用分层事件关系图实现系统仿真与分析*

现有的建模语言如UML、有穷状态自动机、Petri网、DEVS等不能完全满足工业中对时间系统建模的要求,企业常须自行开发建模语言和工具,或人为加工和抽象时间系统的设计以适应已有建模手段。使用事件关系图实现分层设计可以在一定程度上解决这一问题。该方法既方便了对复杂时间系统的设计,也使自动化仿真、分析和代码生成变得简易可行。     

Abnormal behavior detection using dominant sets

Smart surveillance systems are increasingly being used to detect potentially dangerous situations. To do so, the common and easier way is to model normal human behaviors and consider as abnormal any new strange behavior in the scene. In this article, Dominant Sets is adapted to model most frequent behaviors and to detect any unknown event to trigger an alarm. It is proved that after an unsupervised training, Dominant Sets can robustly detect abnormal behaviors. The method is tested in several different cases and compared to other usual clusterization methods such as KNN, mixture of Gaussians or Fuzzy \(K\) -Means to confirm its robustness and performance. The overall performance of abnormal behavior detection based on Dominant Sets is better, being the error ratio at least \(1.5\) points lower than the others.     

A Microeconomic View of Data Mining

We present a rigorous framework, based on optimization, for evaluating data mining operations such as associations and clustering, in terms of their utility in decision-making. This framework leads quickly to some interesting computational problems related to sensitivity analysis, segmentation and the theory of games.     

Texture pattern analysis of kidney tissues for disorder identification and classification using dominant Gabor wavelet

A study on ultrasound kidney images using proposed dominant Gabor wavelet is made for classifying a few important kidney categories. Three kidney categories, namely, normal (NR), medical renal diseases (MRD) and cortical cyst (CC) are considered for the analysis. Of the 30 Gabor wavelets, a unique dominant Gabor wavelet is determined by maximizing the similarity between original pre-processed image and reconstructed Gabor image. The dominant Gabor features “m_mn^D{\mu_{mn}^D } ” and “AAD_mn^D{AAD_{mn}^D } ” are then evaluated to characterize the tissues of kidney region and compared with the Gabor features derived by considering all Gabor wavelets individually and as a whole using the resultant classification efficiency. The results obtained show that the proposed dominant Gabor wavelet features provide the classification efficiency of 86.66% for NR, 76.66% for MRD and 83.33% for CC, while individual wavelet features offer less than 70%, 63.33% and 66% for NR, MRD and CC. The overall classification efficiency improves by 18.89% with dominant Gabor features when compared to the classification efficiency obtained by considering all the Gabor wavelets features. The outputs of the proposed technique are validated with medical experts to assess the actual efficiency. The overall discriminating ability of the systems is also evaluated with performance evaluation measures, F-score and ROC. It has been observed that the dominant Gabor wavelet improves the classification efficiency appreciably and explores the possibility of implementing a computer-aided diagnosis system exclusively for ultrasound kidney images.     

A framework for crime data analysis using relationship among named entities

Neural Computing and Applications - Many crime reports are available online in various blogs and Newswire. Though manual annotation of these massive reports is quite tedious for crime data...     

Scale-invariant template matching using histogram of dominant gradients

This paper presents a histogram-based template matching method that copes with the large scale difference between target and template images. Most of the previous template matching methods are sensitive to the scale difference between target and template images because the features extracted from the images are changed according to the scale of the images. To overcome this limitation, we introduce the concept of dominant gradients and describe an image as the feature that is tolerant to scale changes. To this end, we first extract the dominant gradients of a template image and represent the template image as the grids of histograms of the dominant gradients. Then, the arbitrary regions of a target image with various locations and scales are matched with the template image via histogram matching. Experimental results show that the proposed method is more robust to scale difference than previous template matching techniques.     

Feature aligned quad dominant remeshing using iterative local updates

In this paper we present a new algorithm which turns an unstructured triangle mesh into a quad dominant mesh with edges well aligned to the principal directions of the underlying surface. Instead of computing a globally smooth parameterization or integrating curvature lines along a tangent vector field, we simply apply an iterative relaxation scheme which incrementally aligns the mesh edges to the principal directions. We further obtain the quad dominant mesh by dropping the not-aligned diagonal edges from the triangle mesh. A post-processing stage is introduced to further improve the results. The major advantage of our algorithm is its conceptual simplicity since it is merely based on elementary mesh operations such as edge collapse, flip, and split. Various results are presented in the paper; they show a good alignment to surface features and rather uniform distribution of mesh vertices. This makes them well suited, e.g., as Catmull-Clark Subdivision control meshes.     

