exploring Wrist Pulse Signals using Empirical Mode Decomposition: Emotions

Abstract Emotion recognition is attracting considerable interest among the research community. In this work, Empirical Mode Decomposition has been implemented to derive both statistical and nonlinear features from Wrist Pulse Signal classifying emotions namely anxiety boredom. signals were extracted 24 subjects using TETRIS game as a stimulus Fission Fusion approach. The acquired pre-processed remove unwanted noise artefacts present within signal. addition, various classifiers Naiive Byes, Support Vector Machine, K-Nearest Neighbour, Logistic Regression, Linear Discriminant Analysis, Quadratic Analysis considered. Results these indicate that Regression gave an indistinguishable accuracy of 99.71% (fission) 77.08% (fusion) for state. Moreover, boredom state, highest classification was 66.67 % Bayes fission 64.58% fusion. highlight impact empirical mode decomposition with hilbert transform emotion wrist pulse signals.