We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized data points sampled with noise from a parameterized manifold, the local geometry of the manifold i...We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized data points sampled with noise from a parameterized manifold, the local geometry of the manifold is learned by constructing an approximation for the tangent space at each point, and those tangent spaces are then aligned to give the global coordinates of the data points with respect to the underlying manifold. We also present an error analysis of our algorithm showing that reconstruction errors can be quite small in some cases. We illustrate our algorithm using curves and surfaces both in 2D/3D Euclidean spaces and higher dimensional Euclidean spaces. We also address several theoretical and algorithmic issues for further research and improvements.展开更多
Image feature optimization is an important means to deal with high-dimensional image data in image semantic understanding and its applications. We formulate image feature optimization as the establishment of a mapping...Image feature optimization is an important means to deal with high-dimensional image data in image semantic understanding and its applications. We formulate image feature optimization as the establishment of a mapping between highand low-dimensional space via a five-tuple model. Nonlinear dimensionality reduction based on manifold learning provides a feasible way for solving such a problem. We propose a novel globular neighborhood based locally linear embedding (GNLLE) algorithm using neighborhood update and an incremental neighbor search scheme, which not only can handle sparse datasets but also has strong anti-noise capability and good topological stability. Given that the distance measure adopted in nonlinear dimensionality reduction is usually based on pairwise similarity calculation, we also present a globular neighborhood and path clustering based locally linear embedding (GNPCLLE) algorithm based on path-based clustering. Due to its full consideration of correlations between image data, GNPCLLE can eliminate the distortion of the overall topological structure within the dataset on the manifold. Experimental results on two image sets show the effectiveness and efficiency of the proposed algorithms.展开更多
We present our recent work on both linear and nonlinear data reduction methods and algorithms: for the linear case we discuss results on structure analysis of SVD of columnpartitioned matrices and sparse low-rank appr...We present our recent work on both linear and nonlinear data reduction methods and algorithms: for the linear case we discuss results on structure analysis of SVD of columnpartitioned matrices and sparse low-rank approximation; for the nonlinear case we investigate methods for nonlinear dimensionality reduction and manifold learning. The problems we address have attracted great deal of interest in data mining and machine learning.展开更多
In this study,a k-nearest neighbor(kNN)method based on nonlinear directional dimension reduction is applied to gas-bearing reservoir prediction.The kNN method can select the most relevant training samples to establish...In this study,a k-nearest neighbor(kNN)method based on nonlinear directional dimension reduction is applied to gas-bearing reservoir prediction.The kNN method can select the most relevant training samples to establish a local model according to feature similarities.However,the kNN method cannot extract gas-sensitive attributes and faces dimension problems.The features important to gas-bearing reservoir prediction could not be the main features of the samples.Thus,linear dimension reduction methods,such as principal component analysis,fail to extract relevant features.We thus implemented dimension reduction using a fully connected artifi cial neural network(ANN)with proper architecture.This not only increased the separability of the samples but also maintained the samples’inherent distribution characteristics.Moreover,using the kNN to classify samples after the ANN dimension reduction is also equivalent to replacing the deep structure of the ANN,which is considered to have a linear classifi cation function.When applied to actual data,our method extracted gas-bearing sensitive features from seismic data to a certain extent.The prediction results can characterize gas-bearing reservoirs accurately in a limited scope.展开更多
