摘要
提出了一种小规模数据集下学习贝叶斯网络的有效算法——FCLBN。FCLBN利用bootstrap方法在给定的小样本数据集上进行重抽样,然后用在抽样后数据集上学到的贝叶斯网络来估计原数据集上的贝叶斯网络的高置信度的特征,并用这些特征来指导在原数据集上的贝叶斯网络搜索。用标准的数据集验证了FCLBN的有效性,并将FCLBN应用于酵母菌细胞中蛋白质的定位预测。实验结果表明,FCLBN能够在小规模数据集上学到较好的网络模型。
An efficient algorithm FCLBN for learning Bayesian network from small scale dataset was proposed.FCLBN uses the method of bootstrap to re-sample from the small scale dataset,and estimates the high confidence features of the source small scale dataset from the Bayesian networks learned from the re-sampling small datasets.The high confidence features are taken to guide the search of the best Bayesian network on the source dataset.After being evaluated on the standard benchmark dataset,FCLBN is applied to predict yeast protein localization.The result of the experiments indicates that the FCLBN algorithm can learn relatively accurate network from small scale dataset.
出处
《计算机科学》
CSCD
北大核心
2011年第7期181-184,234,共5页
Computer Science
基金
国家自然科学基金项目(61073017)
北京师范大学-香港浸会大学联合国际学院校内项目(R201109,UIC2010-S-01.8)资助
关键词
学习贝叶斯网络
小规模数据集
特征置信
Learning bayesian network
Small scale dataset
Features confidence