|
|
论文:2013,Vol:31,Issue(5):716-721 |
|
|
引用本文： |
|
|
刘宝宁, 章卫国, 李广文, 刘小雄. 一种改进遗传算法的贝叶斯网络结构学习[J]. 西北工业大学 |
|
|
Liu Baoning, Zhang Weiguo, Li Guangwen, Liu Xiaoxiong. Bayesian Network Structure Learning Based on an Improved Genetic Algorithm[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 一种改进遗传算法的贝叶斯网络结构学习 |
|
| 刘宝宁, 章卫国, 李广文, 刘小雄 |
|
| 西北工业大学 自动化学院, 陕西 西安 710129 |
| 摘要: |
| 针对贝叶斯网络结构学习,标准的遗传算法容易陷入局部最优,无法搜索最好的解,提出一种改进的遗传算法。首先,通过互信息和BIC函数确定最初的贝叶斯边集,通过混沌映射求取邻域的个体和随机过程产生的个体组成初始种群;其次,提出一种以个体列向量为单位,进行多个列的交叉方法,采用轮盘赌的方法进行非法图的修正,缩小搜索空间范围;最后,通过Asia网络和Cancer网络结构验证了提出算法的有效性。 |
| 关键词:
贝叶斯网络
遗传算法
混沌映射
互信息
|
|
| Bayesian Network Structure Learning Based on an Improved Genetic Algorithm |
|
| Liu Baoning, Zhang Weiguo, Li Guangwen, Liu Xiaoxiong |
|
| Department of Automatic Control, Northwestern Polytechnical University, Xi'an 710129, China |
| Abstract: |
| For the structure learning of the Bayesian network,the existing genetic algorithm is apt to fall into local optimum and has no way to search for the best solution. Therefore we propose an improved genetic algorithm. First of all,we use the mutual information and the Bayesian information criterion(BIC) function to determine the initial Bayesian edge set and then calculate individuals and form the initial population with chaotic mapping and random processes respectively. Second,we cross multiple columns in the unit of individual column vector and then use a roulette to select an illegal graph and modify it so as to reduce the scope of search space. Finally,we use the Asia Bayesian network and the Cancer Bayesian network to verify the effectiveness of our improved genetic algorithm. |
| Key words:
functions
genetic algorithms
Bayesian network
chaotic mapping
mutual information
structure learning
|
|
| 收稿日期: 2012-12-10
修回日期:
|
| DOI: |
| 基金项目: 航空科学基金(20125853035)资助 |
| 通讯作者:
Email： |
| 作者简介: 刘宝宁(1987-),西北工业大学博士研究生,主要从事飞行控制与自主决策研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Chickerig D, Heckerman D, Meek C.Large-Sample Learning of Bayesian Networks is NP-Hard.Machine Learning Research,2004, 5: 1287-1330
[2] Cooper G F, Herskovits E.A Bayesian Method for the Induction of Probabilistic Networks from Data.Machine Learning, 1992,9(4): 309-347
[3] 沈佳杰, 林 峰.基于混合自适应 Memetic 算法的贝叶斯网络结构学习.系统工程与电子技术, 2012, 34(6): 1293-1298 Shen Jiajie, Lin Feng.Structure Learning of Bayesian Network Using Adaptive Hybrid Memetic Algorithm.Systems Engineering and Electronics, 2012, 34(6): 1293-1298 (in Chinese)
[4] Bouckaert R R.A Stratified Simulation Scheme for Inference in Bayesian Belief.Proceedings of the Tenth Conference on Uncertainty in Artificial Intelligence, 1994, 110-117
[5] Chickering D, Geiger D, Heckerman D.Learning Bayesian Networks: Search Methods and Experimental Results.Proceedings of the 5th Conference on Artificial Intelligence and Statistics, 1995, 112-128
[6] Chickering D M.Optimal Structure Identification with Greedy Search.Journal of Machine Learning Research, 2002, 11 (3):507-554
[7] Shin F, Yavuz M, Arnavu Z, et al.Fault Diagnosis for Airplane Engines Using Bayesian Networks and Distributed Particle Swarm Optimization.Parallel Computing, 2007, 11 (33): 124-143
[8] 刘金琨.先进 PID 控制 MATLAB 仿真.北京: 电子工业出版社, 2004 Liu Jinkun.Advanced PID Control and Matlab Simulation.Beijing: Publishing House of Electronics Industry, 2004 (in Chinese)
[9] 张 浩, 张铁男, 沈继红等.Tent 混沌粒子群算法及其在结构优化决策中的应用.控制与决策, 2008, 23(8): 857-862 Zhang Hao, Zhang Tienan, Shen Jihong, et al.Research on Decision-Makings of Structure Optimization Based on Improved Tent PSO.Control and Decision, 2008, 23(8): 857-862 (in Chinese)
[10] 陈增强, 周 茜, 袁著祉.基于 Kent 映射的数字喷泉编解码方法研究.系统科学与数学, 2011, 31 (6): 731-741 Chen Zengqiang, Zhou Qian, Yuan Zhuzhi.Research on the Digital Fountain Codes and Decodes Algorithm Based upon Kent Mapping.Journal of System Science and Mathematical Science, 2011, 31 (6): 731-741 (in Chinese) |
|
|
|
|
|
|
|