Augmenting understanding of the relationship between situation awareness and confidence using calibration analysis

The present study represents a preliminary examination of the relationship between situation awareness (SA) and confidence within a distributed information-sharing environment using the calibration methodology. The calibration methodology uses the indices of calibration, resolution and over/under-confidence to examine the relationship between the accuracy of the responses and the degree of confidence that one has in these responses, which leads to a measure of an operator's meta-SA. The results of this study revealed that, although the participants were slightly overconfident in their responses, overall they demonstrated good meta-SA. That is, the participants' subjective probability judgements corresponded to their pattern of SA response accuracy. It is concluded that the use of calibration analysis represents a better methodology for expanding our understanding of the relationship between SA and confidence and ultimately how this relationship can impact decision-making and performance in applied settings than can be achieved by examining SA measures alone.     

On selecting a low-order model using the dominant mode concept

A technique for selecting a low-order system to approximate a high-order model has been suggested by Davison [2]. A critical component in this technique is the criterion used to select the most appropriate order and modes for the low-order approximation. Criteria have been discussed and analyzed by Mahapatra [5], [6], Rao, Lamba, and Rao [7], and Elrazaz and Sinha [3]. In this note we overcome deficiencies in the criteria that have been proposed and we introduce a new criterion which is rigorously justified. The criterion we suggest is also applicable when eigenvalues of the system are nonreal.     

Exploring the relationship between information technology investments and firm performance using regression splines analysis

Identifying the business value of information technology (IT) investments has been a major concern of managers and researchers. Various studies have addressed this issue but have provided contradictory results. Here, we explore the relationship between IT investments and firm performance using a relatively new technique, multivariate adaptive regression splines (MARS), and attempt to answer two questions: (1) do investments in IT have a positive impact on organizational productivity? and (2) for a given level of investment, what portion of the total should be invested in IT to maximize organizational productivity? Our results suggest that depending on the conditions that applied, an unbiased observer could either conclude that investments in IT has a positive statistically significant effect on productivity, or that there is a ‘productivity’ paradox. This suggests that the relationship between IT investments and organizational performance is much more complex than that found in some other studies. Our results could also provide guidance to managers who are responsible for determining the allocation of organizational resources.     

Exploring the relationship between information technology investments and firm performance using regression splines analysis

Identifying the business value of information technology (IT) investments has been a major concern of managers and researchers. Various studies have addressed this issue but have provided contradictory results. Here, we explore the relationship between IT investments and firm performance using a relatively new technique, multivariate adaptive regression splines (MARS), and attempt to answer two questions: (1) do investments in IT have a positive impact on organizational productivity? and (2) for a given level of investment, what portion of the total should be invested in IT to maximize organizational productivity? Our results suggest that depending on the conditions that applied, an unbiased observer could either conclude that investments in IT has a positive statistically significant effect on productivity, or that there is a ‘productivity’ paradox. This suggests that the relationship between IT investments and organizational performance is much more complex than that found in some other studies. Our results could also provide guidance to managers who are responsible for determining the allocation of organizational resources.     

Dissipation and Conditions of Equilibrium for an Open Microeconomic System

An analogy between microeconomic and irreversible thermodynamic systems is shown. The concepts of economic irreversibility, dissipation of capital are introduced and conditions of minimal dissipation are obtained. Problems of optimal control of prices in the processes of resources exchange are solved and the extremal principle for the determination of stationary state of an open microeconomic system is formulated.     

Scan matching method using projection in dominant direction of indoor environment

In this paper, we propose a new scan matching method, which uses the feature of structure in an artificial environment where walls are located parallel or perpendicular to one another. This method can precisely obtain the relative pose between two scan data using the dominant direction with a small calculation cost. Efficacy of this method is proved by an experiment conducted in an indoor environment.     

