Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Korean Institute of Industrial Engineers
Journal Basic Information
Journal DOI :
Korean Institute of Industrial Engineers
Editor in Chief :
Volume & Issues
Volume 26, Issue 4 - Dec 2000
Volume 26, Issue 3 - Sep 2000
Volume 26, Issue 2 - Jun 2000
Volume 26, Issue 1 - Mar 2000
Selecting the target year
A PNN approach for combining multiple forecasts
Jun, Duk-Bin ; Shin, Hyo-Duk ; Lee, Jung-Jin ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 193~199
In many studies, considerable attention has been focussed upon choosing a model which represents underlying process of time series and forecasting the future. In the real world, however, there may be some cases that one model can not reflect all the characteristics of original time series. Under such circumstances, we may get better performance by combining the forecasts from several models. The most popular methods for combining forecasts involve taking a weighted average of multiple forecasts. But the weights are usually unstable. In cases the assumptions of normality and unbiasedness for forecast errors are satisfied, a Bayesian method can be used for updating the weights. In the real world, however, there are many circumstances the Bayesian method is not appropriate. This paper proposes a PNN(Probabilistic Neural Net) approach as a method for combining forecasts that can be applied when the assumption of normality or unbiasedness for forecast errors is not satisfied. In this paper, PNN method, which is similar to Bayesian approach, is suggested as an updating method of the unstable weights in the combination of the forecasts. The PNN method has been usually used in the field of pattern recognition. Unlike the Bayesian approach, it requires no assumption of a specific prior distribution because it gets probabilities by using the distribution estimated from given data. Empirical results reveal that the PNN method offers superior predictive capabilities.
An Economic Design of a Screening and Process Monitoring Procedure for a Normal Model
Kwon, Hyuck-Moo ; Hong, Sung-Hoon ; Lee, Min-Koo ; Kim, Sang-Boo ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 200~205
An economic process monitoring procedure is presented using a surrogate variable for the case where performance variable is dichotomous. Every item is inspected with a surrogate variable and determined whether it should be accepted or rejected. When an item is rejected, the previous number of consecutively accepted items is compared with a predetermined number r to decide whether there is a shift in fraction nonconforming or not. The conditional distribution of the surrogate variable given the performance variable is assumed to be normal. A cost model is constructed which includes costs of inspection, misclassification, illegal signal, undetected out-of-control state, and correction. Methods of finding the optimum number r and screening limit are provided. Numerical studies on the effects of cost coefficients are also performed.
An Approximate Analysis of the M/M/1/1/ Queue with Finite Number of Retrials
Sung, Ki-Won ; Chae, Kyung-Chul ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 206~212
We consider the M/M/1/1 retrial queue where the maximum number of retrials is fixed by a constant. We present an efficient approximate procedure for mean performance measures and the loss probability. The approximate results are satisfactory when compared with simulation results.
Using Dirichlet Probability Model to Combine AHP Priorities
Kim, Sung-Chul ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 213~219
Combination of AHP priorities is essential in combining opinions of multiple experts. There are two ways to get combined priorities: one is to combine the pairwise matrices and obtain the priority from it and another is to combine the individual priorities. In this paper, we use a Dirichlet probability model to combine the priorities from multiple experts. The resulting combined priority is an expected value of the model, which is a function of some measure of the homogeneity and credibility of the group of experts. We give some interpretations of this measure and illustrate them by numerical example.
A linear program approach for optimizing a linear function over an efficient set
Song, Jung-Hwan ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 220~226
The problem (P) of optimizing a linear function
over the set of efficient points for a multiple objective linear program (M) is difficult because the efficient set is nonconvex. There are some interesting properties between the objective linear vector d and the matrix of multiple objectives C and those properties lead us to establish criteria to solve (P) with a linear program. In this paper we investigate a system of the linear equations
= d and construct two linearly independent positive vectors u, v such that
= u - v. From those vectors u, v, solving an weighted sum linear program for finding an efficient extreme point for the (M) is a way of getting an optimal solution of the problem (P). Therefore the theorems presented in this paper provided us an easy way of solving nonconvex program (P) with a weighted sum linear program.
Automatic Enactment of Workflow Processes using Active Databases
Bae, Joon-Soo ; Kim, Yeong-Ho ; Kang, Suk-Ho ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 227~237
A workflow management system is a software system to assist designing processes, controlling and managing the execution of the designed processes. One emerging trend in many recent information systems is the provision of process management functions. In this paper, we propose a method of designing processes for automatic process execution directly from process modeling. First of all, the concept of block is presented which is to define a nested process model. A block is the minimum unit that can specify the relationships of process components, i.e., tasks. A general process can be defined by a combination of the blocks defined in this paper. An algorithm is developed to transform a general flat process model into a nested model. We identify basic types of blocks and build ECA (Event-Condition-Action) rules for each of the basic types. This allows us to automate the execution of the process model by using the active features of active databases.
