A trajectory-based outlier detection method for multi-dimensional data in wireless sensor networks

Abstract

The invention discloses a method for detecting an abnormal value of multidimensional data of a wireless sensor network based on a trajectory. The problems in the existing methods that the spatial correlation between sensor nodes and the temporal correlation of node data cannot be well utilized are mainly considered. The main method comprises the following steps: clustering the sensor nodes, and further training an ellipse comprising all cluster nodes for an obtained clustering result, in order to achieve the purpose of reducing the dimension of data; selecting 10 groups of data within the same time period for all nodes in a network, carrying out corresponding dimensionality reduction processing, fitting 10 pieces of data after dimensionality reduction to a curve to serve as a test curve; similarly, carrying out the same processing on the node data within the same time period on the next day, and making the obtained curve serve as a detection curve; and comparing the trend and similarity of the test curve and the detection curve to judge whether the collected data of the node include the abnormal value. The implementation process of the method for detecting the abnormal value disclosed by the invention is relatively simple, no additional data communication is necessary in the detection process, and meanwhile, the multidimensional data collected by the sensor nodes can also be detected.

Description

technical field [0001] The invention relates to the field of wireless sensors, in particular to multi-dimensional data abnormal value detection in wireless sensor networks, which is used to solve the problem of unreliable data in multi-dimensional data collected by wireless sensor networks. technical background [0002] Wireless sensor networks (WSNs) are composed of a large number of cheap micro-nodes, and the nodes communicate through radio communication. The purpose of the network is to complete the monitoring of the deployment area and transmit the collected data to remote observers through mutual cooperation between nodes. Since most of the network monitoring areas are unsupervised and harsh environments, and due to the consideration of deployment costs, the network usually chooses low-cost and low-quality nodes, resulting in many error data, wrong data, and inconsistencies in the data collected by the sensors. Data may even lose data. There are so many unreliable dat...

AI Technical Summary

Problems solved by technology

[0006] (3) High energy consumption and high load

However, there are only a few anomaly detection methods in the existing literature that consider both time and space correlation, which will inevitably reduce the detection accuracy or increase the detection cost.

Images