Nonlinear dynamic response of nanomechanical resonator is of very important characteristics in its application. Two categories of the tension-dominant and curvaturedominant nonlinearities are analyzed. The dynamic non...Nonlinear dynamic response of nanomechanical resonator is of very important characteristics in its application. Two categories of the tension-dominant and curvaturedominant nonlinearities are analyzed. The dynamic nonlinearity of four beam structures of nanomechanical resonator is quantitatively studied via a dimensional analysis approach. The dimensional analysis shows that for the nanomechanical resonator of tension-dominant nonlinearity, its dynamic nonlinearity decreases monotonically with increasing axial loading and increases monotonically with the increasing aspect ratio of length to thickness; the dynamic nonlinearity can only result in the hardening effects. However, for the nanomechanical resonator of the curvature-dominant nonlinearity, its dynamic nonlinearity is only dependent on axial loading. Compared with the tension-dominant nonlinearity, the curvature-dominant nonlinearity increases monotonically with increasing axial loading; its dynamic nonlinearity展开更多
The (2+1)-dimension nonlocal nonlinear Schrödinger (NLS) equation with the self-induced parity-time symmetric potential is introduced, which provides spatially two-dimensional analogues of the nonlocal NLS equati...The (2+1)-dimension nonlocal nonlinear Schrödinger (NLS) equation with the self-induced parity-time symmetric potential is introduced, which provides spatially two-dimensional analogues of the nonlocal NLS equation introduced by Ablowitz et al. [Phys. Rev. Lett. 110 (2013) 064105]. General periodic solutions are derived by the bilinear method. These periodic solutions behave as growing and decaying periodic line waves arising from the constant background and decaying back to the constant background again. By taking long wave limits of the obtained periodic solutions, rogue waves are obtained. It is also shown that these line rogue waves arise from the constant background with a line profile and disappear into the constant background again in the plane.展开更多
An event-triggered scheme is proposed to solve the problems of robust guaranteed cost control for a class of two-dimensional(2-D)discrete-time systems.Firstly,an eventtriggered scheme is proposed for 2-D discrete-time...An event-triggered scheme is proposed to solve the problems of robust guaranteed cost control for a class of two-dimensional(2-D)discrete-time systems.Firstly,an eventtriggered scheme is proposed for 2-D discrete-time systems with parameter uncertainties and sector nonlinearities.Then,according to the Lyapunov functional method,the sufficient conditions for the existence of event-triggered robust guaranteed cost controller for 2-D discrete-time systems with parameter uncertainties and sector nonlinearities are given.Furthermore,based on the sufficient conditions and the linear matrix inequality(LMI)technique,the problem of designing event-triggered robust guaranteed cost controller is transformed into a feasible solution problem of LMI.Finally,a numerical example is given to demonstrate that,under the proposed event-triggered robust guaranteed cost control,the closed-loop system is asymptotically stable and fewer communication resources are occupied.展开更多
The concise and informative representation of hyperspectral imagery is achieved via the introduced diffusion geometric coordinates derived from nonlinear dimension reduction maps - diffusion maps. The huge-volume high...The concise and informative representation of hyperspectral imagery is achieved via the introduced diffusion geometric coordinates derived from nonlinear dimension reduction maps - diffusion maps. The huge-volume high- dimensional spectral measurements are organized by the affinity graph where each node in this graph only connects to its local neighbors and each edge in this graph represents local similarity information. By normalizing the affinity graph appropriately, the diffusion operator of the underlying hyperspectral imagery is well-defined, which means that the Markov random walk can be simulated on the hyperspectral imagery. Therefore, the diffusion geometric coordinates, derived from the eigenfunctions and the associated eigenvalues of the diffusion operator, can capture the intrinsic geometric information of the hyperspectral imagery well, which gives more enhanced representation results than traditional linear methods, such as principal component analysis based methods. For large-scale full scene hyperspectral imagery, by exploiting the backbone approach, the computation complexity and the memory requirements are acceptable. Experiments also show that selecting suitable symmetrization normalization techniques while forming the diffusion operator is important to hyperspectral imagery representation.展开更多
Over the past few years,nonlinear manifold learning has been widely exploited in data analysis and machine learning.This paper presents a novel manifold learning algorithm,named atlas compatibility transformation(ACT)...Over the past few years,nonlinear manifold learning has been widely exploited in data analysis and machine learning.This paper presents a novel manifold learning algorithm,named atlas compatibility transformation(ACT),It solves two problems which correspond to two key points in the manifold definition:how to chart a given manifold and how to align the patches to a global coordinate space based on compatibility.For the first problem,we divide the manifold into maximal linear patch(MLP) based on normal vector field of the manifold.For the second problem,we align patches into an optimal global system by solving a generalized eigenvalue problem.Compared with the traditional method,the ACT could deal with noise datasets and fragment datasets.Moreover,the mappings between high dimensional space and low dimensional space are given.Experiments on both synthetic data and real-world data indicate the effection of the proposed algorithm.展开更多
