Annotation Framework for the Physical Activity Evaluation in Real-Time

Abstract

Objectives: Work aims to create a portable tool with a decision support, providing relevant methods for purposes of physical activity evaluation in real-time. Methods: We have utilized accelerometer equipped ez430Chronos watch in conjunction with a preconfigured RaspberryPi-based setup. Wireless transmission of accelerometer data into a running web application instance, which served as a user frontend, is provided through the WebSocket protocol. Decision support is based on a Weka classifier. Results: The proposed framework is ready to be used for the annotation and basic evaluation of physical activity data in a Wi-Fi covered areas. Minor issues are related to the occasional instability of data transmission, which has to be handled consequently. Conclusions: We found the overall framework architecture robust enough to serve its purpose. Next steps in the development will lead to an expansion of outlined functionality.