Journal of Intelligence and Information Systems,
Vol. 9, No. 1, June 2003
The Study of a Multi-Mobile Agents System for Online Hotel Reservation
Suwan Kwak, and Mincheol Kang
Vol. 9, No. 1, Page: 1 ~ 21
Keywords : web agents, multi-agents, mobile agents
As electronic commerce(EC) has grown rapidly, agents that work on the behalf of humans on the Internet are being used actively. However, most of the EC agents have some problems. They fail to fully support buyers' decision making behaviors and sellers' information supply activities. Further, they are not suited for mobile computing environment. In this paper, we introduce a Multi-Mobile Agents System (MMAS) that has been developed according to a conceptual framework that corrects the aforementioned problems. Built by using Tokyo IBM ASDK(Aglets Software Development Kit) for the area of hotel reservation, the system consists of buyer- and seller-side agents that interact with each other; buyer-side agents help buyers to make purchasing decisions by collecting and analyzing information through applying a multi-criteria decision making method, while seller-side agents substitute fur sellers by managing databases and providing real-time information to the buyer-side agents. In this system, multiple agents perform their shared tasks at the same time in order to increase efficiency. Users do not have to keep the connection with the system because they are notified when tasks are done.
An Object-Oriented Case-Base Design and Similarity Measures for Bundle Products Recommendation Systems
Dae-Yul Jeong
Vol. 9, No. 1, Page: 23 ~ 51
Keywords : CBR(Case-Based Reasoning), Object-Oriented Case Representation, Similarity Measure
With the recent expansion of internet shopping mall, the importance of intelligent products recommendation agents has been increasing. for the products recommendation, This paper propose case-based reasoning approach, and developed a case-based bundle products recommendation system which can recommend a set of sea food used in family events. To apply CBR approach to the bundle products recommendation, it requires the following 4R steps : \circled1 Retrieval, \circled2 Reuse, \circled3 Revise, \circled4 Retain. To retrieve similar cases from the case-base efficiently, case representation scheme is most important. This paper used OW(Object Modeling Technique) to represent bundle products recommendation cases, and developed a similarity measure method to search similar cases. To measure similarity, we used weight-sum approach basically. Especially This paper propose the meaning and uses of taxonomies for representing case features.
Integrated Procedure of Self-Organizing Map Neural Network and Case-Based Reasoning for Multivariate Process Control
Boo Sik Kang
Vol. 9, No. 1, Page: 53 ~ 69
Keywords : Self-Organizing Map Neural Network, Case-Based Reasoning, Multivariate Process Control
Many process variables in modem manufacturing processes have influence on quality of products with complicated relationships. Therefore, it is necessary to control multiple quality variables in order to monitor abnormal signals in the processes. This study proposes an integrated procedure of self-organizing map (SOM) neural network and case-based reasoning (CBR) for multivariate process control. SOM generates patterns of quality variables. The patterns are compared with the reference patterns in order to decide whether their states are normal or abnormal using the goodness-of-fitness test. For validation, it generates artificial datasets consisting of six patterns, normal and abnormal patterns. Experimental results show that the abnormal patterns can be detected effectively. This study also shows that the CBR procedure enables to keep Type 2 error at very low level and reduce Type 1 error gradually, and then the proposed method can be a solution fur multivariate process control.
Aggregating Prediction Outputs of Multiple Classification Techniques Using Mixed Integer Programming
Hongkyu Jo, and Ingoo Han
Vol. 9, No. 1, Page: 71 ~ 89
Keywords : Bankruptcy prediction, artificial intelligence, hybrid prediction
Although many studies demonstrate that one technique outperforms the others for a given data set, there is often no way to tell a priori which of these techniques will be most effective in the classification problems. Alternatively, it has been suggested that a better approach to classification problem might be to integrate several different forecasting techniques. This study proposes the linearly combining methodology of different classification techniques. The methodology is developed to find the optimal combining weight and compute the weighted-average of different techniques' outputs. The proposed methodology is represented as the form of mixed integer programming. The objective function of proposed combining methodology is to minimize total misclassification cost which is the weighted-sum of two types of misclassification. To simplify the problem solving process, cutoff value is fixed and threshold function is removed. The form of mixed integer programming is solved with the branch and bound methods. The result showed that proposed methodology classified more accurately than any of techniques individually did. It is confirmed that Proposed methodology Predicts significantly better than individual techniques and the other combining methods.
Web-enabled Healthcare System for Hypertension: Hyperlink-based Inference Approach
Yong-Uk Song, Seung-Hee Ho, Young-Moon Chae, and Kyoung-Won Cho
Vol. 9, No. 1, Page: 91 ~ 107
Keywords : Expert Systems, HTML, Hypertension Inference
In the conduct of this study, a web-enabled healthcare system for the management of hypertension was implemented through a hyperlink-based inference approach. The hyperlink-based inference platform was implemented using the hypertext capacity of HTML which ensured accessibility, multimedia facilities, fast response, stability, ease of use and upgrade, and platform independency of expert systems. Many HTML documents, which are hyperlinked to each other based on expert rules, were uploaded beforehand to perform the hyperlink-based inference. The HTML documents were uploaded and maintained automatically by our proprietary tool called the Web-Based Inference System (WeBIS) that supports a graphical user interface (GUI) for the input and edit of decision graphs. Nevertheless, the editing task of the decision graph using the GUI tool is a time consuming and tedious chore when the knowledge engineer must perform it manually. Accordingly, this research implemented an automatic generator of the decision graph for the management of hypertension. As a result, this research suggests a methodology for the development of Web-enabled healthcare systems using the hyperlink-based inference approach and, as an example, implements a Web-enabled healthcare system for hypertension, a platform which performed especially well in the areas of speed and stability.
