• 대한교통학회지
• /
• 제8권2호
• /
• pp.77-97
• /
• 1990

Compared to modal split, the methods of forecasting traffic volumes diverted in various types of I.C.s have not been sufficiently studied. The purpose of this study is to derive a new diversion function that can represent the directional traffic volume in accordance with various geometrics of I.C.s. In general, knowing various traffic impedances and the amount of traffic production and attraction, one can estimate proper traffic volumes associated with directions by using a well-defined diversion function. This function is usually made by a series of process such as surveying directional traffic volumes on several I.C.s, analyzing with a regression method and verifying those results by statistical approaches. The function has been developed by rigorous statistical testings, mainly a regression analysis. This paper presents an effective method in planning and designing new roads, I.C.s and route choice of subway. Finally, some comparisons and improvements and suggested when one uses different types of relevant models and functions.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.338-341
• /
• 2003

Recently, the chaotic method is employed to forecast a near future of uncertain phenomena. This method makes it possible by restructuring an attractor of given time-series data in multi-dimensional space through Takens' embedding theory. However, many economical time-series data are not sufficiently chaotic. In other words, it is hard to forecast the future trend of such economical data on the basis of chaotic theory. In this paper, time-series data are divided into wave components using wavelet transform. It is shown that some divided components of time-series data show much more chaotic in the sense of correlation dimension than the original time-series data. The highly chaotic nature of the divided component enables us to precisely forecast the value or the movement of the time-series data in near future. The up and down movement of TOPICS value is shown so highly predicted by this method as 70％.

• 산업공학
• /
• 제25권4호
• /
• pp.441-449
• /
• 2012

Solar PV(photovoltaic) is paid great attention to as a possible renewable energy source to overcome recent global energy crisis. However to be a viable alternative energy source compared with fossil fuel, its market competitiveness should be attained. Grid parity is one of effective measure of market competitiveness of renewable energy. In this paper, we forecast the grid parity timing of solar PV energy in Korea using two factor learning curve model. Two factors considered in the present model are production capacity and technological improvement. As a result, it is forecasted that the grid parity will be achieved in 2019 in Korea.

• 한국경영과학회지
• /
• 제23권1호
• /
• pp.109-141
• /
• 1998

Many processes in the industrial realm exhibit sstochastic and nonlinear behavior. Consequently, an intelligent system must be able to nonlinear production processes as well as probabilistic phenomena. In order for a knowledge based system to control a manufacturing processes as well as probabilistic phenomena. In order for a knowledge based system to control manufacturing process, an important capability is that of prediction : forecasting the future trajectory of a process as well as the consequences of the control action. This paper examines the robustness of data mining tools under varying levels of noise while predicting nonlinear processes, includinb chaotic behavior. The evaluated models include the perceptron neural network using backpropagation (BPN), the recurrent neural network (RNN) and case based reasoning (CBR). The concepts are crystallized through a case study in predicting a chaotic process in the presence of various patterns of noise.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2006년도 추계학술대회
• /
• pp.161-164
• /
• 2006

The sales of consumer durables are composed of first time purchases and replacement purchases. Since the sales for most mature durable products are dominated by replacement sales, it is necessary to develop a model incorporating replacement component of sales in order to forecast total sales accurately. Several single product diffusion models incorporating replacement demand have been developed, but research addressing the multi-product diffusion models has not considered replacement sales. In this paper, we propose a model based on consumer choice behavior that simultaneously captures the diffusion and the replacement process for multi-product relationships. The proposed model enables the division of replacement sales into repurchase by previous users and transition purchase by users of different products. As a result, the model allows the partitioning of the total sales according to the customer groups (first-time buyers, repurchase buyers, and transition buyers), which allows companies to develop their production and marketing plans based on their customer mix. We apply the proposed model to the Korean automobile market, and compare the fitting and forecasting performance with other Bass-type multi-product models.

