Distributed event detection method based on correlation

Abstract

The invention discloses a distributed event detection method based on a correlation. The temporal correlation of data is analyzed in nodes through a clustering structure based on the locality of a wireless sensor network event area, the spatial correlation of the data is analyzed between adjacent nodes, and the node where an event happens is recognized. The abnormal correlation of the nodes is analyzed through the histogram method, and the detecting accuracy is improved. Due to the fact that the summary information of a histogram is transmitted among the nodes, the communication energy consumption among the nodes is reduced. The occurrence of new events can be effectively detected, the method has a low false alarm rate and low energy consumption, and compared with a centralized abnormality detection method, the distributed event detection method based on the correlation has the advantages of being high in detection performance and obviously reducing communication cost.

Description

technical field [0001] The invention relates to the detection of an abnormal behavior node of a sensor network organized in a cluster structure, in particular to a correlation-based distributed event detection method. Background technique [0002] Wireless Sensor Networks (WSN for short) are full of sensor nodes to detect abnormal conditions. If the deviation between the data sensed by the sensor and the historical data exceeds the specified threshold, it is considered that there is abnormal data; if similar abnormal conditions appear in multiple nodes in a certain area, it can be judged to be an abnormal node, reflecting an abnormal behavior , and need to be reported to the base station in time for the user to process. New events or some events in WSN have no prior knowledge and judgment conditions, so the event threshold cannot be used as the method of event judgment. This type of event detection is also called anomaly detection. In many applications, detecting such even...

AI Technical Summary

Problems solved by technology

However, these methods either only consider the spatial correlation and do not consider the temporal correlation; or the communication cost is high, the scalability is not strong, and it is not suitable for application in large-scale sensor networks.

Jun M C, Jeong H, Jay Kuo CC. Distributed spatio-temporal outlier detection in sensor networks [C]. Proc of SPIE, 2005, 5819: 273-284 It is assumed that the abnormal points conform to the equilibrium α distribution, so as to detect abnormalities; but the actual There is often no prior distribution in , and even if there is a suitable distribution, the new data may not necessarily conform to the known distribution

Images