The task for chromosome analysis and diagnosis by experienced cytogenetists are being concerned as repetitive, time consuming job and expensive. For that reason, intelligent agent based on chromosome knowledge base has been established to be able to analyze chromosomes and obtain necessary advises from the knowledge base instead of human experts. That is to say, knowledge base by IF THEN production rule was implemented to a knowledge domain with normal and abnormal chromosomes, and then the inference results by knowledge base could enter the inference data into the database. Experimental data were composed of normal chromosomes of 2,736 patients 'cases and abnormal chromosomes of 259 patients' cases that have been obtained from GTG-banding metaphase peripheral blood and amniotic fluid samples. The completed intelligent agent for chromosome knowledge base provides variously morphological information by analysis of normal or abnormal chromosomes and it also has the advantage of being able to consult with user on chromosome analysis and diagnosis.

In computer graphics, most animations of characters have been created using the traditional and often highly labor intensive key-framing technique. Recently, character animation is demanded increasingly automated techniques for animation according to interaction with the user or environment of the user. In this paper, we will propose a new method which can animate characters automatical/y with user interactions. The character's behavior is determined as a result of understanding the emotional condition of the user. Psychology and cognitive AI provide some ideas about how to approach this problem. Our study is based mostly on the theories of Ortony, Clore and Collins, which were designed to be implemented computationally. In our system, we can make 22 emotion types and some more behavior features and we apply to some characters.

Any ERP system pushes a company toward full process integration and solves the fragmentation of information. However, the tight process integration can propagate and magnify mistakes made in one department into the other departments in real time. Thus, it can be posited that a central support system for the coordination can help ERP users and administrators dig out problems, take care of tedious validation and verification, and maintain process integration of ERP with great consistency. This paper ,proposes an agent-based ERP operations support system (EOSS) that aims at achieving and maintaining process integration of ERP at the highest level possible. With EOSS, the process integrity is monitored, with anomalies prevented as early as possible and repaired as precisely as possible.

Deleting unsolicited email, popularly known as spam mail, is an annoying task for Internet users. Moreover, spam mail causes a variety of social problems. At present, legal restrictions cannot eradicate spam senders. As a result many technical methods to eliminate spam mail such as spam filtering and online stamps have been introduced. However, the process of blocking spam mail can inadvertently result in suspension of indispensable or beneficial communication. In this paper, we propose a certificate and agent based emailing architecture that can block spam mail, while at the same time approve certified mail. This architecture can be accelerated by synergistic utilization of digital signature and electronic document interchange.

A multi-agent technology has emerged as a new paradigm that can flexibly and promptly cope with various environmental changes and complex problems. Accordingly, many researches are being made to establish multi-agent systems in an effort to solve dynamic problems in many fields. However, most previous researches on the multi-agent frameworks aimed at, on behalf of a user, exchanging and sharing information between agents, reusing agents, and suggesting job cooperation in order to integrate and assimilate heterogeneous agents. That is to say, their frameworks mainly focused on the basic functions of general multi-agent. Therefore, they are not suitable to the development of the proper system for a specific field such ,.s a negotiation. In an effort to solve this problem, this research has tried to design a multi-agent framework-base negotiation system, so that for the sake of a user it can evaluate the negotiation messages, manage the negotiation messages, and quickly and exactly exchange messages between negotiation agents. First of all, we have made research on the basic functions hat are necessary in the development of a negotiation system, and then have analyzed the limitations of existing multi-agent frameworks when trying to apply them to a negotiation system. After these efforts, this study suggests a design of multi-agent framework to develop a negotiation system.

GDS (Grating automatic Drawing System), which is automatic design system of metal products called grating, is a system that produces various detailed drawings on the basis of information within a Plan Drawing that represents layout of the gratings such as locations, shapes, directions, etc However, automatically produced drawings by GDS do not fully satisfy the standard of the general dimension marking method used among the layout designers. The lack of this standard quality mainly results from the fact that overlapping among dimension markings appears frequently. To solve the overlapping problem we applied the rule-based expert system. The rules for the expert system are designed based on the expertise of skilled layout designers within the grating production lines.

