Spatio-temporal EEG source localization using simulated annealing

The estimation of multiple dipole parameters in spatio-temporal source modeling (STSM) of electroencephalographic (EEG) data is a difficult nonlinear optimization problem due to multiple local minima in the cost function. A straightforward iterative optimization approach to such a problem is very susceptible to being trapped in a local minimum, thereby resulting in incorrect estimates of the dipole parameters. Here, the authors present and evaluate a more robust optimization approach based on the simulated annealing algorithm. The complexity of this approach for the STSM problem was reduced by separating the dipole parameters into linear (moment) and nonlinear (location) components. The effectiveness of the proposed method and its superiority over the traditional nonlinear simplex technique in escaping local minima were tested and demonstrated through computer simulations. The annealing algorithm and its implementation for multidipole estimation are also discussed. The authors found the simulated annealing approach to be 7-31% more effective than the simplex method at converging to the true global minimum for a number of different kinds of three-dipole problems simulated in this work. In addition, the computational cost of the proposed approach was only marginally higher than its simplex counterpart. The annealing method also yielded similar solutions irrespective of the initial guesses used. The proposed simulated annealing method is an attractive alternative to the simplex method that is currently more common in dipole estimation applications     

Synthesis of Resonator Filters With Arbitrary Topology Using Hybrid Method

This paper presents a new synthesis method for resonator filters of arbitrary topology using an evolutionary hybrid method. This method consists of a Levenberg-Marquardt algorithm for a local optimizer and genetic algorithm for a global optimizer, respectively. Unlike the conventional hybrid method in which the local optimization is performed after finding appropriate initial values from global optimization, the local optimizer in the proposed method is used as a genetic-algorithm operator to prevent trapping in local minima of the cost function. This method can provide fast convergence and good accuracy to find the final solution from initial population generated by a random number and the known value for the filters with stringent requirements. In addition, multiple coupling matrices to meet the given requirement can be obtained from the initial population based on a random number. Resonator filters with asymmetric eight-pole configurations for single and dual passbands are synthesized using the current method for validation. Excellent agreement between the response computed from characteristic polynomials and the response computed from couplings is obtained from the proposed method.     

K插值单纯形法核极限学习机的研究

针对核极限学习机高斯核函数参数选优难,影响学习机训练收敛速度和分类精度的问题,该文提出一种K插值单纯形法的核极限学习机算法。把核极限学习机的训练看作一个无约束优化问题,在训练迭代过程中,用Nelder-Mead单纯形法搜索高斯核函数的最优核参数,提高所提算法的分类精度。引入K插值为Nelder-Mead单纯形法提供合适的初值,减少单纯形法的迭代次数,提高了新算法的训练收敛效率。通过在UCI数据集上的仿真实验并与其它算法比较,新算法具有更快的收敛速度和更高的分类精度。     

基于改进单纯形算法的DOA估计

利用最大似然估计获得信号的来波方向，其统计性能要比其他算法优越，但由于该方法需要对多维参数进行优化，从而导致较大的计算量，针对该问题文中提出基于改进单纯形算法的来波方向（DOA）估计。首先利用阵列输出的协方差矩阵对来波方向进行粗略估计，并以该估计值为重心构造初始单纯形，由于待估计的参数都有一定的取值范围，所以文中通过定义罚函数，将有约束的优化问题转化为无约束的优化问题，最后结合罚函数和改进单纯形算法进行DOA估计，计算机仿真结果验证了该方法的正确性和有效性。     

Optimization Using a Modified Second-Order Approach With Evolutionary Enhancement

An optimization algorithm is presented which effectively combines the desirable characteristics of both gradient descent and evolutionary computation into a single robust algorithm. The method uses a population-based gradient approximation which allows it to recognize surface behavior on both large and small scales. By adjusting the population radius between iterations, the algorithm is able to escape local minima by shifting its focus onto global trends rather than local behavior. The algorithm is compared experimentally with existing methods over a set of relevant test cases, and each method is ranked on the basis of both reliability and rate of convergence. For each case, the algorithm is shown to outperform other methods in terms of both measures of performance, truly making it the best of both worlds.      

