MyHealthAssistant: A Phone-based body sensor network that captures the wearer's exercises throughout the day

Abstract

This paper presents a novel fitness and preventive health care system with a flexible and easy to deploy platform. By using embedded wearable sensors in combination with a smartphone as an aggregator, both daily activities as well as specific gym exercises and their counts are recognized and logged. The detection is achieved with minimal impact on the system's resources through the use of customized 3D in-ertial sensors embedded in fitness accessories with built-in pre-processing of the initial 100Hz data. It provides a flexible re-training of the classifiers on the phone which allows deploying the system swiftly. A set of evaluations shows a classification performance that is comparable to that of state of the art activity recognition, and that the whole setup is suitable for daily usage with minimal impact on the phone's resources.