An adaptive semi-supervised network traffic classification method, system and equipment
A network traffic and classification method technology, applied in the field of self-adaptive semi-supervised network traffic classification, can solve problems such as the inability to automatically determine the optimal parameters and the inability to realize system parameter adaptation, so as to improve the classification accuracy, ensure reliability and Accuracy, the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 7
[0068] Such as image 3 As shown, the present invention also provides an adaptive semi-supervised network traffic classification system, which includes:
[0069] Acquisition module, vector set processing module, clustering module, classification module, output module;
[0070] The obtaining module is used to obtain marked and unmarked network flows, extract a preset fixed amount of flow characteristics in each network flow, and obtain network flow feature vectors;
[0071] The vector set processing module is used to calculate the centroid of the network flow feature vector set in each type according to the marked network flow feature vector, and obtain the vector set M;
[0072] The clustering module is used to use the vector set M as the initial center point of k-means clustering, and perform adaptive semi-supervised k- Means clustering; specifically, first obtain k clusters and k cluster center points, respectively calculate the specifically defined evaluation function, up...
Embodiment 9
[0080] Such as Figure 4 As shown, the embodiment of the present invention also provides a computer device, which includes: a processor, a memory, and a computer program stored on the memory and operable on the processor, wherein the processing When the program is executed by the computer, the steps of the method described in any one of Embodiment 1 to Embodiment 6 above are realized.
[0081] It should be noted that, in Embodiment 9, the computer equipment of the present invention is used to obtain marked and unmarked network flows, extract a preset fixed amount of flow features in each network flow, and obtain network flow feature vectors, According to the marked network flow feature vector, calculate the center point of each type of network flow that has been marked, and use the center point as the initial clustering center M of the k-means algorithm, for the mixed marked types and Semi-supervised k-means clustering is performed on the unlabeled network flow point set X to...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


