Optimised attribute selection for emotion classification using physiological signals

Personalized Clustering for Emotion Recognition Improvement

Emotion recognition through artificial intelligence and smart sensing of physical and physiological signals (affective computing) is achieving very interesting results in terms of accuracy, inference times, and user-independent models. In this sense, there are applications related to the safety and well-being of people (sexual assaults, gender-based violence, children and elderly abuse, mental health, etc.) that require even more improvements. Emotion detection should be done with fast, discrete, and non-luxurious systems working in real time and real life (wearable devices, wireless communications, battery-powered). Furthermore, emotional reactions to violence are not equal in all people. Then, large general models cannot be applied to a multi-user system for people protection, and health and social workers and law enforcement agents would welcome customized and lightweight AI models. These semi-personalized models will be applicable to clusters of subjects sharing similarities in their emotional reactions to external stimuli. This customization requires several steps: creating clusters of subjects with similar behaviors, creating AI models for every cluster, continually updating these models with new data, and enrolling new subjects in clusters when required. An initial approach for clustering labeled data compiled (physiological data, together with emotional labels) is presented in this work, as well as the method to ensure the enrollment of new users with unlabeled data once the AI models are generated. The idea is that this complete methodology can be exportable to any other expert systems where unlabeled data are added during in-field operation and different profiles exist in terms of data. Experimental results demonstrate an improvement of 5% in accuracy and 4% in F1 score with respect to our baseline general model, along with a 32% to 58% reduction in variability, respectively.

Responses to External Emotions or their Transitions at Central to Peripheral Nervous System Levels: A Methodological Contribution to Mental Health

Background:

Responses to external emotional-stimuli or their transitions might help to elucidate the scientific background and assist the clinical management of psychiatric problems, but pure emotional-materials and their utilization at different levels of neurophysiological processing are few.

Objective:

We aimed to describe the responses at central and peripheral levels in healthy volunteers and psychiatric patients when facing external emotions and their transitions.

Methods:

Using pictures and sounds with pure emotions of Disgust, Erotica, Fear, Happiness, Neutral, and Sadness or their transitions as stimuli, we have developed a series of non-invasive techniques, i.e., the event-related potentials, functional magnetic resonance imaging, excitatory and inhibitory brainstem reflexes, and polygraph, to assess different levels of neurophysiological responses in different populations.

Results:

Sample outcomes on various conditions were specific and distinguishable at cortical to peripheral levels in bipolar I and II disorder patients compared to healthy volunteers.

Conclusions:

Methodologically, designs with these pure emotions and their transitions are applicable, and results per se are specifically interpretable in patients with emotion-related problems.