GPS observation network is deployed in the central part of Ningxia, which is the juncture of the Alxa block, Ordos block and Qinghai-Xizang (Tibet) block. Using the data of five phases of repeated survey sine 1996, th...GPS observation network is deployed in the central part of Ningxia, which is the juncture of the Alxa block, Ordos block and Qinghai-Xizang (Tibet) block. Using the data of five phases of repeated survey sine 1996, the current state of crustal movement in the central part of Ningxia is analyzed. From the result, we can know the following. (1) In the period from Dec. 1996 to May 1999, the central part of Ningxia had the phenomenon of left-lateral movement about the west margin of Ordos (measuring station P2) and the Lingwu fault on the east of the Yinchuan basin displayed the mode of left-lateral reverse strike slip movement. In that region, the direction of the principal stress field was NNE-SSW (with an azimuth of 29.8?; the central part to the south of the measuring station P2 displaced eastward; the vertical deformation was obviously greater than the horizontal deformation in order of magnitude; the Yinchuan basin and Qinghai-Xizang (Tibet) block were in a state of rising; the measuring station P1 in the hinterland of Ordos showed a trend of subsiding year by year; and there may be a hidden fault to exist between the measuring points P3 and P4. (2) About one year before the occurrence of moderately strong earthquakes in the vicinity of the measuring region, deformation anomalies and abnormal changes of principal stress direction can be observed by the GPS measuring stations in that region; before moderately strong earthquakes near the measuring region and before strong earthquakes in adjacent regions, the simulated GPS deformation vector field ofthat region can betoken the approximate position of the coming earthquake. These results can be regarded as the eigenvalues of earthquake prediction for consideration.展开更多
为了解决模糊聚类-矢量量化算法都是强迫模糊分区转变为Crisp集合,降低码本质量,使重构图像丢失了丰富的边缘纹理信息;且其计算代价较高,以及严重依赖初始化等不足。提出了竞争聚类耦合码字定向移动的图像重构模糊矢量量化算法。引入竞...为了解决模糊聚类-矢量量化算法都是强迫模糊分区转变为Crisp集合,降低码本质量,使重构图像丢失了丰富的边缘纹理信息;且其计算代价较高,以及严重依赖初始化等不足。提出了竞争聚类耦合码字定向移动的图像重构模糊矢量量化算法。引入竞争聚类,基于C均值和模糊C均值,设计最优目标函数;结合拉格朗日乘子,推导出最优目标函数的聚类中心和隶属度的求解模型;定义迁移规则,构造了码字定向移动机制,使得小簇群向大簇群移动,形成更大的簇群;以失真度和相似度为评估准则,构造量化反馈机制,优化重构图像。仿真结果显示:与其他矢量量化机制相比,本文算法的编码图像相似度更高,PSNR(peak signal to noise ratio)最高,得到的重构图像质量最佳;且本文算法的时间成本最低。展开更多
基金the Program of the Science and Technology Commission of Ningxia Hui Autonomous Region and Joint Foundation of Seismological Science(197043).
文摘GPS observation network is deployed in the central part of Ningxia, which is the juncture of the Alxa block, Ordos block and Qinghai-Xizang (Tibet) block. Using the data of five phases of repeated survey sine 1996, the current state of crustal movement in the central part of Ningxia is analyzed. From the result, we can know the following. (1) In the period from Dec. 1996 to May 1999, the central part of Ningxia had the phenomenon of left-lateral movement about the west margin of Ordos (measuring station P2) and the Lingwu fault on the east of the Yinchuan basin displayed the mode of left-lateral reverse strike slip movement. In that region, the direction of the principal stress field was NNE-SSW (with an azimuth of 29.8?; the central part to the south of the measuring station P2 displaced eastward; the vertical deformation was obviously greater than the horizontal deformation in order of magnitude; the Yinchuan basin and Qinghai-Xizang (Tibet) block were in a state of rising; the measuring station P1 in the hinterland of Ordos showed a trend of subsiding year by year; and there may be a hidden fault to exist between the measuring points P3 and P4. (2) About one year before the occurrence of moderately strong earthquakes in the vicinity of the measuring region, deformation anomalies and abnormal changes of principal stress direction can be observed by the GPS measuring stations in that region; before moderately strong earthquakes near the measuring region and before strong earthquakes in adjacent regions, the simulated GPS deformation vector field ofthat region can betoken the approximate position of the coming earthquake. These results can be regarded as the eigenvalues of earthquake prediction for consideration.
文摘为了解决模糊聚类-矢量量化算法都是强迫模糊分区转变为Crisp集合,降低码本质量,使重构图像丢失了丰富的边缘纹理信息;且其计算代价较高,以及严重依赖初始化等不足。提出了竞争聚类耦合码字定向移动的图像重构模糊矢量量化算法。引入竞争聚类,基于C均值和模糊C均值,设计最优目标函数;结合拉格朗日乘子,推导出最优目标函数的聚类中心和隶属度的求解模型;定义迁移规则,构造了码字定向移动机制,使得小簇群向大簇群移动,形成更大的簇群;以失真度和相似度为评估准则,构造量化反馈机制,优化重构图像。仿真结果显示:与其他矢量量化机制相比,本文算法的编码图像相似度更高,PSNR(peak signal to noise ratio)最高,得到的重构图像质量最佳;且本文算法的时间成本最低。
