Subject-Dependent Emotion Recognition System Based on Multidimensional Electroencephalographic Signals: A Riemannian Geometry Approach

• Published in: IEEE access Vol. 10; pp. 14993 - 15006
• Main Authors: Abdel-Ghaffar, Eman A., Wu, Yujin, Daoudi, Mohamed
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Affine transformations; Arousal; Computer Science; Covariance matrices; Covariance matrix; Covariance matrix estimation; Decision making; Electroencephalography; Emotion recognition; Emotions; Feature extraction; Goodness of fit; Machine learning; Manifolds; Manifolds (mathematics); Mathematical analysis; multidimensional EEG signals; Normal distribution; Probability distribution; Riemannian manifold; signal analysis; Signal and Image Processing; Signal distribution; Signal processing; SPD matrices; Statistical analysis; Statistical tests; Symmetric matrices; Transfer learning; Emotion recognition; SPD Matrices; Transfer Learning; Multidimensional EEG Signals; Signal Analysis; INDEX TERMS Covariance matrix estimation; Riemannian manifold
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2022.3147461

Emotion recognition plays an important role in human computer interaction systems as it helps the computer in understanding human behavior and their decision making process. Using Electroencephalographic (EEG) signals in emotion recognition offers a direct assessment on the inner state of human mind. This study aims to build a subject dependent emotion recognition system that differentiate between high and low levels of valance and arousal, using multidimensional EEG signals. Our system offers a transfer learning- minimum distance to Riemannian mean (TL-MDRM) framework. In this work, we perform two pre-processing stages. In the first stage, we analyze the EEG signals to investigate their non-Gaussianity and determine the most appropriate signal distribution. Using several statistical and goodness of fit tests, T-distribution was found to be the most appropriate distribution. Covariance matrix estimations plays a crucial step in manifold learning technique, based on the most suitable signal distribution the covariance matrix estimation technique is chosen. In the second stage, we perform transfer learning to deal with cross-session variability by generating a unique reference point for each participant and performing affine transformation for the covariance matrices on the symmetric positive definite (SPD) manifold around this point. The results show that, TL process improved the performance even when assuming Gaussian distribution, while assuming T-distribution with TL improved the performance further.