English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Background: Studies have shown the potential adverse health effects, rangingfrom headaches to cardiovascular disease, associated with long-term negativeemotions and chronic stress. Since many indicators of stress are imperceptibleto observers, the early detection and intervention of stress remains a pressingmedical need. Physiological signals offer a non-invasive method of monitoringemotions and are easily collected by smartwatches. Existing research primarilyfocuses on developing generalized machine learning-based models for emotionclassification. Objective: We aim to study the differences between personalizedand generalized machine learning models for three-class emotion classification(neutral, stress, and amusement) using wearable biosignal data. Methods: Wedeveloped a convolutional encoder for the three-class emotion classificationproblem using data from WESAD, a multimodal dataset with physiological signalsfor 15 subjects. We compared the results between a subject-exclusivegeneralized, subject-inclusive generalized, and personalized model. Results:For the three-class classification problem, our personalized model achieved anaverage accuracy of 95.06% and F1-score of 91.71, our subject-inclusivegeneralized model achieved an average accuracy of 66.95% and F1-score of 42.50,and our subject-exclusive generalized model achieved an average accuracy of67.65% and F1-score of 43.05. Conclusions: Our results emphasize the need forincreased research in personalized emotion recognition models given that theyoutperform generalized models in certain contexts. We also demonstrate thatpersonalized machine learning models for emotion classification are viable andcan achieve high performance.

A Comparison of Personalized and Generalized Approaches to Emotion Recognition Using Consumer Wearable Devices: Machine Learning Study