摘要
在综合利用先验信息与观测信息的基础上,提出了多个粗差探测的Bayes方法。为了有效地防止掩盖和湮没现象的发生,在分析掩盖和湮没现象发生原因的基础上,从识别向量的样本相关系数阵的特征结构出发,提出了多个粗差定位的抗掩盖型Bayes方法,并设计了相应的算法——自适应MCMC抽样算法。
Combining prior information with observing information, Bayesian methods for blunder detection are imposed. Especially a lot of effective measures are used to overcome the masking and swamping. When multiple blunder influence each other, the Bayesian method for blunder positioning based on the posterior probabilities of classification variables sometimes gives birth to masking and swamping which leads to the failure of positioning blunder. Hence, on the basis of seeking the reason of masking and swamping, and analyzing the eigenstructure of sampling correlation matrix of classification variables, the Bayesian unmasking method for positioning multiple blunder is introduced. The corresponding algorithm-adaptable MCMC sampling algorithm is implemented.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2010年第1期1-5,共5页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金资助项目(40974009
40474007)
河南省基础与前沿技术研究计划资助项目(082300410240)
河南省自然科学基金资助项目(0511010100)
