A Prediction Method Based on Complex Event Processing for Cyber Physical System

For flow prediction in intelligent traffic system, one certain model cannot get excellent performance under different environments. Predicting models should also be updated according to data stream. In order to resolve these problems, a prediction method based on complex event processing was proposed. With fuzzy ontology to model historical event context and context clustering to partition events, this method could learn Bayesian network models according to different data during complex event processing. Appropriate Bayesian network model or combination of Bayesian network models could be provided by this method for real-time prediction and analysis of current context of events. The experimental result shows that this method can process events stream of Cyber Physical System (CPS) effectively and has favorable prediction performance.