The AutoActive Research Environment.

There is an ever-growing variety of biomedical sensors and wearables that aim to monitor activity, biomarkers, and vital signs. However, to fully understand the physical and physiological factors of the underlying processes, multiple sensors are often needed in combination with videos. Software for combining, synchronizing, organising and processing sensor data from multiple sensors and videos is therefore essential. Even though multiple open-source solutions like Pyomeca (Martinez et al., 2020) and ALPS (Musmann et al., 2020) exist, existing open source software solutions are limited. None provide the possibility to combine sensor data and videos, few provide tools for synchronising sensors, and none provide tools for synchronising sensors with videos. Furthermore, many solutions rely on cloud storage, which is often unacceptable in biomedical research. There also exist solutions which are not limited in functionality and solve many of the same problems as ARE, such as SensiML Analytics Toolkit (SensiML, cited Jan 2022) and Pasco Capstone Software (scientific, cited Jan 2022), but these are not open source. To meet these limitations, we have developed the AutoActive Research Environment (ARE). The idea of ARE is to create a generic open source methodological framework, especially but not exlusively for the biomedical and sport domains, supporting a wide range of sensors and tools that aid the development, optimization, and evaluation of algorithms.