By Topic

Intelligent Information Technology Application Workshops, 2008. IITAW '08. International Symposium on

Date 21-22 Dec. 2008

Filter Results

Displaying Results 1 - 25 of 280
  • [Front cover]

    Publication Year: 2008 , Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (451 KB)  
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2008 , Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (30 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2008 , Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (121 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2008 , Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (147 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2008 , Page(s): v - xxii
    Save to Project icon | Request Permissions | PDF file iconPDF (194 KB)  
    Freely Available from IEEE
  • Message from Workshops Chairs

    Publication Year: 2008 , Page(s): xxiii
    Save to Project icon | Request Permissions | PDF file iconPDF (119 KB)  
    Freely Available from IEEE
  • Workshops Organizing Committee Members

    Publication Year: 2008 , Page(s): xxiv
    Save to Project icon | Request Permissions | PDF file iconPDF (105 KB)  
    Freely Available from IEEE
  • Workshops Committee Members

    Publication Year: 2008 , Page(s): xxv - xxvi
    Save to Project icon | Request Permissions | PDF file iconPDF (108 KB)  
    Freely Available from IEEE
  • Immunity Genetic Algorithm Based on Elitist Strategy and its Application to the TSP Problem

    Publication Year: 2008 , Page(s): 3 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (266 KB) |  | HTML iconHTML  

    In order to improve searching efficiency and prevent premature in the standard GA, a new immune genetic algorithm is proposed and designed based on elitist strategy of its complete convergence and immune memory mechanism in the immune system. Through comparing the solutions of TSP problem with between the standard GA and IMGA, then complete convergence and good computation complicacy of the IMGA is analyzed to prove much better than the standard GA. The excellent availability on searching efficiency has some practical significance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Improved Attribute Reduction Algorithm Based on Attribute Importance Function

    Publication Year: 2008 , Page(s): 7 - 11
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (127 KB) |  | HTML iconHTML  

    A kind of attribute reduction algorithm of Jiahua Lu was firstly introduced and its performance was analyzed briefly, then aimed to its improvable points, a new attribute reduction algorithm based on the binary discernibility matrix and an improved attribute importance function that utilized the potential information of the information system, which considered attributespsila occurrence number and the lengths of the matrix elements, was proposed in the article. The new algorithm can show the real significance of the attributes, and the matrix scale is significantly reduced, its feasibility and validity and its lower time complexity than the similar ones are proved by the comparative analysis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision-Making Analysis on Industrial and Mining Enterprise Resettlement Projects

    Publication Year: 2008 , Page(s): 12 - 15
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (216 KB) |  | HTML iconHTML  

    In line with the features of Industrial & mining resettlement projects, a practical mathematical model has been set up through such aspects as project arrangement, rational judgment and decision making method of investment alteration; and a concrete county-level mathematical model and application instance have also been given. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Searching Mechanism Based on Dynamic Topology Regularization in Gnutella Network

    Publication Year: 2008 , Page(s): 16 - 19
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (237 KB) |  | HTML iconHTML  

    The searching mechanism of Gnutella in unstructured peer-to-peer network and its working principle are introduced. By analyzing its poor scalability problem, this paper proposes an improvement strategy based on dynamic topology regularization. The simulation results show that the strategy can effectively reduce the resource consumption of network and optimize the load-balancing among peers, and then improve the scalability of Gnutella network and the efficiency of resource search. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Study on Roughness Coefficient Using BP Neural Network

    Publication Year: 2008 , Page(s): 20 - 23
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (291 KB) |  | HTML iconHTML  

    Since 1999, Xiaolangdi reservoir plays an important role in flood control, irrigation and repair and maintenance of the healthy life of Yellow River. At the same time, process which the water and sediment flow into the downstream has been changed by the regulation of reservoir and trigger a number of new phenomenon. The abnormal phenomenon that a flood peak increased in August 2004 , July 2005, August 2006, August 2007 along the lower Yellow River occurred after the density current is poured. The fundamental reason for this phenomenon is the decrease of integrated roughness coefficient. Comprehensive roughness coefficient is an important parameter for the river flow dynamics and mathematical model,whose correct or not directly influence the accuracy of the model. After analyzing the factors influencing roughness, a BP neural network model is built to calculate the roughness. Median grain size of bed load, sediment concentration, median grain size of suspended load, Froude number is the input of the model, the roughness coefficient is the output of the model. Through the verification of the roughness coefficient in the course of the "04.8", "05.7", "06.8", "07.8", the results show that the neural network model can calculate roughness coefficient accurately. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Polygon Auto-Construction Algorithm Based on Vector External Product of Virtual Arc

    Publication Year: 2008 , Page(s): 24 - 27
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (240 KB) |  | HTML iconHTML  

