A method for comparison of 3D surfaces using pyramidal height maps and fussy masks

A method for comparison of 3D surfaces mutually displaced in space is developed. This method is based on the measure of distinction expressed by the volume between two optimally superimposed surfaces. The volume is determined from the height map calculated with respect to a specified plane. Pyramidal representation of height maps is used to reduce the amount of examination. In addition, the maps are calculated using graphic processors. This method can be used in the problem of superposition (and identification) of identically oriented, mutually displaced surfaces.     

Evolutionary decision rules for predicting protein contact maps

Protein structure prediction is currently one of the main open challenges in Bioinformatics. The protein contact map is an useful, and commonly used, representation for protein 3D structure and represents binary proximities (contact or non-contact) between each pair of amino acids of a protein. In this work, we propose a multi-objective evolutionary approach for contact map prediction based on physico-chemical properties of amino acids. The evolutionary algorithm produces a set of decision rules that identifies contacts between amino acids. The rules obtained by the algorithm impose a set of conditions based on amino acid properties to predict contacts. We present results obtained by our approach on four different protein data sets. A statistical study was also performed to extract valid conclusions from the set of prediction rules generated by our algorithm. Results obtained confirm the validity of our proposal.     

Necklace maps

Statistical data associated with geographic regions is nowadays globally available in large amounts and hence automated methods to visually display these data are in high demand. There are several well-established thematic map types for quantitative data on the ratio-scale associated with regions: choropleth maps, cartograms, and proportional symbol maps. However, all these maps suffer from limitations, especially if large data values are associated with small regions. To overcome these limitations, we propose a novel type of quantitative thematic map, the necklace map. In a necklace map, the regions of the underlying two-dimensional map are projected onto intervals on a one-dimensional curve (the necklace) that surrounds the map regions. Symbols are scaled such that their area corresponds to the data of their region and placed without overlap inside the corresponding interval on the necklace. Necklace maps appear clear and uncluttered and allow for comparatively large symbol sizes. They visualize data sets well which are not proportional to region sizes. The linear ordering of the symbols along the necklace facilitates an easy comparison of symbol sizes. One map can contain several nested or disjoint necklaces to visualize clustered data. The advantages of necklace maps come at a price: the association between a symbol and its region is weaker than with other types of maps. Interactivity can help to strengthen this association if necessary. We present an automated approach to generate necklace maps which allows the user to interactively control the final symbol placement. We validate our approach with experiments using various data sets and maps.     

Attributed concept maps: fuzzy integration and fuzzy matching

A concept map, typically depicted as a connected graph, is composed of a collection of propositions. Each proposition forming a semantic unit consists of a small set of concept nodes interconnected to one another with relation links. Concept maps possess a number of appealing features which make them a promising tool for teaching, learning, evaluation, and curriculum planning. We extend concept maps by associating their concept nodes and relation links with attribute values which indicate the relative significance of concepts and relationships in knowledge representation. The resulting maps are called attributed concept maps (ACM). Assessing students will be conducted by matching their ACMs with those prebuilt by experts. The associated techniques are referred to as map matching techniques. The building of an expert ACM has in the past been done by only one specialist. We integrate a number of maps developed by separate experts into a single map, called the master map (MM), which will serve as a prototypical map in map matching. Both map integration and map matching are conceptualized in terms of fuzzy set discipline. Experimental results have shown that the proposed ideas of ACM, MM, fuzzy map integration, and fuzzy map matching are well suited for students with high performances and difficult subject materials.     

基于纠错编码的矢量地图可逆水印算法*

针对当前矢量地图可逆水印算法中缺乏水印提取结果纠错方法研究的问题,提出了一种基于纠错编码的矢量地图可逆水印算法。首先采用二值数组表达版权信息并生成其纠错编码,然后将二者合并组成水印数据,最后将水印数据嵌入地图顶点极坐标以增强算法抵抗几何变换的能力。水印提取后,通过纠错编码对水印提取结果进行纠错,达到提升算法稳健性的目的。实验结果证明：该算法具有严格的可逆性、理想的隐蔽性以及较强的稳健性。     

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.     

A novel hybrid method based on fuzzy cognitive maps and fuzzy clustering algorithms for grading celiac disease

This paper presents a new method based on fuzzy cognitive map (FCM) and possibilistic fuzzy c-means (PFCM) clustering algorithm for categorizing celiac disease (CD). CD is a complex disorder whose development is affected by genetics (HLA alleles) and gluten ingestion. The celiac patients who are not treated are at a high risk of cancer, malignant lymphoma, and small bowel neoplasia. Therefore, CD diagnosis and grading are of paramount importance. The proposed FCM models human thinking for the purpose of classifying patients suffering from CD. We used the latest grading method where three grades A, B1, and B2 are used. To improve FCM efficiency and classification capability, a nonlinear Hebbian learning algorithm is applied for adjusting the FCM weights. To this end, 89 cases are studied. Three experts extracted seven main determinant characteristics of CD which were considered as FCM concepts. The mutual effects of these concepts on one another and on the final concept were expressed in the form of fuzzy rules and linguistic variables. Using the center of gravity defuzzifier, we obtained the numerical values of these weights and obtained the total weight matrix. Ultimately, combining the FCM model with PFCM algorithm, we obtained the grades A, B1, and B2 accuracies as 88, 90, and 91%, respectively. The main advantage of the proposed FCM is the good transparency and interpretability in the decision-making procedure, which make it a suitable tool for daily usage in the clinical practice.

