WEARDA: Recording Wearable Sensor Data for Human Activity Monitoring

TL;DR

WEARDA is an open-source software tool that enables researchers to collect raw sensor data from smartwatches for human activity monitoring, addressing practical challenges for reliable data acquisition.

Contribution

It introduces a comprehensive, open-source solution for recording multi-sensor data from smartwatches, enhancing transparency and control for human activity research.

Findings

Successfully used in a dementia-related study

Supports simultaneous recording from four sensors

Addresses practical challenges in wearable data collection

Abstract

We present WEARDA, the open source WEARable sensor Data Acquisition software package. WEARDA facilitates the acquisition of human activity data with smartwatches and is primarily aimed at researchers who require transparency, full control, and access to raw sensor data. It provides functionality to simultaneously record raw data from four sensors -- tri-axis accelerometer, tri-axis gyroscope, barometer, and GPS -- which should enable researchers to, for example, estimate energy expenditure and mine movement trajectories. A Samsung smartwatch running the Tizen OS was chosen because of 1) the required functionalities of the smartwatch software API, 2) the availability of software development tools and accessible documentation, 3) having the required sensors, and 4) the requirements on case design for acceptance by the target user group. WEARDA addresses five practical challenges concerning preparation, measurement, logistics, privacy preservation, and reproducibility to ensure efficient and errorless data collection. The software package was initially created for the project "Dementia back at the heart of the community", and has been successfully used in that context.