Complex Event Processing over Uncertain Data Streams

TL;DR: This paper proposes an optimized method to not only calculate the probability of outputs of compound events but also obtain the value of confidence of the complex pattern given by user against uncertain raw input data stream generated by distrustful network devices.

Abstract: Pattern matching over event streams is well developed. However, with the increasing demand of measurement accuracy, confidence of more complex events sourced from original, continuously arriving events generated from sensor kind electronic devices is becoming more and more been concerned. Actually, some applications such as RFID-based supply chain management and monitoring in health care require data stream with high reliability, but current hardware and wireless communication techniques cannot support 100% confident data, one stream processing engine which can report confidence for processed complex events over uncertain data is needed. In this paper, we propose an optimized method to not only calculate the probability of outputs of compound events but also obtain the value of confidence of the complex pattern given by user against uncertain raw input data stream generated by distrustful network devices. Our proposal is based on an existing stream processing engine SASE+, and we extend its evaluation model NFAb automaton to a new type of automaton in order to manage the runtime against probabilistic stream. In the design of automaton, we consider optimizations to reduce the computation cost and response time to a realistic degree with long sliding time window.