Quantifying the neighborhood preservation of self-organizingfeature maps

It is shown that a topographic product P, first introduced in nonlinear dynamics, is an appropriate measure of the preservation or violation of neighborhood relations. It is sensitive to large-scale violations of the neighborhood ordering, but does not account for neighborhood ordering distortions caused by varying areal magnification factors. A vanishing value of the topographic product indicates a perfect neighborhood preservation; negative (positive) values indicate a too small (too large) output space dimensionality. In a simple example of maps from a 2D input space onto 1D, 2D, and 3D output spaces, it is demonstrated how the topographic product picks the correct output space dimensionality. In a second example, 19D speech data are mapped onto various output spaces and it is found that a 3D output space (instead of 2D) seems to be optimally suited to the data. This is an agreement with a recent speech recognition experiment on the same data set.     

Auto-SOM: recursive parameter estimation for guidance of self-organizing feature maps

An important technique for exploratory data analysis is to form a mapping from the high-dimensional data space to a low-dimensional representation space such that neighborhoods are preserved. A popular method for achieving this is Kohonen's self-organizing map (SOM) algorithm. However, in its original form, this requires the user to choose the values of several parameters heuristically to achieve good performance. Here we present the Auto-SOM, an algorithm that estimates the learning parameters during the training of SOMs automatically. The application of Auto-SOM provides the facility to avoid neighborhood violations up to a user-defined degree in either mapping direction. Auto-SOM consists of a Kalman filter implementation of the SOM coupled with a recursive parameter estimation method. The Kalman filter trains the neurons' weights with estimated learning coefficients so as to minimize the variance of the estimation error. The recursive parameter estimation method estimates the width of the neighborhood function by minimizing the prediction error variance of the Kalman filter. In addition, the "topographic function" is incorporated to measure neighborhood violations and prevent the map's converging to configurations with neighborhood violations. It is demonstrated that neighborhoods can be preserved in both mapping directions as desired for dimension-reducing applications. The development of neighborhood-preserving maps and their convergence behavior is demonstrated by three examples accounting for the basic applications of self-organizing feature maps.     

Growing a hypercubical output space in a self-organizing featuremap

Neural maps project data from an input space onto a neuron position in a (often lower dimensional) output space grid in a neighborhood preserving way, with neighboring neurons in the output space responding to neighboring data points in the input space. A map-learning algorithm can achieve an optimal neighborhood preservation only, if the output space topology roughly matches the effective structure of the data in the input space. We here present a growth algorithm, called the GSOM or growing self-organizing map, which enhances a widespread map self-organization process, Kohonen's self-organizing feature map (SOFM), by an adaptation of the output space grid during learning. The GSOM restricts the output space structure to the shape of a general hypercubical shape, with the overall dimensionality of the grid and its extensions along the different directions being subject of the adaptation. This constraint meets the demands of many larger information processing systems, of which the neural map can be a part. We apply our GSOM-algorithm to three examples, two of which involve real world data. Using recently developed methods for measuring the degree of neighborhood preservation in neural maps, we find the GSOM-algorithm to produce maps which preserve neighborhoods in a nearly optimal fashion.     

Geogames: Designing Location-Based Games from Classic Board Games

The traditional image of interactive entertainment - games that reduce players' physical involvement to moving a joy stick - is obsolete. Games researchers and designers are already integrating complex movement into games. Location-based games involve body movements beyond figural space - that is, beyond the space of computer screens and small 3D objects. They focus on locomotion in vista space, typically a single room or sports field, or in environmental space, such as a neighborhood or city. Several location-based games have been designed for environmental space using localization technologies such as GPS. Some are adaptations of popular computer games, and others are rather straightforward chase games. A third type of game - what we call challenging location-based games - combines the intellectual and strategic appeal of classic board games with the real-time locomotion and physical involvement of location-based games. Furthermore, a straightforward approach to the spatial mapping of classic board games doesn't work. Instead, we developed the Geogames framework, which uses search techniques to identify a single temporal parameter for balancing sportive versus strategic elements     

Relational generative topographic mapping

The generative topographic mapping (GTM) has been proposed as a statistical model to represent high-dimensional data by a distribution induced by a sparse lattice of points in a low-dimensional latent space, such that visualization, compression, and data inspection become possible. The formulation in terms of a generative statistical model has the benefit that relevant parameters of the model can be determined automatically based on an expectation maximization scheme. Further, the model offers a large flexibility such as a direct out-of-sample extension and the possibility to obtain different degrees of granularity of the visualization without the need of additional training. Original GTM is restricted to Euclidean data points in a given Euclidean vector space. Often, data are not explicitly embedded in a Euclidean vector space, rather pairwise dissimilarities of data can be computed, i.e. the relations between data points are given rather than the data vectors themselves. We propose a method which extends the GTM to relational data and which allows us to achieve a sparse representation of data characterized by pairwise dissimilarities, in latent space. The method, relational GTM, is demonstrated on several benchmarks.     

