Data Analytics in Ubiquitous Sensor-based Health Information Systems

Sensor-based intelligent and ubiquitous systems are important in the context of "Intelligent Infrastructures". In this scenario, healthcare is one area where sensors and mobile platforms will become more useful and the application must have the capability of analysing the data feeds from sensors to extract useful meanings. Various data analytics methods such as data-mining techniques or stream processing and continuous event processing techniques are useful in this regard. This paper is a broad survey article where we look into the emerging trends in Ubiquitous Healthcare Information Systems focussing on the use of analytics techniques to cluster patients into similar groups, or to process streaming data for detecting abnormal medical conditions as early as possible. Considering the size of the population and hence the volume of data, there are several architectural challenges such as scalability and availability of the platforms and support for "big-data" handling. We try to summarise how these problems have been addressed and whether the solutions are adequate or not.