Evolutionary Generalized Radial Basis Function neural networks for improving prediction accuracy in gene classification using feature selection

详细信息	查看全文 | 推荐本文 |

• 作者：Francisco Ferná ; ndez-Navarro^a ; ^{i22fenaf@uco.es} ; Cé ; sar Hervá ; s-Martí ; nez^a ; Roberto Ruiz^c ; Jose C. Riquelme^b
• 关键词：Generalized Radial Basis Function ; Generalized Gaussian Distribution ; Evolutionary algorithm ; Gene classification ; Feature selection
• 刊名：Applied Soft Computing Journal
• 出版年：2012
• 期刊代码：9_15684946
• 类别：cp
• 出版时间：June, 2012
• 卷：12
• 期：6
• 页码：1787-1800
• 文件大小：991 K

摘要

Radial Basis Function Neural Networks (RBFNNs) have been successfully employed in several function approximation and pattern recognition problems. The use of different RBFs in RBFNN has been reported in the literature and here the study centres on the use of the Generalized Radial Basis Function Neural Networks (GRBFNNs). An interesting property of the GRBF is that it can continuously and smoothly reproduce different RBFs by changing a real parameter 蟿. In addition, the mixed use of different RBF shapes in only one RBFNN is allowed. Generalized Radial Basis Function (GRBF) is based on Generalized Gaussian Distribution (GGD), which adds a shape parameter, 蟿, to standard Gaussian Distribution. Moreover, this paper describes a hybrid approach, Hybrid Algorithm (HA), which combines evolutionary and gradient-based learning methods to estimate the architecture, weights and node topology of GRBFNN classifiers. The feasibility and benefits of the approach are demonstrated by means of six gene microarray classification problems taken from bioinformatic and biomedical domains. Three filters were applied: Fast Correlation-Based Filter (FCBF), Best Incremental Ranked Subset (BIRS), and Best Agglomerative Ranked Subset (BARS); this was done in order to identify salient expression genes from among the thousands of genes in microarray data that can directly contribute to determining the class membership of each pattern. After different gene subsets were obtained, the proposed methodology was performed using the selected gene subsets as new input variables. The results confirm that the GRBFNN classifier leads to a promising improvement in accuracy.