流形距离与压缩感知核稀疏投影的局部线性嵌入算法

流形学习算法的目的是发现嵌入在高维数据空间中的低维表示,现有的流形学习算法对邻域参数k和噪声比较敏感。针对此问题,文中提出一种流形距离与压缩感知核稀疏投影的局部线性嵌入算法,其核心思想是集成局部线性嵌入算法对高维流形结构数据的降维有效性与压缩感知核稀疏投影的强鉴别性,以实现高效有降噪流形学习。首先,在选择各样本点的近邻域时,采用流形距离代替欧氏距离度量数据间相似度的方法,创建能够正确反映流形内部结构的邻域图,解决以欧氏距离作为相似性度量时对邻域参数的敏感。其次,利用压缩感知核稀疏投影作为从高维观测空间到低维嵌入空间的映射,增强算法的鉴别性。最后,利用Matlab工具对实验数据集进行仿真,进一步验证所提算法的有效性。     

基于Delaunay三角剖分的多目标进化算法解集分布度评价指标

系统分析目前多目标进化算法(MOEAs)分布度评价指标的特点和不足,提出一种基于Delaunay三角剖分的分布度评价指标。该指标将基于邻域和基于距离的评价思想相结合,利用Delaunay三角网最近邻与邻接性的特点实现自主邻域划分。采用空间映射的方法,有效减少MOEAs解集非支配关系对种群分布度评价的影响。测试结果表明该指标能准确反映MOEAs解集的分布性。     

结合间接邻域的散乱点云三角网格曲面重构

对于非均匀散乱点云,多数基于区域生长方法的曲面重构往往容易出现孔洞等缺陷。针对该问题,在K邻域点集的基础上提出间接邻域点集的概念,对以点为生长对象进行区域生长的三角网格曲面重构方法进行了研究,实现三角网格曲面重构。以生长点的邻域点集为样点估算微切平面,将邻域点投影至该平面上,并按照右手定则、逆时针方向进行排序,通过拓扑正确性原则从点列中去除错误的连接点,优化局部网格,选择较好的连接点,实现网格曲面的区域生长。     

基于邻域保持的流形学习算法评价模型

应力函数和残差只适合于评价距离严格保持的流形学习算法,dy-dx表示法又是一个定性模型。虽然距离比例方差可以比较和评价大多数的流形学习算法,但其需要计算测地线距离,具有较高的计算复杂度。为此,提出一种基于邻域保持的流形学习算法定量评价模型,该模型仅仅需要确定两个空间中每个对象的k个近邻,并计算出每个点在低维空间中的近邻保持情况,不用计算测地线距离。理论分析表明,邻域保持模型的计算复杂度远远低于距离比例方差的复杂度。在三个数据集上比较了两个模型的性能,实验结果表明,利用邻域保持模型不但可以评价同一算法在不同邻域参数下的嵌入效果,而且可以在不同的流形学习算法之间进行比较,并且其评价流形学习算法的性能优于距离比例方差。     

Asymptotic level density in topological feature maps

The Kohonen algorithm entails a topology conserving mapping of an input pattern space X subsetR(n) characterized by an a priori probability distribution P(x), xinX, onto a discrete lattice of neurons r with virtual positions w(r)inX. Extending results obtained by Ritter (1991) the authors show in the one-dimensional case for an arbitrary monotonously decreasing neighborhood function h(|r-r'|) that the point density D(W(r)) of the virtual net is a polynomial function of the probability density P(x) with D(w(r))~P(alpha)(w(r)). Here the distortion exponent is given by alpha=(1+12R)/3(1+6R) and is determined by the normalized second moment R of the neighborhood function. A Gaussian neighborhood interaction is discussed and the analytical results are checked by means of computer simulations.     

