Individual EEG differences in affective valence processing in women with low and high neuroticism

Conscientiousness in Pilots Correlates with Electrodermal Stability: Study on Simulated Flights under Social Stress

For pilots, the capacity to cope with anxiety is crucial during a flight since they may be confronted with stressful situations. According to the Big Five Inventory, this capacity can be modulated by two important personality traits: conscientiousness and neuroticism. The former would be related to concentration skills and the latter to the attention bias towards anxiety-provoking stimuli. Given the current development of monitoring systems for detecting the users’ state, which can be incorporated into cockpits, it is desirable to estimate their robustness to inter-individual personality differences. Indeed, several emotion recognition methods are based on physiological responses that can be modulated by specific personality profiles. The personality traits of twenty pilots were assessed. Afterwards, they performed two consecutive simulated flights without and with induced social stress while electrodermal activity was measured. Their subjective anxiety was assessed before the second flight, prior to the stress-induced condition. The results showed that higher scores in neuroticism correlated positively with cognitive and somatic anxiety. Moreover, under social stress, higher scores in conscientiousness correlated positively with electrodermal stability, i.e., a lower number of skin conductance responses. These results on both self-reported and physiological responses are in favor of the integration of personality differences into pilots’ state monitoring.

Emotional Valence Modulates Low Beta Suppression and Recognition of Social Interactions

Abstract. Emotional valence may have evolutionary adaptive purposes as negative stimuli can be related to survival against threat and positive stimuli to facilitating relationships. This can be seen in the different impact positive and negative stimuli have on human health and well-being, and in the valence-specific cortical activity and neurophysiological patterns reported; for example, negative stimuli are processed more rapidly than positive. Valence-specific patterns are affected by individual differences and personality traits such as empathy, where levels of empathy relate to different reactivity patterns to valence. Here we investigated the effect of valence on neurophysiological responses and interpretation of social interactions depicted by point-light biological motion (PLBM) displays. The meaning of each PLBM display is revealed as the sequence unfolds and is therefore not readily available for snap assessments such as fight or flight responses. We compared electroencephalogram (EEG) reactivity during observation of the displays between individuals with low, moderate, or high levels of empathy. Results indicated that positive displays induced significantly larger suppression in lower beta (13–20 Hz) compared to control displays, while negative displays revealed no difference in suppression compared to scrambled versions. However, no difference between positive and negative displays was observed, suggesting that the rapid processing of negative displays may have been minimized by revealing meaning more slowly. Positive displays were interpreted more accurately, while levels of empathy did not modulate either neurophysiological responses or interpretation, suggesting that empathy under these conditions did not influence the way in which valence was processed or interpreted.

Support Vector Machines and Affective Science

Support vector machines (SVMs) are being used increasingly in affective science as a data-driven classification method and feature reduction technique. Whereas traditional statistical methods typically compare group averages on selected variables, SVMs use a predictive algorithm to learn multivariate patterns that optimally discriminate between groups. In this review, we provide a framework for understanding the methods of SVM-based analyses and summarize the findings of seminal studies that use SVMs for classification or data reduction in the behavioral and neural study of emotion and affective disorders. We conclude by discussing promising directions and potential applications of SVMs in future research in affective science.

A TrAdaBoost Method for Detecting Multiple Subjects' N200 and P300 Potentials Based on Cross-Validation and an Adaptive Threshold

Traditional training methods need to collect a large amount of data for every subject to train a subject-specific classifier, which causes subjects fatigue and training burden. This study proposes a novel training method, TrAdaBoost based on cross-validation and an adaptive threshold (CV-T-TAB), to reduce the amount of data required for training by selecting and combining multiple subjects' classifiers that perform well on a new subject to train a classifier. This method adopts cross-validation to extend the amount of the new subject's training data and sets an adaptive threshold to select the optimal combination of the classifiers. Twenty-five subjects participated in the N200- and P300-based brain-computer interface. The study compares CV-T-TAB to five traditional training methods by testing them on the training of a support vector machine. The accuracy, information transfer rate, area under the curve, recall and precision are used to evaluate the performances under nine conditions with different amounts of data. CV-T-TAB outperforms the other methods and retains a high accuracy even when the amount of data is reduced to one-third of the original amount. The results imply that CV-T-TAB is effective in improving the performance of a subject-specific classifier with a small amount of data by adopting multiple subjects' classifiers, which reduces the training cost.

Regions of interest computed by SVM wrapped method for Alzheimer's disease examination from segmented MRI

Accurate identification of the most relevant brain regions linked to Alzheimer's disease (AD) is crucial in order to improve diagnosis techniques and to better understand this neurodegenerative process. For this purpose, statistical classification is suitable. In this work, a novel method based on support vector machine recursive feature elimination (SVM-RFE) is proposed to be applied on segmented brain MRI for detecting the most discriminant AD regions of interest (ROIs). The analyses are performed both on gray and white matter tissues, achieving up to 100% accuracy after classification and outperforming the results obtained by the standard t-test feature selection. The present method, applied on different subject sets, permits automatically determining high-resolution areas surrounding the hippocampal area without needing to divide the brain images according to any common template.