• 품질경영학회지
• /
• 제50권4호
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• 한국정보과학회논문지:데이타베이스
• /
• 제33권2호
• /
• pp.201-213
• /
• 2006

일정 기간 동안 객체의 변화한 값들을 기록한 것을 그 객체에 대한 시계열 데이타 시퀀스라고 부르며, 이들의 집합을 시계열 데이타베이스라고 한다. 서브시퀀스 매칭은 주어진 질의 시퀀스와 변화의 추세가 유사한 서브시퀀스들을 시계열 데이타베이스로부터 검색하는 연산이다. 본 논문에서는 서브시퀀스 매칭의 성능을 극대화하기 위한 방안을 제시한다. 먼저, 윈도우 크기 효과로 인한 서브시퀀스 매칭의 심각한 성능 저하 현상을 정량적으로 관찰하여, 하나의 윈도우 크기를 대상으로 만든 단 하나의 인덱스만을 이용하는 것은 실제 응용에서 만족할만한 성능을 제공할 수 없다는 것을 규명하였다 또한, 이러한 문제로 인해 다양한 윈도우 크기들을 기반으로 다수의 인덱스들을 구성하여 서브시퀀스 매칭을 수행하는 인덱스 보간법의 응용이 필요함을 보였다. 인덱스 보간법을 응용하여 서브시퀀스 매칭을 수행하기 위해서는 먼저 다수의 인덱스들을 위한 윈도우 크기들을 결정해야 한다. 본 연구에서는 물리적 데이타베이스 설계 방식을 이용하여 이러한 최적의 다수의 윈도우 크기들을 선정하는 문제를 해결하였다. 이를 위하여 시계열 데이터 베이스에서 수행될 예정인 질의 시퀀스들의 집합과 인덱스 구성의 기반이 되는 윈도우들의 크기의 집합이 주어질 때, 전체 서브시퀀스 매칭들을 수행하는 데에 소요되는 비용을 예측할 수 있는 공식을 산출하였다. 또한, 이 비용 공식을 이용하여 전체 서브시퀀스 매칭들의 성능을 극대화 할 수 있는 최적의 윈도우 크기들을 결정하는 알고리즘을 제안하였으며, 이 알고리즘의 최적성과 효율성을 이론적으로 규명하였다. 끝으로, 실제 주식 데이타와 대량의 합성 데이타를 이용한 실험 결과, 제안된 기법은 기존의 단순한 기법과 비교하여 1.5배에서 7.8배 성능이 향상됨을 보였다.

• 한국실내디자인학회논문집
• /
• 제21호
• /
• pp.54-61
• /
• 1999

The Fashion Distribution Business (FDB) is thriving to such an extent that the current period is called "The Era of Fashion." This FDB shows tendencies towards specialzation, globalization and expansion. The domestic FDB has been rapidly globalizing, and thus it is time for us to recognize that the fashion business has grown beyond its former role as a production-oriented retail business to include multiple new roles. This strategy to plant Store Identity on customers is just a Visual Merchandising (VMD) Strategy. That is, a strategy to visualize the Product Planning, which can be called a Complex Visual Expressing Technical System that classifies and arranges products in order to be easily seen, chosen, and bought through exhibition and arrangement. My aim is to break away from the conept that has been focused only on display division and to present product scheme correctly and to establish a VMD Plan which can also contribute to sales promotion by providing infirmation and arranging Store Display efficiently for customers. Additionally, this is aimed to present an efficient and sensitive design process.esign process.

• 대한산업공학회지
• /
• 제32권1호
• /
• pp.9-17
• /
• 2006

This paper deals with a discrete simulation optimization method for designing a complex probabilistic discrete event simulation. The developed algorithm uses the configuration algorithm that can change decision variables and the stopping algorithm that can end simulation in order to satisfy the given objective value during single run. It tries to estimate an auto-regressive model for evaluating correctly the objective function obtained by a small amount of output data. We apply the proposed algorithm to M/M/s model, (s, S) inventory model, and known-function problem. The proposed algorithm can't always guarantee the optimal solution but the method gives an approximate feasible solution in a relatively short time period. We, therefore, show the proposed algorithm can be used as an initial feasible solution of existing optimization methods that need multiple simulation run to search an optimal solution.

