Short-term emotion assessment in a recall paradigm

Abstract

The work presented in this paper aims at assessing human emotions using peripheral as well as electroencephalographic (EEG) physiological signals on shorttime periods. Three specific areas of the valence-arousal emotional space are defined, corresponding to negatively excited, positively excited, and calm-neutral states. An acquisition protocol based on the recall of past emotional life episodes has been designed to acquire data from both peripheral and EEG signals. Pattern classification is used to distinguish between the three areas of the valence-arousal space. The performance of several classifiers has been evaluated on ten participants and different feature sets: peripheral features, EEG time-frequency features, EEG pairwise mutual information features. Comparison of results obtained using either peripheral or EEG signals confirms the interest of using EEG's to assess valence and arousal in emotion recall conditions. The obtained accuracy for the three emotional classes is 63% using EEG time-frequency features which is better than the results obtained from previous studies using EEG and similar classes. Fusion of the different feature sets at the decision level using a summation rule also showed to improve accuracy to 70%. Furthermore, the rejection of non confident samples finally led to a classification accuracy of 80% for the three classes.

A survey of affective brain computer interfaces: principles, state-of-the-art, and challenges

“…We are aware of only two studies which used an interactive situation where the participants were playing games to induce and measure emotions. [27,103] Similarly, two studies [109,110] relied on mental imagery, which is expected to elicit emotional patterns similar to everyday interactions. In all these cases, the experiments were carried out in the lab, and there is thus a strong need to evaluate the performance of aBCI in ecological contexts.…”

Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease

“…Zhang and Lee reported an average accuracy of 73.00% ± 0.33% by using EEG features to categorize subject's status into two emotional states (Zhang and Lee, 2009). Chanel et al obtained an average accuracy of 63% by using EEG time-frequency information as features for three emotional classes (Chanel et al, 2009). Lin et al (2010) used EEG signals to recognize emotions in response to emotional music.…”

Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos

“…In total 53 features were extracted from peripheral physiological responses based on the proposed features in the literature [2,18]. A summary of the features is given below.…”

“…One approach to analysis and recognition of emotions is to directly assess the activity of the central nervous system, specifically brain electrical activity, and study the changes in this activity as the user experiences different emotional states. Several works exist that are related to emotion recognition from electroencephalogram (EEG) [7,14,10,2]. Furthermore, there are a number of experiments pointing to the fact that physiological activity is not an independent variable in autonomous nervous system patterns but reflects experienced emotional states with consistent correlates [1,17].…”

“…There has been a large number of published works in the domain of emotion recognition from physiological signals [11,2,18]. Amongst these studies, few of them studied EEG signals and achieved notable results using video stimuli.…”