• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.208-212
• /
• 1998

This paper suggests the method to recognize the various defect patterns of cold mill strip using binary decision tree constructed by genetic algorithm automatically. In case of classifying the complex the complex patterns with high similarity like the defect patterns of cold mill strip, the selection of the optimal feature set and the structure of recognizer is important for high recognition rate. In this paper genetic algorithm is used to select a subset of the suitable features at each node in binary decision tree. The feature subset of maximum fitness is chosen and the patterns are classified into two classes by linear decision function. After this process is repeated at each node until all the patterns are classified respectively into individual classes. In this way , binary decision tree classifier is constructed automatically. After construction binary decision tree, the final recognizer is accomplished by the learning process of neural network using a set of standard p tterns at each node. In this paper, binary decision tree classifier is applied to recognition of the defect patterns of cold mill strip and the experimental results are given to show the usefulness of the proposed scheme.

• Journal of the Korea Institute of Building Construction
• /
• v.10 no.4
• /
• pp.95-103
• /
• 2010

The purpose of this study is to propose a decision-making technique for selecting waterproofing methods using the Analytic Hierarchy Process (AHP) technique. In this study, a questionnaire survey was given to a group of specialists, which included design specialists, construction specialists, and maintenance specialists, regarding their experience with roof waterproofing methods. The 1st level hierarchy of the questionnaire survey addressed the function, economics, and maintenance of each of the roof waterproofing methods. The rank of 13 items of questionnaire, which is the 2nd level hierarchy of the questionnaire survey, is calculated using Expert Choice Solution. The analysis of questionnaire survey shows that each specialist selects different roof waterproofing methods, and all specialists make much of waterproof performance.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.7
• /
• pp.1223-1233
• /
• 1992

Chemical and mechanical properties of workpieces and tools are important factors for selecting machining parameters in machining process planning. As there is no universal rule representing the machinability defined by metal removal rate, the selection of machining parameters still requires experience-oriented methods. In this paper, a new approach is presented to develop mathematical models for generating optimum machinability in turning processes based on chemical and mechanical properties of workpieces. Neural-Network methodology is introduced to identify mathematical models for machinability. It is confirmed by simulations that the proposed methodology can be used for developing numerical controllers with adaptive control performance.

• Journal of Fashion Business
• /
• v.9 no.3
• /
• pp.22-36
• /
• 2005

This research is to classify psychological risk perceptions in purchases process at counterfeit at fashion luxury brands, into a risk perception on purchase activity itself and a risk perception on the post-purchase situation, and to analyze types and characteristics at risk reduction behaviors to reduce each risk perception. In this research a qualitative method was employed, and research-related data were collected and analyzed through in-depth interviews. Results were shown that risk reduction behaviors at psychological risk perception on purchase activity itself included rationalization of purchase, accompanied purchase, reduction and discontinuance of purchase, and that risk reduction behaviors of psychological risk perception on the post-purchase situation included information search, establishment of selection criteria, establishment of marginal limit, selective purchase, planned and compared purchase, and reduction and discontinuance of purchase. Previous researches suggested brand loyalty, selection of famous brands, utilization of information agents by marketers, pre-purchase usage and guaranteed purchase, but these risk reduction methods were not utilized, this probably being interpreted as a result of characteristics of counterfeit. In addition, risk reduction behavior of one type tended to reduce risk perception of several other types, and risk reduction behaviors of various types were utilized to reduce a certain type's risk perception. Not only types of risk perception but also levels of risk perception appeared to have exerted influence to risk reduction behaviors.

• New & Renewable Energy
• /
• v.7 no.3
• /
• pp.83-91
• /
• 2011

The purpose of this study is to select appropriate location factors for wind power plant, provide detailed classification criteria, and find out appropriate sites for installing wind power plant in Gangwondo. In this study, the following 11 factors were extracted for site selection of wind power plant : wind resource, topography (valley angle, distance to the ridge), forest density, land use, preservation area, national park, Baekdu-Daegan, noise, shade, Transmission Line, and approaching roads. Each factor had relatively different level of importance so that AHP (Analytic Hierarchy Process) technique was used to calculated the weighted value per factor. For overlay analysis, classification criteria were prepared for each factor and each factor was classified into 3 grades : very appropriate, intermediate, poor. According to overlay analysis, the areas which received the highest grade (grade 5) was only in 0.16% of the total area of Gangwondo and had a tendency to exist along the mountain ridge over 600-meter elevation. Through analyzing the yearly average of wind power density, it was proved that the wind power density of areas with grade 4 or 5 had abundant wind resource over $400W/m^2$.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.3 no.2
• /
• pp.31-44
• /
• 2008

