Lee, Kyungmi, and Estivill-Castro, Vladimir (2003) Classification of ultrasonic shaft inspection data using discrete wavelet transform. In: Proceedings of the (AIA 2003) Artificial Intelligence and Applications Conference. pp. 673-678. From: (AIA 2003) Artificial Intelligence and Applications Conferences, 8-10 September, 2003, Benalmádena, Spain.

PDF (Published Version) Restricted to Repository staff only

Abstract

Artificial Neural Networks have been used to process ultrasonic signals for many non-destructive scenarios. However, this scenarios usually involve very shallow surfaces. When testing shafts, the signals are long and the new problem of mode-converted reflections emerges. They are echoes that do not correspond to cracks in the material, neither to characteristics of the shaft. Also, the length of the signals demands the application of feature extraction mechanism to reduce the dimension of the pattern vectors and make classifier training feasible. The results here establish experimentally that DWT provides faster and more reliable feature extraction for ANN in these long signals in shafts. This results match the recent studies for shallow signals where comparisons between FFT and DWT indicate DWT as the preferred feature extraction policy.

Item ID:	10030
Item Type:	Conference Item (Research - E1)
ISBN:	0-88986-390-3
ISSN:	1482-7913
Keywords:	neural networks; learning algorithms and training; wavelets; signal processing applications in engineering
Related URLs:	http://www.actapress.com/Content_of_Proc...
Date Deposited:	12 Jul 2010 04:59
FoR Codes:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation @ 40% 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining @ 60%
SEO Codes:	89 INFORMATION AND COMMUNICATION SERVICES > 8902 Computer Software and Services > 890202 Application Tools and System Utilities @ 60% 89 INFORMATION AND COMMUNICATION SERVICES > 8999 Other Information and Communication Services > 899999 Information and Communication Services not elsewhere classified @ 40%
Downloads:	Total: 4
	More Statistics