Cancer classification based on direction-basis-function neural networks

Automatic molecular classification of cancer based on DNA microarray has many advantages over conventional classification based on morphological appearance of the tumor. Using artificial neural networks is a general approach for automatic classification. In this paper, Direction-Basis-Function neuron and Priority-Ordered algorithm are applied to neural networks. And the leukemia gene expression dataset is used as an example to testify the classifier. The result of our method is compared to that of SVM. It shows that our method makes a better performance than SVM.

Automatic molecular classification of cancer based on DNA microarray has many advantages over conventional classification based on morphological appearance of the tumor. Using artificial neural networks is a general approach for automatic classification. In this paper, Direction-Basis-Function neuron and Priority-Ordered algorithm are applied to neural networks. And the leukemia gene expression dataset is used as an example to testify the classifier. The result of our method is compared to that of SVM. It shows that our method makes a better performance than SVM.

zhangdi于2010-03-09批量导入

Made available in DSpace on 2010-03-09T02:12:00Z (GMT). No. of bitstreams: 0 Previous issue date: 2007

作者关键词: gene expression; direction basis function; priority ordered neural networks; cancer classification

[Wang, Shoujue; Zhou, Lingfei] CAS, Inst Semicond, Beijing 100083, Peoples R China

作者关键词: gene expression; direction basis function; priority ordered neural networks; cancer classification