Abstract | ||
---|---|---|
To Ensure QoE (quality of experience) to the users when they access so many Internet applications every day, ISPs are faced with challenge and opportunity in bandwidth management. They need some ways to identify each application's flows generated by user hosts, especially the application classes with large flows because of the higher bandwidth occupation comparing with the other classes with small flows. A novel method is presented to modularize flow size using information gain ratio. The origin dataset is properly partitioned into large flow and small flow subsets by a threshold that is achieved when the data complexity of large flow subset is minimized. The searching algorithm of the partitioned threshold is independent of classification performance. The specific classifiers can be trained to identify large flows and small flows properly on each subset in generalization. Experimental results on real world traffic datasets show that byte accuracy increased 30% averagely when our method is compared with original. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICCW.2014.6881259 | ICC Workshops |
Keywords | Field | DocType |
machine learning,bandwidth occupation,byte accuracy,isp,large flows,information gain ratio,learning (artificial intelligence),bandwidth management,small flow subsets,bandwidth allocation,qoe,internet applications,flow size modularization,searching algorithm,internet,internet traffic classification,quality of experience,telecommunication traffic,traffic flows classification method,data complexity minimization,large flow subsets,quality-of-experience | Data mining,Search algorithm,Computer science,Bandwidth allocation,Internet traffic classification,Computer network,Real-time computing,Information gain ratio,Statistical classification,Bandwidth management | Conference |
ISSN | Citations | PageRank |
2164-7038 | 5 | 0.44 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qiong Liu | 1 | 6 | 0.79 |
Zhen Liu | 2 | 5 | 0.78 |
Ruoyu Wang | 3 | 5 | 0.44 |
Changqiao Xu | 4 | 730 | 71.39 |