As modern weapons and equipment undergo increasing levels of informatization,intelligence,and networking,the topology and traffic characteristics of battlefield data networks built with tactical data links are becomin...As modern weapons and equipment undergo increasing levels of informatization,intelligence,and networking,the topology and traffic characteristics of battlefield data networks built with tactical data links are becoming progressively complex.In this paper,we employ a traffic matrix to model the tactical data link network.We propose a method that utilizes the Maximum Variance Unfolding(MVU)algorithm to conduct nonlinear dimensionality reduction analysis on high-dimensional open network traffic matrix datasets.This approach introduces novel ideas and methods for future applications,including traffic prediction and anomaly analysis in real battlefield network environments.展开更多
In the present paper we study the maximum dissipative extension of Schrodingeroperator.introduce the generalized indefinite metvic space and get the representation ofmaximum dissipative extension of Schrodinger operat...In the present paper we study the maximum dissipative extension of Schrodingeroperator.introduce the generalized indefinite metvic space and get the representation ofmaximum dissipative extension of Schrodinger operator in natural boundary space.make preparation for the further study longtime chaotic behaxior of infinite dimensiondynamics system in nonlinear Schrodinger equation.展开更多
This paper investigates a real version of a (2 + 1) dimensional nonlinear Schr?dinger equation through adoption of Painlevé test by means of which the (2 + 1) dimensional nonlinear Schr?dinger equation is studied...This paper investigates a real version of a (2 + 1) dimensional nonlinear Schr?dinger equation through adoption of Painlevé test by means of which the (2 + 1) dimensional nonlinear Schr?dinger equation is studied according to the Weiss et al. method and Kruskal’s simplification algorithms. According to Painlevé test, it is found that the number of arbitrary functions required for explaining the Cauchy-Kovalevskaya theorem exist. Finally, the associated B?cklund transformation and bilinear form is directly obtained from the Painlevé test.展开更多
Dynamic transient responses of rotating twisted plate under the air-blast loading and step loading respectively considering the geometric nonlinear relationships are investigated using classical shallow shell theory.B...Dynamic transient responses of rotating twisted plate under the air-blast loading and step loading respectively considering the geometric nonlinear relationships are investigated using classical shallow shell theory.By applying energy principle,a novel high dimensional nonlinear dynamic system of the rotating cantilever twisted plate is derived for the first time.The use of variable mode functions by polynomial functions according to the twist angles and geometric of the plate makes it more accurate to describe the dynamic system than that using the classic cantilever beam functions and the free-free beam functions.The comparison researches are carried out between the present results and other literatures to validate present model,formulation and computer process.Equations of motion describing the transient high dimensional nonlinear dynamic response are reduced to a four degree of freedom dynamic system which expressed by out-plane displacement.The effects of twisted angle,stagger angle,rotation speed,load intensity and viscous damping on nonlinear dynamic transient responses of the twisted plate have been investigated.It’s important to note that although the homogeneous and isotropic material is applied here,it might be helpful for laminated composite,functionally graded material as long as the equivalent material parameters are obtained.展开更多
An improved model for numerically predicting nonlinear wave forces exerted on an offshore structure is pro- posed.In a previous work[9],the authors presented a model for the same purpose with an open boundary condi- t...An improved model for numerically predicting nonlinear wave forces exerted on an offshore structure is pro- posed.In a previous work[9],the authors presented a model for the same purpose with an open boundary condi- tion imposed,where the wave celerity has been defined constant.Generally,the value of wave celerity is time-de- pendent and varying with spatial location.With the present model the wave celerity is evaluated by an upwind dif- ference scheme,which enables the method to be extended to conditions of variable finite water depth,where the value of wave celerity varies with time as the wave approaches the offshore structure.The finite difference method incorporated with the time-stepping technique in time domain developed here makes the numerical evolution effec- tive and stable.Computational examples on interactions between a surface-piercing vertical cylinder and a solitary wave or a cnoidal wave train demonstrates the validity of this program.展开更多
