Recognition of Human Emotions Using Machine Learning and Deep Learning Algorithms

Dear Colleagues,

Emotion is a psycho–physiological response triggered by conscious and/or unconscious stimuli. Emotion cannot be explained by scientific principles such as rational thought, logical arguments, testable hypotheses, and repeatable experiments. Emotions play a crucial role in human communication and can be expressed by multidimensional cues, such as vocabulary, intonation of voice, facial expressions, and gestures. The recognition of emotions in the affective computing scenario may lead to understanding human cognitive processes, such as attention, memory, and decision making. For instance, (i) modeling emotional feelings and (ii) considering their behavioral implication (i.e., stress-related implications) are useful in preventing emotions from having a negative effect on the workplace. Accordingly, the decision-making process should discard emotion whenever possible: Both positive and negative emotions can distort the validity of a decision.

Machine learning and deep learning techniques have already been applied to consistently recognize human emotion using physiological data, facial expression, body gestures, speech, and text. However, several challenges are still present. The learning model should be robust against high dimensional and heterogeneous data, unbalanced classes, and time ambiguity. For instance, modeling and predicting the emotional state over time is not a trivial problem, because continuous data labeling is costly and not always feasible. This is a crucial issue in real-world applications, where the labeling of the features is sparse and eventually describes only the most prominent emotional events.

This Special Issue on “Recognition of Human Emotions Using Machine Learning and Deep Learning Algorithms” calls for manuscripts proposing new machine learning and deep learning methods, approaches, and applications able to face the challenges related to human motion recognition. Manuscripts focused on interpretable models which also provide explanations as to why and how the learning model achieved a prediction are particularly welcome.

Dr. Luca Romeo
Dr. Sara Moccia
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.