A Support Vector Machine Model for Pipe Crack Size Classification : Reseach on SVM Classification

Chuxiong Miao

ISBN 10: 363929405X / ISBN 13: 9783639294057

Published by VDM Verlag Dr. Müller, 2010

About this Item

nach der Bestellung gedruckt Neuware - Printed after ordering - The classification of pipe crack size from its pulse- echo ultrasonic signal is a difficult task but greatly significant for defect evaluation in pipe testing and the maintenance strategy making. In this book, we use Support Vector Machines (SVM) to classify the pipe crack into correct categories, large size or small size, with the ultrasonic signal data. In order to acquire an optimal input data set, we first select the features from the time and frequency domain on the ultrasonic data. Then a combined method, Sequential Backward Selection (SBS) and Sequential Forward Selection (SFS), is used for features reduction. These two steps are referred as data preprocessing in this book. To build SVM classifier, parameter selection is critical. In this book, a Kernel Fisher Discriminant Ratio (KFD Ratio) is proposed for speeding the parameter selection of the SVM classifier. As an indicator, KFD Ratio can greatly shorten computation time for finding the best parameters. To further improve the performance of the SVM classifier in terms of classification accuracy, a data dependent kernel is adopted for creating a more effective one.

Seller Inventory # 9783639294057

Bibliographic Details

• Title: A Support Vector Machine Model for Pipe Crack Size Classification : Reseach on SVM Classification
• Publisher: VDM Verlag Dr. Müller
• Publication Date: 2010
• Language: English
• ISBN 10: 363929405X
• ISBN 13: 9783639294057
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 22W x 15H x 0.5D centimeters 22 centimeters width by 15 centimeters height by 0.5 centimeters depth
• Weight: 159 grams

About this title

Synopsis

The classification of pipe crack size from its pulse- echo ultrasonic signal is a difficult task but greatly significant for defect evaluation in pipe testing and the maintenance strategy making. In this book, we use Support Vector Machines (SVM) to classify the pipe crack into correct categories, large size or small size, with the ultrasonic signal data. In order to acquire an optimal input data set, we first select the features from the time and frequency domain on the ultrasonic data. Then a combined method, Sequential Backward Selection (SBS) and Sequential Forward Selection (SFS), is used for features reduction. These two steps are referred as data preprocessing in this book. To build SVM classifier, parameter selection is critical. In this book, a Kernel Fisher Discriminant Ratio (KFD Ratio) is proposed for speeding the parameter selection of the SVM classifier. As an indicator, KFD Ratio can greatly shorten computation time for finding the best parameters. To further improve the performance of the SVM classifier in terms of classification accuracy, a data dependent kernel is adopted for creating a more effective one.

About the Authors

Chuxiong Miao, M.Sc Professional Engineer in Canada

Chuxiong Miao, M.Sc Professional Engineer in Canada