     

Compressed shadow maps

Shadow mapping has been subject to extensive investigation, but previous shadow map algorithms cannot usually generate high-quality shadows with a small memory footprint. In this paper, we present compressed shadow maps as a solution to this problem. A compressed shadow map reduces memory consumption by representing lit surfaces with endpoints of intermediate line segments as opposed to the conventional array-based pixel structures. Compressed shadow maps are only discretized in the vertical direction while the horizontal direction is represented by floating-point accuracy. The compression also helps with the shadow map self-shadowing problems. We compare our algorithm against all of the most popular shadow map algorithms and show, on average, order of magnitude improvements in storage requirements in our test scenes. The algorithm is simple to implement, can be added easily to existing software renderers, and lets us use graphics hardware for shadow visualization.     

Matching aerial images to 3-D terrain maps

A terrain-matching algorithm is presented for use in a passive aircraft navigation system. A sequence of aerial images is matched to a reference digital map of the 3-D terrain. Stereo analysis of successive images results in a recovered elevation map. A cliff map is then used as a novel compact representation of the 3-D surfaces. The position and heading of the aircraft are determined with a terrain-matching algorithm that locates the unknown cliff map within the reference cliff map. The robustness of the matching algorithm is demonstrated by experimental results using real terrain data     

Computing global visibility maps for regions on the boundaries of polyhedra using Minkowski sums

A global visibility map is a spherical image built to describe the complete set of global visible view directions for a surface. In this paper, we consider the computation of global visibility maps for regions on the boundary of a polyhedron. Both the self-occlusions introduced by a region and the global occlusions introduced by the rest of the surfaces on the boundary of the polyhedron are considered for computing a global visibility map. We show that the occluded view directions introduced between a pair of polyhedral surfaces can be computed from the spherical projection of the Minkowski sum of one surface and the reflection of the other. A suitable subset of the Minkowski sum, which shares the identical spherical projection with the complete Minkowski sum, is constructed to obtain the spherical images representing global occlusions. Our method has been successfully tested on many CAD models. It extends the previous methods for computing global visibility maps using convex decomposition, and it exhibits a better performance.     

The self-organizing field [Kohonen maps]

Many of the properties of the well-known Kohonen map algorithm are not easily derivable from its discrete formulation. For instance, the "projection" implemented by the map from a high dimensional input space to a lower dimensional map space must be properly regarded as a projection from a smooth manifold to a lattice and, in this framework, some of its properties are not easily identified. This paper describes the self-organizing field: a continuous embedding of a smooth manifold (the map) into another (the input manifold) that implements a topological map by self-organization. The adaptation of the self-organizing field is governed by a set of differential equations analogous to the difference equations that determine weights updates in the Kohonen map. This paper derives several properties of the self-organizing field, and shows that the emergence of certain structures on the brain-like the columnar organization in the primary visual cortex-arise naturally in the new model.     

Circa 2014 African land-cover maps compatible with FROM-GLC and GLC2000 classification schemes based on multi-seasonal Landsat data

A new African land-cover data set has been developed using multi-seasonal Landsat Operational Land Imager (OLI) imagery mainly acquired around 2014, supplemented by Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+). Each path/row location was covered by five images, including one in the growing season of vegetation and the others in four meteorological seasons (i.e. spring, summer, autumn, and winter), choosing the image with the least cloud coverage. The data set has two classification schemes, i.e. Finer Resolution Observation and Monitoring – Global Land Cover (FROM-GLC) and Global Land Cover 2000 (GLC2000), providing greater flexibility in product comparisons and applications. Random forest was used as the classifier in this project. Overall accuracies were 71% and 67% for the maps in the FROM-GLC classification scheme at level 1 and level 2, respectively, and 70% for the map in the GLC2000 classification scheme. The newly developed African land-cover map achieved a greater improvement in accuracy compared to previous products in the FROM-GLC project. Multi-seasonal imagery helped increase the mapping accuracy by better differentiating vegetation types with similar spectral features in one specific season and identifying vegetation with a shorter growing season. Night light data with 1 km resolution was used to identify the potential area of impervious surfaces to avoid overestimating the distribution of impervious surfaces without decreasing the spatial resolution. Stacking multi-seasonal mapping results could adequately minimize the disturbance of cloud and shade.     