In the development of complex software system, it is important to use hierarchical use case model due to the complex scope of development procedure. The use case model is core factor of the OMG (Object Management Group)'s UML (Unified Modeling Language) diagrams. In this paper, we propose a novel method to check syntactic consistency automatically in use case models at the different level of abstraction. This method is a rule-based approach which utilizes actor tree, use case tree and use case description. The proposed method is simulated on ITS (Intelligent Transportation System) architecture for the verification.

Achieving the beneficiary goal of recent discovery in human genome project still needs a way to retrieve and analyze the exponentially expanding bio-related information. Research on bio-related fields naturally applies knowledge discovered to the current problem and make inferences to extract new information where shared concepts and data containing information need to be defined and used in a coherent way. In such a professional domain, while the need to help users reduce their work and to improve search results has been emerged. methods for systematic retrieval and adequate exchange of relevant information are still in their infancy. The design of our system aims at improving the quality of information retrieval in a professional domain by utilizing both corpus-based and concept-based ontology. Meta-rules of helping users to make an adequate query are formed into an ontology in the domain. The integration of those knowledge permits the system to retrieve relevant information in a more semantic and systematic fashion. This work mainly describes the query models with details of GUI and a secondary query generation of the system.

As complex mathematical models are increasingly adopted for business decision-making, difficulties arise in reusing solvers (i.e., model solving algorithms) against diverse models and data sets and thus the collaboration among users (model/solver builders and decision makers) in multiple departments becomes very difficult. To facilitate the solver reuse, this paper adopts the Web services technologies as the base technologies for linking the solvers to the models, both of which are created on different modeling paradigms and different system platforms, in unified system architecture. Specifically, this paper focuses on designing an ontology that represents the interfacing semantics of the model-solver interactions in a general and standardized form. By referring to the ontology, a model management system (MMS) can autonomously suggest a set of compatible solvers and apply them to individual models even though the decision makers are not knowledgeable enough about all the details of the models and the solvers. Thus, this Web services based MMS would improve the reusability of the solvers by relieving the decision makers from the risk of erroneous application of a solver to syntactically and semantically incompatible models and the burden of considerable understanding of model and solver semantics.

In managing organizational tacit knowledge, recent researches have shown that it is more applicable in many ways to provide expert search mechanisms in KMS to pinpoint experts in the organizations with searched expertise. In this paper, we propose an intelligent expert search framework to provide search capabilities for experts in similar or related fields according to the user's information needs. In enabling intelligent expert searches, Fuzzy Abstraction Hierarchy (FAH) framework has been adopted, through which finding experts with similar or related expertise is possible according to the subject field hierarchy defined in the system. To improve FAH, a text categorization approach called Vector Space Model is utilized. To test applicability and practicality of the proposed framework, the prototype system, "Knowledge Portal for Researchers in Science and Technology" sponsored by the Ministry of Science and Technology (MOST) of Korea, was developed.

A Genetic algorithm is a searching algorithm that based on the law of the survival of the fittest. Multi-population Genetic Algorithms are a modified form of genetic algorithm. Therefore, experience with fuzzy logic and genetic algorithm has proven to be that a combination of them can efficiently make up for their own deficiency. The Multi-population Genetic Algorithms independently evolve subpopulations. In this paper, we suggest a new coding method that independently evolves subpopulations using the fuzzy logic controller. The fuzzy logic controller has applied two fuzzy logic controllers that are implemented to adaptively adjust the crossover rate and mutation rate during the optimization process. The migration scheme in the multi-population genetic algorithms using fuzzy logic controllers is tested for a function optimization problem, and compared with other group migration schemes, therefore the groups migration scheme is then performed. The results demonstrate that the migration scheme in the multi-population genetic algorithms using fuzzy logic controller has a much better performance.

This paper proposes the enhanced REF network, which arbitrates learning rate and momentum dynamically by using the fuzzy system, to arbitrate the connected weight effectively between the middle layer of REF network and the output layer of REF network. ART2 is applied to as the learning structure between the input layer and the middle layer and the proposed auto-turning method of arbitrating the learning rate as the method of arbitrating the connected weight between the middle layer and the output layer. The enhancement of proposed method in terms of learning speed and convergence is verified as a result of comparing it with the conventional delta-bar-delta algorithm and the REF network on the basis of the ART2 to evaluate the efficiency of learning of the proposed method.

