Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Intelligence and Information Systems
Journal Basic Information
Journal DOI :
Korea Inteligent Information System Society
Editor in Chief :
Volume & Issues
Volume 7, Issue 2 - Dec 2001
Volume 7, Issue 1 - Jun 2001
Selecting the target year
Agent-Based Decision-Supporting System for Taguchi Experiment Planning
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 1~17
This paper deals with an agent-based decision-supporting system for Taguchi experiment planning. Among the four major parts of Taguchi experiment, the planning phase includes the most important decision-making issues such as determination of experiment objectives, quality characteristics, and control factors. The planning phase, however, has not been paid proper attention by experiment designers. In this research, an agent-based decision-supporting system for Taguchi experiment planning has been developed to facilitate the planning tasks of experiment designer. The decision-supporting system is composed of two agent-based mechanisms. The first employs an Internet agent that collects the domain knowledge from knowledge providers who may be distributed in remote places. Another agent then visualizes the collected knowledge and reports it to the experiment designer. Engineers who would normally have difficulties in collaborating because of limitations on their time or because they are in different places can easily work together in the same experiment team and brainstorm to make good decisions. The second agent-based mechanism offers context-sensitive advice generated by another intelligent agent during the experiment planning process. it prevents the experiment designer from making improper decisions, which will increase the feasibility of the experiment and minimize the unnecessary expense of time and resources.
Selection of Input Nodes in Artificial Neural Network for Bankruptcy Prediction by Link Weight Analysis Approach
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 19~33
Link weight analysis approach is suggested as a heuristic for selection of input nodes in artificial neural network for bankruptcy prediction. That is to analyze each input node\\\\`s link weight-absolute value of link weight between an input node and a hidden node in a well-trained neural network model. Prediction accuracy of three methods in this approach, -weak-linked-neurons elimination method, strong-linked-neurons selection method and integrated link weight model-is compared with that of decision tree and multivariate discrimination analysis. In result, the methods suggested in this study show higher accuracy than decision tree and multivariate discrimination analysis. Especially an integrated model has much higher accuracy than any individual models.
인위적 데이터를 이용한 군집분석 프로그램간의 비교에 대한 연구
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 35~49
Over the years, cluster analysis has become a popular tool for marketing and segmentation researchers. There are various methods for cluster analysis. Among them, K-means partitioning cluster analysis is the most popular segmentation method. However, because the cluster analysis is very sensitive to the initial configurations of the data set at hand, it becomes an important issue to select an appropriate starting configuration that is comparable with the clustering of the whole data so as to improve the reliability of the clustering results. Many programs for K-mean cluster analysis employ various methods to choose the initial seeds and compute the centroids of clusters. In this paper, we suggest a methodology to evaluate various clustering programs. Furthermore, to explore the usability of the methodology, we evaluate four clustering programs by using the methodology.
Feature Subset Selection in the Induction Algorithm using Sensitivity Analysis of Neural Networks
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 51~63
In supervised machine learning, an induction algorithm, which is able to extract rules from data with learning capability, provides a useful tool for data mining. Practical induction algorithms are known to degrade in prediction accuracy and generate complex rules unnecessarily when trained on data containing superfluous features. Thus it needs feature subset selection for better performance of them. In feature subset selection on the induction algorithm, wrapper method is repeatedly run it on the dataset using various feature subsets. But it is impractical to search the whole space exhaustively unless the features are small. This study proposes a heuristic method that uses sensitivity analysis of neural networks to the wrapper method for generating rules with higher possible accuracy. First it gives priority to all features using sensitivity analysis of neural networks. And it uses the wrapper method that searches the ordered feature space. In experiments to three datasets, we show that the suggested method is capable of selecting a feature subset that improves the performance of the induction algorithm within certain iteration.
Development of the Knowledge-Base Module for the STAFS Expert System Using Rule Derivation Methodology
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 65~81
This paper presets the process of knowledge aquisition by partitioning the phase of analysis & design for knowledge-base module construction of Expert System into five steps to derive rule systematically. Also, this paper presents the process and the task that knowledge engineer must do work each step. The knowledge-base module of STAFS expert system was constructed by considering the destruction rate and the commander\`s intention using the proposed rule derivation methodology.
A GA-based Rule Extraction for Bankruptcy Prediction Modeling
Shin, Kyung-shik ;
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 83~93
Prediction of corporate failure using past financial data is well-documented topic. Early studies of bankruptcy prediction used statistical techniques such as multiple discriminant analysis, logit and probit. Recently, however, numerous studies have demonstrated that artificial intelligence such as neural networks (NNs) can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. Although numerous theoretical and experimental studies reported the usefulness or neural networks in classification studies, there exists a major drawback in building and using the model. That is, the user can not readily comprehend the final rules that the neural network models acquire. We propose a genetic algorithms (GAs) approach in this study and illustrate how GAs can be applied to corporate failure prediction modeling. An advantage of GAs approach offers is that it is capable of extracting rules that are easy to understand for users like expert systems. The preliminary results show that rule extraction approach using GAs for bankruptcy prediction modeling is promising.