A note on self-organizing semantic maps

This paper discusses Kohonen's self-organizing semantic map (SOSM). We show that augmentation and normalization of numerical feature data as recommended for the SOSM is entirely unnecessary to obtain semantic maps that exhibit semantic similarities between objects represented by the data. Visual displays of a small data set of 13 animals based on principal components, Sammon's algorithm, and Kohonen's (unsupervised) self-organizing feature map (SOFM) possess exactly the same qualitative information as the much more complicated SOSM display does.     

融合双特征图信息的图像显著性检测方法

目的 图像的显著性检测是将图像中最重要的、包含丰富信息的区域标记出来,并应用到图像分割、图像压缩、图像检索、目标识别等重要领域。针对现有研究方法显著性目标检测结果不完整以及单一依靠颜色差异检测方法的局限性,提出一种综合图像底层颜色对比特征图和图像颜色空间分布特征图的显著性检测方法,能够有效而完整地检测出图像中的显著性区域。方法 本文方法结合了SLIC超像素分割和K-means聚类算法进行图像特征的提取。首先,对图像进行SLIC（simple linear iterative clustering）分割,根据像素块之间的颜色差异求取颜色对比特征图;其次,按照颜色特征对图像进行K-means聚类,依据空间分布紧凑性和颜色分布统一性计算每个类的初步颜色空间分布特征。由于聚类结果中不包含空间信息,本文将聚类后的结果映射到超像素分割的像素块上,进一步优化颜色空间分布图;最后,通过融合颜色对比显著图和图像颜色空间分布特征图得到最终的显著图。结果 针对公开的图像测试数据库MSRA-1000,本文方法与当前几种流行的显著性检测算法进行了对比实验,实验结果表明,本文方法得到的显著性区域更准确、更完整。结论 本文提出了一种简单有效的显著性检测方法,结合颜色对比特征图和图像颜色空间分布特征图可以准确的检测出显著性区域。该结果可用于目标检测等实际问题,但该方法存在一定的不足,对于背景色彩过于丰富且与特征区域有近似颜色的图像,该方法得到的结果有待改进。今后对此算法的优化更加侧重于通用性。     

Knowledge maps for e-learning

Maps such as concept maps and knowledge maps are often used as learning materials. These maps have nodes and links, nodes as key concepts and links as relationships between key concepts. From a map, the user can recognize the important concepts and the relationships between them. To build concept or knowledge maps, domain experts are needed. Therefore, since these experts are hard to obtain, the cost of map creation is high. In this study, an attempt was made to automatically build a domain knowledge map for e-learning using text mining techniques. From a set of documents about a specific topic, keywords are extracted using the TF/IDF algorithm. A domain knowledge map (K-map) is based on ranking pairs of keywords according to the number of appearances in a sentence and the number of words in a sentence. The experiments analyzed the number of relations required to identify the important ideas in the text. In addition, the experiments compared K-map learning to document learning and found that K-map identifies the more important ideas.     

Combinatorial Benders cuts for decomposing IMRT fluence maps using rectangular apertures

We consider the problem of decomposing Intensity Modulated Radiation Therapy (IMRT) fluence maps using rectangular apertures. A fluence map can be represented as an integer matrix, which denotes the intensity profile to be delivered to a patient through a given beam angle. We consider IMRT treatment machinery that can form rectangular apertures using conventional jaws, and hence, do not need sophisticated multi-leaf collimator (MLC) devices. The number of apertures used to deliver the fluence map needs to be minimized in order to treat the patient efficiently. From a mathematical point of view, the problem is equivalent to a minimum cardinality matrix decomposition problem. We propose a combinatorial Benders decomposition approach to solve this problem to optimality. We demonstrate the efficacy of our approach on a set of test instances derived from actual clinical data. We also compare our results with the literature and solutions obtained by solving a mixed-integer programming formulation of the problem.     

Good-visibility maps visualization

Given a set V of viewpoints and a set S of obstacles in an environmental space, the good-visibility depth of a point q in relation to V and S is a measure of how deep or central q is with respect to the points in V that see q while minding the obstacles of S. The good-visibility map determined by V and S is the subdivision of the environmental space in good-visibility regions where all points have the same fixed good-visibility depth. In this paper we present algorithms for computing and efficiently visualizing, using graphics hardware capabilities, good-visibility maps in the plane as well as on triangulated terrains, where the obstacles are the terrain faces. Finally, we present experimental results obtained with the implementation of our algorithms.     

Asynchronous self-organizing maps

A recently defined energy function which leads to a self-organizing map is used as a foundation for an asynchronous neural-network algorithm. We generalize the existing stochastic gradient approach to an asynchronous parallel stochastic gradient method for generating a topological map on a distributed computer system (MIMD). A convergence proof is presented and simulation results on a set of problems are included. A practical problem using the energy function approach is that a summation over the entire network is required during the computation of updates. Using simulations we demonstrate effective algorithms that use efficient sampling for the approximation of these sums.