Emotion Detection in Ageing Adults from Physiological Sensors

The increasing life expectancy is causing a fast ageing population around the globe, which is raising the demand on assistive systems based on ambient intelligence. While numerous papers have focused on the physical aspects in elderly, only a few works have attempted to regulate their emotional state. In this work, a new approach for monitoring and detecting the emotional state in elderly is presented. First, different physiological signals are acquired by means of wearable sensors, and data are transmitted to the embedded system. Next, noise and artifacts are removed by applying different signal processing techniques, depending on the signal behavior. Finally, several temporal and statistical markers are extracted and used to feed the classification model. In this very first version, a logistic regression model is used to detect two possible emotional states. In order to calibrate the model and adjust the boundary decision, twenty volunteers have agreed to be monitored and recorded to train the model. Finally, a decision maker regulates the environment, acting directly upon the elderly’s emotional state.