网络视频流量分类的特征选择方法研究-计算机工程与应用.PDFVIP

Computer Engineering and Applications 计算机工程与应用 2018 ，54（6 ） 7 网络视频流量分类的特征选择方法研究 用 吴 争，董育宁 应 WU Zheng, DONG Yuning 与 南京邮电大学 通信与信息工程学院，南京 210003 程 College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, g Nanjing 210003, China 工 r o . j WU Zheng, DONG Yuning. Contrastive analysis of features selection on network video traffic classification. Com- 机 a puter Engineering and Applications, 2018, 54 （6 ）：7-13. 算 e c . Abstract ：Accurate identification and categorization of multimedia traffic is the premise of end to end QoS （Quality of 计 w Service）guarantees. Today, the dramatic growth of data volume takes challenge to network traffic classification. There- fore, using feature selection methods for multimedia flow identification and classification is particularly important in the w big data era. This paper introduces related works on feature selection using identification and categorization of multimedia w traffic, which is divided into three categories ：Filter, Wrapper, Embedded and analyzes the performance of these methods. Then, this paper compares the performance of various feature selection algorithms using latest dataset from three aspects ： The running speed, the feature compression rate and the feature selection accuracy. Besides, to improve classification accura- cy, this paper proposes a hierarchical structure to reach fine-grained classification, according to the dataset. Key words ：features selection;