B-spline surface fitting based on adaptive knot placement using dominant columns

By expanding the idea of B-spline curve fitting using dominant points (Park and Lee 2007 [13]), we propose a new approach to B-spline surface fitting to rectangular grid points, which is based on adaptive knot placement using dominant columns along u- and v-directions. The approach basically takes approximate B-spline surface lofting which performs adaptive multiple B-spline curve fitting along and across rows of the grid points to construct a resulting B-spline surface. In multiple B-spline curve fitting, rows of points are fitted by compatible B-spline curves with a common knot vector whose knots are computed by averaging the parameter values of dominant columns selected from the points. We address how to select dominant columns which play a key role in realizing adaptive knot placement and thereby yielding better surface fitting. Some examples demonstrate the usefulness and quality of the proposed approach.     

基于边缘模式和主导学习框架的相似纹理分类

边缘是进行相似纹理图像分类的有效特征之一,为了提高边缘检测精度,使用可变化的局部边缘模式（Varied Local Edge Pattern,VLEP）算法,利用像元及其近邻的灰度变化进行区域统计,同时从多尺度和多方向的角度提取纹理边缘特征。然而,当图像分辨率发生变化,或图像受到光照、反射的影响时,纹理计算可能会出现较大偏差。为此,在VLEP算法的基础上,提出主导学习框架相似纹理分类方法,通过构建全局主导模式集,解决纹理计算偏差导致的类间距离小和类内距离大的问题。实验结果表明,主导边缘模式思想可以有效地提高相似纹理图像的分类准确率。     

氯代芳烃对戈卑鱼毒性的定量构效关系解析

基于定量结构-活性相关（QSAR）研究氯代芳烃的性质具有重要意义。对22种氯代芳烃化合物进行DFT-B3LYP/6-311G**水平全优化计算。据所得量子化学参数建立氯代芳烃对戈卑鱼急毒性(-IgLC₅₀)的QSAR模型。对训练集样本经逐步多元回归分析后,所建QSAR模型的复相关系数R²及去一法（LOO）交互检验复相关系数R²_cv分别为0.963和0.962,用预测集样本进行了外部预测,所得外部预测样本复相关系数R²_ext和外部预测集交互检验Q²_ext分别为0.968和0.820,表明所建立的QSAR方程具有较好的稳定性和预测能力。模型结果表明:氯代芳烃化合物的毒性与分子总能量（E_γ）、分子体积（V）及分子次最低空轨道能(E_NLUMO)的相关性较好。     

Microeconomic model of residential location incorporating life cycle and social expectations

This paper is focused on the dynamics of residential location decisions based on the microeconomic theory of urban land use, in which we assume that each property is assigned to the agent with the highest bid. The agents' behavior includes expectations of their future based on the life cycle or social influence processes, which are anticipated or solved using a hypothesis of imitation of the behavior of other households currently living in those situations. Relocation decisions are then modeled, incorporating expected utilities by means of transition probabilities among households. An imitation multi-objective bid function is postulated for each alternative location depending on the expected income per unit of time, the current household value of amenities and the expected value obtained by the imitated agent in this location. A multinomial logit model is assumed to calculate the location equilibrium, where willingness to pay is determined by dwelling characteristics and spatial socioeconomic segregation (location externalities). Numerical examples and simulations are presented using linear bid functions to explain the proposed modeling approach and the impact of imitation on the dynamics of residential segregation.     

复杂系统完备因子协同学主导分析基础

如何从根本动力学关系基础上将外部条件和内部动因结合起来去研究系统的演化,这是理论拓展的一个基本方向．本文将基本动力学关系和因素归结为”资源配置“与“资源荷载“、”系统功效”与”系统损耗”方面．在建立复杂巨系统基本协同因子动力学分析的基础上,在复杂系统和环境体系之间,围绕内外部耦合关系,我们可以探讨建立复杂巨系统资源配置动力学完备协同因子动态学分析．     

High-level feature recognition using feature relationship graphs

In this paper, we present a method to extract user-specific features from common features. This contrasts with other approaches which work directly off B-rep geometric models. Here, user-specific features are called high-level features which are a set of common features combined in a user-specific manner. A feature relationship graph is used to organize common features in a part and to define high-level feature patterns. The research presented in this paper focuses mainly on feature relationship graph construction and high-level feature recognition using subgraph isomorphic techniques.