Physical activity estimation using accelerometer and facility information for elderly healthcare

This paper proposes a novel framework to estimate the amount of physical activity at a place where people stayed, by utilizing facility information and user's acceleration data. The total amount of physical activities, energy expenditure of a physical activity is a good scale. Our framework provides a physical activity scale based on typical energy expenditure of the activity given by existing researches already. To estimates the energy expenditure, we use typical value of metabolic equivalents to task (MET) which is used as practical scale. Unlike the other studies for monitoring physical activity, we estimate the type of user's activity using facility information which are obtained from road map and land-use/land-cover map. To confirm the feasibility of our approach, we have conducted a long-term experiment on monitoring the activity of elderly people living in less-populated area. As a result, our framework provides good summarization of daily activities of participants.

I. Introduction

Monitoring and assistive technologies for elderly people are becoming important since the world's population is aging. Continuous monitoring of the daily activity level can provide important clues to estimate the health status[2]. Smartphone, as wearable sensors connected to wide area network, is highly suitable device for the continuous telemonitoring of outdoor activities of elderly people. Recently, there are several studies to estimate the energy expenditure of physical activities using sensors embedded in smartphone [6], [7]. Most of them utilize machine learning approach to recognize human activity from motion sensors. However, it is still difficult to recognize complex human activity accurately from only the motion data of smartphone even in the recent studies[11]. One way of improving the accuracy of human activity recognition is to reduce the number of activities.