【摘要】 贝叶斯网络是数据挖掘领域的研究热点,它是一种确定事物间不确定性依赖关系的有效工具。本文研究传统贝叶斯网络结构学习算法的优点和不足,并针对原算法的不足之处提出了改进。将改进后的算法应用于健康大数据集上,确定了数据集中各个健康属性之间的依赖关系,建立了相关属性依赖关系的网络结构。最终运用该网络结构对数据集中的数据进行自动分类。实验结果表明,本文基于贝叶斯网络建立的健康大数据分类模型具有良好的性能,实现了预期效果。更多还原

【Abstract】 Bayesian network is a research hotspot in the field of data mining.It is an effective tool for the determination of the uncertain dependencies.This paper studies the advantages and disadvantages of the traditional Bayesian network structure learning algorithm,and determines the dependencies among the various health attributes in the data set,establishes the network structure of dependency relation between related attributes.Finally,the network structure is used to automatically classify the data in the data set.Experiments show that the health big data classification model based on Bayesian network has a good performance and achieves the expected effect.更多还原