论文信息 - Feature Selection for Support Vector Machines

Feature Selection for Support Vector Machines

This paper deals with the application of saliency analysis to Support Vector Machines (SVMs) for feature selection. The importance of feature is ranked by evaluating the sensitivity of the network output to the feature input in terms of the partial derivative. A systematic approach to remove irrelevant features based on the sensitivity is developed. Five futures contracts are examined in the experiment. Based on the simulation results, it is shown that that saliency analysis is effective in SVMs for identifying important features.

Francis Eng Hock Tay | Lijuan Cao | F. Tay | Lijuan Cao

[1] Alexander J. Smola,et al. Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[2] Wright-Patterson Afb,et al. Feature Selection Using a Multilayer Perceptron , 1990 .

[3] Victor L. Brailovsky,et al. On domain knowledge and feature selection using a support vector machine , 1999, Pattern Recognit. Lett..

[4] Russell Reed,et al. Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[5] Jacek M. Zurada,et al. Perturbation method for deleting redundant inputs of perceptron networks , 1997, Neurocomputing.

[6] Gunnar Rätsch,et al. Predicting Time Series with Support Vector Machines , 1997, ICANN.

[7] Kenneth W. Bauer,et al. Feature saliency measures , 1997 .

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