摘要
针对单个人工神经网络稳定性差、分类精度不高的缺点,提出了基于样本过滤的人工神经网络集成算法,并用于基因表达数据分类.采用基因表达数据集Leukemia进行实验仿真,并与单个BP神经网络、Bagging神经网络集成和支持向量机进行比较.结果表明,样本过滤算法具有更好的稳定性和更高的分类精度.
Introduced a new algorithm in artificial neural network ensemble based on sample filtering that is used to classify gene expression data. Simulations were carried out to verify the proposed strategy using Leukemia data sets, and the test results were compared with those of BP neural network, Bagging neural network ensemble and support vector machine. The results indicate that sample filtering algorithm has better stability and higher classification accuracy.
出处
《中国计量学院学报》
2009年第3期254-258,共5页
Journal of China Jiliang University
基金
国家自然科学基金资助项目(No.60842008
10602055)
关键词
基因表达
样本过滤
人工神经网络集成
gene expression
sample filtering
artificial neural network ensemble