An Intelligent Agent Based Supply Chain Operation Architecture under Adaptive Relationship between Multiple Suppliers and Customers
Han Seong Yoon
Vol. 9, No. 1, Page: 109 ~ 123
The relationship between suppliers and customers is treated importantly not only in the traditional business-to-business (BtoB) commerce but also in today's Internet environments. On the one hand, most of Internet-based BtoB commerce services like customer-centric e-procurement, supplier-centric e-sales or intermediary-centric e-marketplace focus mainly on the selection of partners according to bidding, auction, etc. This point may result in the problem of overlooking the relationships between suppliers and customers. To overcome this problem in this paper, an intelligent agents-based supply chain operation architecture is proposed and appraised considering the relationship and its adaptation.
Development of a System for Recognizing Stamp Images
Min Jeong Song, and Kyungsook Han
Vol. 9, No. 1, Page: 125 ~ 137
Keywords : stamp image recognition, stretching, matching
In eastern countries stamps have been used more commonly than signatures when approving contracts and documents. Unlike finger prints, stamp images do not share similar patterns to each other and the resolution of stamp images is determined by the input status such as pressure under which stamps are put. This paper discusses the development of a system for recognizing stamp images of Korean or Chinese characters. Recognition of stamp images consists of several steps: acquisition of stamp images from an input device, digitization, contrast stretching, noise removal, and matching. We tested the system on 50 stamp images (20 stamp images of Korean characters, 20 images of Chinese characters, and 10 similar images). There was little difference in discrimination rate between the stamp images of Korean character and those of Chinese characters. 46 stamps images out of 50 were successfully recognized, resulting in 92% discrimination rate. Orientation and pressure under which stamps are put played an important role in determining discrimination rate. Automated stamp image recognition can be made more practical and useful by extending the types of stamp images to ellipses and rectangles and by improving the discrimination rate.
A Study on the Combined Decision Tree(C4.5) and Neural Network Algorithm for Classification of Mobile Telecommunication Customer
Keukno Lee, and Hongchul Lee
Vol. 9, No. 1, Page: 139 ~ 155
Keywords : Combined C4.5 and Neural Network, Classification, Prediction, Data Mining
This paper presents the new methodology of analyzing and classifying patterns of customers in mobile telecommunication market to enhance the performance of predicting the credit information based on the decision tree and neural network. With the application of variance selection process from decision tree, the systemic process of defining input vector's value and the rule generation were developed. In point of customer management, this research analyzes current customers and produces the patterns of them so that the company can maintain good customer relationship and makes special management on the customer who has huh potential of getting out of contract in advance. The real implementation of proposed method shows that the predicted accuracy is higher than existing methods such as decision tree(CART, C4.5), regression, neural network and combined model(CART and NN).
Application of data mining for improving and predicting yield in wafer fabrication system
Dong-Hyun Baek, and Chang-Hee Han
Vol. 9, No. 1, Page: 157 ~ 177
Keywords : data mining, wafer fabrication, yield
This paper presents a comprehensive and successful application of data mining methodologies to improve and predict wafer yield in a semiconductor wafer fabrication system. As the wafer fabrication process is getting more complex and the volume of technological data gathered continues to be vast, it is difficult to analyze the cause of yield deterioration effectively by means of statistical or heuristic approaches. To begin with this paper applies a clustering method to automatically identify AUF (Area Uniform Failure) phenomenon from data instead of naked eye that bad chips occurs in a specific area of wafer. Next, sequential pattern analysis and classification methods are applied to and out machines and parameters that are cause of low yield, respectively. Furthermore, radial bases function method is used to predict yield of wafers that are in process. Finally, this paper demonstrates an information system, Y2R-PLUS (Yield Rapid Ramp-up, Prediction, analysis & Up Support), that is developed in order to analyze and predict wafer yield in a korea semiconductor manufacturer.
Transactions Clustering based on Item Similarity
Sang Wook Lee, and Jae Yearn Kim
Vol. 9, No. 1, Page: 179 ~ 193
Keywords : clustering, item similarity, target marketing
Clustering is a data mining method which help discovering interesting data groups in large databases. In traditional data clustering, similarity between objects in the cluster is measured by pairwise similarity of objects. But we devise an advanced measurement called item similarity in this paper, in terms of nature of clustering transaction data and use this measurement to perform clustering. This new algorithm show the similarity by accepting the concept of relationship between different attributes. With this item similarity measurement, we develop an efficient clustering algorithm for target marketing in each group.

Advanced Search
Date Range