Network traffic classification method based on feature strong correlation

Abstract

The invention provides a network traffic classification method based on feature strong correlation, which comprises the following four steps of: inputting data to be trained, and performing feature extraction on the input data to form a multi-dimensional feature vector set; calculating the correlation between the features by using the mutual information between the features and the response variables; calculating redundancy among the features according to the mutual information, and selecting the feature with the highest score as a final feature vector through iterative calculation; and constructing a network traffic classification model based on feature strong correlation according to the classification target and obtaining a classification result. According to the method, the correlationbetween features can be fully utilized, and the feature with the maximum correlation and the minimum redundancy is extracted in the learner training process. Under the same classification model, theclassification efficiency can be effectively improved on the premise that the classification precision is guaranteed, and the defect caused by the fact that correlation between features is not considered in an existing feature selection method based on heuristic search is overcome.

Description

technical field [0001] The invention relates to data processing and machine learning, in particular to a method for classifying network traffic based on strong correlation of features. Background technique [0002] With the development of network technology, the traffic in the network increases very rapidly. However, while promoting the further development of the network, it also brings many problems. The ever-expanding data scale and increasing application types will lead to a decrease in the utilization rate of network resources. Some links have a high throughput, while some links are almost idle, which will lead to a decrease in the utilization of network resources. [0003] Therefore, in the past few years, network traffic classification techniques have attracted more and more attention. From a security perspective, quickly identifying malicious traffic will help secure containment and isolate attackers. From a QoS perspective, accurate classification of different tr...

AI Technical Summary

Problems solved by technology

However, while promoting the further development of the network, it also brings a lot of problems

The ever-expanding data scale and the increasing number of application types will lead to a decrease in the utilization of network resources

Some links have high throughput, while some links are almost idle, which will lead to a decrease in the utilization of network resources

Images