Unsupervised image matching based on manifold alignment

This paper challenges the issue of automatic matching between two image sets with similar intrinsic structures and different appearances, especially when there is no prior correspondence. An unsupervised manifold alignment framework is proposed to establish correspondence between data sets by a mapping function in the mutual embedding space. We introduce a local similarity metric based on parameterized distance curves to represent the connection of one point with the rest of the manifold. A small set of valid feature pairs can be found without manual interactions by matching the distance curve of one manifold with the curve cluster of the other manifold. To avoid potential confusions in image matching, we propose an extended affine transformation to solve the nonrigid alignment in the embedding space. The comparatively tight alignments and the structure preservation can be obtained simultaneously. The point pairs with the minimum distance after alignment are viewed as the matchings. We apply manifold alignment to image set matching problems. The correspondence between image sets of different poses, illuminations, and identities can be established effectively by our approach.     

一种快速映射Isomap算法

传统的Isomap算法仅侧重于当前数据的分析,不能提供由高维空间到低维空间的快速直接映射,因此无法用于特征提取和高维数据检索.针对这一问题,文中提出一种基于Isornap的快速数据检索算法.该算法能够快速得到新样本的低维嵌入坐标,并基于此坐标检索与输入样本最相似的参考样本.在典型测试集上的实验结果表明,该算法在实现新样本到低维流形快速映射的同时,能较好保留样本的近邻关系.     

Constrained Self Organizing Maps for Data Clusters Visualization

High dimensional data visualization is one of the main tasks in the field of data mining and pattern recognition. The self organizing maps (SOM) is one of the topology visualizing tool that contains a set of neurons that gradually adapt to input data space by competitive learning and form clusters. The topology preservation of the SOM strongly depends on the learning process. Due to this limitation one cannot guarantee the convergence of the SOM in data sets with clusters of arbitrary shape. In this paper, we introduce Constrained SOM (CSOM), the new version of the SOM by modifying the learning algorithm. The idea is to introduce an adaptive constraint parameter to the learning process to improve the topology preservation and mapping quality of the basic SOM. The computational complexity of the CSOM is less than those with the SOM. The proposed algorithm is compared with similar topology preservation algorithms and the numerical results on eight small to large real-world data sets demonstrate the efficiency of the proposed algorithm.     

Three-way decision reduction in neighborhood systems

Rough set reduction has been used as an important preprocessing tool for pattern recognition, machine learning and data mining. As the classical Pawlak rough sets can just be used to evaluate categorical features, a neighborhood rough set model is introduced to deal with numerical data sets. Three-way decision theory proposed by Yao comes from Pawlak rough sets and probability rough sets for trading off different types of classification error in order to obtain a minimum cost ternary classifier. In this paper, we discuss reduction questions based on three-way decisions and neighborhood rough sets. First, the three-way decision reducts of positive region preservation, boundary region preservation and negative region preservation are introduced into the neighborhood rough set model. Second, three condition entropy measures are constructed based on three-way decision regions by considering variants of neighborhood classes. The monotonic principles of entropy measures are proved, from which we can obtain the heuristic reduction algorithms in neighborhood systems. Finally, the experimental results show that the three-way decision reduction approaches are effective feature selection techniques for addressing numerical data sets.     

On the correct convergence of the EM algorithm for Gaussian mixtures

It is well-known that the EM algorithm generally converges to a local maximum likelihood estimate. However, there have been many evidences to show that the EM algorithm can converge correctly to the true parameters as long as the overlap of Gaussians in the sample data is small enough. This paper studies this correct convergence problem asymptotically on the EM algorithm for Gaussian mixtures. It has been proved that the EM algorithm becomes a contraction mapping of the parameters within a neighborhood of the consistent solution of the maximum likelihood when the measure of average overlap among Gaussians in the original mixture is small enough and the number of samples is large enough. That is, if the initial parameters are set within the neighborhood, the EM algorithm will always converge to the consistent solution, i.e., the expected result. Moreover, the simulation results further demonstrate that this correct convergence neighborhood becomes larger as the average overlap becomes smaller.     

