Flow classification method using average opinion sub-mean feature of video services

A technology of video business and average opinion, applied in TV, instrument, character and pattern recognition, etc., can solve the problem of single and low sample recognition rate, and achieve good classification effect and high classification accuracy

Active Publication Date: 2017-08-01
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The advantage of using this method is that the model is simple and the calculation process is relatively efficient, but the disadvantage of this method is that only the peak value of the downlink rate is considered, the selected feature is relatively single, and the recognition rate of untrained samples is low

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
  • Flow classification method using average opinion sub-mean feature of video services
  • Flow classification method using average opinion sub-mean feature of video services
  • Flow classification method using average opinion sub-mean feature of video services

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0030] An embodiment is provided now, comprising the steps:

[0031] Step 1, data set and data preprocessing: 1) Use network packet analysis software, such as WireShark, in a specific network, such as a campus network environment, to capture the required video data stream, and then save the captured original data stream A standard text format containing five columns of data, including five columns of packet arrival time (s), source IP address, destination IP address, protocol type, and data packet size, is defined as the original data set. 2) Filter out the data packets of the first 5 minutes of each video stream in the original data set, filter out the upstream data packets, and define it as the data set DataSet1. 3) Cut off each video stream of DataSet1 by 5000 data packets, and obtain 1446 data packets in standard definition sample streams, 2665 sample st...

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 flow classification method using the average opinion sub-mean feature of video services. The method comprises the steps of data set preprocessing and feature extraction, PDF mean feature calculating of three video services MOS and SVM classification. According to the step of data set preprocessing and feature extraction, video data flow in a required network is captured by network packet analysis software; the captured original data flow is saved in a standard text format; a number of flow statistics features are calculated; and the downstream byte rate is selected as the most feature of the information gain rate. According to the step of SVM classification, the mean feature of each video flow is combined with the downstream byte rate and is defined as the optimal feature subset; the feature subset is supervised and discretized; and an SVM-based ten-fold cross validation method is used for flow identification and classification. According to the invention, the experience quality of video viewing of a client can be guaranteed; the distribution of the MOS value of three video services is analyzed; three kinds of videos are identified and classified with effective feature combination; and a better classification effect is realized.

Description

technical field [0001] The invention belongs to the technical field of stream identification and classification, and in particular relates to a stream classification method using the average opinion score feature of video services. Background technique [0002] In recent years, with the rapid development of wireless communication technologies such as Wifi, LTE, 4G and WiMAX, the traffic of streaming video services has increased dramatically. increase. According to the statistical report on China's Internet development, as of June 2016, the number of online video users in my country reached 514 million, an increase of 10 million from the end of 2015. The number of people watching Internet videos accounts for 72.4% of all Internet users, and this value has been growing. At the same time, multimedia video services such as Web video have high requirements on transmission bandwidth, delay, and jitter, which will inevitably bring severe challenges to the transmission of video se...

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 Applications(China)
IPC IPC(8): H04L29/06H04N17/00G06K9/62
CPCH04L65/60H04L65/80H04N17/00G06F18/2411
Inventor 董育宁易小华
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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