Emotion on the Edge: Air Quality Sensors Decoded as a Real-World Emotion Indicator

As the research community increasingly focuses on quantifying emotional states in real-world scenarios, there is a growing need for edge computing. In this work, we present a novel approach to on-device emotion classification through the development of a low-cost hand-held device. This device incorporates a range of environmental air quality factors, including Particulate Matter, Nitrogen Dioxide, Carbon Monoxide, Ammonia, and Noise. Our research addresses the current limitations in the field of emotional state measurement by leveraging environmental air quality data, which has been previously linked to affective states. This on-device approach not only offers an alternative to resource-intensive emotion recognition methods but also contributes to the development of more practical and affordable solutions for emotion assessment. The preliminary results of our device’s performance in real-world scenarios suggest its effectiveness in quantifying emotional states through air quality factors, with the model achieving 95% accuracy demonstrating accurate on-device classification without the need for external high-processing power.