一种快速在线图形识别与规整化方法

1.引言因特网的迅速发展以及个人电脑的广泛使用促成了数量惊人的电子文档的出现。相比纸质资料,数字媒体内容更为丰富,形式更为多样化。随着计算机的介入,传统的设计方式发生了革命性的变革。设计工作不再是单纯的人为任务,而是一个人机不断交互的过程。因此,需要有一种新的技术和工具,能将传统设计方法与计算机辅助设计的优点有机地结合起     

A Bayesian approach to SAR imaging

We introduce a new approach using the Bayesian framework for the reconstruction of sparse Synthetic Aperture Radar (SAR) images. The algorithm, named SLIM, can be thought of as a sparse signal recovery algorithm with excellent sidelobe suppression and high resolution properties. For a given sparsity promoting prior, SLIM cyclically minimizes a regularized least square cost function. We show how SLIM can be used for SAR image reconstruction as well as SAR image enhancement. We evaluate the performance of SLIM by using realistically simulated complex-valued backscattered data from a backhoe vehicle. The numerical results show that SLIM can satisfactorily suppress the sidelobes and yield higher resolution than the conventional matched filter or delay-and-sum (DAS) approach. SLIM outperforms the widely used compressive sampling matching pursuit (CoSaMP) algorithm, which requires the delicate choice of user parameters. Compared with the recently developed iterative adaptive approach (IAA), which iteratively solves a weighted least squares problem, SLIM is much faster. Due to the computational complexity involved with SAR imaging, we show how SLIM can be made even more computationally efficient by utilizing the fast Fourier transform (FFT) and conjugate gradient (CG) method to carry out its computations. Furthermore, since SLIM is derived under the Bayesian model, the a posteriori distribution given by the algorithm provides us with a confident measure regarding the statistical properties of the SAR image pixels.     

Multiaccess in a Nonqueueing Mailbox Environment

A new and flexible solution to the problem of multiple users accessing a single resource, such as communication bandwidth or composite object in memory, is derived. The means of communication consists of sending and receiving messages in known locations (or equivalently, mailboxes without queueing). Any particular user is able to deposit, and hence destroy, previous messages in a mailbox. It is assumed that exclusive access to a mailbox is supplied by an underlying system. The major results of this paper are: 1) a simple tree-based algorithm that guarantees ? no user or group of users can conspire to prevent access by some other user to the resource; ? only one user accesses the resource at a time; ? if there are N users, an individual user is guaranteed access, when requested, to the resource in no more than N-1 turns; Knuth's solution [6] can delay a user up to 2** (N-1)-1 turns; 2) an extension of Dekker's algorithm (2 users) [2] that allows the relative rates of reservations for access to the resource to be proportional to a set of N integers. When a reservation is not being used by its ``owner,' it will be assigned to another contending request. The assignment is optimal for periodic requests.     

一种改进的正则图象

把正则图象的误差分成两部分：一部分为逼近误差，它是和原图象相关的确定型误差，另一部分为噪声传递误差，它是和噪声相关的随机型误差．通过正则图象代替原图象，求得逼近误差的近似值，然后将逼近误差近似值补给正则解，得到改进型正则解．对正则解以及逼近误差的计算，提出了快速算法，并有严密的理论推导．实验结果表明改进型正则图象的恢复效果优于传统正则解．在一敷的正则化方法中，可以借鉴本文提到的方法改进正则解．     

BC-AW协同过滤推荐算法研究

针对现有协同过滤算法普遍存在数据稀疏、可扩展性低、计算量大的缺点,提出一种基于BC-AW的协同过滤推荐算法,引入联合聚类（BlockClust,BC）和正则化迭代最小二乘法（Alternating least squares with Weighted regularization,AW）,首先对原评分矩阵进行用户—项目双维度的联合聚类,接着产生具有相同模式评分块的多个子矩阵,通过分析得出这些子矩阵规模远小于原评分矩阵,从而有效降低预测阶段的计算量.然后分别对每个子矩阵应用正则化迭代最小二乘法来预测子矩阵的未知评分,进而实现推荐.经仿真实验表明,本文算法与传统的协同过滤算法比较,能有效改善稀疏性、可扩展性和计算量的问题.     

