Kalman Filter as a pre-processing technique to improve the support vector machine

The Support Vector Machine is widely used as a classification tool to analyze data and recognize patterns. In certain applications of Support Vector Machine, noisy data can greatly affect accuracy and performance. To improve the accuracy of the system, the Kalman Filter has been proposed as a suitable pre-processing technique which can be implemented before using the Support Vector Machine to classify the information. This system has been tested using a dataset obtained from a pipeline defect monitoring system in the department's pipeline laboratory. This test rig uses long range ultrasonic testing to detect minor defects inside a stainless steel pipe. MATLAB simulations show promising results where Kalman Filter and Support Vector Machine combination in a single system produced higher accuracy compared to the discrete wavelet transform in a noisy environment.

[1]  L. Rose,et al.  Wave reflection and transmission in beams containing delamination and inhomogeneity , 2003 .

[2]  R. W. Smith,et al.  Evaluation of Methods for Detecting and Monitoring of Corrosion Damage in Risers , 2005 .

[3]  Greg Welch,et al.  An Introduction to Kalman Filter , 1995, SIGGRAPH 2001.

[4]  Scott Lebsack.  Non-invasive inspection method for unpiggable pipeline sections , 2002 .

[5]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[6]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[7]  Pei-wen Que,et al.  Wavelet based noise suppression technique and its application to ultrasonic flaw detection. , 2006, Ultrasonics.

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[10]  Ruxu Du,et al.  Fault diagnosis using support vector machine with an application in sheet metal stamping operations , 2004 .

[11]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice Using MATLAB , 2001 .

[12]  Peter Cawley,et al.  THE REFLECTION OF GUIDED WAVES FROM NOTCHES IN PIPES: A GUIDE FOR INTERPRETING CORROSION MEASUREMENTS , 2004 .

[13]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[14]  P. Testoni,et al.  Artificial neural networks for non-destructive evaluation with ultrasonic waves in not accessible pipes , 2005, Fourtieth IAS Annual Meeting. Conference Record of the 2005 Industry Applications Conference, 2005..

[15]  Martin Veidt,et al.  Pattern recognition of guided waves for damage evaluation in bars , 2009, Pattern Recognit. Lett..

[16]  Rajparthiban Kumar Rajkumar,et al.  Pipeline Defect Detection Using Support Vector Machines , 2007 .

[17]  Ivan Bartoli,et al.  Defect Classification in Pipes by Neural Networks Using Multiple Guided Ultrasonic Wave Features Extracted After Wavelet Processing , 2005 .

[18]  R. W. Smith,et al.  Evaluation of Methods for Detecting and Monitoring of Corrosion Damage in Risers , 2003 .

[19]  J. L. Roux.  An Introduction to the Kalman Filter , 2003 .