Abstract:

This paper focuses on sharing and discussing efficient system design and architectural concepts developed and tested acquisition and processing of biomedical data in large-scale systems for medical monitoring and reasoning. A major area of the research included utilization of wearable and mobile technologies to enable the collection of high volumes of inertial and biomedical data used to support data fusion and decision-making algorithms as well as medical inferencing. Although medical diagnostics and decision algorithms have not been the main aim of the research, this preliminary phase was crucial to test the capabilities of existing off-the-shelf technologies and the functional responsibilities of the system’s logic components. Architecture variants contained several schemes for data processing moving the responsibility for signal feature extraction, data classification, and pattern recognition from wearable to mobile up to server facilities. Analysis of transmission and processing delays provided architecture variants pros and cons but most of all knowledge about possible applications in medical, military, and fitness domains. To construct, evaluate and test architectures, a set of alternative technology stacks was prepared and compared using and quantitative metrics. The major architecture characteristics (high availability, scalability, reliability) have been defined imposing asynchronous processing of sensor data, efficient data representation, iterative reporting, event-driven processing, and restricting pulling operations. Sensor data processing persists the original data on handhelds but is mainly aimed at extracting chosen set of signal features calculated for specific time windows – varying for analyzed signals and the sensor data acquisition rates. Long-term monitoring of patients required the development of mechanisms, which probe the patient and in case of detecting anomalies or dangerous characteristic changes tune the data acquisition process. This paper describes experiences connected with the design of scalable decision support tools and evaluation techniques for architectural concepts implemented within the mobile and server software.