• 응용통계연구
• /
• 제13권2호
• /
• pp.307-320
• /
• 2000

송이버섯 생산량과 기후인자와의 관계를 통계적으로 규명하기 위한 노력이 꾸준이 진행되어 왔다. 최근 박현 등(1998)은 송이버섯 생산량과 기후인자의 관계를 자기회귀모형을 이용하여 분석하였으나 예측력이 떨어지는 것으로 나타났다. 본 논문에서는 예측의 정확성을 높이기 위한 방법으로 송이버섯 생산이 있다는 조건을 이용한 조건부 자기 회귀모형을 제안하였다. 두 모형의 예측력을 비교한 결과 조건부 자기회귀모형이 더 우수한 것으로 나타났다.

• 품질경영학회지
• /
• 제36권4호
• /
• pp.93-101
• /
• 2008

The rare metals, used for semiconductors, PDP-LCS and other specialized metal areas necessarily, has been playing a key role for the Korean economic development. Rare metals are influenced by exogenous variables, such as production quantity, price and supplied areas. Nowadays the supply base of rare metals is threatened by the sudden increase in price. For the stable supply of rare metals, a rational demand outlook is needed. In this study, focusing on the domestic demand for chromium, the uncertainty and probability materializing from demand and price is analyzed, further, a demand forecast model, which takes into account various exogenous variables, is suggested, differing from the previously static model. Also, through the OOS(out-of-sampling) method, comparing to the preexistence ARIMA model, ARMAX model, multiple regression analysis model and ECM(Error Correction Mode) model, we will verify the superiority of suggested model in this study.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2001년도 International Meeting on Information Display
• /
• pp.9-12
• /
• 2001

With the explosive growth of Note-PC and Desktop monitor market, TFT LCD market confronted a entire supply shortage during 1999. Forecasting a more booming stage for the next several years, many TFT-LCD panel manufacturers continue to expand the capacity of their existing plants and also make an additional investment in building new plants. The new investment is concentrated on the $4^{th}$ generation TFT LCD line in order to improve investment efficiency. The set up of the Samsung's Gen 3.5 line progressed with satisfactorily performance using $600{\times}720mm$ glass size. We have continuously reviewed several issues regarding the glass size for our next Gen. 4 line, which leads to adopt $730{\times}920mm$. Due to the continuous enlargement of a substrate size and following difficulty in transferring cassettes, the next line is expected to be the last line that employs "cassette transfer". The layout of the next line will shift from conventional "concentration-type" to "separation-type" configuration for the purpose of reducing transfer distance as well as transfer time. The details will be discussed in this paper.

• 산업공학
• /
• 제21권3호
• /
• pp.343-353
• /
• 2008

Vendor-managed inventory(VMI) is a supply chain strategy to improve the inventory turnover and customer service in supply chain management. Unfortunately, many VMI programs fail because they simply transfer the transactional aspects of placing replenishment orders from customer to vendor. In fact, such VMI programs often degrade supply chain performance because vendors lack capability to plan the VMI operations effectively in an integrated way under the dynamic, complex, and stochastic VMI supply chain environment. This paper presents a decision support system, termed DSSV, for VMI in the retail supply chain. DSSV supports the market forecasting, vendor's production planning, retailer's inventory replenishment planning, vehicle routing, determination of the system operating parameter values, retailer's purchase price decision, and what-if analysis. The potential benefits of DSSV include the provision of guidance, solution, and simulation environment for enterprises to reduce risks for their VMI supply chain operations.

• Earthquakes and Structures
• /
• 제11권5호
• /
• pp.861-871
• /
• 2016

The Groningen gas field shows exponential growth in earthquake event counts around a magnitude M1 with a doubling time of 6-9 years since 2001. This behavior is identified with dimensionless curvature in land subsidence, which has been evolving at a constant rate over the last few decades essentially uncorrelated to gas production. We demonstrate our mechanism by a tabletop crack formation experiment. The observed skewed distribution of event magnitudes is matched by that of maxima of event clusters with a normal distribution. It predicts about one event < M5 per day in 2025, pointing to increasing stress to human living conditions.