The automatic recognition of transport containers using image processing is very hard because of the irregular size and position of identifiers, diverse colors of background and identifiers, and the impaired shapes of identifiers caused by container damages and the bent surface of container, etc. We proposed and evaluated the novel recognition algorithm of container identifiers that overcomes effectively the hardness and recognizes identifiers from container images captured in the various environments. The proposed algorithm, first, extracts the area including only all identifiers from container images by using CANNY masking and bi-directional histogram method. The extracted identifier area is binarized by the fuzzy binarization method newly proposed in this paper and by applying contour tracking method to the binarized area, container identifiers which are targets of recognition are extracted. We proposed and applied the ART2-based RBF network for recognition of container identifiers. The results of experiment for performance evaluation on the real container images showed that the proposed algorithm has more improved performance in the extraction and recognition of container identifiers than the previous algorithms.

In this research, we proposed the mechanism to develop self evolving expert systems (SEES) based on data mining (DM), fuzzy neural networks (FNN), and relational database (RDB)-driven forward/backward inference engine. Most former researchers tried to develop a text-oriented knowledge base (KB) and inference engine (IE). However, thy have some limitations such as 1) automatic rule extraction, 2) manipulation of ambiguousness in knowledge, 3) expandability of knowledge base, and 4) speed of inference. To overcome these limitations, many of researchers had tried to develop an automatic knowledge extraction and refining mechanisms. As a result, the adaptability of the expert systems was improved. Nonetheless, they didn't suggest a hybrid and generalized solution to develop self-evolving expert systems. To this purpose, in this study, we propose an automatic knowledge acquisition and composite inference mechanism based on DM, FNN, and RDB-driven inference. Our proposed mechanism has five advantages empirically. First, it could extract and reduce the specific domain knowledge from incomplete database by using data mining algorithm. Second, our proposed mechanism could manipulate the ambiguousness in knowledge by using fuzzy membership functions. Third, it could construct the relational knowledge base and expand the knowledge base unlimitedly with RDBMS (relational database management systems). Fourth, our proposed hybrid data mining mechanism can reflect both association rule-based logical inference and complicate fuzzy logic. Fifth, RDB-driven forward and backward inference is faster than the traditional text-oriented inference.

Collaborative filtering is one of the methodologies that are most widely used for recommendation system. It is based on a data matrix of each customer's preferences of products. There could be a lot of missing values in such preference. data matrix. This incomplete data is one of the reasons to deteriorate the accuracy of recommendation system. Multiple imputation method imputes m values for each missing value. It overcomes flaws of single imputation approaches through considering the uncertainty of missing values.. The objective of this paper is to suggest multiple imputation-based collaborative filtering approach for recommendation system to improve the accuracy in prediction performance. The experimental works show that the proposed approach provides better performance than the traditional Collaborative filtering approach, especially in case that there are a lot of missing values in dataset used for recommendation system.

As the wireless communication technology advances rapidly, a personalization technology can be incorporated with the mobile Internet environment, which is based on location-based services to support more accurate personalized services. A location-based personalized recommender system is one of the essential technologies of the location-based application services, and is also a crucial technology for the ubiquitous environment. In this paper we propose a framework of a location-based personalized recommender system for the mobile Internet environment. The proposed system consists of three modules the interface module, the neighbor selection module and the prediction and recommendation module. The proposed system incorporates the concept of the recommendation system in the Electronic Commerce along with that of the mobile devices for possible expansion of services on the mobile devices. Finally a service scenario for entertainment recommendation based on the proposed recommender system is described.

In data mining, having access to large amount of data sets for the purpose of predictive data does not guarantee good method, even where the size of Real data is Mobile commerce unlimited. In addition to searching expected Goods objects for Users, it becomes necessary to develop a recommendation service based on XML. In this paper, we design the optimized XML Recommender product data. Efficient XML data preprocessing is required, include of formatting, structural, and attribute representation with dependent on User Profile Information. Our goal is to find a relationship among user interested products from E-Commerce and M-Commerce to XDB. Firstly, analyzing user profiles information. In the result creating clusters with analyzed user profile such as with set of sex, age, job. Secondly, it is clustering XML data which are associative products classify from user profile in shopping mall. Thirdly, after composing categories and goods data in which associative objects exist from the first clustering, it represent categories and goods in shopping mall and optimized clustering XML data which are personalized products. The proposed personalized user profile clustering method has been designed and simulated to demonstrate it's efficient.

