Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing

•A comparative study on different feature extraction techniques is presented.•PCA is used to provide a compact set of representative features.•Statistical significance tests prove to be an interesting alternative to PCA.•Different neural network based classifier designs are evaluated. This work stud...

Full description

Saved in:

Bibliographic Details
Published in:	Ultrasonics Vol. 73; pp. 1 - 8
Main Authors:	Cruz, F.C., Simas Filho, E.F., Albuquerque, M.C.S., Silva, I.C., Farias, C.T.T., Gouvêa, L.L.
Format:	Journal Article
Language:	English
Published:	Netherlands Elsevier B.V 01-01-2017
Subjects:	Feature extraction Neural networks PCA Ultrasonic evaluation Welded joints Welded joints Feature extraction Neural networks Ultrasonic evaluation PCA
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•A comparative study on different feature extraction techniques is presented.•PCA is used to provide a compact set of representative features.•Statistical significance tests prove to be an interesting alternative to PCA.•Different neural network based classifier designs are evaluated. This work studies methods for efficient extraction and selection of features in the context of a decision support system based on neural networks. The data comes from ultrasonic testing of steel welded joints, in which are found three types of flaws. The discrete Fourier, wavelet and cosine transforms are applied for feature extraction. Statistical techniques such as principal component analysis and the Wilcoxon-Mann-Whitney test are used for optimal feature selection. Two different artificial neural network architectures are used for automatic classification. Through the proposed approach, it is achieved a high discrimination efficiency by using only 20 features to feed the classifier, instead of the original 2500 A-scan sample points.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0041-624X 1874-9968
DOI:	10.1016/j.ultras.2016.08.017