Automated Feature Extraction on AsMap for Emotion Classification using EEG

Emotion recognition using EEG has been widely studied to address the challenges associated with affective computing. Using manual feature extraction method on EEG signals result in sub-optimal performance by the learning models. With the advancements in deep learning as a tool for automated feature engineering, in this work a hybrid of manual and automatic feature extraction method has been proposed. The asymmetry in the different brain regions are captured in a 2-D vector, termed as AsMap from the differential entropy (DE) features of EEG signals. These AsMaps are then used to extract features automatically using Convolutional Neural Network (CNN) model. The proposed feature extraction method has been compared with DE and other DE-based feature extraction methods such as RASM, DASM and DCAU. Experiments are conducted using DEAP and SEED dataset on different classification problems based on number of classes. Results obtained indicate that the proposed method of feature extraction results in higher classification accuracy outperforming the DE based feature extraction methods. Highest classification accuracy of 97.10% is achieved on 3-class classification problem using SEED dataset. Further, the impact of window size on classification accuracy has also been assessed in this work.