Functional Connectivity Analysis in Multi-channel EEG for Emotion Detection with Phase Locking Value and 3D CNN

The noise-assisted multivariate Empirical mode decomposition (NA-MEMD) is applied to multi-channel EEG signals to obtain narrow-band scale-aligned intrinsic mode functions (IMFs) upon which functional connectivity analysis is performed. The connectivity pattern in relation to inherent functional activity of brain is estimated with the phase locking value (PLV). Instantaneous phase difference among different EEG channels gives PLV that is used to build the functional connectivity map. The connectivity map yields spatial-temporal feature representation which is taken as input of the proposed emotion detection system. The spatial-temporal features can be learned with a 3D convolutional neural network for classifying emotion states. The proposed system is evaluated on two publicly available DEAP and SEED dataset for binary and multi-class emotion classification. On detecting low versus high level in the valence and arousal dimensions, the attained accuracy values are 97.37% and 96.26% respectively. Meanwhile, this system yields 94.78% and 99.54% accuracy on multi-class task on DEAP and SEED, which outperform previously reported systems with other deep learning models and conventional EEG features.