Subject Independent Emotion Recognition using EEG Signals Employing Attention Driven Neural Networks

Electroencephalogram (EEG) based emotional analysis has been employed in medical science, security and human-computer interaction with good success. In the recent past, deep learning-based approaches have significantly improved the classification accuracy when compared to classical signal processing and machine learning based frameworks. But most of them were subject-dependent studies which were not able to generalize on the subject-independent tasks due to the inter-subject variability in EEG. In this work, a novel deep learning framework capable of doing subject-independent emotion recognition is presented, consisting of two parts. First, an unsupervised Long Short-Term Memory (LSTM) with channel-attention autoencoder is proposed for getting a correlated lower dimensional latent space representation of the EEG data for each subject. Secondly, a convolutional neural network (CNN) with attention framework, which takes the first component as input, is presented for performing the task of subject-independent emotion recognition. With the attention mechanism, the proposed approach could highlight the channel of interest as well as the temporal localization of the EEG signal, which contributes to the emotion under consideration as validated by the results. The proposed approach has been validated using various widely employed datasets for EEG signals including DEAP dataset, SEED dataset and CHB-MIT dataset. With proposed methodology, average subject independent accuracies of 65.9%, 69.5% for valence and arousal classification in the DEAP dataset, 76.7% for positive-negative classification in SEED dataset is obtained and further for the CHB-MIT dataset average subject independent accuracies of 69.1%, 67.6%, 72.3% for Pre-Ictal Vs Ictal, Inter-Ictal Vs Ictal, Pre-Ictal Vs Inter-Ictal classification is obtained.