A Self-Organizing Map Neural Network Approach to Segmenting Knowledge Management Type of Venture Businesses in KOSDAG
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 95~115
We propose classifying the venture firms into four types of knowledge management. For this purpose, we collected questionnaire data from 101 venture firms listed in KOSDAQ, and applied a unsupervised neural network algorithm SOM to obtain four clusters representing knowledge management types-High Tech Type, Organizational Knowledge Type, Information Technology Type, and Beginner Type. Based on the results, we conclude that the venture firms listed in KOSDAQ should first know its own knowledge management type, and then apply appropriate strategies to take advantage of the knowledge management impacts on the competitiveness.
Decision Supprot System fr Arrival/Departure of Ships in Port by using Enhanced Genetic Programming
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 117~127
The Main object of this research is directed to LG Oil company harbor in kwangyang-hang, where various ships ranging from 300 ton to 48000ton DWT use seven berths in the harbor. This harbor suffered from inefficient and unsafe management procedures since it is difficult to set guidelines for arrival and departure of ships according to the weather conditions and the current guidelines dose not offer clear basis of its implications. Therefore, it has long been suggested that these guidelines should be improved. This paper proposes a decision-support system, which can quantitatively decide the possibility of entry or departure on a harbor by analyzing the weather conditions (wind, current, and wave) and taking account of factors such as harbor characteristics, ship characteristics, weight condition, and operator characteristics. This system has been verified using 5
berth in Kwangyang-hang harbor. Machine learning technique using genetic programming(GP) is introduced to the system to quantitatively decide and produce results about the possibility of entry or arrival, and weighted linear associative memory (WLAM) method is also used to reduce the amount of calculation the GP has to perform. Group of additive genetic programming trees (GAGPT) is also used to improve learning performance by making it easy to find global optimum.mum.
Design and Evaluation of Corporate Identity Symbol Marks by Hybrid Kansei Engineering
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 129~141
Kansei engineering or image technology is a tool to analyze relation between product design components and the impression or feeling of human for physical products. This paper attempts to construct the designer\`s aid tool for developing corporate identity(CI) symbol mark based on the hybrid Kansei engineering. It combines the forward Kansei engineering for translating consumer\`s feeling into design components of CI symbol mark and the backward Kansei engineering for evaluating consumer\`s feeling for CI symbol mark. The semantic differential(SD) evaluation experiment is carried out to find the relations between image and design. The backward Kansei engineering system is modelled by fuzzy neural network. This research is expected to contribute to the development of CI symbol mark that correspond to comsumer\`s image.
An On-Line Signature Verification Algorithm Based On Neural Network
Lee, Wan-Suck ; Kim, Seong-Hoon ;
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 143~151
This paper investigates the development of a neural network based system for automated signature authentication that relies on an autoregressive characterization for the segments of a signature. The primary contributions of this work are tow-fold: a) the development of the neural network architecture and the modalities of training it, b) adaptation of the dynamic time warping algorithm to fomulate a new method for enabling consistent segmentation of multiple signatures from the same writer. The performance of the signature verification system has been tested using a sizable database that includes a comprehensive set of simulated and realistic forgeries. False Acceptance and False Rejection error rates of 0.78% and 1.6% respectively were obtained in tests conducted using 1920 skilled forgeries.
Development of Intelligent Internet Shopping Mall Supporting Tool Based on Software Agents and Knowledge Discovery Technology
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 153~177
Nowadays, product recommendation is one of the important issues regarding both CRM and Internet shopping mall. Generally, a recommendation system tracks past actions of a group of users to make a recommendation to individual members of the group. The computer-mediated marketing and commerce have grown rapidly and thereby automatic recommendation methodologies have got great attentions. But the researches and commercial tools for product recommendation so far, still have many aspects that merit further considerations. To supplement those aspects, we devise a recommendation methodology by which we can get further recommendation effectiveness when applied to Internet shopping mall. The suggested methodology is based on web log information, product taxonomy, association rule mining, and decision tree learning. To implement this we also design and intelligent Internet shopping mall support system based on agent technology and develop it as a prototype system. We applied this methodology and the prototype system to a leading Korean Internet shopping mall and provide some experimental results. Through the experiment, we found that the suggested methodology can perform recommendation tasks both effectively and efficiently in real world problems. Its systematic validity issues are also discussed.
Exporting Business Process Modeling using IDEF3 and UML
Journal of Intelligence and Information Systems , volume 7, issue 2, 2001, Pages 179~193
A good modeling technique for system analysis and design is an essential area for the implementation of information system. Structured and object-oriented techniques are regarded as two standard in system modeling. This paper reviewed and implemented two system analysis and design techniques based-on IDEF3 and UML. IDEF3 is the first method used to analyze business process, which has the advantage of simplicity and brevity. UML provides visual standard which can represent the idea of system analysis from the people who participate in the system development process. UML is accepted as an industry standard from the object management group with the advantage of graphical representation of developer\`s view. This paper proposes system design and modeling perspectives based-on IDEF3 and UML techniques about the semi-structured business process for the medium-sized trading company.