Although the research on electronic commerce is plentiful, there is little empirical research related to Web-Based Shopping Systems (WBSS). This is especially so in global electronic commerce circumstances. WBSS are the fastest growing segment of digital economies and are perceived as driving forces of electronic commerce in terms of global markets and digital business. Using WBSS, organizations have a new chance of their business evolving successfully as global marketers. This paper develops a unified model to assess the diffusion of WBSS. Factors that impact WBSS diffusion are identified and analyzed as the basis for empirical testing. A set of propositions is developed that allows operationalization of the model. The ultimate goal is to provide the new research insights for the academic circles and the practical guidelines for organizations wishing to undertake WBSS.

Customer retention is a common concern for many industries and a critical issue for the survival in today's greatly compressed marketplace. Current customer retention models only focus on detection of potential defectors based on the likelihood of defection by using demographic and customer profile information. In this paper, we propose a dynamic procedure for defection detection and prevention using past and current customer behavior by utilizing SOM and Markov chain. The basic idea originates from the observation that a customer has a tendency to change his behavior (i.e. trim-out his usage volumes) before his eventual withdrawal. This gradual pulling out process offers the company the opportunity to detect the defection signals. With this approach, we have two significant benefits compared with existing defection detection studies. First, our procedure can predict when the potential defectors could withdraw and this feature helps to give marketing managers ample lead-time for preparing defection prevention plans. The second benefit is that our approach can provide a procedure for not only defection detection but also defection prevention, which could suggest the desirable behavior state for the next period so as to lower the likelihood of defection. We applied our dynamic procedure for defection detection and prevention to the online gaming industry. Our suggested procedure could predict potential defectors without deterioration of prediction accuracy compared to that of the MLP neural network and DT.

Credit scoring system (CSS) starts from an analysis of delinquency trend of each individual or industry. This paper conducts a research on credit card delinquency of bank customers as a preliminary step for building effective credit scoring system to prevent excess loan or bad credit status. To serve this purpose, we use association rules that ore generating method. Specifically, we generate sets of rules of customers who are in bad credit status because of delinquency by using association rules. We expect that the sets of rules generated by association rules could act as an estimator of good or bad credit status classifier.

Today's network consists of a large number of routers and servers running a variety of applications. Policy-based network provides a means by which the management process can be simplified and largely automated. In this paper we build a foundation of policy-based network modeling and simulation environment. The procedure and structure for the induction of policy rules from vulnerabilities stored in SVDB (Simulation based Vulnerability Data Base) are developed. The structure also transforms the policy rules into PCIM (Policy Core Information Model). The effect on a particular policy can be tested and analyzed through the simulation with the PCIMs and SVDB.

This paper investigates the lifestyles in Korean market. We will classify the groups using cluster analysis, and exploit the characteristics of innovators. These groups can be verified by multiple comparisons. This research is accomplished by sample survey between June 92003 and June 27 2003. Korean market for innovation can be classified into four groups such as innovators, early adopters, late majority, and laggards, which are similar to Rodger's classification. The ratios of four groups are 11%, 24.4%, 48.9%, 15.7% respectively. innovators, and late majority are heavy groups in that early adopter group is omitted on the contrary. Whereas innovators have a tendency to adopt the innovation quickly, rest groups have resistance for innovations and adopt slowly. The brief demographic characteristics of innovators are that the ratio of students is 44.44%, the ratio of single is 69.44%, the age between 15 and 25 is 56.95%, and the salary is relatively low compared with other cluster. The summary of lifestyle of innovators is that they are active, want to do worldwide business, want to have good relationship with high society, want to know the information of innovations, etc.

