基于Map/Reduce的朴素贝叶斯数据分类算法研究  

Research on naive Bayesian data classification algorithm based on Map/Reduce

作　　者：崔良中[1] 郭福亮[1] 宋建新 CUI Liang-zhong;GUO Fu-liang;SONG Jian-xin(College of Electronic Engineering. Naval Univ, of Engineering. Wuhan 430033, China;Planning and Development Bureau. Naval Staff, Beijing 100036. China)

机构地区：[1]海军工程大学电子工程学院,武汉430033 [2]海军参谋部规划和编制局,北京100036

出　　处：《海军工程大学学报》2019年第4期7-10,共4页Journal of Naval University of Engineering

基　　金：国家自然科学基金资助项目(61701517);2017年度海军教育理论研究资助项目

摘　　要：针对目前机器学习研究领域中的数据分类问题,选择朴素贝叶斯算法作为研究对象。首先,通过对样本数据特征属性的权重进行加权调整,提高算法处理的准确率;然后,改进朴素贝叶斯算法分类器模型,使其能够利用Map/Reduce并行编程模型,采用多计算资源节点并行处理,进一步提高处理速度。最后,对UCI dataset数据库进行实验验证,结果表明:改进后的算法在海量数据分类处理中具有更好的性能表现。Aiming at the application of data classification in the field of machine learning research, the naive Bayesian algorithm is chosen as the object of study. Firstly,the processing accuracy of the algorithm is achieved by optimizing the selection of the data characteristics, and then, the improved algorithm flow can make use of Map/Reduce parallel programming model and parallel processing with multiple computing resource nodes to further improve the processing speed. Experimental results show that the improved algorithm has better performance in classification processing of mass data.

关 键 词：Map/Reduce并行编程模型 数据分类算法 贝叶斯算法 海量数据处理 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]