In the present study, a new methodology is proposed for recognition of emotional state mediated by affective video film clips. Principal Component Analysis (PCA) is applied to full-band specific Phase Space Trajectory Matrix extracted from short emotional EEG segment of 6 s, then the first Principal Component is used as emotional feature in terms of neuro-cortical complexity levels in discriminating nine discrete emotions (fear, anger, happiness, sadness, amusement, surprise, excitement, calmness, disgust) from baseline through Convolutional Neural Networks (CNNs). In tests, the performance of CNNs is compared to another deep learning application called Long-Short term Memory Networks and Support Vector Machine classifiers with different kernels as well as Naive Bayes classifier. In applications, two concepts (gender classification and emotion classification) have been considered with respect to both instants (single feature extracted from single epoch) and subjects (large number of features extracted from single subject in an emotional state). The resulting performance of the proposed method has also been examined for longer segment statement of 12 s. Experimental data was downloaded from an internationally publicly available dataset called DREAMER. The results show that healthy young females differ from males in amusement such that the difference becomes higher when subject classification is performed. Regarding the combined features extracted from females and males, the other emotional states are clearly discriminated from baseline with considerably high accuracy levels by using CNNs in both instant and subject classification manners. The results reveal that emotion formation is mostly influenced by individual experiences rather than gender. In detail, local neuronal complexity is mostly sensitive to the affective valance rating. PCA can be proposed as secondary process on phase domain EEG space in order to obtain useful emotional features. CNN provides high performance for emotion recognition.

Resting-state brain networks represent the intrinsic state of the brain during the majority of cognitive and sensorimotor tasks. However, no study has yet presented concise predictors of task-induced vigilance variability from spectro-spatial features of the resting-state electroencephalograms (EEG). In this study, ten healthy volunteers have participated in fixed-sequence, varying-duration sessions of sustained attention to response task (SART) for over 100 minutes. A novel and adaptive cumulative vigilance scoring (CVS) scheme is proposed based on tonic performance and response time. Multiple linear regression (MLR) using feature relevance analysis has shown that average CVS, average response time, and variabilities of these scores can be predicted (p<0.05) from the resting-state band-power ratios of EEG signals. Cross-validated neural networks also captured different associations for narrow-band beta and wide-band gamma and differences between the high- and low-attention networks in temporal regions. The proposed framework and these first findings on stable and significant attention predictors from the power ratios of resting-state EEG can be useful in brain-computer interfacing and vigilance monitoring applications.