Abstract | ||
---|---|---|
Online traffic classification has been widely used in quality of service measurements, network management and security monitoring. Currently, more and more research works tend to apply machine learning techniques to online traffic classification, and most of them are based on supervised learning and unsupervised learning techniques. Although supervised learning method has exhibited good classification performance, it needs lots of labeled training samples which are difficult to collect. The co-training method is a semi-supervised learning method, which can use little labeled samples and plenty of unlabeled samples to enhance the performance of supervised learning method. In this paper, we investigate the co-training algorithm for online traffic classification. The co-training algorithm needs two separate features which are sufficient to train a good classifier. We choose packet size and inter-packet time of the first packets of a traffic flow as two features. However, the inter-packet time is dependent to network conditions and will be impacted by network jitter. This paper constructs a robust inter-packet time feature named "Netipt" which is resilient to network jitter, and we integrate Netipt feature to co-training algorithm. We test our co-training algorithm based on two real-world traffic datasets. The results show that the co-training algorithm can enhance the accuracy of traffic classification drastically even when there are very few training samples. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/PDCAT.2012.105 | PDCAT |
Keywords | Field | DocType |
traffic classification,training sample,semi-supervised learning method,online traffic classification,service measurements,network jitter,learning (artificial intelligence),pattern classification,inter-packet time,labeled training samples,netipt,real-world traffic datasets,packet size,co-training algorithm,unlabeled samples,network management,machine learning techniques,co-training method,telecommunication computing,security monitoring,telecommunication network management,supervised learning method,telecommunication security,telecommunication traffic,subnet,semisupervised learning method,robust interpacket time feature,co-training,cotraining method,learning artificial intelligence | Traffic classification,Data mining,Traffic flow,Semi-supervised learning,Computer science,Network packet,Co-training,Supervised learning,Unsupervised learning,Artificial intelligence,Network management,Machine learning | Conference |
ISBN | Citations | PageRank |
978-0-7695-4879-1 | 2 | 0.40 |
References | Authors | |
14 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jinghua Yan | 1 | 2 | 0.40 |
Xiao-Chun Yun | 2 | 215 | 41.96 |
Zhi-gang Wu | 3 | 5 | 2.86 |
Hao Luo | 4 | 7 | 3.60 |
Shuzhuang Zhang | 5 | 5 | 4.59 |
Shuyuan Jin | 6 | 80 | 9.24 |
Zhibin Zhang | 7 | 116 | 12.97 |