DocumentCode :
2701590
Title :
Aircrafts type recognition based on shortwave communication
Author :
Zhang, Xinyu ; Li, Xueyao ; Zhang, Rubo ; Liu, Guanqun
Author_Institution :
Coll. of Comput. Sci. & Technol., Harbin Eng. Univ., Harbin
fYear :
2008
fDate :
20-23 June 2008
Firstpage :
1328
Lastpage :
1332
Abstract :
There is an important military significance about aircrafts type recognition based on shortwave communication. Acoustic signals received by shortwave radio about aircrafts are complex and they contain some valuable information. It is very difficult to identify the aircraft type based on background sound signals of shortwave communication. In order to solve this problem, in this paper two methods for aircrafts type recognition based on shortwave communication are presented. The acoustic signals characteristics of aircrafts are extracted by wavelet packet decomposition (WPD). Support vector machine (SVM) and back propagation (BP) artificial neural network (ANN) as classifiers are adopted to identify five kinds of aircrafts respectively. From results of experiments about classification and recognition of five kinds of aircrafts, the combination of WPD as feature extraction method and SVM as the classifier has better performance and recognition rate than the combination of WPD and BP ANN.
Keywords :
acoustic signal processing; aircraft communication; backpropagation; feature extraction; military computing; neural nets; support vector machines; wavelet transforms; acoustic signals characteristics; aircrafts type recognition; back propagation artificial neural network; background sound signals; feature extraction method; shortwave communication; shortwave radio; support vector machine; wavelet packet decomposition; Acoustic propagation; Acoustic waves; Artificial neural networks; Data mining; Military aircraft; Military communication; Signal processing; Support vector machine classification; Support vector machines; Wavelet packets;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information and Automation, 2008. ICIA 2008. International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4244-2183-1
Electronic_ISBN :
978-1-4244-2184-8
Type :
conf
DOI :
10.1109/ICINFA.2008.4608207
Filename :
4608207
Link To Document :
بازگشت