    Various vector data to establish topological relation and association are the key issues of geographic information system, patch of the surface, that is polygon, whose generation is the core of establishing topology. This paper put forward auto-construction algorithm is to judge polygon's direction that based on azimuth left turn algorithm. Patch (polygon) auto-construction algorithm calculates azimuth, turning left to construct polygon. In the judge of polygon direction, establishing virtual arcs, calculating all of their relative vector external product, judging polygonal search direction is left or right, to certify search direction is unique. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Hybrid Ant Colony Algorithm for Clustering Problem

    Publication Year: 2008 , Page(s): 28 - 31
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (226 KB) |  | HTML iconHTML  

    The known mathematical model for clustering problems is given in this paper. With the K-Means algorithm, the simulated annealing algorithm and a novel hybrid ant colony algorithm is integrated with the K-means algorithm to solve clustering problems. The advantages and shortages of K-Means algorithm, simulated annealing algorithm and the hybrid ant colony algorithm are then analyzed, so that effectiveness of the hybrid ant colony algorithm would be illustrated through results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Environmental Quality Evaluation Based on BP Neural Network and PSO and Case Study

    Publication Year: 2008 , Page(s): 32 - 35
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (241 KB) |  | HTML iconHTML  

    Using particle swarm optimization (PSO) to optimize BP neural network model is proposed in this paper. The new model is more quickly and accurate. The basic idea of this model is: Firstly PSO is used to optimize the BP neural network's initialized weights, an optimized result is got; then based on the optimized result the BP neural network is used for further optimization. We can use this model for the environmental quality evaluation of Qinhuangdao Port regional. Finally we can get exactly appraise, this can be direct the environmental protection. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combined Kernel SVM and Its Application on Network Security Risk Evaluation

    Publication Year: 2008 , Page(s): 36 - 39
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (231 KB) |  | HTML iconHTML  

    Support vector machine SVM is a branch of artificial intelligence. SVM has many advantages in solving small sample size, nonlinear and high dimensional pattern recognition problem. Kernel function is the key technology of SVM, the choice of Kernel function will affect the learning ability and generalization ability of SVM, and different kernel function will construct different SVMS. At present, there are two types of kernel function, local kernel function which has better learning ability and whole kernel function which has better extensive ability. Since every traditional kernel function has its advantages and disadvantages, this paper analyze the principle of traditional kernel function and adopt a new kernel function of combined two kernel function, which called combined kernel function. It has better generalization ability and better learning ability, and adopt the combined kernel SVM into network security risk evaluation, compared with the SVM using traditional kernel. The result shows that the SVM based on combined kernels advance the speed of classification and has better classification precision than that with traditional kernels. The superiority and validity of this method is approved through experiment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application Research of Support Vector Machine in Network Security Risk Evaluation

    Publication Year: 2008 , Page(s): 40 - 43
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (223 KB) |  | HTML iconHTML  

    Along with the extensive application of the network, network security has received increasing attention recently.This paper researches on the network security risk evaluation and analyze the traditional risk evaluation methods, then proposes a new network security risk evaluation method based on Support Vector Machine (SVM) and Binary tree. Unlike the traditional risk evaluation methods, SVM is a novel type of learning machine technique which developed on structural risk minimization principle.SVM has many advantages in solving small sample size, nonlinear and high dimensional pattern recognition problem.The principles of SVM and binary tree are introduced in detail and apply it into network security risk assessment, it divided risk rate of network security into 4 different rates and more .Compare to ANN about the Classification precision, Generalization Performance, learning and testing time, it indicates that SVM has higher Classification precision, better generalization Performance and less learning and testing time, especially get a better assessment performance under small samples. It indicates that SVM has absolute superiority on network security risk evaluation, the validity and superiority of this method is approved through the experiment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward Domain-Driven Data Mining

    Publication Year: 2008 , Page(s): 44 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (285 KB) |  | HTML iconHTML  

    Traditional data mining is a data-driven trial-an-error process. It stops at discovered pattern/rule, either views data mining as an autonomous process, or only analyzes the issues in an isolated and case-by-case manner. As a result, the knowledge discovered is not interesting and actionable to constrained business. However, in many real world data mining tasks, for instance financial data mining in capital markets are highly constraint-based and domain- oriented. This paper proposes a new methodology named domain-driven data mining (DDDM), aims to discovery interesting and actionable knowledge for real user needs, overcome the gap between academia and business. DDDM integrates domain knowledge, expert experience, user interestingness, rule action ability and data into mining system. In this paper, A few basic concepts and methodologies are introduced firstly, after that the architecture is proposed and working detail is addressed. Finally, we specify issues that are either not addressed or insufficiently suited yet. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selection of Suppliers Based on Rough Set Theory and VIKOR Algorithm

