Quality of user experience evaluation with emotion recognition from peripheral physiological signals

Abstract

Quality of Experience (QoE), which is a measure of a user’s degree of delight or annoyance, is traditionally captured using human reports which are subjective by nature. Similarly, estimation of human emotions is grouped into subjective self reports as well as two other categories: behavioural (facial expression, eye tracking, body movement) and physiological (EEG, ECG, HR, GSR etc). Wearables such as smart watches with sensors to accurately measure physiological data can be combined with Artificial intelligence (AI) machine learning and deep learning techniques to objectively extract information such as emotion categories from the sensor data.