Regularized shallow water equations and a new method of numerical simulation of the open channel flows

The regularized shallow water (RSW) equation system is proposed together with a central-difference algorithm for its numerical solution. The possibilities of the new computational model are demonstrated for a 1D dam break and Le-Veque’s perturbation tests, and for 2D asymmetric dam break test problems.     

结合评分习惯加权的稀疏矩阵插值推荐技术

插值估计可缓解推荐系统的稀疏问题,但其效果会影响预测性能。以logistic用户习惯（habit）评分加权改进Jaccard（HabJac）相似度量,并通过K近邻获得插补评分。进而,通过融合正则化奇异值分解（RSVD）技术提出了新的HISVD推荐算法,并获得最终预测。用户的习惯评分被定义为其出现频次最高的评分,并且logistic权值同评分与习惯评分之间的欧氏距离正相关。在四个现实数据集上的实验结果表明：a）HISVD在不同数据集上,最优情况下的参数比较稳定;b）HISVD在MAE和RSME指标上均超过了主流算法。     

A stochastic algorithm for makespan minimized multi-agent path planning in discrete space

Makespan minimized multi-agent path planning (MAPP) requires the minimization of the time taken by the slowest agents to reach its destination. The resulting minimax objective function is non-smooth and the search for an optimal solution in MAPP can be intractable. In this work, a maximum entropy function is adopted to approximate the minimax objective function. An iterative algorithm named probabilistic iterative makespan minimization (PIMM) is then proposed to approximate a makespan minimized MAPP solution by solving a sequence of computationally hard MAPP minimization problems with a linear objective function. At each iteration, a novel local search algorithm called probabilistic iterative path coordination (PIPC) is used to find a sufficiently good solution for each MAPP minimization problem. Experimental results from comparative studies with existing MAPP algorithms show that the proposed algorithm strikes a good tradeoff between the quality of the makespan minimized solution and the computational cost incurred.     

A joint antenna and user selection scheme for multiuser MIMO system

In this paper, we present a low-complexity algorithm for real-time joint user scheduling and receive antenna selection (JUSRAS) in multiuser MIMO systems. The computational complexity of exhaustive search for JUSRAS problem grows exponentially with the number of users and receives antennas. We apply binary particle swarm optimization (BPSO) to the joint user scheduling and receive antenna selection problem. In addition to applying the conventional BPSO to JUSRAS, we also present a specific improvement to this population-based heuristic algorithm; namely, we feed cyclically shifted initial population, so that the number of iterations until reaching an acceptable solution is reduced. The proposed BPSO for JUSRAS problem has a low computational complexity, and its effectiveness is verified through simulation results.     

Edit Propagation via Edge-Aware Filtering

This paper presents a novel framework for efficiently propagating the stroke-based user edits to the regions with similar colors and locations in high resolution images and videos.Our framework is based on the key observation that the edit propagation intrinsically can also be achieved by utilizing recently proposed edge-preserving filters.Therefore,instead of adopting the traditional global optimization which may involve a time-consuming solution,our algorithm propagates edits with the aid of the edge-preserve filters.Such a propagation scheme has low computational complexity and supports multiple kinds of strokes for more flexible user interactions.Further,our method can be easily and efficiently implemented in GPU.The experimental results demonstrate the efficiency and user-friendliness of our approach.     

Piecewise linear solution paths with application to direct weight optimization

Recently, pathfollowing algorithms for parametric optimization problems with piecewise linear solution paths have been developed within the field of regularized regression. This paper presents a generalization of these algorithms to a wider class of problems. It is shown that the approach can be applied to the nonparametric system identification method, Direct Weight Optimization (DWO), and be used to enhance the computational efficiency of this method. The most important design parameter in the DWO method is a parameter (λ) controlling the bias-variance trade-off, and the use of parametric optimization with piecewise linear solution paths means that the DWO estimates can be efficiently computed for all values of λ simultaneously. This allows for designing computationally attractive adaptive bandwidth selection algorithms. One such algorithm for DWO is proposed and demonstrated in two examples.     

