Intrusion detection feature selection method based on weight integration

Abstract

The invention discloses an intrusion detection feature selection method based on weight integration, which comprises the following steps: firstly, deleting data with redundant features from an intrusion detection data set by adopting a variance selection method, dividing the intrusion detection data set obtained by processing into a data set A and a data set B, inputting the data set A into each preset feature selection method for feature selection, determining the score of the selected feature in the feature selection method, then performing intrusion detection test on each feature selection method by adopting an intrusion detection data set, and counting the accuracy of an intrusion detection result corresponding to the feature selection method, determining the weight of the feature selection result of each feature selection method according to the accuracy of the intrusion detection result, integrating the feature selection results according to the weights, performing correlation analysis on the selected features, deleting redundant features, and obtaining the final feature selection result. According to the method, the integration effect can be improved, the robustness of the finally selected feature set is higher, and then the intrusion detection precision is improved.

Description

technical field [0001] The invention belongs to the technical field of intrusion detection, and more specifically relates to an intrusion detection feature selection method based on weight integration. Background technique [0002] The popularization of the Internet has promoted the progress and development of society, but the network environment is also deteriorating, and the intensity and frequency of intrusions in the network are increasing. Loss. Therefore, intrusion detection is needed to defend against abnormal attacks, and an important part of intrusion detection is feature selection. This is because the dimensions of intrusion detection samples are too high and contain redundant features. Feature selection is required to reduce the dimensionality and extract important features to improve the efficiency and accuracy of intrusion detection. [0003] There are many ways to complete the feature selection method of intrusion detection, among which the specific methods w...

AI Technical Summary

Problems solved by technology

Some intrusion detection methods integrate multiple feature selection methods for feature selection when performing feature selection, but most of these integration methods simply vote or average the feature selection results to select the final feature, and different methods are different for the data set. Depending on the degree of fitness, the selected features have different effects on the classification performance. This method often fails to achieve the ideal integration effect.

Images