Automatic EEG Based Emotion Recognition Using Extreme Learning Machine

Emotion is very essential natural feeling of humans. Emotion recognition is often used in brain-computer interface devices to assist impaired people. Electroencephalogram (EEG) signal is essential for identifying emotional states since it reacts instantly to every variation in the individual's brain. In this work, the usefulness of the tunable-Q wavelet transform (TQWT) for classifying various emotions in EEG signals is studied. TQWT breaks the EEG signals into sub-bands and extracts statistical momemts from the sub-bands. The extracted moments are features which are fed to classifier named extreme learning machine, which classifies different emotions. In comparison to other existing approaches, the experimental results of the proposed technique acheived improved emotion recognition performance on open-source datasets, SEED, SEED-IV, and DEAP. The maximum accuracy obtained with the proposed emotion recognition system is 95.2%, 95%, and 93.8% using SEED, SEED-IV, and DEAP databases, respectively, which is higher compared to the state-of-art methods.