Mobile App traffic flow statistical feature selection method
A feature selection method and traffic statistics technology, which is applied in the field of mobile app traffic statistics feature selection, can solve the problems that cannot be used to select feature subsets, fail to analyze feature stability, etc.
Active Publication Date: 2019-03-01
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although this invention eliminates redundant features for network traffic data, it does not have the stability of analyzing features and cannot be used to select a more stable feature subset
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0071] Such as figure 1 Shown, a kind of Mobile App traffic statistical characteristic selection method, comprises the following steps:
[0072] Step S1, obtaining the original traffic data set of the mobile App, extracting the flow statistical features of the mobile App traffic, obtaining the labeled data set LD for training, and the unlabeled data set UD to be classified;
[0073] Step S2, on the LD data set, use the information gain rate to evaluate the distinguishing ability of each flow statistical feature between classes;
[0074] Step S3, on the LD and UD data sets, calculate the value distribution of each flow statistical feature, use the Hellinger distance to evaluate the difference of the feature value distribution, and evaluate the drift degree of the flow statistical feature;
[0075] Step S4, using the degree of drift as a penalty factor for feature discrimination ability, and calculating the comprehensive evaluation value of flow statistical features;
[0076] ...
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
Login to View More Abstract
The invention discloses a mobile App traffic flow statistical feature selection method. The method comprises the following steps: S1, acquiring a traffic flow data set of an original mobile App, extracting flow statistical features of mobile App traffic flow, and acquiring a labeled data seat LD used for training as well as a to-be-classified unlabeled data set UD; S2, on the data set LD, evaluating inter-class distinguishing capability of each flow statistical feature by utilizing an information gain ratio; S3, on the data sets LD and UD, calculating value distribution of each flow statistical feature, evaluating difference of value distribution of the features by utilizing Hellinger distance, and evaluating drift degree of the flow statistical features; S4, taking the drift degree as a penalty factor of the distinguishing capability, and calculating a comprehensive evaluation value of the flow statistical features; and S5, based on the comprehensive evaluation value, searching a flowstatistical feature subset with strong distinguishing capability and low drift degree. The method disclosed by the invention relates to a mobile App traffic flow classification technology in the field of mobile Internet traffic flow measurement, reduces data dimension and improves classification robust performance.
Description
technical field [0001] The invention relates to the technical field of traffic classification in the field of traffic measurement, in particular to a method for selecting mobile App traffic statistics features. Background technique [0002] The mobile app traffic classification technology based on machine learning is described as follows: the original traffic is grouped based on the five-tuple {source IP, destination IP, source port, destination port, transport layer protocol} group flow, and the traffic is extracted from the statistical characteristics of the flow to establish a flow sample set. for training classification models. A variety of flow statistical features have been proposed. For example, Moore et al. proposed 248 flow statistical features in 2005 (A.Moore, D.Zuev, M.Crogan. Discriminators for use in flow-based classification. Queen Mary and Westfield College, Department of ComputerScience, 2005.), including: statistical characteristics of packet size (minimum...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/851
CPCH04L47/2441
Inventor 王若愚张凌刘珍
Owner SOUTH CHINA UNIV OF TECH