Solving a generalized traveling salesperson problem with stochastic customers

In this paper, a probabilistic generalized traveling salesperson problem (PGTSP) is introduced to address several applications. In the PGTSP, each customer belongs to a cluster that consists of a set of customers. Whether or not any given customer will be present during actual operations is known a priori only probabilistically. The PGTSP seeks the minimum expected length tour to visit a subset of all customers such that the tour traverses each cluster at least once. If when implementing the tour it is revealed that there is no demand for service within the cluster to which a customer stop belongs, that stop will be skipped. An exact solution algorithm based on the integer L-shaped method and three tour construction-based heuristics for quickly solving this problem are described in the paper. Computational experiments were conducted to assess computational requirements and solution quality of the proposed solution techniques. These experiments show that the exact method is able to solve small- and moderate-size problems to optimality. In addition, one of the proposed heuristics (the MMI heuristic), in particular, gives good approximate solutions (often a few percent from optimal) in very reasonable computational time.     

基于SRank的社交网络影响力分析

针对社交网络中用户影响力的评价问题,提出了一种基于SRank的评价算法。基于从社交网络中收集的大规模数据集,结合最近社会学理论研究成果分析PageRank及其改进算法应用于此场景中的不足。在此基础上总结社交网络中信息传播的规律,将用户与社交网络的关系强度定义为用户的人缘值,用来表示用户作为粉丝的信息再传播能力。然后提出了一个通过预测用户信息传播能力大小来分析和度量用户影响力的SRank用户影响力模型。在同样的数据集下相对于PageRank及其改进算法,SRank用户影响力模型获得了更好的影响力预测结果。基于大规模数据的实验结果表明,提出的方法是较为有效的。     

On the use of particle swarm optimization for adaptive resource allocation in orthogonal frequency division multiple access systems with proportional rate constraints

Orthogonal frequency division multiple access (OFDMA) is a promising technique, which can provide high downlink capacity for future wireless systems. The total capacity of OFDMA can be maximized by adaptively assigning subchannels to the user with the best gain for that subchannel, with power subsequently distributed by water-filling algorithm. In this paper we have proposed the use of a customized particle swarm optimization (PSO) aided algorithm to allocate the subchannels. The PSO algorithm is population-based: a set of potential solutions evolves to approach a near-optimal solution for the problem under study. The customized algorithm works for discrete particle positions unlike the classical PSO algorithm which is valid for only continuous particle positions. It is shown that the proposed method obtains higher sum capacities as compared to that obtained by previous works, with comparable computational complexity.     

Goal-Oriented Adaptivity and Multilevel Preconditioning for the Poisson-Boltzmann Equation

In this article, we develop goal-oriented error indicators to drive adaptive refinement algorithms for the Poisson-Boltzmann equation. Empirical results for the solvation free energy linear functional demonstrate that goal-oriented indicators are not sufficient on their own to lead to a superior refinement algorithm. To remedy this, we propose a problem-specific marking strategy using the solvation free energy computed from the solution of the linear regularized Poisson-Boltzmann equation. The convergence of the solvation free energy using this marking strategy, combined with goal-oriented refinement, compares favorably to adaptive methods using an energy-based error indicator. Due to the use of adaptive mesh refinement, it is critical to use multilevel preconditioning in order to maintain optimal computational complexity. We use variants of the classical multigrid method, which can be viewed as generalizations of the hierarchical basis multigrid and Bramble-Pasciak-Xu (BPX) preconditioners.     

Partially observable Markov decision processes with imprecise parameters

This study extends the framework of partially observable Markov decision processes (POMDPs) to allow their parameters, i.e., the probability values in the state transition functions and the observation functions, to be imprecisely specified. It is shown that this extension can reduce the computational costs associated with the solution of these problems. First, the new framework, POMDPs with imprecise parameters (POMDPIPs), is formulated. We consider (1) the interval case, in which each parameter is imprecisely specified by an interval that indicates possible values of the parameter, and (2) the point-set case, in which each probability distribution is imprecisely specified by a set of possible distributions. Second, a new optimality criterion for POMDPIPs is introduced. As in POMDPs, the criterion is to regard a policy, i.e., an action-selection rule, as optimal if it maximizes the expected total reward. The expected total reward, however, cannot be calculated precisely in POMDPIPs, because of the parameter imprecision. Instead, we estimate the total reward by adopting arbitrary second-order beliefs, i.e., beliefs in the imprecisely specified state transition functions and observation functions. Although there are many possible choices for these second-order beliefs, we regard a policy as optimal as long as there is at least one of such choices with which the policy maximizes the total reward. Thus there can be multiple optimal policies for a POMDPIP. We regard these policies as equally optimal, and aim at obtaining one of them. By appropriately choosing which second-order beliefs to use in estimating the total reward, computational costs incurred in obtaining such an optimal policy can be reduced significantly. We provide an exact solution algorithm for POMDPIPs that does this efficiently. Third, the performance of such an optimal policy, as well as the computational complexity of the algorithm, are analyzed theoretically. Last, empirical studies show that our algorithm quickly obtains satisfactory policies to many POMDPIPs.     

Conflict-based pruning of a solution space within a constructive geometric constraint solver

The Computer-Aided Design field has developed sketching systems that automatically instantiate geometric objects from a rough sketch, annotated with dimensions and constraints input by the user. Geometric problems defined by constraints have an exponential number of solution instances in the number of geometric elements involved. The user is only interested in the intended solution that, besides fulfilling the geometric constraints, exhibits some additional properties. Metaheuristics have been successfully applied to solve this problem named as Root Identification Problem. However, these methods are very time-consuming because of the time required to evaluate every candidate solution. Pruning the search space is paramount to simplify the number of solution instances evaluated before finding the intended solution. In this work, we present an algorithm for pruning based on the detection of conflicts, i.e. patterns that drive to non-feasible solutions. Subsequent solutions will not be evaluated in case of matching a neighborhood corresponding to a previously detected conflicting pattern. The algorithm may be integrated in the evaluation phase of techniques that dynamically explore the search space, like metaheuristics, significantly improving the required computational time.     

A Parallel Method for Earth Mover’s Distance

We propose a new algorithm to approximate the Earth Mover’s distance (EMD). Our main idea is motivated by the theory of optimal transport, in which EMD can be reformulated as a familiar \(L_1\) type minimization. We use a regularization which gives us a unique solution for this \(L_1\) type problem. The new regularized minimization is very similar to problems which have been solved in the fields of compressed sensing and image processing, where several fast methods are available. In this paper, we adopt a primal-dual algorithm designed there, which uses very simple updates at each iteration and is shown to converge very rapidly. Several numerical examples are provided.     

A Kernel-Based Two-Class Classifier for Imbalanced Data Sets

Many kernel classifier construction algorithms adopt classification accuracy as performance metrics in model evaluation. Moreover, equal weighting is often applied to each data sample in parameter estimation. These modeling practices often become problematic if the data sets are imbalanced. We present a kernel classifier construction algorithm using orthogonal forward selection (OFS) in order to optimize the model generalization for imbalanced two-class data sets. This kernel classifier identification algorithm is based on a new regularized orthogonal weighted least squares (ROWLS) estimator and the model selection criterion of maximal leave-one-out area under curve (LOO-AUC) of the receiver operating characteristics (ROCs). It is shown that, owing to the orthogonalization procedure, the LOO-AUC can be calculated via an analytic formula based on the new regularized orthogonal weighted least squares parameter estimator, without actually splitting the estimation data set. The proposed algorithm can achieve minimal computational expense via a set of forward recursive updating formula in searching model terms with maximal incremental LOO-AUC value. Numerical examples are used to demonstrate the efficacy of the algorithm     

Confidence level solutions for stochastic programming

We propose an alternative approach to stochastic programming based on Monte-Carlo sampling and stochastic gradient optimization. The procedure is by essence probabilistic and the computed solution is a random variable. We propose a solution concept in which the probability that the random algorithm produces a solution with an expected objective value departing from the optimal one by more than ? is small enough. We derive complexity bounds on the number of iterations of this process. We show that by repeating the basic process on independent samples, one can significantly reduce the number of iterations.