In recent years, the volume of data collected from devices and wearable sensors has significantly increased, with a tenfold growth annually. As a result, data models have become essential tools for organizing data, defining relationships between elements and standardizing data, especially in areas where wearable sensors are increasingly prevalent, such as mobility and healthcare. This study presents an extensible and robust data reference model designed to address the challenges of data integration across health, environment and mobility domains. The model was inspired by the data requirements and challenges derived from RAISE pilot project, and it leverages the FIWARE Smart Data Models initiative to ensure interoperability, scalability and adaptability to evolving data requirements. Three domain specific models were developed, each tailored to meet the unique data needs and implementation requirements of the respective pilots. Additionally, Fitbit measurements were incorporated to capture health data from wearable sensors, expanding the model's capability to handle data from wearables. In cases where alignment with FIWARE Smart Data Models was not feasible, the Open mHealth standard was utilized to ensure comprehensive data representation. Descriptive statistics were also applied to analyze main features of the data and capture metadata across all pilot variables. The proposed model provides a shared, flexible and common schema capable of representing and handling data from diverse sources, devices or platforms, ultimately enabling meaningful metadata generation and improved data interoperability across domains. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.