A New Modified GM (1,1) Model: Grey Optimization Model

1. INTaODUCTIONRecently,the grey prediction based on the GM (1,1) model has been applied to mad new helds such as safetysystem engineering 11,2], forecasting control [3], and so on. But in GM (1,1), it is difficult to determine theoptimal prediction values. In order to solve this problem, many improved models and methods aze developedsuch as residual modified model [4], grey step model [5], and heuristic method [6]. In tall paper, a new modaledGM (1,1) model called grey optindzation mod…     

On the stability of two-step predictive controller based on state observer

1.INTRODUCTIONCompared with MPCs based-on input/output model,i mpulse response model and step response model,MPCs based onstate-space model have attracted moreattention in recent years.This is mainly due to thefact that the state-space model can describe a largernumber of systems and cope with much more realproblems.For state-space MPCs,the control lawhasa formof(explicit or i mplicit)state feedback.If thestate is i mmeasurable,state observer is adopted[1,2].References[3~5]haveinvesti…     

Simulated Annealing for Earliness/Tardiness Production Planning Model

1　 IntroductionSince the real-world resource requirements are usually time-dependent,nonlinear,andnonconvex,a much more elaborated model is needed to study earliness/ tardinessproduction scheduling problems.A semi-infinite programming model[2 ,3] can closely modelthe earliness/ tardiness production planning problem.Because it has infinitely manynonconvex constraints,it is very difficult to solve the model.The complexity of theproblem has been discussed in [1 ] .The presented bestmethod in so…     

Nonsynchronous Trading Model and Return Analysis

Nonsynchronous trading is one of the hot issues in financial high-frequency data processing. This paper extends the nonsynchronous trading model studied in [1] and [2] for the financial security, and considers the moment functions of the observable return series for the extended model. At last. the estimators of parameters are obtained.     

Agent- oriented Software Engineering

1　IntroductionAn increasing number of computer systems are being viewed in terms of autonomousagents.Agents are being espoused as a new theoretical model of computation that moreclosely reflects current computing reality than Turing Machines[1 ] .Agents are beingadvocated as a next generation model for engineering complex and distributed systems[2 ] .Agents are also being used as an overarching framework for bringing together thecomponent AI subdisciplines that are necessary to design and b…     

SYNTHESIS AND ANALYSIS OF A FEEDBACK CONTROL SYSTEM

In this paper, supposing that the received signals at the input are of the formv(t)=s_1[t, x_1(t)]s_2[t, x_2(t)]+n(t) where s_i are FM signals (i=1, 2), a novel cross-coupledphase-locked loop (CCPLL(M)) and its mathematical model are obtained. The globalqualitativestructural analysis of the mathematical model of the first-order loop, the acqui-sition region and synchronization region of the first-order loop, and the synchronizationregion of the second-order loop are obtained.     

PORTFOLIO SELECTION THEORY WITH STRICTLY POSITIVE SUPPLY OF RISKLESS ASSET

1. IntroductionH. Ma.kowitz[1] developped the mean-variance model of asset choice where there are morethan two risky assets traded in a frictionless economys unlimited short selling is allowed and therates of return on these assets have finite variances. N. Gonz.lez--GaverraL2] and R. Merton[3]gave a detailed discussion. Maily results of N. Gonzalez--Gaverra[2] were later independentlyderived by R. Roll[4]. G. Chamberlain[5] characterizes the complete family of distributions thatare neces…     

Color-texture based unsupervised segmentation using JSEG with fuzzy connectedness

1.INTRODUCTIONJSEG[1]is a distinguished one in many existing seg-mentation methods based on color-texture[1,4,6~8].Itis computationally more feasible than many othermethods[1]because JSEGis to test the homogeneityof a given color-texture pattern,instead of doing pa-rameter esti mationfor a specific model like many oth-er texture segmentation algorithms.The segmentation results produced by JSEGaremainly based on a class-mapformed by the color classlabel of every pixel,which is the prod…     

A New Criterion for Stability of Large-Scale Systems with Delay

1. INTanDUCTIONIn recent years, a number of research efforts have been made on stability analysis ed design for large-scaletime--delay systems. Hmamed [1] adopted a generalized linear system model and solxred the complex LyaPu-novequation to obtain the main results. Mori, et al.[2I worked ont a stability criterion for large--scale systemswith time delays by using comparison methods and M--matrix properties. Suh and Bien [3l and Lewis andAnderson [4] deve1oped some stability criteria for…     

Color-texture segmentation using JSEG based on Gaussian mixture modeling

1.INTRODUCTIONColor i mage segmentation is useful in many applica-tions.Fromthe segmentationresults,it is possible toidentify regions of interest and objectsinthe scene.Avariety of techniques have been proposed,for exam-ple:stochastic model based approaches[1,4,9],mor-phological watershed based region growing[11],energydiffusion[10],and graph partitioning[7].However,due tothe difficult nature of the problem,there are few auto-matic algorithms that can work well on alarge variety ofdata.Th…     

Evolutionary Programming for IP/MIP Problems with Linear Constraints

1. INTSODUCTIONThe common illteger programming (lP) is a mathematical model which is designed to find aset of non-negative variables to medmize (or minimize) a nonlinear objective function whilesatisfying a set of constraints under integer restrictions of variables. An lP model with somevariables reqllired to be real is a mixed integer programming (MIP).The history of solving lP/MIP problems is not very old. According to reference [1], ageneral method for solvillg such problems may not…     

