Feature Discriminability for Pattern Classification Based on Neural Incremental Attribute Learning

Feature ordering is important in Incremental Attribute Learning where features are gradually trained in one or more size. Apart from time-consuming contribution-based feature ordering methods, feature ordering also can be derived by filter criteria. In this paper, a novel criterion based on a new metric called Discriminability is presented to give ranks for feature ordering. Final results show that the new metric not only is applicable for IAL, but also exhibits better performance in lower error rates.

[1]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[2]  Sholom M. Weiss,et al.  Predictive data mining - a practical guide , 1997 .

[3]  Jun Liu,et al.  Incremental Ordered Neural Network Training , 2002 .

[4]  Steven Guan,et al.  Parallel growing and training of neural networks using output parallelism , 2002, IEEE Trans. Neural Networks.

[5]  Jun Liu,et al.  Incremental Neural Network Training with an Increasing Input Dimension , 2004 .

[6]  Steven Guan,et al.  Incremental Learning with Respect to New Incoming Input Attributes , 2004, Neural Processing Letters.

[7]  Steven Guan,et al.  Ordered incremental training for GA-based classifiers , 2005, Pattern Recognit. Lett..

[8]  Jun Liu,et al.  Feature Selection for Modular Networks Based on Incremental Training , 2005 .

[9]  Chris H. Q. Ding,et al.  Evolving Feature Selection , 2005, IEEE Intell. Syst..

[10]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  R. K. Agrawal,et al.  Incremental Bayesian classification for multivariate normal distribution data , 2008, Pattern Recognit. Lett..

[12]  Fai Wong,et al.  An incremental decision tree learning methodology regarding attributes in medical data mining , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[13]  Jose Miguel Puerta,et al.  A GRASP algorithm for fast hybrid (filter-wrapper) feature subset selection in high-dimensional datasets , 2011, Pattern Recognit. Lett..

[14]  Jose Miguel Puerta,et al.  Fast wrapper feature subset selection in high-dimensional datasets by means of filter re-ranking , 2012, Knowl. Based Syst..