30 March 2006 Defect classification of highly noisy NDE data using classifier ensembles
Author Affiliations +
Abstract
In this paper, we present a feature selection and classification approach that was used to assess highly noisy sensor data from a NDE field study. Multiple, heterogeneous NDT sensors were employed to examine the solid structure. The goal was to differentiate between two types of phenomena occurring in a solid structure where one phenomenon was benign, the other was malignant. Manual distinction between these two types is almost impossible. To address these issues, we used sensor validation techniques to select the best available sensor that had the least noise effects and the best defect signature in the region of interest. Hundreds of features were formulated and extracted from data of the selected sensors. Next, we employed separability measures and correlation measures to select the most promising set of features. Because the NDE sensors poorly described the different defect types under consideration, the resulting features also exhibited poor separability. The focus of this paper is on how one can improve the classification under these constraints while minimizing the risk of overfitting (the number of field data was small). Results are shown from a number of different classifiers and classifier ensembles that were tuned to a set true positive rate using the Neyman-Pearson criterion.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kai F. Goebel, Kai F. Goebel, Weizhong Yan, Weizhong Yan, Neil H. W. Eklund, Neil H. W. Eklund, Xiao Hu, Xiao Hu, Viswanath Avasarala, Viswanath Avasarala, Jose R. Celaya, Jose R. Celaya, } "Defect classification of highly noisy NDE data using classifier ensembles", Proc. SPIE 6167, Smart Structures and Materials 2006: Smart Sensor Monitoring Systems and Applications, 61671O (30 March 2006); doi: 10.1117/12.659704; https://doi.org/10.1117/12.659704
PROCEEDINGS
12 PAGES


SHARE
Back to Top