Emotion Detection Using Noninvasive Low Cost Sensors
This addresses the problem of expensive or uncomfortable multi-electrode sensors for emotion detection in applications like healthcare, offering a more practical solution.
The study tackled emotion recognition by using noninvasive low-cost sensors (EEG, EMG, GSR) to classify high vs. low emotional valence and arousal, achieving state-of-the-art classification performance in a cross-subject setting with 19 subjects.
Emotion recognition from biometrics is relevant to a wide range of application domains, including healthcare. Existing approaches usually adopt multi-electrodes sensors that could be expensive or uncomfortable to be used in real-life situations. In this study, we investigate whether we can reliably recognize high vs. low emotional valence and arousal by relying on noninvasive low cost EEG, EMG, and GSR sensors. We report the results of an empirical study involving 19 subjects. We achieve state-of-the- art classification performance for both valence and arousal even in a cross-subject classification setting, which eliminates the need for individual training and tuning of classification models.