In-Home Activity Monitoring Using Radars
Abstract
We propose novel non-contact real-time cloud-based in-home activityrecognition and gait monitoring systems. We present standalone
IoT-based mm-wave radar systems coupled with deep learning
algorithms as the basis of an autonomous in-home free-living
physical activity recognition and gait monitoring system. Using the
mm-wave radar system, human spectrograms (time-varying micro-
Doppler patterns) are used to train deep Gated Recurrent Network
(GRU) to identify physical activities performed by a subject in his/her
living environment. An overall model accuracy of 93% was achieved
to classify in-home physical activities.