基于多元优化算法的路径规划

本文提出了一种基于多元优化算法和贝塞尔曲线的启发式智能路径规划方法.该方法通过用贝塞尔曲线描述路径的方法把路径规划问题转化成最优化问题.然后,使用多元优化算法来寻找最优的贝塞尔曲线控制点以获得最优路径.多元优化算法智能搜素个体协同合作交替的对解空间进行全局、局部迭代搜索以找到最优解.多元优化算法的搜索个体（元）按照分工不同可以分为全局元和局部元.在一次迭代中,全局元首先探索整个解空间以找出更优的潜在解区域.然后,局部元在各个潜在解区域进行局部开采以改善解质量.可见,搜索元具有分工不同的多元化特点,多元优化算法也就因此而得名.分工不同的搜索元之间高效的沟通和合作保证了多元优化算法的良好性能.为了评估多元优化算法的性能,我们基于标准测试地图比较了多元优化算法与其它三种经典启发式智能路径规划算法.结果表明,我们提出的方法在最优性,稳定性和有效性上方面优于其它方法.     

An inspection-maintenance model for systems with multiple competing processes

In some applications, the failure rate of the system depends not only on the time, but also upon the status of the system, such as vibration level, efficiency, number of random shocks on the system, etc., which causes degradation. In this paper, we develop a generalized condition-based maintenance model subject to multiple competing failure processes including two degradation processes, and random shocks. An average long-run maintenance cost rate function is derived based on the expressions for the degradation paths & cumulative shock damage, which are measurable. A geometric sequence is employed to develop the inter-inspection sequence. Upon inspection, one needs to decide whether to perform a maintenance, such as preventive or corrective, or to do nothing. The preventive maintenance thresholds for degradation processes & inspection sequences are the decision variables of the proposed model. We also present an algorithm based on the Nelder-Mead downhill simplex method to calculate the optimum policy that minimizes the average long-run maintenance cost rate. Numerical examples are given to illustrate the results using the optimization algorithm.     

改进RANSAC算法在多光谱图像匹配中的应用

为了提高多光谱图像匹配的速度和精度,提出一种改进的随机抽样一致性(RANSAC)算法。针对传统RANSAC算法迭代次数多、运行效率低、单应性矩阵模型精度低等问题,在采用SIFT算法完成初始特征匹配的基础上,从合理减少样本集中元素个数以提高局内点在样本中所占的比例以及采用预检验快速舍弃不合理的初始参数模型等方面对RANSAC算法进行改进,从而极大地减少了算法的迭代次数,提高了算法的运行效率和估计精度。实验结果表明,所提改进算法不仅提高了图像匹配的精度,而且在处理相同数据的前提下,其所用时间不足传统RANSAC算法的60%,有效减少了算法的运行时间,提高了算法效率。     

基于加权主动形状建模的人脸特征定位方法

主动形状建模是面部特征定位和人脸识别等模式识别领域中常用的一种方法。然而,由于受到初始情况、光照等诸多因素的影响,主动形状建模经常会陷入最优化过程中的局部最小问题,从而导致其性能下降。该文在传统主动形状模型基础上,提出了一种加权主动形状建模的方法,该方法可以有效地解决上述局部最小问题,并且更好地捕捉局部点的特征信息,从而更精确地进行面部特征定位。最后通过实验验证了上面的结论。     

Sparse signal reconstruction from limited data using FOCUSS: are-weighted minimum norm algorithm

We present a nonparametric algorithm for finding localized energy solutions from limited data. The problem we address is underdetermined, and no prior knowledge of the shape of the region on which the solution is nonzero is assumed. Termed the FOcal Underdetermined System Solver (FOCUSS), the algorithm has two integral parts: a low-resolution initial estimate of the real signal and the iteration process that refines the initial estimate to the final localized energy solution. The iterations are based on weighted norm minimization of the dependent variable with the weights being a function of the preceding iterative solutions. The algorithm is presented as a general estimation tool usable across different applications. A detailed analysis laying the theoretical foundation for the algorithm is given and includes proofs of global and local convergence and a derivation of the rate of convergence. A view of the algorithm as a novel optimization method which combines desirable characteristics of both classical optimization and learning-based algorithms is provided. Mathematical results on conditions for uniqueness of sparse solutions are also given. Applications of the algorithm are illustrated on problems in direction-of-arrival (DOA) estimation and neuromagnetic imaging     