An AGV control policy reflecting the current and future status information of a semiconductor and LCD production shop
Suh, Jung-Dae ; Jang, Jae-Jin ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 238~248
Facilities are getting more automated and informative in modern manufacturing systems, especially in semiconductor and LCD plants. These systems keep a great deal of such information on its current and near-future status as the arrival time and job completion time of their parts. This paper presents an efficient policy for AGV and part routing using information on the future status of the system where AGVs are playing a central role for material handling. Efficient control of AGVs is very important because AGV systems often become the bottleneck and limit the total production capacity of a very expensive plant. The cell controller records the future events chronologically in Next Event Schedule, and uses this list to determine to which place the AGVs and parts to be sent.
Bond Immunization Model with Non-parallel shift Term-Structure using Partial Duration
Park, Woo-Cheol ; Choi, Gyung-Hyun ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 249~256
Bond immunization model is used to minimize interest rate risk for investing in fixed-income market, the model equalizes asset and liability values using the duration which is the sensitivity of portfolio value with respect to the interest rate. However this model might generate an error in practice because the model is based on unreal hypothesis, so called "Parallel Shift Term Structure". In this paper, we use the neural network approach to overcome the parallel shift term structure and try to employ this term structure function to the traditional immunization model. Finally, we present some computational test results that show the superiority of the partial immunization model to the traditional methods.
A Development of an Occupant Packaging Tool Using 3-Dimensional Coordinates in Passenger Vehicle's Driver Space
Chung, Sung-Jae ; Park, Min-Yong ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 257~264
This research suggested a method by which the driver space can be designed to best accommodate the driver's anthropometric characteristics. Three-dimensional manikins and a variable seating buck were developed and used for this study. Manikins were designed with 18 links comprising the 95th percentile male and 5th percentile female data. The seating buck was built to create various driving environments using the distance and the height between the H-point(hip pivot) of the seat and the AHP(accelerator heel point), the angle of the back rest, the angle of the steering wheel, the vertical distance of the steering wheel, and the location of the T.G.S.(transmission gear shift) knob. Measurements of each variable were collected with a coordinate measuring machine by positioning the 3-D manikin under various combinations of the design factors of the seating buck, which was constructed based on mid-size domestic passenger cars. The data were then converted to the joint angles of the driver. The combination of the measurements for an optimal driving environment is suggested by applying sets of the joint angles at which the driver feels comfortable.
Product Liability and a Product Safety Policy
Byun, Seong-Nam ; Lee, Dong-Hoon ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 265~282
Despite manufacturers' effort to provide safe and reliable products, a number of product-related accidents occur all over the world resulting in much damage to property, personal injury and even loss of life. Considerable evidence indicates that some accidents arise from user negligence, but most are due to the design, manufacture, and distribution of unreasonably dangerous products when compared to their use. As a result, a tremendous number of product liability lawsuits have been filed, many times causing huge amount of financial damages to manufacturers. Furthermore, with increasing government regulation and growing power of consumer lobbies, manufacturers might be more exposed to product liability claims in the future than now. The objectives of this study are twofold: to provide a framework of future research on product liability and safety and to introduce a product safety policy. To accomplish these objectives, previous studies on product liability and safety were reviewed thoroughly. The product safety policy consists of two parts: (1) an engineering design strategy for reducing product-related risks and (2) a management program for a product liability loss prevention plan. The policy is essential to preventing manufacturers' liability exposure as well as designing a safer product.
Alternative Expressions for the Decomposition Property in the M/G/1 Queue with Generalized Vacations
Chang, Seok-Ho ; Chae, Kyung-Chul ; Lee, Ho-Woo ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 283~288
We present several alternative expressions for the decomposition property of the M/G/1 queue with generalized vacations so that a user can choose the most convenient expression for his/her own purpose.
A Modified Genetic Algorithm for Minimum Weight Triangulation
Lee, Bum-Joo ; Han, Chi-Geun ;
Journal of Korean Institute of Industrial Engineers, volume 26, issue 3, 2000, Pages 289~295
The triangulation problem is to make triangles using the given points on the space. The Minimum Weight Triangulation(MWT) is the problem of finding a set of triangles with the minimum weight among possible set of the triangles. In this paper, a modified genetic algorithm(GA) based on an existing genetic algorithm and multispace smoothing technique is proposed. Through the computational results, we can find the tendency that the proposed GA finds good solutions though it needs longer time than the existing GA does as the problem size increases.