Title :
Modified Support Vector Regression in outlier detection
Author :
Nishiguchi, Junya ; Kaseda, Chosei ; Nakayama, Hirotaka ; Arakawa, Masao ; Yun, Yeboon
Author_Institution :
Yamatake Corp., Fujisawa, Japan
Abstract :
In order to construct approximation functions on real-life data, it is necessary to remove outliers from the measured raw data before modeling. Although the standard Support Vector Regression based outlier detection methods for non-linear function with multidimensional input have achieved good performance, they have practical issues in computational costs and parameter adjustment. In this paper we propose a practical approach to outlier detection using modified SVR, which reduces computational cost and defines outlier threshold appropriately. We apply this method to both test and industrial data sets for validation.
Keywords :
data analysis; function approximation; regression analysis; support vector machines; approximation function; computational cost reduction; modified support vector regression; nonlinear function; outlier detection; outlier threshold; raw data measurement; Energy consumption; Kernel; Noise; Pollution measurement; Robustness; Support vector machines; Upper bound;
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6916-1
DOI :
10.1109/IJCNN.2010.5596976