Wireless sensor network anomaly detection method

Abstract

The invention discloses a wireless sensor network anomaly detection method. A fuzzy support vector machine is applied to the field of wireless sensor network anomaly detection based on a drosophila optimization algorithm, and the method comprises the following steps: a training stage: S1, collecting sensor detection data, and preprocessing the data to form a training data set; S2, establishing a wireless sensor network anomaly detection model based on the FSVM technology; S3, establishing an IFOA-FSVM model, and performing anomaly detection training on the data set; in the detection stage: S4,collecting and preprocessing sensor detection data to form a to-be-detected sample; and S5, inputting the to-be-detected sample into an IFOA-FSVM model for detection, and judging whether the to-be-detected sample is abnormal or not.

Description

technical field [0001] The invention relates to the field of wireless sensor network information security, in particular to a wireless sensor network abnormality detection method. Background technique [0002] Wireless sensor network is a special mobile ad hoc network which is different from traditional wired network. Wireless sensor networks are widely used in various fields, such as military fields such as national defense and anti-terrorism, due to the advantages of simple node networking, self-organization to form a network, and low node cost. When the wireless network sensor is abnormal, it is of great significance to detect abnormal data in the sensor network in real time and efficiently, no matter for the early warning and prevention of external emergencies, or for the health status monitoring of the sensor network itself. [0003] In recent years, there have been many achievements in the research of abnormal data detection methods in wireless sensor networks at home...

AI Technical Summary

Problems solved by technology

However, most of the existing SVM (Support Vector Machine)-based wireless sensor network anomaly detection models do not introduce fuzzy theory, resulting in weak generalization ability of such models for data sets containing noisy samples compared with support vector machine models based on fuzzy theory.

Images