Support vector machine based dedicated network flow classification method
A support vector machine, dedicated network technology, applied in the field of dedicated network traffic classification based on support vector machine, can solve the problems of lack of exclusivity of the protocol, lack of unified coordination and planning, and the inability of the first three classification methods to reduce support vector Dimensionality, simple implementation, and the effect of improving expansion efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0037] Example
[0038] A dedicated network flow classification method based on support vector machine includes the following steps:
[0039] First, extract the known types of data flows in the network, calculate the flow characteristics, and establish a sample library. The number of samples of each type of flow is M.
[0040] Second, run the SVM (Support Vector Machine) learning method on the basis of the sample library to generate a 1-to-N classification function library. How to classify in a two-dimensional plane requires a kernel function to map each flow vector to a high-dimensional For classification, in the present invention, it is recommended to use a radial basis kernel, that is, an RBF kernel. This kernel function is suitable for low-dimensional, high-dimensional, small samples, large samples, etc., and is currently a relatively good classification basis function.
[0041] Third, collect a certain number of new types of data sets An.
[0042] Fourth, the data in the data set ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap