Pattern detection in Cyber-Physical Systems

A Cyber-Physical System (CPS) integrates physical devices (i.e., sensors) with cyber (i.e., informational) components to form a context sensitive system that responds intelligently to dynamic changes in real-world situations. A core element of CPS is the collection and assessment of information from noisy, dynamic, and uncertain physical environments that must be transformed into usable knowledge in real-time. Machine learning algorithms such as cluster analysis can be used to extract useful information and patterns from data generated from physical devices based on which novel applications of CPS can make informed decisions. In this paper we propose to use a density-based data stream clustering algorithm, built on the Multiple Species Flocking model, for the monitoring of big data, generated from numerous applications such as machine monitoring, health monitoring, sensor networks. In the proposed approach, approximate results are available on demand at anytime, so it is particularly apt for real life monitoring applications.