    Publication Year: 2008 , Page(s): 49 - 52
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (207 KB) |  | HTML iconHTML  

    Selection of suppliers is the precondition and foundation of supply chain operation. It is an important aspect to choose the best supplier for supply chain management. During recent years, how to determine suitable suppliers in the supply chain has become a key strategic consideration. However, the nature of these decisions usually is complex and unstructured. The proposed methodology consists of two parts: 1) The RST is a fairly new methodology developed for dealing with imprecise, uncertain, and vague information. We assure the weight in the selection of a supplier based on Rough Set Theory (RST) model. 2) According to index systems we have established for selection of suppliers, we use VIKOR algorithm to select the best suppliers. At last, an example was shown and validation was proved. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Application of Intelligent System on Transforming Process of Alcohol

    Publication Year: 2008 , Page(s): 53 - 57
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (260 KB) |  | HTML iconHTML  

    With more and more cars be the usual commodities of people, drink-driving become a real intractable problem. For the characteristics of the process of drinking, the article use the signal system theory and dynamic equations to solve the problem. In this paper firstly describe the drinking process, and then according to the theory of atria-ventricle and state-variable analysis, establish the continuous system analysis model. Secondly by the use of dynamic equation theory, establish the dynamic equations for the entire transmission of the signal process. At last the paper give an application of this model. And by this means, not only can reflect the substance of the issue, but also be very good to be resolved. The result of the analysis will be helpful to the people who have the habit of drinking. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Construction of Index System Based on Improved Genetic Algorithm and Neural Network

    Publication Year: 2008 , Page(s): 58 - 61
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (227 KB) |  | HTML iconHTML  

    Artificial neural network (ANN) and genetic algorithm (GA) have both prevalent uses in large area. Along with the development of technology a method based on the combination of Artificial neural network (ANN) and genetic algorithm (GA) aroused. Now there is not a quantitative way on the problem of constructing the index system. In such a case, the paper uses the combination of Artificial neural network(ANN) and genetic algorithm (GA) to solve this problem. This paper firstly establishing feedforward neural network model and make sure about the input and output variables. Secondly improved genetic algorithm is used to solve the problem of network weight and threshold value which is constitute by three steps real codes, random selection and Genetic Manipulation of Chromosome. Moreover as it know to all, error back propagation(BP) algorithm is effective in local searching so adding error back propagation(BP) algorithm to genetic algorithm is a good way to get the satisfying result. Thirdly the paper gets the output of index effectiveness. Thirdly according to the entropy theory that the summation of effective value which could be involved in the index system should be larger than a certain critical value, the paper screened out the final index. Thus, in theory, gives a quantitative method of constructing the index system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Application of Genetic Algorithm on the Training of Neural Network for Acoustic Target Classification

    Publication Year: 2008 , Page(s): 62 - 65
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (270 KB) |  | HTML iconHTML  

    The paper adopted back-propagation neural network to classify acoustic target the wheeled and tracked vehicles was the researched target of this paper. Genetic Algorithm (GA) was first used to make global search of the suitable combination of the number of hidden nodes, the learning rate and momentum coefficient, the experiment in this paper will show that the neural network trained by GA has better performance in classifying wheeled and tracked target. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling of the Combustion Optimizing Based on Fuzzy Neural Networks

    Publication Year: 2008 , Page(s): 66 - 69
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (271 KB) |  | HTML iconHTML  

    A combustion optimizing model based on fuzzy neural networks is set up, and the optimization of providing coal volume is actualized. At the same time, the simulation model is established by MATLAB. The simulation research is processed. The simulation result indicates: in the stabilization state, if the boiler load, power plant coal character (the distinctness of coal heat glowing volume), combustion supplying air volume or combustion inducing air volume changes, the combustion optimizing model based on fuzzy neural networks can find the optimum value of providing coal volume. This result lays a strong base for optimal control and on-line prediction of the boiler. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimization Study on Resource Equilibrium with Fixed Time Limit for a Project Based on SPSO Algorithm

    Publication Year: 2008 , Page(s): 70 - 73
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (227 KB) |  | HTML iconHTML  

    During the course of construction, how to keep the utilization of resource balance, and avoid frequent and serious peak or low-vale of utilization is an important problem. The reasonable solution of the problem can reduce the scale of temporary establishments and economize expenditure furthest. The algorithm of SPSO was introduced into the optimization solution of resource equilibrium with fixed time limit for a project, the model considering multi-resource optimization was established and was improved at the aspect of algorithm to make it more adaptable to the calculation of SPSO. The sample analysis shows that the SPSO is superior to the traditional methods in resource optimization, and it can not only converge on the globally optimal solution effectively but also achieve different optimization schemes to provide several schemes for construction decision-making. The research fruits have important reference value on the construction management plan of a project. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.