A new manifold learning method, called incremental alignment method （IAM）, is proposed for nonlinear dimensionality reduction of high dimensional data with intrinsic low dimensionality. The main idea is to increment...A new manifold learning method, called incremental alignment method （IAM）, is proposed for nonlinear dimensionality reduction of high dimensional data with intrinsic low dimensionality. The main idea is to incrementally align low-dimensional coordinates of input data patch-by-patch to iteratively generate the representation of the entire data.set. The method consists of two major steps, the incremental step and the alignment step. The incremental step incrementally searches neighborhood patch to be aligned in the next step, and the alignment step iteratively aligns the low-dimensional coordinates of the neighborhood patch searched to generate the embeddings of the entire dataset. Compared with the existing manifold learning methods, the proposed method dominates in several aspects： high efficiency, easy out-of-sample extension, well metric-preserving, and averting of the local minima issue. All these properties are supported by a series of experiments performed on the synthetic and real-life datasets. In addition, the computational complexity of the proposed method is analyzed, and its efficiency is theoretically argued and experimentally demonstrated.展开更多
The Rao-Blackwellized Particle Filter （RBPF） is widely used for high dimensional nonlinear sys- tems, often with a linear Gaussian substructure. However, the RBPF is just a specific method in the class of Rao-Blackw...The Rao-Blackwellized Particle Filter （RBPF） is widely used for high dimensional nonlinear sys- tems, often with a linear Gaussian substructure. However, the RBPF is just a specific method in the class of Rao-Blackwellized Filtering （RBF）. This paper analyzes the recursive structure of the RBF from a more gen- eral perspective. The research starts from a general system model and studies the interconnected relation- ships between the two subspaces during the iterations. The results illustrate the working mechanisms of the RBF with an extensible framework for easily building Rao-Blackwellized algorithms with common nonlinear filters. Several examples are given to illustrate how to build new filters using this framework.展开更多
文摘We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized data points sampled with noise from a parameterized manifold, the local geometry of the manifold is learned by constructing an approximation for the tangent space at each point, and those tangent spaces are then aligned to give the global coordinates of the data points with respect to the underlying manifold. We also present an error analysis of our algorithm showing that reconstruction errors can be quite small in some cases. We illustrate our algorithm using curves and surfaces both in 2D/3D Euclidean spaces and higher dimensional Euclidean spaces. We also address several theoretical and algorithmic issues for further research and improvements.
基金Project (No 2008AA01Z132) supported by the National High-Tech Research and Development Program of China
文摘Image feature optimization is an important means to deal with high-dimensional image data in image semantic understanding and its applications. We formulate image feature optimization as the establishment of a mapping between highand low-dimensional space via a five-tuple model. Nonlinear dimensionality reduction based on manifold learning provides a feasible way for solving such a problem. We propose a novel globular neighborhood based locally linear embedding (GNLLE) algorithm using neighborhood update and an incremental neighbor search scheme, which not only can handle sparse datasets but also has strong anti-noise capability and good topological stability. Given that the distance measure adopted in nonlinear dimensionality reduction is usually based on pairwise similarity calculation, we also present a globular neighborhood and path clustering based locally linear embedding (GNPCLLE) algorithm based on path-based clustering. Due to its full consideration of correlations between image data, GNPCLLE can eliminate the distortion of the overall topological structure within the dataset on the manifold. Experimental results on two image sets show the effectiveness and efficiency of the proposed algorithms.
基金This work was supported in part by the Special Funds for Major State Basic Research Projectsthe National Natural Science Foundation of China(Grants No.60372033 and 9901936)NSF CCR9901986,DMS 0311800.
