PROJECT TITLE :

Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks

ABSTRACT:

To investigate important frequency bands and channels, this paper introduces deep belief networks (DBNs) to constructing EEG-based mostly emotion recognition models for three emotions: positive, neutral and negative. We have a tendency to develop an EEG dataset acquired from fifteen subjects. Every subject performs the experiments twice at the interval of a few days. DBNs are trained with differential entropy options extracted from multichannel EEG knowledge. We have a tendency to examine the weights of the trained DBNs and investigate the critical frequency bands and channels. Four different profiles of 4, half-dozen, 9, and twelve channels are selected. The recognition accuracies of those four profiles are comparatively stable with the best accuracy of 86.65percent, that is even better than that of the original 62 channels. The vital frequency bands and channels determined by using the weights of trained DBNs are consistent with the existing observations. Moreover, our experiment results show that neural signatures associated with totally different emotions do exist and they share commonality across sessions and people. We have a tendency to compare the performance of deep models with shallow models. The common accuracies of DBN, SVM, LR, and KNN are 86.08%, eighty three.ninety nine%, eighty two.70percent, and 72.60%, respectively.