Individual Communication Transmitter Classification of Weighted Feature Set Based on RST

Author

Zhou, Yajian ; Na, Sun ; Yang, Yixian

Author_Institution

State Key Lab. of Networking & Switching Technol., Beijing Univ. of Posts & Telecommun., Beijing, China

fYear

2009

fDate

21-22 Dec. 2009

Firstpage

316

Lastpage

319

Abstract

Feature extraction for individual communication transmitter identification is one of the major issues in the identifying process. A neighborhood rough set is proposed in this paper, in order to search for the good feature subset. Then we present a SVM classification approach of weighted feature set based on the significance of an attribute. The result of experiments shows that the reduced feature subset is acquired ,and the classification accuracy of weighted feature subset is much better than that of non-weighted feature subset.

Keywords

feature extraction; pattern classification; radio transmitters; rough set theory; support vector machines; telecommunication computing; SVM classification approach; feature extraction; individual communication transmitter classification; neighborhood rough set; nonweighted feature subset; weighted feature set; Computer networks; Data mining; IP networks; Information security; Laboratories; Random variables; Support vector machines; Telecommunication computing; Telecommunication switching; Transmitters; feature selection; neighborhood rough set; support vector machine(SVM); transmitter identification; weighted feature set;

fLanguage

English

Publisher

ieee

Conference_Titel

Internet Computing for Science and Engineering (ICICSE), 2009 Fourth International Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4244-6754-9

Type

conf

DOI

10.1109/ICICSE.2009.11

Filename

5521394