文摘We present our recent work on both linear and nonlinear data reduction methods and algorithms: for the linear case we discuss results on structure analysis of SVD of columnpartitioned matrices and sparse low-rank approximation; for the nonlinear case we investigate methods for nonlinear dimensionality reduction and manifold learning. The problems we address have attracted great deal of interest in data mining and machine learning.
基金supported by the National Key R&D Program of China(No.2018YFA0702504)the National Natural Science Foundation of China(No.42174152 and No.41974140)the Strategic Cooperation Technology Projects of CNPC and CUPB(No.ZLZX2020-03).
文摘In this study,a k-nearest neighbor(kNN)method based on nonlinear directional dimension reduction is applied to gas-bearing reservoir prediction.The kNN method can select the most relevant training samples to establish a local model according to feature similarities.However,the kNN method cannot extract gas-sensitive attributes and faces dimension problems.The features important to gas-bearing reservoir prediction could not be the main features of the samples.Thus,linear dimension reduction methods,such as principal component analysis,fail to extract relevant features.We thus implemented dimension reduction using a fully connected artifi cial neural network(ANN)with proper architecture.This not only increased the separability of the samples but also maintained the samples’inherent distribution characteristics.Moreover,using the kNN to classify samples after the ANN dimension reduction is also equivalent to replacing the deep structure of the ANN,which is considered to have a linear classifi cation function.When applied to actual data,our method extracted gas-bearing sensitive features from seismic data to a certain extent.The prediction results can characterize gas-bearing reservoirs accurately in a limited scope.
基金supported by the National Natural Science Foundation of China (10721202 and 11023001)the Chinese Academy of Sciences (KJCX2-EW-L03)
文摘Nonlinear dynamic response of nanomechanical resonator is of very important characteristics in its application. Two categories of the tension-dominant and curvaturedominant nonlinearities are analyzed. The dynamic nonlinearity of four beam structures of nanomechanical resonator is quantitatively studied via a dimensional analysis approach. The dimensional analysis shows that for the nanomechanical resonator of tension-dominant nonlinearity, its dynamic nonlinearity decreases monotonically with increasing axial loading and increases monotonically with the increasing aspect ratio of length to thickness; the dynamic nonlinearity can only result in the hardening effects. However, for the nanomechanical resonator of the curvature-dominant nonlinearity, its dynamic nonlinearity is only dependent on axial loading. Compared with the tension-dominant nonlinearity, the curvature-dominant nonlinearity increases monotonically with increasing axial loading; its dynamic nonlinearity
基金Supported by the National Natural Science Foundation of China under Grant Nos 11271211,11275072 and 11435005the Ningbo Natural Science Foundation under Grant No 2015A610159+1 种基金the Opening Project of Zhejiang Provincial Top Key Discipline of Physics Sciences in Ningbo University under Grant No xkzw11502the K.C.Wong Magna Fund in Ningbo University
文摘The (2+1)-dimension nonlocal nonlinear Schrödinger (NLS) equation with the self-induced parity-time symmetric potential is introduced, which provides spatially two-dimensional analogues of the nonlocal NLS equation introduced by Ablowitz et al. [Phys. Rev. Lett. 110 (2013) 064105]. General periodic solutions are derived by the bilinear method. These periodic solutions behave as growing and decaying periodic line waves arising from the constant background and decaying back to the constant background again. By taking long wave limits of the obtained periodic solutions, rogue waves are obtained. It is also shown that these line rogue waves arise from the constant background with a line profile and disappear into the constant background again in the plane.
