Title :
Mahalanobis Space Learning Machine for Quality Diagnosis
Author :
Zeng Jianghui ; Wang Bangjun ; Hao Jianchun ; Fang, Fang
Author_Institution :
Quality Eng. Center, China Aero- Polytechnology Establ., Beijing, China
Abstract :
In this paper, a pattern classification algorithm based on Mahalanobis space and its solving via second order cone programming were discussed. The method of selecting feature through Mahalanobis Taguchi System and integrating the Mahalanobis Taguchi System and Mahalanobis space learning machine for pattern classification were proposed. At last, an example of gear quality diagnosis was presented on real data, and the effect of this methodology was proved.
Keywords :
Taguchi methods; learning (artificial intelligence); pattern classification; support vector machines; Mahalanobis Taguchi System; Mahalanobis space learning machine; feature selection; pattern classification algorithm; quality diagnosis; second order cone programming; support vector machines; Covariance matrix; Gears; Kernel; Machine learning; Support vector machines; Testing; Training; Mahalanobis Space; Pattern classification; learning machine; quality diagnosis;
Conference_Titel :
Intelligent Systems (GCIS), 2010 Second WRI Global Congress on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9247-3
DOI :
10.1109/GCIS.2010.215