基于改进的等距离映射算法的人脸识别

针对等距离映射(Isomap)算法在处理扰动图像时拓扑结构不稳定的缺点,提出了一种改进算法。改进算法将图像欧氏距离(IMED)嵌入到等距离映射算法之中。首先引入坐标度量系数计算图像的坐标度量矩阵,通过线性变换将原始图像从欧氏距离(ED)空间转换到图像欧氏距离空间;然后计算变换空间中样本的欧氏距离矩阵,并在此基础上构建样本邻域图,得到近似测地距离矩阵;最后采用多维标度(MDS)分析算法构造样本的低维表示。对ORL和Yale人脸数据库降维并结合最近邻分类器进行实验,基于改进算法的识别率平均分别提高了5.57%和3.95%,表明与原算法相比,改进算法在人脸识别中对图像扰动具有较好的鲁棒性。     

Different Aspects of Clustering The Self-Organizing Maps

Self-organizing map (SOM) is an artificial neural network tool that is trained using unsupervised learning to produce a low dimensional representation of the input space, called a map. This map is generally the object of a clustering analysis step which aims to partition the referents vectors (map neurons) into compact and well-separated groups. In this paper, we consider the problem of the clustering SOM using different aspects: partitioning, hierarchical and graph coloring based techniques. Unlike the traditional clustering SOM techniques, which use k-means or hierarchical clustering, the graph-based approaches have the advantage of providing a partitioning of the SOM by simultaneously using dissimilarities and neighborhood relations provided by the map. We present the experimental results of several comparisons between these different ways of clustering.     

微创外科机器人导航系统空间映射精度分析与仿真

论文分析了微创外科机器人导航系统空间映射误差的主要来源,定义了空 间映射中的四种误差类型。并对每种误差都做了详细的介绍,同时也简要介绍了其他误差源。 通过仿真分析标记点定位误差即基准点定位误差对基于仿射坐标系的空间映射精度的影响, 得出基准点定位误差与靶点映射误差成正比,基准点在两个空间的定位误差变化范围的差距 较小时靶点映射误差较小的结论;通过仿真分析标记点的分布方式对基于仿射坐标系的空间 映射精度的影响,得出对空间映射精度影响较大的两种标记点分布方式：共面分布和不能将 靶点包围在其分布范围内的标记点分布。共面分布会导致利用仿射坐标系求解映射矩阵时发 生畸变,导致映射误差发生突变;靶点在标记点包围区域外时,与靶点在标记点包围区域内 时的空间映射相比也会产生很大的靶点映射误差。     

基于自适应锚定邻域回归的图像超分辨率算法

在基于字典的图像超分辨率（SR）算法中，锚定邻域回归超分辨率（ANR）算法由于其优越的重建速度和质量引起了人们的广泛关注。然而，ANR算法的锚定邻域投影并不稳定，以致于不足以涵盖各种样式的映射关系。因此提出一种基于自适应锚定邻域回归的图像SR算法，根据样本分布自适应地计算邻域中心从而以更精确的邻域来预计算投影矩阵。首先，以图像块为中心，运用K均值聚类算法将训练样本聚类成不同的簇；然后，用每个簇的聚类中心替换字典原子来计算相应的邻域；最后，运用这些邻域来预计算从低分辨率（LR）空间到高分辨率（HR）空间的映射矩阵。实验结果表明，所提算法在Set14上平均重建效果以31.56 dB的峰值信噪比（PSNR）及0.8712的结构相似性（SSIM）优于其他基于字典的先进算法，甚至胜过超分辨率卷积神经网络（SRCNN）算法。同时，在主观表现上看，所提算法恢复出了尖锐的图像边缘且产生的伪影较少。     

Self-organizing maps with asymmetric neighborhood function

The self-organizing map (SOM) is an unsupervised learning method as well as a type of nonlinear principal component analysis that forms a topologically ordered mapping from the high-dimensional data space to a low-dimensional representation space. It has recently found wide applications in such areas as visualization, classification, and mining of various data. However, when the data sets to be processed are very large, a copious amount of time is often required to train the map, which seems to restrict the range of putative applications. One of the major culprits for this slow ordering time is that a kind of topological defect (e.g., a kink in one dimension or a twist in two dimensions) gets created in the map during training. Once such a defect appears in the map during training, the ordered map cannot be obtained until the defect is eliminated, for which the number of iterations required is typically several times larger than in the absence of the defect. In order to overcome this weakness, we propose that an asymmetric neighborhood function be used for the SOM algorithm. Compared with the commonly used symmetric neighborhood function, we found that an asymmetric neighborhood function accelerates the ordering process of the SOM algorithm, though this asymmetry tends to distort the generated ordered map. We demonstrate that the distortion of the map can be suppressed by improving the asymmetric neighborhood function SOM algorithm. The number of learning steps required for perfect ordering in the case of the one-dimensional SOM is numerically shown to be reduced from O(N(3)) to O(N(2)) with an asymmetric neighborhood function, even when the improved algorithm is used to get the final map without distortion.