基于极坐标中蛇模型的类圆目标轮廓提取技术研究

提出了转化到极坐标中的蛇模型.通过把蛇模型转化到极坐标中,使轮廓的候选点得以更有序的排列.由于采用了动态规划法并在整个能量空间中搜索能量泛函的极值,算法对能量泛函的局部极值有较强的鲁棒性.所提出的模型不需要确定初始轮廓,可以用非迭代方法直接求解.与传统的动态规划法和贪婪算法进行了比较实验.结果表明,所提出的算法对极坐标中极点的位置不是很敏感.     

实现运动估计算法的优化技术

针对H.263编码器,通过研究软件实现提高运动估计算法效率的优化技术,提出一种基于位标识的重复搜索点的识别方法,其思想是根据运动矢量各向非均匀分布特性设置模板内各搜索点顺序,并通过实验验证了该优化方案的有效性。其恢复图像的整像素和半像素搜索点数均有较大的减少,平均每帧的压缩时间大大缩短,而且平均每帧的编码码长也有不同程度的缩短。     

一种改进的稀疏度自适应匹配追踪算法

压缩感知理论是一种充分利用信号稀疏性或可压缩性的全新信号获取和处理理论。针对未知稀疏度信号重构,提出了一种改进的稀疏度自适应匹配追踪算法。该算法首先利用一种基于原子匹配测试的方法得到信号稀疏度的初始估计,然后在稀疏度自适应匹配追踪(SAMP)框架下采用变步长分阶段思想实现稀疏度的逼近,在初始阶段利用大步长实现稀疏度的快速粗接近,以提高收敛速度,在随后的迭代中逐渐减小步长,实现稀疏度的精逼近,最终实现信号的精确重构。理论分析和仿真结果表明,该算法在一定程度上解决了SAMP算法在大稀疏度条件下运算量较大以及固定步长导致的欠估计和过估计问题,较好地实现了未知稀疏度信号的精确重建,并且重建性能和重建效率均优于现有的同类算法。      

The application of mean field theory to image motion estimation

Previously, Markov random field (MRF) model-based techniques have been proposed for image motion estimation. Since motion estimation is usually an ill-posed problem, various constraints are needed to obtain a unique and stable solution. The main advantage of the MRF approach is its capacity to incorporate such constraints, for instance, motion continuity within an object and motion discontinuity at the boundaries between objects. In the MRF approach, motion estimation is often formulated as an optimization problem, and two frequently used optimization methods are simulated annealing (SA) and iterative-conditional mode (ICM). Although the SA is theoretically optimal in the sense of finding the global optimum, it usually takes many iterations to converge. The ICM, on the other hand, converges quickly, but its results are often unsatisfactory due to its "hard decision" nature. Previously, the authors have applied the mean field theory to image segmentation and image restoration problems. It provides results nearly as good as SA but with much faster convergence. The present paper shows how the mean field theory can be applied to MRF model-based motion estimation. This approach is demonstrated on both synthetic and real-world images, where it produced good motion estimates.     

HAMMER: hierarchical attribute matching mechanism for elastic registration

A new approach is presented for elastic registration of medical images, and is applied to magnetic resonance images of the brain. Experimental results demonstrate very high accuracy in superposition of images from different subjects. There are two major novelties in the proposed algorithm. First, it uses an attribute vector, i.e., a set of geometric moment invariants (GMIs) that are defined on each voxel in an image and are calculated from the tissue maps, to reflect the underlying anatomy at different scales. The attribute vector, if rich enough, can distinguish between different parts of an image, which helps establish anatomical correspondences in the deformation procedure; it also helps reduce local minima, by reducing ambiguity in potential matches. This is a fundamental deviation of our method, referred to as the hierarchical attribute matching mechanism for elastic registration (HAMMER), from other volumetric deformation methods, which are typically based on maximizing image similarity. Second, in order to avoid being trapped by local minima, i.e., suboptimal poor matches, HAMMER uses a successive approximation of the energy function being optimized by lower dimensional smooth energy functions, which are constructed to have significantly fewer local minima. This is achieved by hierarchically selecting the driving features that have distinct attribute vectors, thus, drastically reducing ambiguity in finding correspondence. A number of experiments demonstrate that the proposed algorithm results in accurate superposition of image data from individuals with significant anatomical differences.     

