Feature Selection based on the Kullback-Leibler Distance and its application on fault diagnosis

The core concept of pattern recognition is that digs inner mode between data in the same class. The within-class data has a similar distribution, while between-class data has some distinction in different forms. Feature selection utilizes the difference between two-class data to reduce the number of features in the training models. A large amount of feature selection methods have widely used in different fields. This paper proposes a novel feature selection method based on the Kullback-Leibler distance which measures the distance of distribution between two features. For fault diagnosis, the proposed feature selection method is combined with support vector machine to improve its performance. Experimental results validate the effectiveness and superior of the proposed feature selection method, and the proposed diagnosis model can increase the detection rate in chemistry process.