Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor

In this paper, we present a real-time algorithm for automatic recognition of not only physical activities, but also, in some cases, their intensities, using five triaxial wireless accelerometers and a wireless heart rate monitor. The algorithm has been evaluated using datasets consisting of 30 physical gymnasium activities collected from a total of 21 people at two different labs. On these activities, we have obtained a recognition accuracy performance of 94.6% using subject-dependent training and 56.3% using subject-independent training. The addition of heart rate data improves subject-dependent recognition accuracy only by 1.2% and subject-independent recognition only by 2.1%. When recognizing activity type without differentiating intensity levels, we obtain a subject-independent performance of 80.6%. We discuss why heart rate data has such little discriminatory power.

1. Introduction

Automatic detection of physical activity (PA) might enable new types of health assessment and intervention tools that help people maintain their energy balance and stay physically fit and healthy. Recent research has shown that wearable accelerometers can be used to reliably detect some physical activity types when tested on small datasets (e.g. [1] – [4]). We are unaware; however, of work showing the same algorithm can detect not only activity type but also, in some cases, the same activity at different intensities. Furthermore, most work with accelerometers has either used cumbersome wired sensors [3] or sensors that store data locally for off-line processing [1], [4], [5]. Here we show how wireless sensors transmitting raw data in real-time (and thus susceptible to signal loss) could be used for automatic PA and PA-intensity recognition.