Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Web Browsing and Video Classification Method Based on Feature Selection Method

A feature selection method and video classification technology, which is applied in the directions of instruments, calculations, character and pattern recognition, etc., can solve the problems of easy violation of user privacy and the decline of the effectiveness of deep packet detection methods, so as to improve classification performance, reduce time and space Cost, efficiency improvement effect

Active Publication Date: 2019-08-02
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is easy to violate user privacy, and with the emergence of encryption and applications, the effectiveness of deep packet inspection methods has gradually declined

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Web Browsing and Video Classification Method Based on Feature Selection Method
  • Web Browsing and Video Classification Method Based on Feature Selection Method
  • Web Browsing and Video Classification Method Based on Feature Selection Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The invention will be described in further detail below in conjunction with the accompanying drawings.

[0040] Such as figure 1 As shown, a kind of network browsing and video classification method based on the feature selection method proposed by the present invention, the method includes network traffic flow acquisition and statistical feature calculation, QoS feature selection and analysis based on coefficient of variation, and K-nearest neighbor classifier-based Network service flow classification, etc., including the following steps:

[0041] Step 1. Acquisition of network service flow and calculation of statistical features: Obtain web browsing and network video service flow data through the network packet analysis tool wireshark, mainly including Skype voice, online video viewing (ie, non-live broadcast), online video live broadcast, HTTP download 1. Web browsing (that is, the content of the web page is text and pictures), and web browsing (including video) six ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for web browsing and video classification based on a novel feature selection method. The feature selection of the method judges the importance of features by calculating the coefficient of variation within and between categories. Compared with existing methods, this method has lower computational complexity, and can effectively reduce the time and space complexity of the feature selection process. Simultaneously, the method of the present invention is applied to six business classifications of Skype voice, online video viewing (i.e. non-live broadcast), online video live broadcast, HTTP download, web browsing (i.e. web page content is text and pictures), web browsing (i.e. including video) . Experimental results show that the method of the present invention can obtain better classification performance than existing methods, which proves the effectiveness and rationality of the method of the present invention. In addition, the present invention considers the impact of webpage browsing content factors on QoS, classifies webpage browsing in a fine-grained manner for the first time, and can provide users with better QoS guarantee.

Description

technical field [0001] The invention relates to the technical field of pattern recognition and classification, in particular to a method for web browsing and video classification based on a feature selection method. Background technique [0002] Accurate identification of network traffic flows plays an indispensable role in network management, cloud computing and big data center architecture, and QoS guarantee. With the continuous growth of HTTP-based network services (such as web page browsing, network audio, video, etc.), network service flow identification and classification are faced with this huge challenge. A web page based on the HTTP protocol is no longer a simple static text, but an information carrier containing a large number of pictures and videos, as well as a network platform carrying various applications. With the rise of cloud computing, browsers based on HTTP protocol also provide a quick way for any device to access cloud data. Rich network applications a...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/2415G06F18/2431G06F18/10
Inventor 董育宁王凯
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com