Practical Approach to Outlier Detection Using Support Vector Regression

@inproceedings{Nishiguchi2008PracticalAT,
  title={Practical Approach to Outlier Detection Using Support Vector Regression},
  author={Junya Nishiguchi and Chosei Kaseda and Hirotaka Nakayama and Masao Arakawa and Yeboon Yun},
  booktitle={ICONIP},
  year={2008}
}
For precise estimation with soft sensors, it is necessary to remove outliers from the measured raw data before constructing the model. Conventionally, visualization and maximum residual error have been used for outlier detection, but they often fail to detect outliers for nonlinear function with multidimensional input. In this paper we propose a practical approach to outlier detection using Support Vector Regression, which reduces computational cost and defines outlier threshold appropriately… CONTINUE READING