• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1998년도 추계학술대회 논문집
• /
• pp.137-140
• /
• 1998

In this study, we have developed algorithms to find more effective solutions for compensatory decision-making problems in the case of the decision maker with fuzziness which can occur in a real world fuzzy environment. We have applied the algorithm to the problems related to the structural reform of the capital and the number of workers in the local industry. We have selected Taegu city for this study. In this study, we have determined the capital and the number of workers, satisfying maximum productivity and minimum air and water pollution under the constraints such as capital-labor ratio, the demand for land and water and the fluctuation of the capital and the number of workers. The determined capital and the number of workers could improve the competitive advantage of Taegu city and could be utilized as criteria for the compilation of the budget, determination of policy for supporting plan of companies, the forecast of number of workers and the training plan of workers.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.211-218
• /
• 1994

Stochastic computation employs random pulse streams to represent numbers. In this paper, we study a new method to implement the number system which uses the ratio of the numbers of ones and zeros in the pulse streams. In this number system. if P is the probability that a pulse is one in a pulse stream then the number X represented by the pulse stream is defined as P/(1-P). We propose circuits to implement the basic operations such as addition multiplication and sigmoid function with this number system and examine the error characteristics of such operations in stochastic computation. We also propose a neuron model and derive a learning algorithm based on backpropagation for the 3-layered feedforward neural networks. We apply this learning algorithm to a digit recognition problem. To analyze the results, we discuss the errors due to the variance of the random pulse streams and the quantization noise of finite length register.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1990년도 춘계공동학술대회논문집; 한국과학기술원; 28 Apr. 1990
• /
• pp.222-244
• /
• 1990

A multi-echelon structure of manufacturing and distribution system in considered, where the raw materials are transformed into a finished good through a number to manufacturing echelons and it is distributed to the lower echelons(retailers, or customers). The raw material, work-in-process, finished good inventory and the distribution costs are unified into one model. The objective is to determine the ordering policy of raw materials, manufacturing lot size, the number of sub-batch and the distribution policy of the finished good which minimize the annual total system cost. A computer program for a heuristic search technique is developed, by which a numerical example is examined.

• 한국경영과학회지
• /
• 제42권3호
• /
• pp.25-34
• /
• 2017

K-means is a popular and efficient data clustering method that only uses intra-cluster distance to establish a valid index with a previously fixed number of clusters. K-means is useless without a suitable number of clusters for unsupervised data. This paper aimsto propose the Group Search Optimization (GSO) using Silhouette to find the optimal data clustering solution with a number of clusters for unsupervised data. Silhouette can be used as valid index to decide the number of clusters and optimal solution by simultaneously considering intra- and inter-cluster distances. The performance of GSO using Silhouette is validated through several experiment and analysis of data sets.

• 한국경영과학회지
• /
• 제1권1호
• /
• pp.147-150
• /
• 1976

Optimal stopping problem without recall from a multivariate distribution is solved by using the concept of an equilibrium point which was introduced by J. Nash. The solution is derived for the two cases: 1. The case where the observation cost C is positive and the given upper bound K on the number of observations is infinite. 2. The case where the observation cost C is zero and the given upper bound K on the number of observations is finite.

• 한국경영과학회지
• /
• 제34권4호
• /
• pp.139-151
• /
• 2009

Based on single-vendor single-buyer integrated production-inventory problem, a model considering freight costs discounts is suggested when the cargo capacity is constrained. With the cost function formulated, several properties of the model are derived and analyzed. An efficient algorithm to find solutions such as shipment lot size, number of shipments and number of full truckloads using properties derived is suggested. Numerical results are provided to illustrate the proposed solution procedures and to provide additional insights.

• 한국경영과학회지
• /
• 제6권2호
• /
• pp.35-49
• /
• 1981

This paper is concerned with developing a Multi-period Behavioral Model for the portfolio selection problem. The unique feature of the model is that it treats a number of factors and decision variables considered germane in decision making on an interrelated basis. The formulated problem has the structure of a Chance Constrained programming Model. Then empoloying arguments of Central Limit Theorem and normality assumption the stochastic model is reduced to that of a Non-Linear Programming Model. Finally, a number of interesting properties for the reduced model are established.

• 한국국방경영분석학회지
• /
• 제24권1호
• /
• pp.157-175
• /
• 1998

This paper develops multiple objective manpower planning model in order to design and adjust manpower structure and flow when advance rate for officer's native is considered. The state transition in manpower structure is analyzed using Markov chains. Multiple objectives in the model are security of advance rate, satisfaction of rank's number of personnel, and stability of the number of recruit personnel for officer's native. Trade - off of these objectives is made to evaluate manpower structure and flow. Solutions of this model are obtained by LINGO package.

• 한국경영과학회지
• /
• 제31권2호
• /
• pp.87-98
• /
• 2006

In many cases of cluster analysis we are forced to perform clustering without any prior knowledge on the number of clusters. But in some clustering methods such as k-means algorithm it is required to provide the number of clusters beforehand. In this study, we focus on the problem to determine the number of clusters in the given data. We follow the 2 stage approach of ASA clustering algorithm and mainly try to improve the performance of the first stage of the algorithm. We verify the usefulness of the method by applying it for various kinds of simulated data. Also, we apply the method for clustering two kinds of real life qualitative data.

• 한국경영과학회지
• /
• 제38권2호
• /
• pp.141-157
• /
• 2013

In this paper, we consider the minimization of the total weighted earliness-tardiness penalty of jobs, regarding the partial precedences between jobs. We present an optimal scheduling algorithm in O(n(n+m log m)) where n is the number of jobs and m is the number of partial precedences. In the algorithm, the optimal schedule is constructed iteratively by considering each group of contiguous jobs as a block that is represented by a tree.