Sensor-based detection of abnormal events for elderly people using deep belief networks

Various technological developments in home-care systems have allowed elderly people to live independently without compromising their safety. A pilot study employing deep learning algorithm was conducted to study the daily routines of elderly people. We monitored unsupervised, diverse daily activities of elderly people such as household chores, sleeping, cooking, cleaning, using the bathroom, watching television, and meditating. The activities were monitored to track human-environment interactions by using motion sensors, actuators, and surveillance systems that were mounted inside living rooms, bedrooms, and kitchens and on bathroom doorways to detect safety hazards in the environment for elderly people. Such collected data were used in deep belief networks to ascertain and identify activities that are related to various health and self-care problems. Simulation results show that the proposed system outperforms the support vector machines in terms of F1 score and accuracy in identifying daily activities.