Abstract
Emotion recognition and monitoring based on commonly used wearable devices can play an important role in psychological health monitoring and human-computer interaction. However, the existing methods cannot rely on the common smart bracelets or watches for emotion monitoring in daily life. To address this issue, our study proposes a method for emotional recognition using heart rate data from a wearable smart bracelet. A ‘neutral + target’ pair emotion stimulation experimental paradigm was presented, and a dataset of heart rate from 25 subjects was established, where neutral plus target emotion (neutral, happy, and sad) stimulation video pairs from China’s standard Emotional Video Stimuli materials (CEVS) were applied to the recruited subjects. Normalized features from the data of target emotions normalized by the baseline data of neutral mood were adopted. Emotion recognition experiment results approved the effectiveness of ‘neutral + target’ video pair simulation experimental paradigm, the baseline setting using neutral mood data, and the normalized features, as well as the classifiers of Adaboost and GBDT on this dataset. This method will promote the development of wearable consumer electronic devices for monitoring human emotional moods.
Highlights
Emotions can significantly impact on our daily lives and work
To make the emotion recognition feasible on wearable devices, our study proposed a method for recognizing emotional states of subjects via the heart rate signals from a wearable bracelet
Except the regular rest period between two emotional stimulation which let the subjects enter the resting state, the neutral stimulation video was added as the first part of each video pair as a control, which was conducive to the induction of target emotion
Summary
Emotions can significantly impact on our daily lives and work. can emotions reflect a person’s mental state, but they present a strong connection with people’s physical health [1].Negative emotions have become key factors affecting human health. Emotional recognition based on behavior performance is intuitive and convenient, people can deliberately disguise emotional states in some situations. It is well known that physiological signals are affected by the human endocrine system and the autonomic nervous system These systems are less affected by human subjective consciousness and can reflect the real emotional state more objectively and accurately [4]. From this perspective, emotion recognition based on physiological signals makes the results more objective
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