非线性回归模型参数估计的区间分析方法

现有很多方法都属局部搜索方法,不能保证得到问题的全部全局最优解,而基于区间分析的区间全局优化算法则能在给定精度范围内求出问题的全部全局最优解,并能给出满足要求的包含最优解的任意小区间。基于此,给出了非线性回归模型参数估计的区间全局优化算法,论述了算法求解问题的基本思想、解算步骤、基本算法和加速工具等,并将其应用于非线性回归模型参数估计中,仿真实验结果验证了所给算法的可行性和有效性．     

A comparative study of graph-based, eikonal, and monodomain simulations for the estimation of cardiac activation times

The bidomain and monodomain equations are well established as the standard set of equations for the simulation of cardiac electrophysiological behavior. However, the computational cost of detailed bidomain/monodomain simulations limits their applicability in scenarios where a large number of simulations needs to be performed (e.g., parameter estimation). In this study, we present a graph-based method, which relies on point-to-point path finding to estimate activation times for single points in cardiac tissue with minimal computational costs. To validate our approach, activation times are compared to monodomain simulation results for an anatomically based rabbit ventricular model, incorporating realistic fiber orientation and conduction heterogeneities. Differences in activation times between the graph-based method and monodomain results are less than 10% of the total activation time, and computational performance is orders of magnitude faster with the proposed method when calculating activation times at single points. These results suggest that the graph-based method is well suited for estimating activation times when the need for fast performance justifies a limited loss of accuracy.     

Generalized Simulation-Based Posynomial Model Generation for Analog Integrated Circuits

This paper presents a new method to automatically generate posynomial symbolic expressions for the performance characteristics of analog integrated circuits. Both the coefficient set as well as the exponent set of the posynomial expression, for some performance as a function of the design variables, are determined based on performance data extracted from SPICE simulation results with device-level accuracy. Techniques from design of experiments (DOE) are used to generate an optimal set of sample points to fit the models. We will prove that the optimization problem formulated for this problem typically corresponds to a non-convex problem, but has no local minima. The presented method is capable of generating posynomial performance expressions for both linear and nonlinear circuits and circuit characteristics. This approach allows to automatically generate an accurate sizing model that can be used to compose a geometric program that fully describes the analog circuit sizing problem. The automatic generation avoids the time-consuming nature of hand-crafted analytic model generation. Experimental results illustrate the capabilities of the presented modeling technique.     

自适应局部邻域特征点提取和匹配的点云配准

点云配准是三维重建的关键技术之一。针对点云匹配中迭代最近点算法(ICP)速率低、对初始位置要求高的问题,提出了一种基于自适应局部邻域特征点提取和匹配的点云配准方法。首先根据局部表面变化因子与平均变化因子的大小关系,自适应地提取特征点;其次利用快速点特征直方图（FPFH）综合描述每个特征点的局部信息,结合随机抽样一致性（RANSAC）算法实现粗配准;最后根据得到的初始变换矩阵和基于特征点的ICP算法实现精配准。对斯坦福数据集、含噪声的点云以及场景点云进行配准实验,实验结果表明:所提出的特征点提取算法能高效地提取点云的特征;相比于其他特征点检测方法,所提方法在粗配准中的配准精度和配准速度更高,且抗噪性能更好;与ICP算法相比,基于文中特征点的ICP算法在斯坦福数据集和场景点云中的配准速度提升了约10倍,在含噪声的点云中,能根据所提取的特征点高效地进行配准。该研究为提高三维重建和目标识别的匹配效率提供了一种高效的方法。