Multi-Sensor-Fusion Approach for a Data-Science-Oriented Preventive Health Management System: Concept and Development of a Decentralized Data Collection Approach for Heterogeneous Data Sources

• Main Authors: Sebastian Neubert, André Geißler, Thomas Roddelkopf, Regina Stoll, Karl-Heinz Sandmann, Julius Neumann, Kerstin Thurow
• Format: Article
• Language: English
• Published: Hindawi Limited 2019-01-01
• Series: International Journal of Telemedicine and Applications
• Online Access: http://dx.doi.org/10.1155/2019/9864246

Investigations in preventive and occupational medicine are often based on the acquisition of data in the customer’s daily routine. This requires convenient measurement solutions including physiological, psychological, physical, and sometimes emotional parameters. In this paper, the introduction of a decentralized multi-sensor-fusion approach for a preventive health-management system is described. The aim is the provision of a flexible mobile data-collection platform, which can be used in many different health-care related applications. Different heterogeneous data sources can be integrated and measured data are prepared and transferred to a superordinated data-science-oriented cloud-solution. The presented novel approach focuses on the integration and fusion of different mobile data sources on a mobile data collection system (mDCS). This includes directly coupled wireless sensor devices, indirectly coupled devices offering the datasets via vendor-specific cloud solutions (as e.g., Fitbit, San Francisco, USA and Nokia, Espoo, Finland) and questionnaires to acquire subjective and objective parameters. The mDCS functions as a user-specific interface adapter and data concentrator decentralized from a data-science-oriented processing cloud. A low-level data fusion in the mDCS includes the synchronization of the data sources, the individual selection of required data sets and the execution of pre-processing procedures. Thus, the mDCS increases the availability of the processing cloud and in consequence also of the higher level data-fusion procedures. The developed system can be easily adapted to changing health-care applications by using different sensor combinations. The complex processing for data analysis can be supported and intervention measures can be provided.