一类随机动态过程基于q阶树的多尺度建模方法
A qth-order Tree-based Method for Multiscale Modeling of Stochastic Dynamic Processes
-
摘要: 利用多尺度随机模型能建立处理问题有效并行算法的这一优势,提出一类随机动态过程基于一般q阶树的多尺度建模方法。首先,利用Markov过程的条件独立性给出一类过程基于q阶树的多尺度表示方法;其次,基于q阶树多尺度表示和具体实例推导出多尺度模型中的状态转移矩阵、扰动阵、初始状态和相应的协方差矩阵等的具体形式,为具有Markov统计特性的过程或信号建立起多尺度随机模型,这将为有效地解决多源同类信息和多源异类信息的数据融合等实际问题提供了理论基础;最后,给出一类Gauss-Markov过程基于三阶树和五阶树多尺度表示的计算机仿真结果,进一步验证建立模型的实用性和有效性。Abstract: In this paper, by using the advantage of an extremely efficient and highly parallelizable algorithm deriving from the multiscaie stochastic model to deal with a lot of practical problem, a general qth-order tree-based method for multiscale modeling of stochastic dynamic processes is developed. Firstly, using the property of conditional independence of Markov processes, a qth-order tree-based method for multiscale representation of a class of process is presented. Secondly, the representation forms of the parameters in the model, such as the state transition matrix, the disturbance matrix, the initial state and the corresponding covariance are deduced by example in detail based on
-
文成林,周东华.多尺度估计理论及其应用[M].北京:清华大学出版社,2002:184-203.[2]Willsky A S. Multiresolution Markov models for signal and image processing [J].Proc. IEEE.2002, 90(8):1396-[3]Luettgen M R. Image processing with multiscale stochastic models. [PhD],MIT, 1993.[4]Chou K C, Willsky A S, Benveniste A. Multiscale recursive estimation data fusion, and regularization[J].IEEE Trans. on Automatic Control.1994, 39(3):464-[5]Slatton K C. Adaptive multiscale estimation for fusing image data.[PhD], The University of Texas at Austin, 2001.[6]张延锋.随机动态过程的多尺度表示方法研究.[硕士论文],开封:河南大学,2004,4.[7]张延锋,葛泉波,文成林.随机动态过程基于q阶树的多尺度建模方法. 2004 World Congress on Intelligent Control and Automation. WCICA2004:231 -235. (EI收录)[8]文成林,陈志国,闫莉萍,周东华.基于多速率传感器动态系统的多尺度递归融合估计[J].电子与信息学报.2003,25(3):306-312浏览[9]王洁,韩崇昭,李晓榕.异步传感器数据融合[J].控制与决策,2001,16(6):877-881.[10]郭徽东,章新华.多传感器异步数据融合模型分析[J].火力与指挥控制,2003,28(3):9-11. -
计量
- 文章访问数: 2095
- HTML全文浏览量: 85
- PDF下载量: 642
- 被引次数: 0
下载:
