基于混合特征的非刚性点阵配准算法

提出一种基于混合特征的非刚性点阵配准算法.该算法包含了对应关系评估与空间变换更新两个相互交替的步骤.首先定义了两个特征描述法用于描述两个点阵之间的全局和局部几何结构特征差异,随后合并这两个特征描述法建立一个基于混合特征的能量优化方程.该能量优化方程可以利用线性分配技术进行求解,同时可以灵活地选择使用最小化全局结构特征差异或最小化局部结构特征差异来评估两个点阵之间的对应关系.为了增强前述两个步骤之间的协调性,我们利用能量权重调节在整个配准过程中控制能量优化从最小化局部结构特征差异逐步转变为最小化全局结构特征差异,同时控制用于空间变换的薄板样条函数（Thin plate spline）的更新从刚性变换逐步转变为非刚性变换.我们在二维轮廓配准、三维轮廓配准、序列图像配准和图像特征点配准下对本文算法进行了各项性能测试,同时也与当前8种流行算法进行了性能比较.本文算法展现了卓越的非刚性配准性能,并在大部分实验中超越了当前的相关算法.     

特征级融合方法及其在医学图像方面的应用

特征级融合是图像处理领域的重要内容之一,从特征变换和特征选择两个角度对特征级融合方法及其在医学图像处理中的应用进行较为全面的总结。以医学图像特征级融合为例介绍其基本流程,将特征级融合方法分为特征变换和特征选择。在特征变换方面,按照方法是否线性可分和是否监督学习两个维度进行划分总结,详细介绍线性变换方法中奇异值分解法和非负矩阵分解法,非线性变换中的人工神经网、支持向量机和模糊集五种方法及其在医学图像方面的应用。总结特征选择方法的整体流程,分别从搜索策略和评价准则的角度对方法进行分类总结,详细介绍粗糙集和遗传算法两种随机搜索算法的改进及其在医学图像方面的应用,并阐述停止条件和结果验证过程。对特征级融合方法的发展方向进行总结和展望。特征级融合算法的总结对其进一步发展具有积极意义。     

非线性系统广义模糊跟踪控制

研究一种给定 H∞ 模型参考跟踪特性的非线性系统的 T-S 广义模糊跟踪控制问题. 通过把一般的模糊模型等价变换到广义模糊模型, 引入了松弛变量, 并基于线性矩阵不等式 (LMI) 给出了新的 H∞ 跟踪控制器设计方法. 控制器参数在一组线性矩阵不等式中同时得到求解, 避免了原有方法分步求解的困难, 方法简单易行且具有鲁棒性. 两个算例表明了结论的有效性.     

具有线性结构的弹性函数非线性度的新上界

讨论了具有线性结构的弹性函数的两个指标:沃什谱和非线性度,得到了具有线性结构的布尔函数的一些性质.利用沃尔什变换和汉明重量的方法,发现了:如果V是n元布尔函数,f(x)的线性结构,那么得到f(x)的沃尔什变换在为零这一事实,同时得到了一个布尔函数没有k(k≥0)维线性结构的充分条件.最后,利用以上结果推出了具有线性结构的弹性函数的非线性度的上界表达式.     

具有多非线性和多未建模动态系统的鲁棒绝对稳定性

研究了同时具有多个扇形非线性环节和多个未建模动态的多变量系统的鲁棒绝对 稳定性.用带有Popov乘子的线性分式变换模型对线性和非线性不确定性进行了统一处理. 得到了系统的鲁棒绝对稳定性判据,并将这一判据的计算化为凸优化问题,最后给出了计 算示例.     

基于池的无监督线性回归主动学习

在许多现实的机器学习应用场景中, 获取大量未标注的数据是很容易的, 但标注过程需要花费大量的时间和经济成本. 因此, 在这种情况下, 需要选择一些最有价值的样本进行标注, 从而只利用较少的标注数据就能训练出较好的机器学习模型. 目前, 主动学习(Active learning)已广泛应用于解决这种场景下的问题. 但是, 大多数现有的主动学习方法都是基于有监督场景: 能够从少量带标签的样本中训练初始模型, 基于模型查询新的样本, 然后迭代更新模型. 无监督情况下的主动学习却很少有人考虑, 即在不知道任何标签信息的情况下最佳地选择要标注的初始训练样本. 这种场景下, 主动学习问题变得更加困难, 因为无法利用任何标签信息. 针对这一场景, 本文研究了基于池的无监督线性回归问题, 提出了一种新的主动学习方法, 该方法同时考虑了信息性、代表性和多样性这三个标准. 本文在3个不同的线性回归模型(岭回归、LASSO (Least absolute shrinkage and selection operator)和线性支持向量回归)和来自不同应用领域的12个数据集上进行了广泛的实验, 验证了其有效性.     

一种基于变分相关向量机的特征选择和分类结合方法

相关向量机(Relevance vector machine, RVM)是一种函数形式等价于支持向量机(Support vector machine, SVM)的全概率模型,利用变分贝叶斯(Variational Bayesian, VB)方法求解的RVM可以给出所有参数的后验分布. 进一步,通过对样本所在原始特征空间的稀疏化,基于线性核的RVM可以在分类的同时实现对原始特征的线性选择. 本文在传统VB-RVM的基础上提出一种特征选择和分类结合方法. 该方法采用Probit模型将分类问题与回归问题有机地结合起来, 同时,通过对特征维的幂变换扩展,不仅在分类时增加了样本的信息量, 可以构造非线性分类面,而且实现了非线性特征选择的功能. 通过对仿真数据和实测数据分别进行实验, 证明了该特征选择和分类结合方法的实用性和有效性.     

基于多模态特征子集选择性集成建模的磨机负荷参数预测方法

如何融合球磨机系统研磨过程所产生的多模态机械信号构建磨机负荷参数预测(Mill load parameter forecasting, MLPF)模型是当前研究的热点. 针对上述问题, 本文提出一种基于多模态特征子集选择性集成(Selective ensemble, SEN)建模的MLPF方法. 首先, 对多模态机械信号进行时频域变换得到高维频谱数据; 接着, 采用相关系数法和互信息法对多模态频谱进行线性和非线性特征子集的自适应选择; 最后, 采用优化和加权算法对上述特征子集的候选子模型进行自适应地选择与合并, 得到基于SEN机制的MLPF模型. 采用磨矿过程实验球磨机的机械信号仿真验证了所提方法的有效性.     

具有QoS保证的流媒体业务服务组合算法*

针对采用服务组合方式实现流媒体业务提供过程中的服务路径选择问题,从物理资源和逻辑资源两个角度出发,选择时延、带宽、丢包率和服务实例可用服务能力作为参数,建立了多约束归一化线性模型;同时,根据模型特点,采用线性整数规划迭代求解,提高了处理效率。仿真实验证明,该模型和算法能够有效地保障业务服务质量,并具备良好的负载均衡效果。     

基因选择的0-1规划模型和算法

基因选择是基因表达数据分析中的重点问题.然而现有的方法没有综合考虑样本不平衡和基因间的相互作用。借鉴聚类的验证技术提出了基因选择的0-1规划模型,同时考虑了样本不平衡和基因间的相互作用。进一步根据0-1规划模型的特点,给出了基于贪心思想的启发式算法来求解所提出的优化问题。在3个真实的基因表达数据上对提出的方法进行测试并与两个对照的方法比较,结果表明所提出模型和算法是有效的且稳健的。     

Response modeling methodology (RMM)—maximum likelihood estimation procedures

Response modeling methodology (RMM) is a new approach for empirical modeling. ML estimation procedures for the RMM model are developed. For relational modeling, the RMM model is estimated in two phases. In the first phase, the structure of the linear predictor (LP) is determined and its parameters estimated. This is accomplished by combining canonical correlation analysis with linear regression analysis. The former procedure is used to estimate coefficients in a Taylor series approximation to an unspecified response transformation. Canonical scores are then used in the latter procedure as response values in order to estimate coefficients of the LP. In the second phase, the parameters of the RMM model are estimated via ML, given the LP estimated earlier. For modeling random variation, it is assumed that the LP is constant and a new simple percentile-based estimating procedure is developed. The new estimation procedures are demonstrated for some published data.     

Controllability and observability covariance matrices for the analysis and order reduction of stable nonlinear systems

This paper presents a framework for nonlinear systems analysis that is based upon controllability and observability covariance matrices. These matrices are introduced in the paper and it is shown that gramians for linear systems form special cases of the covariance matrices. The covariance matrices can be transformed via a balancing-like transformation and nonlinearity measures are defined based upon these transformed covariance matrices. Subsequently, the covariance matrices are used for reduction of the nonlinear model. It is shown that the model reduction procedure reduces to balanced model truncation for linear systems for impulse inputs. Furthermore, it is also shown that several model reduction procedures that were developed by other researchers, and assumed to be independent from one another, are related. The findings are illustrated with an example.     

Functional linear regression after spline transformation

Functional linear regression has been widely used to model the relationship between a scalar response and functional predictors. If the original data do not satisfy the linear assumption, an intuitive solution is to perform some transformation such that transformed data will be linearly related. The problem of finding such transformations has been rather neglected in the development of functional data analysis tools. In this paper, we consider transformation on the response variable in functional linear regression and propose a nonparametric transformation model in which we use spline functions to construct the transformation function. The functional regression coefficients are then estimated by an innovative procedure called mixed data canonical correlation analysis (MDCCA). MDCCA is analogous to the canonical correlation analysis between two multivariate samples, but is between a multivariate sample and a set of functional data. Here, we apply the MDCCA to the projection of the transformation function on the B-spline space and the functional predictors. We then show that our estimates agree with the regularized functional least squares estimate for the transformation model subject to a scale multiplication. The dimension of the space of spline transformations can be determined by a model selection principle. Typically, a very small number of B-spline knots is needed. Real and simulation data examples are further presented to demonstrate the value of this approach.     

Computational aspects of robust estimators for linear regressions

This paper presents estimation procedures for some robust regression methods: the Bounded-Influence estimator for both a single linear equation (Krasker and Welsch, 1982) and a linear simultaneous equation model (Krasker and Welsch, 1985); the linear version of the Huber estimator for both a single equation (Huber, 1973, 1981) and a simultaneous equations model.The procedures are written in the RATS econometric language, which is widely available on microcomputers and mainframes.     

Two-view multibody structure-and-motion with outliers through model selection

Multibody structure-and-motion (MSaM) is the problem in establishing the multiple-view geometry of several views of a 3D scene taken at different times, where the scene consists of multiple rigid objects moving relative to each other. We examine the case of two views. The setting is the following: Given are a set of corresponding image points in two images, which originate from an unknown number of moving scene objects, each giving rise to a motion model. Furthermore, the measurement noise is unknown, and there are a number of gross errors, which are outliers to all models. The task is to find an optimal set of motion models for the measurements. It is solved through Monte-Carlo sampling, careful statistical analysis of the sampled set of motion models, and simultaneous selection of multiple motion models to best explain the measurements. The framework is not restricted to any particular model selection mechanism because it is developed from a Bayesian viewpoint: different model selection criteria are seen as different priors for the set of moving objects, which allow one to bias the selection procedure for different purposes.     

A variational integrators approach to second order modeling and identification of linear mechanical systems

The theory of variational integration provides a systematic procedure to discretize the equations of motion of a mechanical system, preserving key properties of the continuous time flow. The discrete-time model obtained by variational integration theory inherits structural conditions which in general are not guaranteed under general discretization procedures. We discuss a simple class of variational integrators for linear second order mechanical systems and propose a constrained identification technique which employs simple linear transformation formulas to recover the continuous time parameters of the system from the discrete-time identified model. We test this approach on a simulated eight degrees of freedom system and show that the new procedure leads to an accurate identification of the continuous-time parameters of second-order mechanical systems starting from discrete measured data.     

Simultaneous pole placement of M discrete-time plants using a M-periodic controller

A generic procedure for designing a M-periodic controller (sought in the controller canonical form) for the simultaneous placement of the closed-loop poles of M (=2,3,4,...) discrete, time-invariant plants is presented. The procedure is a two-stage one: first, a set of M simultaneous, linear, polynomial equations, arising out of the M given plants and the corresponding desired closed-loop pole locations, are solved via a generalized Sylvester matrix approach to obtain a set of (M+1) intermediate polynomials; and next, the controller parameters are obtained solving another set of simultaneous, linear polynomial equations that involve the above intermediate polynomials. Thus, both the computational steps are linear algebraic in nature. A list of the isolated plant configurations for which solutions do not exist is given. An example illustrates the procedure.     

Reduced-order modelling of linear discrete-time systems via continued-fraction expansion of a z transfer function about z = 1 and z = a alternately

A new time-domain procedure is suggested for obtaining reduced-order models of linear time-invariant discrete-time systems. The procedure is based on presenting a new form of continued-fraction expansion (CFE) about z = 1 and z = a alternately, and deriving a realization form for the CFE. An algorithm is presented for obtaining the new CFE of the z transfer function of a linear discrete-time system from its state-space model directly, without having to determine the corresponding rational z transfer function. Also presented is a systematic approach to deriving two similarity transformation matrices: one is used to transform a state-space model from a general form to the CFE canonical form, and the other is used to transform a state-space model from the phase-variable canonical form to the CFE canonical form. Finally, an approximate aggregation matrix is constructed to relate the state vector of the original system to that of a reduced model obtained by the present method. The proposed procedure is illustrated with examples.     

A new approach for EEG signal classification of schizophrenic and control participants

This paper is concerned with a two stage procedure for analysis and classification of electroencephalogram (EEG) signals for twenty schizophrenic patients and twenty age-matched control participants. For each case, 20 channels of EEG are recorded. First, the more informative channels are selected using the mutual information techniques. Then, genetic programming is employed to select the best features from the selected channels. Several features including autoregressive model parameters, band power and fractal dimension are used for the purpose of classification. Both linear discriminant analysis (LDA) and adaptive boosting (Adaboost) are trained using tenfold cross validation to classify the reduced feature set and a classification accuracy of 85.90% and 91.94% is obtained by LDA and Adaboost, respectively. Another interesting observation from the channel selection procedure is that most of the selected channels are located in the prefrontal and temporal lobes confirming neuropsychological and neuroanatomical findings. The results obtained by the proposed approach are compared with a one stage procedure, the principal component analysis (PCA)-based feature selection, utilizing only 100 features selected from all channels. It is illustrated that the two stage procedure consisting of channel selection followed by feature reduction gives a more enhanced results in an efficient computation time.     

Complete identification of some non-linear closed-loop systems†

The problem of complete identification of some non-linear closed-loop systems is dealt with in this paper. The basic system consists of two linear parts and a nonlinear one between them. Two special cases of this are produced by removing each one of the two linear parts. The nonlinear character of the systems is determined by static testing. Dynamic testing (.e. using entire input and output, signals) allows the linear transfer functions to be determined. Two procedures are suggested corresponding, one to one, to the two special cases. A theoretical procedure is also developed for the full basic system.