Service-Aware Algorithm Based on DT-KSVM

Hao Dong; Hua Qu; Jihong Zhao; Liangjun Chen; Huijun Dai

doi:10.11959/j.issn.1000-0801.2015227

您当前的位置：

首页 >

文章列表页 >

Service-Aware Algorithm Based on DT-KSVM

research and development | 更新时间：2024-06-05

- Service-Aware Algorithm Based on DT-KSVM
- Telecommunications Science Vol. 31, Issue 11, Pages: 67-71(2015)
- 作者机构：
  
  1. 西安交通大学软件学院西安 710049
  2. 西安交通大学电子与信息工程学院西安 710049
  3. 西安邮电大学通信与信息工程学院西安 710061
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2015227
  CLC：
- Published Online：2015-11，
  
  Published：20 November 2015
- 稿件说明：
移动端阅览
Hao Dong, Hua Qu, Jihong Zhao, et al. Service-Aware Algorithm Based on DT-KSVM[J]. Telecommunications science, 2015, 31(11): 67-71.
DOI：

Hao Dong, Hua Qu, Jihong Zhao, et al. Service-Aware Algorithm Based on DT-KSVM[J]. Telecommunications science, 2015, 31(11): 67-71. DOI： 10.11959/j.issn.1000-0801.2015227.

摘要

提出一种新的基于DT-KSVM（decision tree kernel support vector machine，决策树支持向量机）的业务感知算法，利用ReliefF特征选择算法提取特征，提出样本间类别可分度计算方法排序不同业务感知难度，优先感知易分业务。在实际网络业务数据集上与传统一对一（one-versus-one）SVM感知方法进行对比，结果表明该方法具有较高的业务识别准确率和更好的时间性能。

Abstract

A novel service-aware method based on decision tree kernel support vector machine（DT-KSVM） algorithm was proposed.A service-aware model was developed by using ReliefF algorithm to extract service characteristics

and proposing the separable degree between samples to simply the service-aware process.Through experiment comparison between this proposed model and traditional one-versus-one SVM method

it is shown that the proposed method has a better service-aware accuracy and time performance.

关键词

Keywords

references

Kawahara R , Kamei S , Kamiyama N , et al . A Method of Constructing QoS Overlay Network and Its Evaluation . Technical Report of IEICE Cq , 2009

Lu X M , Pei J , Zhou Y J . A new P2P traffic identification model based on node status . Proceedings of the 2010 International Conference on Management and Service Science （MASS 2010） , Wuhan,China , 2010 : 1 ～ 4

Song H , Han I Y , Kim Y , et al . The NADPH oxidase inhibitor DPI can abolish hypoxia-induced apoptosis of human kidney proximal tubular epithelial cells through Bcl2 up-regulation via ERK activation without ROS reduction . Life Sciences , 2015 （ 126 ）: 69 ～ 75

Witten I H , Frank E , Hall M A . Data Mining:Practical Machine Learning Tools and Techniques . Amstel dam : Elsevier , 2011

Yuan R X , Li Z , Guan X H , et al . An SVM-based machine learning method for accurate internet traffic classification . Information Systems Frontiers , 2010 , 12 （ 2 ）: 149 ～ 156

Rocha A , Goldenstein S K . Multiclass from binary:expanding one-versus-all,one-versus-one and ecoc-based approaches . IEEE Transactions on Neural Networks and Learning Systems , 2014 , 25 （ 2 ）: 289 ～ 302

Ng S S Y , Tse P W , Tsui K L . MA one-versus-all class binarization strategy for bearing diagnostics of concurrent defects . Sensors , 2014 , 14 （ 1 ）: 1295 ～ 1321

戴慧珺．基于业务分类识别流量预测的覆盖网QoS 路由算法（博士学位论文）．西安：西安交通大学， 2015

Dai H J . Research on QoS routing based on traffic identification and flow prediction in overlay network（doctor dissertation） . Xi'an : Xi'an Jiaotong University , 2015

Zhou Q , Ding J , Ning Y , et al . Stable feature selection with ensembles of multi-reliefF . Proceedings of the 10th International Conference Natural Computation（ICNC 2014） , Xiamen,China , 2014 : 742 ～ 747

Moore A W , Zuev D . Internet traffic classification using bayesian analysis techniques . Proceedings of 2005 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems , New York,USA , 2005 : 50 ～ 60

Views

894

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Delay-sensitive traffic intellisense scheduling based on optimal decision tree

Research on 4G/5G voice quality optimization based on data mining and geographic visualization

Application of big data method in forecasting potential sensitive customers of electric power

Locating causes of abnormality of EPG experience based on decision tree

Research on terminal switch interval based on DTL

Related Author

Zhengzhi TANG

Xuerong WANG

Liang ZHANG

Jianbo ZHU

Meiyu QI

Yinchuan LI

Jian HU

Lei SUN

Related Institution

Research Institute of China Telecom Co., Ltd.

Beijing Huawei Digital Technologies Co., Ltd.

China Mobile Group Yunnan Co., Ltd.

Nokia Shanghai Bell Co., Ltd.

⁰