A selection technique for innovative projects on the beginning stage has been presented in this article. It can be applied in projects assessment in HEI, enterprises, development institutes, etc. It is rather difficult to assess the project quality on the beginning stage of R&D due to the uncertainty in the technical and economic indices but the new development analysis on this stage is of a great interest. By innovative project quality as a management object we will mean those characteristics relating to the results capacity of the projects and its realization process to satisfy the requirements to the innovative products competitiveness and their innovative attractiveness for investors. The most important question in the innovative projects management is the determination of its quality level under modern conditions. The aim of the research is to analyze and evaluate the decision making during the project management process. The objectives and hypotheses are assessment of an innovative project with the application of McKinsey's model is better to realizes by 3 stages: a) selection of optimal criteria; b) determination of weighing coefficients; c) projects positioning in a matrix.

• Journal of Korean Institute of Industrial Engineers
• /
• v.21 no.1
• /
• pp.85-101
• /
• 1995

Automated Guided Vehicles(AGVs) are widely used in computer integrated manufacturing(CIM) systems for material handling purposes. Although automated guided vehicles provide higher levels of flexibility and computer integrability, the installations are limited in number and one of the critical reasons lies in the complexity involved in the operation. The main objective of this research is to alleviate this problem by proposing efficient integrated operational control methods for AGV-based CIM systems. Particularly, this research is concerned with the mixed problem of dispatching automated guided vehicles and scheduling machines operation. The proposed dynamic heuristic algorithm uses various priority schemes and relevant information concerning the load of the system, the status of queues, and the position of AGVs in the scheduling process. The scheduling decision process is hierarchical in the sense that different decision criteria are applied sequentially to identify the most appropriate part to be served. This algorithm consists of two sections, the section of part selection by AGVs for the next service whenever an AGV completes the current assignment, and the section of part selection by machines for next service whenever a machine completes the current operation. The proposed algorithm has been compared with other scheduling schemes using the performance measure of mean flow-time and mean tardiness. Simulation results indicate that the proposed algorithm can reduce the mean flow-time and mean tardiness significantly.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.3
• /
• pp.89-97
• /
• 1997

A genetic algorithm (GA) is a stochastic direct search strategy that mimics the process of genetic evolution. The GA applied herein works on a population of structural designs at any one time, and uses a structured information exchange based on the principles of natural selection and wurvival of the fittest to recombine the most desirable features of the designs over a sequence of generations until the process converges to a "maximum fitness" design. Principles of genetics are adapted into a search procedure for structural optimization. The methods consist of three genetics operations mainly named selection, cross- over and mutation. In this study, a method of finding the optimum topology of truss/beam structure is pro- posed by using the GA. In order to use GA in the optimum topology problem, chromosomes to FEM elements are assigned, and a penalty function is used to include constraints into fitness function. The results show that the GA has the potential to be an effective tool for the optimal design of structures accounting for sizing, geometrical and topological variables.variables.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.857-866
• /
• 2011

The role of admissions officers is to evaluate the overall qualification of applicants, which consists of various qualitative and subjective metrics The core requirement of admissions officers is not only assessment of students' qualification based on the application but also verification of the data stem from the various sources. The issue for fairness on selection is the crucial agenda for the whole process of university entrance. The educational program aimed on the enhancement the expertise of admissions officers is required to guarantee the fair selection of whole evaluation process. In this paper we developed educational training program for admissions officers of J university. The 9 core dimensions of curriculum is presented to train admissions officers and the stepwise requirements of achieving each subject's goal are defined.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.8 no.1
• /
• pp.10-17
• /
• 2009

Spindle design is very important for the improvement of the competitive power in production cost of high quality machine tools. The important factor in spindle design is not only to improve the natural frequency of spindle but also to reduce displacement of spindle end. In this paper, parameters those influence on static and dynamic stiffness of high-speed spindle have selected form preceding studies. And those selected parameters are applied to Taguchi Method. To perform FEM analysis, bearing conditions are selected with optimized condition. To know how to improve static and dynamic stiffness of machine tool spindle, natural frequency and displacement of spindle end are obtained by FEM analysis. The Taguchi Method was used to draw optimized condition of bearing position and it's stiffness. From these results, amplitude of vibration is enough good less than $3{\mu}m$ pk-pk of the spindle of 40,000rpm manufactured in this work by the optimal design.