Ultrasonic pattern recognition based on ANN and PCA techniques

Author

Ochoa, A. ; Hernández, A. ; Ureña, J. ; Mazo, M. ; Jiménez, J.A. ; García, J.J. ; Jiménez, A.

Author_Institution

Dept. of Electron., Alcala Univ., Madrid, Spain

Volume

3

fYear

2005

fDate

20-23 June 2005

Firstpage

1215

Abstract

The reflector classification has been used in ultrasonic sensorial systems to develop tasks, as environment mapping or navigation items. This work proposes a new ultrasound-based sensorial structure, where times-of-flight are used for classification purposes with an artificial neural network (ANN). PCA technique is used before to reduce the data amount managed by the neural network. The system allows the discrimination among planes, edges and corners. The recognition is achieved with an error of 5%.

Keywords

acoustic signal processing; neural nets; pattern classification; principal component analysis; signal classification; ultrasonic transducers; ANN techniques; PCA techniques; artificial neural network; ultrasonic pattern recognition; ultrasound-based sensorial structure; Artificial neural networks; Biological neural networks; Navigation; Neurons; Pattern recognition; Principal component analysis; Signal processing algorithms; Target recognition; Ultrasonic imaging; Ultrasonic transducers;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics, 2005. ISIE 2005. Proceedings of the IEEE International Symposium on

Conference_Location

Dubrovnik, Croatia

Print_ISBN

0-7803-8738-4

Type

conf

DOI

10.1109/ISIE.2005.1529098

Filename

1529098