计算机应用研究2016，Vol.33Issue(5)：1327-1334,8.DOI:10.3969/j.issn.1001-3695.2016.05.011
一般贝叶斯网络分类器及其学习算法
Algorithm for exact recovery of Bayesian network for classification
摘要
Abstract
General Bayesian network classifier (GBNC)was the effective local section of the Bayesian network (BN)facing classification problem.Conventionally,it had to learn the global BN first,and existing structure learning algorithm imposed re-striction on possible problem scale.The paper developed an algorithm called IPC-GBNC for the exact recovery of GBNC with only local search.It conducted a breadth-first search with depth no more than 2 given the class node as the center.It proved its soundness,and experiments on synthetic and UCI real-world datasets demonstrate the merits of IPC-GBNC over classical PC al-gorithm which conducted global search:a)it produces same as or even higher quality of structure than PC,b)it saves considera-ble computation over PC,and c)effective dimension reduction is realized.As compared with state-of-the-art classifiers,GBNC not only performs as well on prediction,but inherits merits from being graphical model,like compact representation and power-ful inference ability.关键词
贝叶斯网络/马尔可夫毯/贝叶斯分类器/结构学习/特征选择/局部搜索Key words
Bayesian network/Markov blanket/Bayes classifier/structure learning/feature selection/local search分类
信息技术与安全科学引用本文复制引用
Sein Minn,傅顺开,吕天依,蔡奕侨..一般贝叶斯网络分类器及其学习算法[J].计算机应用研究,2016,33(5):1327-1334,8.基金项目
国家自然科学基金资助项目（61305058，61300139，61102163）；厦门科技计划基金资助项目（3505Z20133027）；华侨大学科研基金资助项目（11Y0274，12HJY18）；中央高校基本科研基金资助项目 （）
