Human Physical Activity Recognition Using Smartphone Sensors

TLDR

The growing elderly population makes aging in place a key concern in ambient assisted living. This study proposes a smartphone-based human physical activity recognition system. The system uses a classifier built from the phone’s accelerometer, gyroscope, and gravity sensors to detect walking, running, sitting, standing, and stair ascent/descent, and is evaluated on internal and external datasets. It achieves high accuracy across all six activities, especially walking, running, sitting, and standing, and is fully implemented as an Android application.

Abstract

Because the number of elderly people is predicted to increase quickly in the upcoming years, “aging in place” (which refers to living at home regardless of age and other factors) is becoming an important topic in the area of ambient assisted living. Therefore, in this paper, we propose a human physical activity recognition system based on data collected from smartphone sensors. The proposed approach implies developing a classifier using three sensors available on a smartphone: accelerometer, gyroscope, and gravity sensor. We have chosen to implement our solution on mobile phones because they are ubiquitous and do not require the subjects to carry additional sensors that might impede their activities. For our proposal, we target walking, running, sitting, standing, ascending, and descending stairs. We evaluate the solution against two datasets (an internal one collected by us and an external one) with great effect. Results show good accuracy for recognizing all six activities, with especially good results obtained for walking, running, sitting, and standing. The system is fully implemented on a mobile device as an Android application.