Title :
A New Method for Modulation Classification Based on Bootstrap Technique
Author :
Wang, Feng ; Li, Bing-bing
Author_Institution :
Nat. Key Lab. of ISN, Xidian Univ., Xian, China
Abstract :
This paper presents a new method based on bootstrap technique for modulation recognition under the low SNR and multi-path conditions. The bootstrap method is performed when only few samples are available at the receiver. A new neural network is also proposed to select effective features and classifies signals. Extensive simulations show that the new method has preferable performance in low SNR and multi-path environment.
Keywords :
modulation; neural nets; signal classification; SNR; bootstrap technique; modulation classification; modulation recognition; multipath conditions; multipath environment; neural network; signal classification; AWGN; Additive white noise; Computer science; Demodulation; Euclidean distance; Nearest neighbor searches; Neural networks; Pattern recognition; Software radio; Surveillance; Bootstrap; modulation classification; neural network;
Conference_Titel :
Computer Science and Computational Technology, 2008. ISCSCT '08. International Symposium on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3746-7
DOI :
10.1109/ISCSCT.2008.27
