Title :
Ultrasonic Target Recognition Based on Wavelet Packet and Neural Network
Author :
Xueqin Kou ; Lichen Gu
Abstract :
Target recognition is one of the key technologies of the ultrasonic detection. In this paper, with wavelet packet analysis method, energy feature is extracted for actual ultrasonic echo signal to obtain target energy feature information in different frequency bands, then the neural network classifier is used to identify the target. Test results show that this method is effective in detecting real ultrasonic signals.
Keywords :
acoustic signal detection; feature extraction; neural nets; signal classification; wavelet transforms; energy feature extraction; neural network; neural network classifier; target energy feature information; ultrasonic detection; ultrasonic echo signal; ultrasonic target recognition; wavelet packet analysis method; Acoustics; Feature extraction; Neural networks; Target recognition; Wavelet analysis; Wavelet packets; Feature extraction; Neural network; Target recognition; Wavelet packet analysis;
Conference_Titel :
Computational Intelligence and Security (CIS), 2012 Eighth International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4673-4725-9
DOI :
10.1109/CIS.2012.67
