A New Fractal Pattern Feature Generation Function based Emotion Recognition Method using EEG

Electroencephalogram (EEG) signal analysis is one of the mostly studied research areas in biomedicalsignal processing, and machine learning. Emotion recognition through machine intelligence plays criticalrole in understanding the brain activities as well as in developing decision-making systems. In thisresearch, an automated EEG based emotion recognition method with a novel fractal pattern feature extractionapproach is presented. The presented fractal pattern is inspired by Firat University Logo andnamed fractal Firat pattern (FFP). By using FFP and Tunable Q-factor Wavelet Transform (TQWT) signaldecomposition technique, a multilevel feature generator is presented. In the feature selection phase, animproved iterative selector is utilized. The shallow classifiers have been considered to denote the successof the presented TQWT and FFP based feature generation. This model has been tested on emotional EEGsignals with 14 channels using linear discriminant (LDA), k-nearest neighborhood (k-NN), support vectormachine (SVM). The proposed framework achieved 99.82% with SVM classifier.