A project planning is one of the most important processes that determines success and failure of the project. A pre-project planning is also essential job for information system implementations at the early stage of project planning, especially for management information system like ERP. However, pre-project planning is very difficult, because lots of factors and their relationships should be considered. Pre-project planning of ERP implementation has been done by project manager's own knowledge and experiences. In this article, we propose a system that help project manager to make a pre-project plan of ERP project with case-based reasoning(CBR) framework. The proposed CBR system saves previous cases of ERP pre-project planning in the case base. Then, the system finds the best similar case with the current pre-project planning problem. Project manager can make a pre-project plan by adjusting the most similar case. From the interview with project managers, we collect some field cases of ERP implementation. We organized these cases by using XML(Extensible Markup Language), which is good for representing hierarchical information. XML gives us some flexibilities to correct and maintain cases. We make a prototype system, PPSS(Project Planning Support System) that help project manager to make a pre-project plan of ERP implementations. The object of the system is to support project manager to make a pre-project plan of ERP. We hope the result of the study can be applied to other information systems. Our research should be extended to cover other stages of project planning.

Case-based reasoning (CBR) often shows significant promise for improving effectiveness of complex and unstructured decision making. Consequently, it has been applied to various problem-solving areas including manufacturing, finance and marketing. However, the design of appropriate case indexing and retrieval mechanisms to improve the performance of CBR is still challenging issue. Most of previous studies to improve the effectiveness for CBR have focused on the similarity function or optimization of case features and their weights. However, according to some of prior researches, finding the optimal k parameter for k-nearest neighbor (k-NN) is also crucial to improve the performance of CBR system. Nonetheless, there have been few attempts which have tried to optimize the number of neighbors, especially using artificial intelligence (AI) techniques. In this study, we introduce a genetic algorithm (GA) to optimize the number of neighbors to combine. This study applies the new model to the real-world case provided by an online shopping mall in Korea. Experimental results show that a GA-optimized k-NN approach outperforms other AI techniques for purchasing behavior forecasting.

Due to the rapid growth of Internet, means of communication with customers in a traditional customer support environment such as telephone calls are being replaced by mainly e-mail in a Web-based customer support system. Although such a Web-based support is efficient and promises potential benefits for firms, including reduced transaction costs, reduced time, and high quality of support, there are some difficulties associated with responding to many types of customer’s inbound e-mails appropriately .As many types of e-mail are received, considerable attention is being paid to methods for increasing the efficiency of managing and responding e-mails. This research proposes an intelligent system for managing customer’s inbound e-mails in organizations by applying case based reasoning technique for responding to various customers' inbound e-mails more effectively. In this approach, a case is represented as a frame-typed data structure corresponding to an inbound e-mail, keywords, and its reply e-mail. In the retrieval procedure, keywords and affinity set is developed to index a case, and then the case is represented as a vector, a case vector. Also, cosines value is calculated to measure the similarity between a new inbound e-mail and the cases in the case base. In the adaptation procedure, we provide several adaptation strategies to adapt and modify the retrieved case. The strategies guide to make an outbound e-mail using product databases, databases for customer support, etc. Additionally, the Web-based system architecture is proposed to implement our methodology. The proposed methodology and system will be helpful for developing more efficient Web-based customer support.

Product factory is a real-time financial product design system for the Internet customers. Recently, as the number of the Internet customers increases, the importance of the product factory becomes more emphasized. However, there is not much research performed regarding its definition, properties, requirements, nor implementation. In this research, we make a clear definition of product factory, and analyze the requirements of the system from the perspectives of functions and services, and we propose an architecture that reflects the analyzed requirements. In additions, we implemented a prototypical system based on the proposed architecture to prove the usefulness of this research.

With the growing usage of the networks, the world-wide Internet has become the main means to exchange data and carry out transactions. It has also become the main means to attack hosts. To solve the security problems which occur in the network such as Internet, we import software products of network security elements like an IDS (Intrusion Detection System) and a firewall. In this paper, we have designed and constructed the General Simulation Environment of Network Security model composed of multiple IDSes and a firewall which coordinate by CNP (Contract Net Protocol) for the effective detection of the intrusion. The CNP, the methodology for efficient integration of computer systems on heterogeneous environment such as distributed systems, is essentially a collection of agents, which cooperate to resolve a problem. Command console in the CNP is a manager who controls tie execution of agents or a contractee, who performs intrusion detection. In the Network Security model, each model of simulation environment is hierarchically designed by DEVS (Discrete EVent system Specification) formalism. The purpose of this simulation is to evaluate the characteristics and performance of CNP architecture with rete pattern matching algorithm and the application of rete pattern matching algorithm for the speeding up the inference cycle phases of the intrusion detection expert system.

