Easy-Assist: An Intelligent Haptic-based Affective framework for Assisted Living
Prabha Sundaravadivel, Ashton Fitzgerald, Saraju P. Mohanty, Elias Kougianos · 2020
Unlike the younger population that uses wearables such as smartwatches for monitoring health on daily basis, elderly people need assistance in the use of technology and interpreting the data obtained through these smart connected frameworks. The current monitoring systems are primarily designed to monitor the physiological signals on daily basis. The aim of this proposed research, Easy-Assist, is to help older people to maintain their emotional well-being. This research is focused on developing a wearable affective framework, which can help in detecting the emotions of the user in addition to monitoring their physiological signals. The proposed framework can be used in an automated assisted living environment, where the user's emotional state can be balanced using a haptic-based emotional elicitation system after the user's emotion is recognized, detected and interpreted in real-time. The proposed framework is validated using a fall detection algorithm deployed in a custom-built watch wearable, built using off-the-shelf components and an emotion detection framework built using a single board computer. A dataset of 21700 samples acquired using the proposed framework yielded a maximum efficiency of 97.25%, 96 %, and 94 %, in classifying the state and emotion classes into Alert, Active and Normal classes respectively, using multi-class SVM model. The overall latency of the proposed research was in few orders of milli-seconds.