Title :
A New Method of Combined Classifier Design Based on Fuzzy Integral and Support Vector Machines
Author :
Jia, Kexin ; Lu, Youxin
Author_Institution :
Univ. of Electron. Sci. & Technol. of China, Chengdu
Abstract :
To make the modulation classification system more suitable for signals in a wide range of signal noise rate (SNR), a novel method of designing combined classifier based on fuzzy integral and multi-class support vector machines (MSVM) is presented in this paper. The method employs multi-class support vector machines classifiers and fuzzy integral to improve recognition reliability. Experimental results illustrate that the proposed combined classifier has high recognition rate with large variation range of SNR (success rates are over 98.2% when SNR is not lower than 5 dB).
Keywords :
fuzzy set theory; integral equations; modulation; signal classification; support vector machines; telecommunication computing; combined classifier design; fuzzy integral; signal modulation classification system; support vector machine; Design methodology; Electronic mail; Fuzzy sets; Fuzzy systems; Signal design; Signal processing; Signal to noise ratio; Support vector machine classification; Support vector machines; Training data;
Conference_Titel :
Communications, Circuits and Systems, 2007. ICCCAS 2007. International Conference on
Conference_Location :
Kokura
Print_ISBN :
978-1-4244-1473-4
DOI :
10.1109/ICCCAS.2007.4348204
