共查询到20条相似文献,搜索用时 15 毫秒
1.
2.
Jian Wang Tuan Le Vang A. A. Pyrkin S. A. Kolyubin A. A. Bobtsov 《Automation and Remote Control》2018,79(12):2159-2168
We consider the problem of identifying unknown nonstationary piecewise linear parameters for a linear regression model. A new algorithm is proposed that allows, in the case of a number of assumptions on the elements of the regressor, to provide an estimate of unknown non-stationary parameters. We analyze in detail the case with two unknown parameters, which makes it possible to understand the main idea of the proposed approach. We also consider a generalization to the case of an arbitrary number of parameters. We give an example of computer simulation that illustrates the efficiency of the proposed approach. 相似文献
3.
最小二乘法分段直线拟合 总被引:14,自引:2,他引:12
曲线拟合是图像分析中非常重要的描述符号。最常用的曲线拟合方法是最小二乘法,然而一般的最小二乘法有一定的局限性,已经有不少学者对其进行了一些改进。进一步对最小二乘法进行改进,提出一种新的分段直线拟合算法来代替多项式曲线拟合,以达到简化数学模型的建立和减少计算的目的,使其能够更好地对点序列进行拟合。 相似文献
4.
Nonlinear classification models have better classification performance than the linear classifiers. However, for many nonlinear classification problems, piecewise-linear discriminant functions can approximate nonlinear discriminant functions. In this study, we combine the algorithm of data envelopment analysis (DEA) with classification information, and propose a novel DEA-based classifier to construct a piecewise-linear discriminant function, in this classifier, the nonnegative conditions of DEA model are loosed and class information is added; Finally, experiments are performed using a UCI data set to demonstrate the accuracy and efficiency of the proposed model. 相似文献
5.
6.
《Neural Networks, IEEE Transactions on》2006,17(5):1101-1115
We present an efficient feature selection algorithm for the general regression problem, which utilizes a piecewise linear orthonormal least squares (OLS) procedure. The algorithm 1) determines an appropriate piecewise linear network (PLN) model for the given data set, 2) applies the OLS procedure to the PLN model, and 3) searches for useful feature subsets using a floating search algorithm. The floating search prevents the “nesting effect.” The proposed algorithm is computationally very efficient because only one data pass is required. Several examples are given to demonstrate the effectiveness of the proposed algorithm. 相似文献
7.
Approximating points by piecewise linear functions is an intensively researched topic in computational geometry. In this paper, we study, based on the uniform error metric, an array of variations of this problem in 2-D and 3-D, including points with weights, approximation with violations, using step functions or more generally piecewise linear functions. We consider both the min-# (i.e., given an error tolerance ?, minimizing the size k of the approximating function) and min-? (i.e., given a size k of the approximating function, minimizing the error tolerance ?) versions of the problems. Our algorithms either improve on the previously best-known solutions or are the first known results for the respective problems. Our approaches are based on interesting geometric observations and algorithmic techniques. Some data structures we develop are of independent interest and may find other applications. 相似文献
8.
提出了一种新的基于混沌理论的分组密码算法,把128比特的明文加密为128比特的密文.整个加密过程包含了8个轮变换,每一个轮变换由替换变换、移位变换和置换变换3部分组成.所有的轮密钥都由128位的比特流K和由分段线性映射产生的128比特随机二进制序列导出.理论与实验分析表明该算法克服了一些纯混沌密码系统的固有缺陷,具有较高的性能. 相似文献
9.
A piecewise linear projection algorithm, based on kohonen's Self-Organizing Map, is presented. Using this new algorithm, neural network is able to adapt its neural weights to accommodate with input space, while obtaining reduced 2-dimensional subspaces at each neural node. After completion of learning process, first project input data into their corresponding 2-D subspaces, then project all data in the 2-D subspaces into a reference 2-D subspace defined by a reference neural node. By piecewise linear projection, we can more easily deal with large data sets than other projection algorithms like Sammon's nonlinear mapping (NLM). There is no need to re-compute all the input data to interpolate new input data to the 2-D output space. 相似文献
10.
有理三角曲面的分片线性逼近在参数曲面的求交、绘制等方面有着重要应用.已有研究主要采用曲面的二阶导矢界来估计逼近误差, 而有理曲面的导矢界估计是一项困难的工作.为解决上述问题, 利用齐次坐标, 给出了一种定义域为任意三角形的有理三角曲面的分片线性逼近算法.该算法有效地避免了有理三角曲面的导矢界估计, 并且离散段数可先验地给出.此外, 通过重新参数化技术来缩小有理三角Bézier曲面的权因子之间的比值, 进一步提高了算法的效率. 相似文献
11.
12.
