Feature Extraction Analysis for Emotion Recognition from ICEEMD of Multimodal Physiological Signals
| Autor: | Cristian Mejía-Arboleda, Javier Revelo-Fuelagán, O. A. Ordonez-Bolanos, J. Rodriguez, Andrés Eduardo Castro-Ospina, Miguel A. Becerra, Diego Hernán Peluffo-Ordóñez, J. F. Gomez-Lara, C. Duque-Mejía |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Discrete wavelet transform
Signal processing business.industry Computer science Feature vector Feature extraction Pattern recognition 02 engineering and technology Linear discriminant analysis Hilbert–Huang transform Random forest 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business 030217 neurology & neurosurgery Curse of dimensionality |
| Zdroj: | Intelligent Information and Database Systems ISBN: 9783030147983 ACIIDS (1) |
| Popis: | The emotions identification is a very complex task due to depending on multiple variables individually and as a group. They are evaluated by different criteria such as arousal, valence, and dominance mainly. Several investigations have been focused on building prediction systems. Nevertheless, this is still an open research field. The main objective of this paper is the analysis of the Improved Complementary Ensemble Empirical Mode Decomposition (ICEEMD) for feature extraction from physiological signals for emotions prediction. Physiological signals and metadata of the DEAP database were used. First, the signals were preprocessed, then three decompositions were carried out using ICEEMD, Discrete Wavelet Transform (DWT), and Maximal overlap DWT. Feature extraction was carried out using Hermite coefficients, and multiple statistic measures from IMFs, coefficients DWT, and MODWT, and signals. Then, Relief F selection algorithms were applied to reducing the dimensionality of the feature space. Finally, Linear Discriminant Classifier (LDC) and K-NN cascade, and Random Forest classifiers were tested. The different decomposition techniques were compared, and the relevant signals and measures were established. The results demonstrated the capability of ICEEMD decomposition for emotions analysis from physiological signals. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|