基金supported by the National Natural Science Foundation of China(61573129 U1804147)+2 种基金the Innovative Scientists and Technicians Team of Henan Provincial High Education(20IRTSTHN019)the Innovative Scientists and Technicians Team of Henan Polytechnic University(T2019-2 T2017-1)
文摘An event-triggered scheme is proposed to solve the problems of robust guaranteed cost control for a class of two-dimensional(2-D)discrete-time systems.Firstly,an eventtriggered scheme is proposed for 2-D discrete-time systems with parameter uncertainties and sector nonlinearities.Then,according to the Lyapunov functional method,the sufficient conditions for the existence of event-triggered robust guaranteed cost controller for 2-D discrete-time systems with parameter uncertainties and sector nonlinearities are given.Furthermore,based on the sufficient conditions and the linear matrix inequality(LMI)technique,the problem of designing event-triggered robust guaranteed cost controller is transformed into a feasible solution problem of LMI.Finally,a numerical example is given to demonstrate that,under the proposed event-triggered robust guaranteed cost control,the closed-loop system is asymptotically stable and fewer communication resources are occupied.
基金The National Key Technologies R & D Program during the 11th Five-Year Plan Period (No.2006BAB15B01)
文摘The concise and informative representation of hyperspectral imagery is achieved via the introduced diffusion geometric coordinates derived from nonlinear dimension reduction maps - diffusion maps. The huge-volume high- dimensional spectral measurements are organized by the affinity graph where each node in this graph only connects to its local neighbors and each edge in this graph represents local similarity information. By normalizing the affinity graph appropriately, the diffusion operator of the underlying hyperspectral imagery is well-defined, which means that the Markov random walk can be simulated on the hyperspectral imagery. Therefore, the diffusion geometric coordinates, derived from the eigenfunctions and the associated eigenvalues of the diffusion operator, can capture the intrinsic geometric information of the hyperspectral imagery well, which gives more enhanced representation results than traditional linear methods, such as principal component analysis based methods. For large-scale full scene hyperspectral imagery, by exploiting the backbone approach, the computation complexity and the memory requirements are acceptable. Experiments also show that selecting suitable symmetrization normalization techniques while forming the diffusion operator is important to hyperspectral imagery representation.
基金supported by National Natural Science Foundation of China(No.61171145)Shanghai Educational Development Fundation(No.12ZZ083)
文摘Over the past few years,nonlinear manifold learning has been widely exploited in data analysis and machine learning.This paper presents a novel manifold learning algorithm,named atlas compatibility transformation(ACT),It solves two problems which correspond to two key points in the manifold definition:how to chart a given manifold and how to align the patches to a global coordinate space based on compatibility.For the first problem,we divide the manifold into maximal linear patch(MLP) based on normal vector field of the manifold.For the second problem,we align patches into an optimal global system by solving a generalized eigenvalue problem.Compared with the traditional method,the ACT could deal with noise datasets and fragment datasets.Moreover,the mappings between high dimensional space and low dimensional space are given.Experiments on both synthetic data and real-world data indicate the effection of the proposed algorithm.
文摘As modern weapons and equipment undergo increasing levels of informatization,intelligence,and networking,the topology and traffic characteristics of battlefield data networks built with tactical data links are becoming progressively complex.In this paper,we employ a traffic matrix to model the tactical data link network.We propose a method that utilizes the Maximum Variance Unfolding(MVU)algorithm to conduct nonlinear dimensionality reduction analysis on high-dimensional open network traffic matrix datasets.This approach introduces novel ideas and methods for future applications,including traffic prediction and anomaly analysis in real battlefield network environments.
文摘In the present paper we study the maximum dissipative extension of Schrodingeroperator.introduce the generalized indefinite metvic space and get the representation ofmaximum dissipative extension of Schrodinger operator in natural boundary space.make preparation for the further study longtime chaotic behaxior of infinite dimensiondynamics system in nonlinear Schrodinger equation.
基金supported by the National Natural Science Foundation of China(grant No.11371361)the Innovation Team of Jiangsu Province hosted by China University of Mining and Technology(2014)the Key Discipline Construction by China University of Mining and Technology(Grant No.XZD 201602).
文摘This paper investigates a real version of a (2 + 1) dimensional nonlinear Schr?dinger equation through adoption of Painlevé test by means of which the (2 + 1) dimensional nonlinear Schr?dinger equation is studied according to the Weiss et al. method and Kruskal’s simplification algorithms. According to Painlevé test, it is found that the number of arbitrary functions required for explaining the Cauchy-Kovalevskaya theorem exist. Finally, the associated B?cklund transformation and bilinear form is directly obtained from the Painlevé test.