Conventional image skeletonization techniques implicitly assume the pixel level connectivity. However, noise inside the object regions destroys the
connectivity and exhibits sparseness in the image. We present a skeletonization algorithm designed for these kinds of sparse shapes. The skeletons are
produced quickly by using three operations. First, initial skeleton nodes are selected by farthest point sampling with circles containing the maximum effective
information. A skeleton graph of these nodes is imposed via inheriting the neighborhood of their associated pixels, followed by an edge collapse operation.
Then a skeleton tting process based on feature-preserving Laplacian smoothing is applied. Finally, a re nement step is proposed to further improve the
quality of the skeleton and deal with noise or different local shape scales. Numerous experiments demonstrate that our algorithm can effectively handle
several disconnected shapes in an image simultaneously, and generate more faithful skeletons for shapes with intersections or different local scales than
classic methods. 相似文献
13.
This article considers the cost dependent construction of linear and piecewise linear classifiers. Classical learning algorithms from the fields of artificial neural networks and machine learning consider either no costs at all or allow only costs that depend on the classes of the examples that are used for learning. In contrast to class dependent costs, we consider costs that are example, i.e. feature and class dependent. We present a cost sensitive extension of a modified version of the well-known perceptron algorithm that can also be applied in cases, where the classes are linearly non-separable. We also present an extended version of the hybrid learning algorithm DIPOL, that can be applied in the case of linear non-separability, multi-modal class distributions, and multi-class learning problems. We show that the consideration of example dependent costs is a true extension of class dependent costs. The approach is general and can be extended to other neural network architectures like multi-layer perceptrons and radial basis function networks. 相似文献
14.
15.
Gregory Gutin Arash Rafiey Stefan Szeider Anders Yeo 《Theory of Computing Systems》2007,41(3):521-538
A linear arrangement (LA) is an assignment of distinct integers to the vertices of a graph. The cost of an LA is the sum
of lengths of the edges of the graph, where the length of an edge is defined as the absolute value of the difference of the
integers assigned to its ends. For many application one hopes to find an LA with small cost. However, it is a classical
NP-complete problem to decide whether a given graph G admits an LA of cost bounded by a given integer. Since every edge of
G contributes at least one to the cost of any LA, the problem becomes trivially fixed-parameter tractable (FPT) if parameterized
by the upper bound of the cost. Fernau asked whether the problem remains FPT if parameterized by the upper bound of the cost
minus the number of edges of the given graph; thus whether the problem is FPT "parameterized above guaranteed value." We
answer this question positively by deriving an algorithm which decides in time O(m + n + 5.88k) whether a given graph with m edges and n vertices admits an LA of cost at most m + k (the algorithm computes such an LA
if it exists). Our algorithm is based on a procedure which generates a problem kernel of linear size in linear time for a
connected graph G. We also prove that more general parameterized LA problems stated by Serna and Thilikos are not FPT, unless
P = NP. 相似文献
16.
基于矢量斜率的分段线性拟合* 总被引:4,自引:0,他引:4
介绍了用统计矢量斜率进行平面数据点分段线性拟合的算法.对于欲拟合的一系列平面数据点,一般是有先后顺序的.首先给出了矢量斜率的定义,然后计算每个平面数据点的统计矢量斜率,根据各点矢量斜率值接近的情况,将数据点分割成组,拟合各组数据形成线段,把各线段首尾连接起来就得到了平面数据点的分段线性拟合.定义的矢量斜率包含大小和方向两方面信息,主值区间为(-4~+4),它在主值区间的变化与角度在(-180°~180°)区间中的变化一一对应,且它们的关系曲线有很好的线性度.使用传统斜率进行分段线性拟合,存在斜率值与角度的关系曲线线性度差、斜率取值有时趋向无穷等问题,这些问题影响了拟合的精度,并限制了算法的使用范围.矢量斜率克服了上述问题,从而提供了拟合曲线的质量,且算法可适用于任意曲线.算法时间复杂度为线性. 相似文献
17.
18.
Gang Tao 《Asian journal of control》2013,15(4):933-943
A piecewise linear system consists of a set of linear time‐invariant (LTI) subsystems, with a switching sequence specifying an active subsystem at each time instant. This paper studies the adaptive control problem of single‐input, single‐output (SISO) piecewise linear systems. By employing the knowledge of the time instant indicator functions of system parameter switches, a new controller structure parametrization is proposed for the development of a stable adaptive control scheme with reduced modeling error in the estimation error signal used for parameter adaptive laws. This key feature is achieved by the new control scheme's ability to avoid a major parameter swapping term in the error model, with the help of indicator functions whose knowledge is available in many applications. A direct state feedback model reference adaptive control (MRAC) scheme is presented for such systems to achieve closed‐loop signal boundedness and small output tracking error in the mean square sense, under the usual slow system parameter switching condition. Simulation results on linearized NASA GTM models are presented to demonstrate the effectiveness of the proposed scheme. 相似文献
19.
20.