小数据集条件下基于数据再利用的BN参数学习

杨宇; 高晓光; 郭志高

doi:10.16383/j.aas.2015.c140838

小数据集条件下基于数据再利用的BN参数学习

doi: 10.16383/j.aas.2015.c140838

1.
西北工业大学电子信息学院西安 710129

基金项目:

国家自然科学基金(60774064,61573285),教育部博士点基金(20116102110026)资助

详细信息

作者简介:
杨宇西北工业大学电子信息学院博士研究生. 主要研究方向为小数据集条件下贝叶斯网络结构和参数学习.E-mail: youngiv@126.com

通讯作者:
高晓光西北工业大学电子信息学院教授.主要研究方向为智能决策, 复杂系统建模与效能分析.本文通信作者.

计量
- 文章访问数: 1479
- HTML全文浏览量: 94
- PDF下载量: 1637
- 被引次数: 0
出版历程
- 收稿日期: 2014-12-04
- 修回日期: 2015-07-21
- 刊出日期: 2015-12-20

Learning BN Parameters with Small Data Sets Based by Data Reutilization

1.
School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710129

Funds:

Supported by National Natural Science Foundation of China (60774064, 61573285) and Research Fund for the Doctoral Program Higher Education of China (20116102110026)

摘要

摘要: 着重研究了小数据集条件下结合凸约束的离散贝叶斯网络(Bayesian network, BN)参数学习问题, 主要任务是用先验知识弥补数据的不足以提高参数学习精度. 已有成果认为数据和先验知识是独立的, 在参数学习算法中仅将二者机械结合. 经过理论研究后, 本文认为数据和先验知识并不独立, 原有算法浪费了这部分有用信息. 本文立足于数据信息分类, 深入挖掘数据和先验知识之间的约束信息来提高参数学习精度, 提出了新的BN 参数学习算法 --凸约束条件下基于数据再利用的贝叶斯估计. 通过仿真实验展示了所提算法在精度和其他性能上的优势, 进一步证明数据和先验知识不独立思想的合理性.
- 贝叶斯网络 /
- 参数学习 /
- 小数据集 /
- 数据信息分类 /
- 数据再利用
Abstract: In this paper, parameters learning of discrete Bayesian networks (BNs) with small data sets with convex constraints is investigated, and the main task is improving the accuracy of parameter learning through offsetting the lack of data with prior knowledge. Data and prior knowledge are often mechanically integrated in most existing algorithms because they are treated independent. However, after a theoretical study, they are found dependent on each other, and the existing algorithms have dissipated this relevance. A novel parameter learning algorithm --Bayesian estimation based on data reutilization under convex constraints, is proposed with deeply mining the information between data and prior knowledge based on classification of data information. Finally, simulations demonstrate the advantages of novel algorithm in precision and other indexes, which in turn tells the dependance between data and prior information.
- Bayesian network (BN) /
- parameter learning /
- small data sets /
- classification about data information /
- reutilization of data

HTML全文

参考文献(24)