STOCHASTIC ADAPTIVE SWITCHING CONTROL BASED ON MULTIPLE MODELS

1 IntroductionIn an uncertain and complex environment, the approach of "optimal" switching is often usedfor making decisions through predicting and comparing the effects of multiple schemes. In thearea of control, the mu1tipIe model approach, which has been used to improve estimations andcontrol accuracies, can be traced back at least to 1960s--1970s(see, e.g., [1l--[3l). Some practicalapplications have also been reported[4,']. In adaptive control, switching cootroller based onmultiple models…     

mproving the Input of Classified Neural Networks Through Feature Construction

SOFTWARE,ALGORITHM AND SIMULATION1. Pas~EClassification, as an important program of data mining, is to build a classified function or model that is able tomap the item Of database to one of given classes. The classification algorithm in common use mainly includebayesian, decision trees, mule induction and neural networks [1].The classification algorithm based on decision trees has been in maturity earlier in 1980s', typical of whichis ID3 by J. R. Quinlan [21, it introduced the …     

MODELLING AND STABILITY ANALYSIS OF POPULATION GROWTH WITH SPATIAL DIFFUSION

In recent years, population growth models with spatial diffusion have beenextensively studied by many authors (for example, see [1-5]). In this paper, a populationgrowth model is considered with a discrete age-dependence and spatial diffusion, and isinvestigated in a semigroup framework. The spectral properties of the population oper-ator are given. On the basis of such spectral consideration, the asymptotic behaviourof the semigroup generated by the population operator is obtained. Finally, a nonlinearpopulation growth model is considered and its stability is analyzed.     

GLOBAL STABILITY AND HOPF BIFURCATION OF AN SIS EPIDEMIC MODEL WITH TIME DELAYS

1 IntroductionFor epidemic model with delays, many people have done a lot of work and many valuableresults have been obtained. In SIS ePidemiologic models, susceptibles become infectious aftersufficieot contact with an infective and then become susceptible again after they have recoveredfrom the infection. SIS models with a time delay in the infectious class and a constan poWulation size were analyzed by Cooke and Yorke[1] and Greenberg and Hoppensteadt[2J. TheyfOund that aJl solutions a…     

Expansion modelling of discrete grey model based on multi-factor information aggregation

This paper aims to study a novel expansion discrete grey forecasting model, which could aggregate input information more effectively. In general, existing multi-factor grey forecasting models, such as one order and h variables grey forecasting model （GM （1, h））, always aggregate the main system variable and independent variables in a linear form rather than a nonlinear form, while a nonlinear form could be used in more cases than the linear form. And the nonlinear form could aggregate collinear independent factors, which widely lie in many multi-factor forecasting problems. To overcome this problem, a new approach, named as the Solow residual method, is proposed to aggregate independent factors. And a new expansion model, feedback multi-factor discrete grey forecasting model based on the Solow residual method （abbreviated as FDGM （1, h））, is proposed accordingly. Then the feedback control equation and the parameters＇ solution of the FDGM （1, h） model are given. Finally, a real application is used to test the modelling accuracy of the FDGM （1, h） model. Results show that the FDGM （1, h） model is much better than the nonhomogeneous discrete grey forecasting model （NDGM） and the GM （1, h） model.     

Capacity of Multi- vehicle- types Mixed Traffic Flow

1　IntroductionFig.1　Different traffic streams on2× 2cross intersectionThree capacity terms have been used inthis paper:potential capacity,modelcapacity and field capacity.Potentialcapacity is defined as the capacity of non-priority traffic stream in relation toconflicting traffic move-ment[1 ] ,and it isthe capacity of a theoretical model basedon two conflicting traffic movements.Fig.1 shows the different traffic streamson a cross intersection of 2× 2 type.Model capacity is the capacity p…     

A NOTE ON COMPLETELY POSITIVE GRAPHS

1. IlltroductionPioneered by M. Hall Jr. in 195811] and investigated by A. Berman [2--4] and J. H. Drew, C.R. Johnson and Loewy[5] et al., completely positive matrices have been shown their importancenot only in the study of block designs in combinatorial analysis[6], but also in establishingeconomic model.[7].Recall that an n x n matrix A is said to be completely positive, denoted by A E CPu, ifthere edest m nonnegative column vectors hi,'', ba such thatwhere I denotes transpose. The …     

Multi-resolution image segmentation based on Gaussian mixture model

1. INTRODUCTION Image segmentation, which groups an image’s pixels into some homogeneous regions with respect to one or more characteristics such as gray-level, color and texture, is a basic and challenging problem in image processing. Many researchers have devoted their efforts to this problem and many segmentation algorithms have been proposed[1], histogram based thresholding algorithm, edge detection method and region growing and merging method for instance. Gaussian mixture model bas…     

Non-Photorealistic Rendering in Chinese Painting of Animals

1 Introduction1 Non-photorealistic rendering (NPR) is a newly developed rendering technique in recent years. The goal of NPR is not rendering objects realistically but more creatively such as in simulating various painting styles. Curtis, et al. [1] simulates the physical property of media and substrate in watercolor. But his work only focused on 2D image processing and does not use the information of 3D model in 3D scene rendering. There is another important artistic style in NPR call…