基金support of National Natural Science Foundation of China through grant Nos.11872127,11832002 and 11732005,Fundamental Research Program of Shenzhen Municipality No.JCYJ20160608153749600 and the Project of Highlevel Innovative Team Building Plan for Beijing Municipal Colleges and Universities No.IDHT20180513 and the project of Qin Xin Talents Cultivation Program,Beijing Information Science&Technology University QXTCP A201901.
文摘Dynamic transient responses of rotating twisted plate under the air-blast loading and step loading respectively considering the geometric nonlinear relationships are investigated using classical shallow shell theory.By applying energy principle,a novel high dimensional nonlinear dynamic system of the rotating cantilever twisted plate is derived for the first time.The use of variable mode functions by polynomial functions according to the twist angles and geometric of the plate makes it more accurate to describe the dynamic system than that using the classic cantilever beam functions and the free-free beam functions.The comparison researches are carried out between the present results and other literatures to validate present model,formulation and computer process.Equations of motion describing the transient high dimensional nonlinear dynamic response are reduced to a four degree of freedom dynamic system which expressed by out-plane displacement.The effects of twisted angle,stagger angle,rotation speed,load intensity and viscous damping on nonlinear dynamic transient responses of the twisted plate have been investigated.It’s important to note that although the homogeneous and isotropic material is applied here,it might be helpful for laminated composite,functionally graded material as long as the equivalent material parameters are obtained.
基金China National Sicence Foundation with Grant No.91870003
文摘An improved model for numerically predicting nonlinear wave forces exerted on an offshore structure is pro- posed.In a previous work[9],the authors presented a model for the same purpose with an open boundary condi- tion imposed,where the wave celerity has been defined constant.Generally,the value of wave celerity is time-de- pendent and varying with spatial location.With the present model the wave celerity is evaluated by an upwind dif- ference scheme,which enables the method to be extended to conditions of variable finite water depth,where the value of wave celerity varies with time as the wave approaches the offshore structure.The finite difference method incorporated with the time-stepping technique in time domain developed here makes the numerical evolution effec- tive and stable.Computational examples on interactions between a surface-piercing vertical cylinder and a solitary wave or a cnoidal wave train demonstrates the validity of this program.
基金supported by the National Basic Research 973 Program of China under Grant No.2007CB311002the National Natural Science Foundation of China under Grant No.60905003
文摘A new manifold learning method, called incremental alignment method （IAM）, is proposed for nonlinear dimensionality reduction of high dimensional data with intrinsic low dimensionality. The main idea is to incrementally align low-dimensional coordinates of input data patch-by-patch to iteratively generate the representation of the entire data.set. The method consists of two major steps, the incremental step and the alignment step. The incremental step incrementally searches neighborhood patch to be aligned in the next step, and the alignment step iteratively aligns the low-dimensional coordinates of the neighborhood patch searched to generate the embeddings of the entire dataset. Compared with the existing manifold learning methods, the proposed method dominates in several aspects： high efficiency, easy out-of-sample extension, well metric-preserving, and averting of the local minima issue. All these properties are supported by a series of experiments performed on the synthetic and real-life datasets. In addition, the computational complexity of the proposed method is analyzed, and its efficiency is theoretically argued and experimentally demonstrated.
文摘The Rao-Blackwellized Particle Filter （RBPF） is widely used for high dimensional nonlinear sys- tems, often with a linear Gaussian substructure. However, the RBPF is just a specific method in the class of Rao-Blackwellized Filtering （RBF）. This paper analyzes the recursive structure of the RBF from a more gen- eral perspective. The research starts from a general system model and studies the interconnected relation- ships between the two subspaces during the iterations. The results illustrate the working mechanisms of the RBF with an extensible framework for easily building Rao-Blackwellized algorithms with common nonlinear filters. Several examples are given to illustrate how to build new filters using this framework.
