Emotion Detection Using Noninvasive Low Cost Sensors

TL;DR

This study demonstrates that noninvasive, low-cost sensors like EEG, EMG, and GSR can reliably classify high versus low emotional valence and arousal, achieving state-of-the-art results without individual model tuning.

Contribution

It shows that affordable, noninvasive sensors can effectively recognize emotional states, reducing the need for expensive or uncomfortable multi-electrode setups.

Findings

Achieved high classification accuracy for valence and arousal.

Performed successful cross-subject classification without individual training.

Validated the effectiveness of low-cost sensors in emotion recognition.

Abstract

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.