[1]	Pearl J. Probabilistic Reasoning in Intelligent Systems. Massachusetts: Morgan Kaufmann, 1988.
[2]	Jin Nai-Gao, Yin Fu-Liang, Chen Zhe. Audio-visual speaker tracking based on dynamic Bayesian network. Acta Automatica Sinica, 2008, 34(9): 1083-1089(金乃高, 殷福亮, 陈喆. 基于动态贝叶斯网络的音视频联合说话人跟踪. 自动化学报, 2008, 34(9): 1083-1089)
[3]	Chen Hai-Yang, Gao Xiao-Guang, Fan Hao. Inference algorithm of variable structure DDBNs and multi-target recognition. Acta Aeronautica Et Astronautica Sinica, 2010, 31(11): 2222-2227(陈海洋, 高晓光, 樊昊. 变结构DDBNS的推理算法与多目标识别. 航空学报, 2010, 31(11): 2222-2227)
[4]	Du You-Tian, Chen Feng, Xu Wen-Li. Approach to human activity multi-scale analysis and recognition based on multi-layer dynamic Bayesian network. Acta Automatica Sinica, 2009, 35(3): 225-232(杜友田, 陈峰, 徐文立. 基于多层动态贝叶斯网络的人的行为多尺度分析及识别方法. 自动化学报, 2009, 35(3): 225-232)
[5]	Wan Jiu-Qing, Liu Qing-Yun. Data association in visual sensor networks based on high-order spatio-temporal model. Acta Automatica Sinica, 2012, 38(2): 236-247(万九卿, 刘青云. 基于高阶时空模型的视觉传感网络数据关联方法. 自动化学报, 2012, 38(2): 236-247)
[6]	Tamda Y, Imoto S, Araki H, Nagasaki M, Printe C, Charnock-Jones D S, Miyano S. Estimating genome-wide gene networks using nonparametric Bayesian network models on massively parallel computers. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2011, 8(3): 683-697
[7]	Chang R, Shoemaker R, Wang W. A novel knowledge-driven systems biology approach for phenotype prediction upon genetic intervention. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2011, 8(5): 1170-1182
[8]	Ibrahim W, Beiu V. Using Bayesian networks to accurately calculate the reliability of complementary metal oxide semiconductor gates. IEEE Transactions on Reliability, 2011, 60(3): 538-549
[9]	Jin Can-Can, Zuo Hong-Fu, Zhang Ying, Bai Fang. Research on risk evaluation for airlines based on BBN. Acta Aeronautica ET Astronautica Sinica, 2013, 34(3): 588-596(金灿灿, 左洪福, 张营, 白芳. 基于BBN的航空公司风险评估技术研究. 航空学报, 2013, 34(3): 588-596)
[10]	Yin Xiao-Wei, Qian Wen-Xue, Xie Li-Yang. A method for system reliabiltiy assessment based on Bayesian networks. Acta Aeronautica ET Astronautica Sinica, 2008, 29(6): 1482-1489(尹晓伟, 钱文学, 谢里阳. 系统可靠性的贝叶斯网络评估方法. 航空学报, 2008, 29(6): 1482-1489)
[11]	Druzdzel M J. Probabilistic Reasoning in Decision Support Systems: From Computation to Common Sense [Ph.D. dissertation], Carnegie Mellon University, Pennsylvania, 1993.
[12]	Druzdzel M, van der Gaag L C. Building probabilistic networks: "where do the numbers come from?" guest editors' introduction. IEEE Transactions on Knowledge and Data Engineering, 2000, 12(4): 481-486
[13]	Sijbers J, den Dekker A J, Scheunders P, Van Dyck D. Maximum-likelihood estimation of Rician distribution parameters. IEEE Transactions on Medical Imaging, 1998, 17(3): 357-361
[14]	Helsper E M, van der Gaag L C, Groenendaal F. Designing a procedure for the acquisition of probability constraints for Bayesian networks. In: Proceedings of the 14th Conference on Engineering Knowledge in the Age of the Semantic Web. Whittlebury Hall, UK: Springer, 2004. 280-292
[15]	Guo Zhi-Gao, Gao Xiao-Guang, Di Ruo-Hai. Learning Bayesian network parameters under dual constraints from small data set. Acta Automatica Sinica, 2014, 40(7): 15091516(郭志高, 高晓光, 邸若海. 小数据集条件下基于双重约束的BN参数学习. 自动化学报, 2014, 40(7): 1509-1516)
[16]	Wittig F, Jameson A. Exploiting qualitative knowledge in the learning of conditional probabilities of Bayesian networks. In: Proceedings of the 16th International Conference on Uncertainty in Artificial Intelligence. San Francisco, CA, USA: Morgan Kaufmann Publishers, 2000. 644-652
[17]	Altendorf E E, Restificar A C, Dietterich T G. Learning from sparse data by exploiting monotonicity constraints. In: Proceedings of the 21st International Conference on Uncertainty in Artificial Intelligence. Arlington, Virginia: AUAI Press, 2005. 18-26
[18]	Liao W H, Ji Q. Learning Bayesian network parameters under incomplete data with domain knowledge. Pattern Recognition, 2009, 42(11): 3046-3056
[19]	de Campos C P, Tong Y, Ji Q. Constrained maximum likelihood learning of Bayesian networks for facial action recognition. In: Proceedings of the 10th European Conference on Computer Vision. Marseille, France: Springer, 2008. 168181
[20]	de Campos C P, Ji Q. Improving Bayesian network parameter learning using constraints. In: Proceedings of the 19th International Conference on Pattern Recognition. Tampa, Florida: IEEE: 2008. 1-4
[21]	Feelders A, van der Gaag L C. Learning Bayesian network parameters under order constraints. International Journal of Approximate Reasoning, 2006, 42(1-2): 37-53
[22]	Chang R, Wang W. Novel algorithm for Bayesian network parameter learning with informative prior constraints. In: Proceedings of the 2010 International Joint Conference on Neural Networks. Barcelona: IEEE, 2010. 1-8
[23]	Zhang Lian-Wen, Guo Hai-Peng. Introduction to Bayesian Networks. Beijing: Science Press, 2006.(张连文, 郭海鹏. 贝叶斯网引论. 北京: 科学出版社, 2006.)
[24]	Zhou Y, Fenton N, Neil M. Bayesian network approach to multinomial parameter learning using data and expert judgments. International Journal of Approximate Reasoning, 2014, 55(5): 1252-1268