摘要
提出一种基于蒙特卡洛思想的数据查询处理算法QueryMC.在查询计算过程中,根据小枝查询模式确定待处理多维随机变量联合概率密度函数及查询区域,通过构造相同区域上的均匀分布随机变量将查询问题建模成相应复合函数的期望,利用算法同时产生的随机样本集估计该期望的取值作为问题的解,避免了传统的降维操作,有效地减少了处理时间.实验结果表明,在取得理想精度的同时,算法具有高效性.
An effective algorithm QueryMC based on Monte-Carlo method is proposed. According to the twig query pattern, the joint probability density funtion and the region of query are identified. Furthermore the problem of query in QueryMC is modelled into expectation of composite function by structuring random variables of uniform distribution of the same region. It could be used to avoid the traditional dimensionality reduction operation and to reduce the processing time by estimating the expectation with the random sample set. Meanwhile, the results show that the algorithm is highly effcient with ideal precision.
出处
《微电子学与计算机》
CSCD
北大核心
2013年第6期30-33,共4页
Microelectronics & Computer
基金
国家自然科学基金资助项目(61163015)
内蒙古自然科学基金重点资助项目(20080404Zd21)
关键词
连续不确定XML
多维随机变量
小枝查询模式
联合概率密度
蒙特卡洛
continuous uncertain XML
multidimensional random variables
twig query pattern
joint probabilitydensity
Monte-Carlo