[Cross-subject electroencephalogram emotion recognition based on maximum classifier discrepancy].

Affective brain-computer interfaces (aBCIs) has important application value in the field of human-computer interaction. Electroencephalogram (EEG) has been widely concerned in the field of emotion recognition due to its advantages in time resolution, reliability and accuracy. However, the non-stationary characteristics and individual differences of EEG limit the generalization of emotion recognition model in different time and different subjects. In this paper, in order to realize the recognition of emotional states across different subjects and sessions, we proposed a new domain adaptation method, the maximum classifier difference for domain adversarial neural networks (MCD_DA). By establishing a neural network emotion recognition model, the shallow feature extractor was used to resist the domain classifier and the emotion classifier, respectively, so that the feature extractor could produce domain invariant expression, and train the decision boundary of classifier learning task specificity while realizing approximate joint distribution adaptation. The experimental results showed that the average classification accuracy of this method was 88.33% compared with 58.23% of the traditional general classifier. It improves the generalization ability of emotion brain-computer interface in practical application, and provides a new method for aBCIs to be used in practice.

Cross-subject electroencephalogram emotion recognition based on maximum classifier discrepancy / 生物医学工程学杂志

Affective brain-computer interfaces (aBCIs) has important application value in the field of human-computer interaction. Electroencephalogram (EEG) has been widely concerned in the field of emotion recognition due to its advantages in time resolution, reliability and accuracy. However, the non-stationary characteristics and individual differences of EEG limit the generalization of emotion recognition model in different time and different subjects. In this paper, in order to realize the recognition of emotional states across different subjects and sessions, we proposed a new domain adaptation method, the maximum classifier difference for domain adversarial neural networks (MCD_DA). By establishing a neural network emotion recognition model, the shallow feature extractor was used to resist the domain classifier and the emotion classifier, respectively, so that the feature extractor could produce domain invariant expression, and train the decision boundary of classifier learning task specificity while realizing approximate joint distribution adaptation. The experimental results showed that the average classification accuracy of this method was 88.33% compared with 58.23% of the traditional general classifier. It improves the generalization ability of emotion brain-computer interface in practical application, and provides a new method for aBCIs to be used in practice.

Affective brain-computer interfaces: Choosing a meaningful performance measuring metric.

Affective brain-computer interfaces are a relatively new area of research in affective computing. Estimation of affective states can improve human-computer interaction as well as improve the care of people with severe disabilities. To assess the effectiveness of EEG recordings for recognizing affective states, we used data collected in our lab as well as the publicly available DEAP database. We also reviewed the articles that used the DEAP database and found that a significant number of articles did not consider the presence of the class imbalance in the DEAP. Failing to consider class imbalance creates misleading results. Further, ignoring class imbalance makes the comparison of the results between studies using different datasets impossible, since different datasets will have different class imbalances. Class imbalance also shifts the chance level, hence it is vital to consider class bias while determining if the results are above chance. To properly account for the effect of class imbalance, we suggest the use of balanced accuracy as a performance metric, and its posterior distribution for computing credible intervals. For classification, we used features from the literature as well as theta beta-1 ratio. Results from DEAP and our data suggest that the beta band power, theta band power, and theta beta-1 ratio are better feature sets for classifying valence, arousal, and dominance, respectively.

Extracting neurophysiological signals reflecting users' emotional and affective responses to BCI use: A systematic literature review.

BACKGROUND: Brain-computer interfaces (BCIs) allow persons with impaired mobility to communicate and interact with the environment, supporting goal-directed thinking and cognitive function. Ideally, a BCI should be able to recognize a user's internal state and adapt to it in real-time, to improve interaction. OBJECTIVE: Our aim was to examine studies investigating the recognition of affective states from neurophysiological signals, evaluating how current achievements can be applied to improve BCIs. METHODS: Following the PRISMA guidelines, we performed a literature search using PubMed and ProQuest databases. We considered peer-reviewed research articles in English, focusing on the recognition of emotions from neurophysiological signals in view of enhancing BCI use. RESULTS: Of the 526 identified records, 30 articles comprising 32 studies were eligible for review. Their analysis shows that the affective BCI field is developing, with a variety of combinations of neuroimaging techniques, selected neurophysiological features, and classification algorithms currently being tested. Nevertheless, there is a gap between laboratory experiments and their translation to everyday situations. CONCLUSIONS: BCI developers should focus on testing emotion classification with patients in ecological settings and in real-time, with more precise definitions of what they are investigating, and communicating results in a standardized way.