CSense: A Stream-Processing Toolkit for Robust and High-rate Mobile Health Systems

This paper presents CSense – a stream-processing toolkit for developing robust and high-rate mHealth systems in Java. CSense addresses the needs of these systems by providing a new programming model that supports flexible application configuration, a high-level concurrency model, memory management, and compiler analyses and optimizations. The compiler analyses detect a range of programming errors including application composition errors, improper use of memory management, and data races. We identify that memory management and concurrency limit the scalability of stream processing systems. We incorporate memory pools, frame conversion optimizations, and custom synchronization primitives to develop a scalable runtime. CSense is evaluated on Galaxy Nexus phones running Android. Empirical results indicate that our run-time achieves 25 times higher steam processing rate compared to a realistic baseline implementation. Moreover, our frame analysis optimizes the exchange of data between components to achieve an additional 45% improvement in stream rate. We demonstrate the versatility of CSense by developing three mHealth systems.