数据中的数据转折点一般代表某种变化或者异常，因此数据转折点准确查找对于数据分析和处理来说具有重要的作用和意义，在气象，水文，金融，故障诊断等领域有广泛的应用。目前数据转折点的主要检测方法有Mann—Kendall算法，Cumulative...数据中的数据转折点一般代表某种变化或者异常，因此数据转折点准确查找对于数据分析和处理来说具有重要的作用和意义，在气象，水文，金融，故障诊断等领域有广泛的应用。目前数据转折点的主要检测方法有Mann—Kendall算法，Cumulative Sum Charts（CUSUM）算法，最小方差法，小波变换法等。为了克服以上方法中的准确性和局限性问题，通过不断地变换尺度的方法来缩小计算范围；通过直线拟合的方法不断获取数据中的变化趋势。在比较分割后各小段数据的变化趋势，寻找趋势变化最大的数据段。在该数据段中将原来的尺度缩小为原来的一半，继续进行变化趋势的对比，直至数据长度变为2，最终逼近并找出原始数据中的转折点。通过多种类型的数据对该方法验证，说明了该方法的有效性和准确性。展开更多
A class of singularly perturbed problem of third order equation with two para-meters is studied. Using singular perturbation method, the structure of solutions to the problem is discussed in three different cases abou...A class of singularly perturbed problem of third order equation with two para-meters is studied. Using singular perturbation method, the structure of solutions to the problem is discussed in three different cases about two small parameters. The asymptotic solutions to the problem are given. The structure of solutions and the different limit behaviors are revealed. And the solutions are compared with the exact solutions to the equation in which the coefficients are constants and a relatively more perfect result is obtained.展开更多
We construct a positive type difference scheme for a singularly perturbed boundary value problem with a turning point. It's proved that this scheme is the second order convergence, uniformly in ? , to the solution...We construct a positive type difference scheme for a singularly perturbed boundary value problem with a turning point. It's proved that this scheme is the second order convergence, uniformly in ? , to the solution of the singularly perturbed B. V.P. Numerical examples are provided.展开更多
针对可见光图像弱小目标检测中的背景抑制和去噪问题,提出了奇异值分解(Singular Value Decomposition,SVD)带通滤波新方法.首先分析了图像奇异值与目标、噪声和图像背景的关系,结果表明奇异值的高序部分更多地反映图像噪声,中序部分更...针对可见光图像弱小目标检测中的背景抑制和去噪问题,提出了奇异值分解(Singular Value Decomposition,SVD)带通滤波新方法.首先分析了图像奇异值与目标、噪声和图像背景的关系,结果表明奇异值的高序部分更多地反映图像噪声,中序部分更多地反映目标性质,而低序部分更多地反映图像背景.以此为依据提出了SVD-Ⅰ型和SVD-Ⅱ型两种带通滤波器,并给出了奇异值曲线转折点法和门限准则法两种滤波器参数确定方法.实验表明SVD带通滤波能有效抑制图像背景,去除噪声,进而提高弱小目标的信噪比.展开更多
基金Supported by the National Natural Science Foundation of China(11202106)the Natural Science Foundation from the Education Bureau of Anhui Province(KJ2011A135)
文摘数据中的数据转折点一般代表某种变化或者异常，因此数据转折点准确查找对于数据分析和处理来说具有重要的作用和意义，在气象，水文，金融，故障诊断等领域有广泛的应用。目前数据转折点的主要检测方法有Mann—Kendall算法，Cumulative Sum Charts（CUSUM）算法，最小方差法，小波变换法等。为了克服以上方法中的准确性和局限性问题，通过不断地变换尺度的方法来缩小计算范围；通过直线拟合的方法不断获取数据中的变化趋势。在比较分割后各小段数据的变化趋势，寻找趋势变化最大的数据段。在该数据段中将原来的尺度缩小为原来的一半，继续进行变化趋势的对比，直至数据长度变为2，最终逼近并找出原始数据中的转折点。通过多种类型的数据对该方法验证，说明了该方法的有效性和准确性。
基金Supported by the National Natural Science Foundation of China(No.11071205)the Natural Foundation of Zhejiang Province (No.Y6110502)
文摘A class of singularly perturbed problem of third order equation with two para-meters is studied. Using singular perturbation method, the structure of solutions to the problem is discussed in three different cases about two small parameters. The asymptotic solutions to the problem are given. The structure of solutions and the different limit behaviors are revealed. And the solutions are compared with the exact solutions to the equation in which the coefficients are constants and a relatively more perfect result is obtained.
文摘We construct a positive type difference scheme for a singularly perturbed boundary value problem with a turning point. It's proved that this scheme is the second order convergence, uniformly in ? , to the solution of the singularly perturbed B. V.P. Numerical examples are provided.
文摘针对可见光图像弱小目标检测中的背景抑制和去噪问题,提出了奇异值分解(Singular Value Decomposition,SVD)带通滤波新方法.首先分析了图像奇异值与目标、噪声和图像背景的关系,结果表明奇异值的高序部分更多地反映图像噪声,中序部分更多地反映目标性质,而低序部分更多地反映图像背景.以此为依据提出了SVD-Ⅰ型和SVD-Ⅱ型两种带通滤波器,并给出了奇异值曲线转折点法和门限准则法两种滤波器参数确定方法.实验表明SVD带通滤波能有效抑制图像背景,去除噪声,进而提高弱小目标的信噪比.