For the effective use of information in the information society, information should be protected and outflow of information by illegal users should be prevented. This study sets up user authentication policy, user authentication regulations and procedures for information protection and builds information protection key distribution center and encryption user Authentication system, which can protect information from illegal users.

Network security should be first considered in a distributed computing environment with frequent information interchange through internet. Clear classification is needed for information users should protect and for information open outside. Basically proper encrypted database system should be constructed for information security, and security policy should be planned for each site. This paper describes access control, user authentication, and User Security and Encryption technology for the construction of database security system from network users. We propose model of network encrypted database security system for combining these elements through the analysis of operational and technological elements. Systematic combination of operational and technological elements with proposed model can construct encrypted database security system secured from unauthorized users in distributed computing environment.

Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e 'g', documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors, and are usually high-dimensional data. The performance of conventional multidimensional data structures(e'g', R- Tree family, K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R＊-tree is the most successful variant of the R-tree. In this paper, we propose a SOM-based R＊-tree as a new indexing method for high-dimensional feature vectors.The SOM-based R＊-tree combines SOM and R＊-tree to achieve search performance more scalable to high dimensionalities. Self-Organizing Maps (SOMs) provide mapping from high-dimensional feature vectors onto a two dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological of the feature map, and preserves the mutual relationship (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. Each node of the topological feature map holds a codebook vector. A best-matching-image-list. (BMIL) holds similar images that are closest to each codebook vector. In a topological feature map, there are empty nodes in which no image is classified. When we build an R＊-tree, we use codebook vectors of topological feature map which eliminates the empty nodes that cause unnecessary disk access and degrade retrieval performance. We experimentally compare the retrieval time cost of a SOM-based R＊-tree with that of an SOM and an R＊-tree using color feature vectors extracted from 40, 000 images. The result show that the SOM-based R＊-tree outperforms both the SOM and R＊-tree due to the reduction of the number of nodes required to build R＊-tree and retrieval time cost.

Network infrastructure has spread to an unprecedented extent and is used in various computing devices, such as smart appliances, smart phones, and embedded devices with sensors, which have all been appearing in the computing environment. To accommodate this trend, for a more intelligent service environment, the service platform needs to have abilities that facilitate the operation between services, dynamically share distributed computing resources, and manage appropriate contextual information. We have simulated a service platform to provide intelligent services using contextual information after having implemented the context management service. The context management service gathers raw contextual information from sensors and stores these in the context database. For a consistent basis of contextual information, time and location are used as the key values of the contextual information. The context management service also performs normalization to provide computable contextual information to context-aware applications. In this paper, a service platform based on Jini technology is proposed for constructing an interoperable, dynamic, and . intelligent service environment using contextual information.

ATM ABR service controls network traffic using feedback information on the network congestion situation in order to guarantee the demanded service qualities and the available cell rates. In this paper we apply the control method using queue length prediction to the formation of feedback information for more efficient ABR traffic control. If backward node receive the longer delayed feedback information on the impending congestion, the switch can be already congested from the uncontrolled arriving traffic and the fluctuation of queue length can be inefficiently high in the continuing time intervals. The feedback control method proposed in this paper predicts the queue length in the switch using the slope of queue length prediction function and queue length changes in time-series. The predicted congestion information is backward to the node. NLMS and neural network are used as the predictive control functions, and they are compared from performance on the queue length prediction. Simulation results show the efficiency of the proposed method compared to the feedback control method without the prediction. Therefore, we conclude that the efficient congestion and stability of the queue length controls are possible using the prediction scheme that can resolve the problems caused from the longer delays of the feedback information.

This system is unionized form about GPS and a pocket game machine. This game machine of the use only for the game with an existing system but the function of various purposes which carries out service relevant to a user's position information. This system have the game function, the function to offer space guidance service by the theme interlocked with a user's position, and the traffic safety education function.