Prediction of subjective ratings of emotional pictures by EEG features

Abstract

Emotion dysregulation is an important aspect of many psychiatric disorders. Brain-computer interface (BCI) technology could be a powerful new approach to facilitating therapeutic self-regulation of emotions. One possible BCI method would be to provide stimulus-specific feedback based on subject-specific electroencephalographic (EEG) responses to emotion-eliciting stimuli. To assess the feasibility of this approach, we studied the relationships between emotional valence/arousal and three EEG features: amplitude of alpha activity over frontal cortex; amplitude of theta activity over frontal midline cortex; and the late positive potential over central and posterior mid-line areas. For each feature, we evaluated its ability to predict emotional valence/arousal on both an individual and a group basis. Twenty healthy participants (9 men, 11 women; ages 22–68) rated each of 192 pictures from the IAPS collection in terms of valence and arousal twice (96 pictures on each of 4 days over 2 weeks). EEG was collected simultaneously and used to develop models based on canonical correlation to predict subject-specific single-trial ratings. Separate models were evaluated for the three EEG features: frontal alpha activity; frontal midline theta; and the late positive potential. In each case, these features were used to simultaneously predict both the normed ratings and the subject-specific ratings. Models using each of the three EEG features with data from individual subjects were generally successful at predicting subjective ratings on training data, but generalization to test data was less successful. Sparse models performed better than models without regularization. The results suggest that the frontal midline theta is a better candidate than frontal alpha activity or the late positive potential for use in a BCI-based paradigm designed to modify emotional reactions.

Classifying the Perceptual Interpretations of a Bistable Image Using EEG and Artificial Neural Networks

“…The accuracy ρ was averaged over all 1,000 training ANNs. One can see that the accuracy reached its maximum in the range of [0.75, 1.75] s. Therefore, we chose the duration of the EEG trials for further analysis to be equal to T = 1 s. Also, it should be noted that, when working in on-line regime (for example, for brain-computer interfaces development; Bell et al, 2008 ; Maksimenko et al, 2017 ; McFarland et al, 2017 ), the analysis of short time series will be more preferable.…”

“…The developed approach provides a solid experimental basis for further understanding of brain functionality. The rather simple way to quantitatively characterize brain activity related to perception of ambiguous images seems to be a powerful tool, which may be used in neurotechnology, e.g., for the brain-computer interface (BCI) task (Bell et al, 2008 ; McFarland et al, 2017 ) and in medicine for diagnostic and prognostic purposes (Ovchinnikov et al, 2010 ; Maksimenko et al, 2017 ). The efficiency of BCI is known to be defined by the ability of the operator to generate certain stable EEG patterns.…”

Therapeutic applications of BCI technologies

“…For example, most prior investigations of neural signals associated with emotion have involved averaging results across trials and subjects. Prediction of emotional responses on individual trials, a prerequisite for BCI-based feedback, is more challenging [27]. At the same time, there is great potential for modifying the activity of brain regions that could result in therapeutic benefit, provided that we acquire the necessary knowledge.…”

Image Quality in Augmented Binocular Vision: QoE Approximations with QoS and EEG

“…Earlier findings, such as in [25] indicate that the gamma frequency band might be of interest in the evaluation of visual stimuli, with a connection to memory processing in, e.g., [26]. Given the affective influence on the overall QoE as subjective metric, a BCI-based prediction of emotional state was presented in [27].…”