traffic real-time classification method based on a shell vector type SVM incremental learning model

Abstract

The invention discloses a traffic real-time classification method based on a shell vector type SVM incremental learning model. According to the method, redundant features and irrelevant features of ahigh-dimensional training set are deleted through a symmetric uncertain FCBF algorithm, then dimension reduction processing is conducted through a linear superposition PCA algorithm, a new training set is obtained, an SVM model is trained according to the new training set, and then network flow classification is achieved; In the incremental learning process, the same data preprocessing is adoptedfor the real-time network flow, the union set of the new sample data violating the KKT condition and the shell vector serves as a new training set to train the SVM model again, and therefore the incremental learning of the SVM is achieved.

Description

technical field [0001] The invention relates to an incremental learning algorithm for real-time online classification of network traffic based on SVM under the background of large-scale data. Background technique [0002] The realization of network traffic classification is an important basis for operating and optimizing various network resources, and plays an important role in network resource management and intrusion detection. In the research of network traffic identification, the classification technology has mainly gone through three stages: the stage of traffic classification based on fixed port numbers, the stage of classification based on Deep Packet Inspection (DPI), and the stage of traffic classification based on machine learning. With the emergence of dynamic port technology and masquerade port technology, it brings severe challenges to the traffic classification system based on fixed ports. In order to solve the shortcomings of the port-based traffic classifica...

AI Technical Summary

Problems solved by technology

[0017] However, when the SVM algorithm trains data samples, there are problems such as long training time, large memory usage, long response time, poor real-time performance, low incremental learning efficiency, and high cost, which seriously affect the management of network traffic and the detection of abnormal intrusions, especially In the context of big data, the traditional SVM algorithm is becoming more and more stretched

Images