• 한국임상보건과학회지
• /
• 제3권1호
• /
• pp.256-267
• /
• 2015

Purpose. The objective of this study was to investigate factors influencing turnover intention index of work environment, emotional labor by hospital nurses Methods. A survey was conducted with 290 nurses who were working hospital. Data were analyzed using descriptive statistics, t-test, ANOVA, Pearson correlation coefficients and multiple regression with SPSS window 18.0 program. Result. Findings revealed that; 1) The mean scores were 2.81 [range : 1-5] for work environment, 3.24 [range : 1-5] for emotional labor, 3.43 [range : 1-5] for turnover intention. 2) Pearson's correlation revealed work environment was negatively correlated with turnover intention but emotional labor positively correlated with the turnover intention. 3) Hrarchical multiple regression analysis showed work environment, ages, assign ward, period in current hospital, emotional labor significantly influenced turnover intention in hospital nurses. Conclusion. These findings can be utilized to development of strategies to improving the work environment, managing the emotional labor for decreasing turnover intention of hospital nurses so that can be long time.

• 한국자기공명학회논문지
• /
• 제12권2호
• /
• pp.81-88
• /
• 2008

Solid HETCOR (Hetero-Correlation) requires homo-dipolar decoupling between proton spins during the evolution and the mixing period in 2D-NMR. There are two different ways of achieving it with pulse sequences. One is based on the multiple pulse (MP) sequence where thousands of intense radio frequency (rf) pulses are used to remove the homo-dipolar interaction between protons. The other is utilizing the so-called Lee-Goldburg (LG) off-resonance scheme where a continuous rf-irradiation is used. In this report, the advantage of one technique to the other, is analyzed. LG version is evaluated better in S/N and easier in setup procedure with the same experimental time.

• Journal of Chest Surgery
• /
• 제27권10호
• /
• pp.838-845
• /
• 1994

From April, 1982 to December, 1992, multiple valve replacement was performed in 100 patients. Mitral and aortic valve replacement were done in 86 patients, 9 underwent mitral and tricuspid valve replacement, 4 patients underwent triple valve replacement and 1 patient underwent aortic and tricuspid valve replacement. Of the valve implanted, 100 were St. Jude, 64 Duromedics, 19 Carpentier-Edwards, 13 Bj rk-Shiley, 6 Ionescu-Shiley, and 2 Medronics.The hospital mortality rate was 15%[15 patients] and the late mortality rate was 7%[7 patients], the mortality rate was high in early operative period but decreased with time[20% at 1986, 18.2% at 1987, 9.5% at 1988, 11.1% at 1989, 12.5% at 1990, 11.8% at 1991, 0% at 1992]. The causes of death were low cardiac output in 8, sudden death in 3, CHF in 3, bleeding in 2, cerebral thromboembolism in 1, leukemia in 1, multiorgan failure in 1 and so on. The actuarial survival rate excluding operative death was 73% at 10 years.

• 대한기계학회논문집B
• /
• 제22권12호
• /
• pp.1784-1795
• /
• 1998

Natural convection of low Prandtl number fluids with $Pr{\leq}0.2$ in a narrow horizontal annulus is numerically investigated. For $Pr{\leq}0.2$, hydrodynamic instability induces oscillatory multicellular flows consisting of multiple like-rotating cells. For a fluid with $Pr{\approx}0$, the region in which instability of conduction regime first forms is near the vertical section of annulus, and the multiple cells are distributed uniformly in the lower and upper regions of annulus. As Pr increases, however, the cells are shifted upwards. The like-rotating cells drift downward, as time goes on, and the speed of travel increases with increase of Pr. For a fluid with Pr=0.1, a flow with period-4 solution is observed between chaotic states.

• International Journal of Control, Automation, and Systems
• /
• 제6권1호
• /
• pp.44-53
• /
• 2008

An interacting multiple model (IMM) estimation algorithm based on the mixing of the predicted state estimates is proposed in this paper for a right continuous jump-linear system model different from the left-continuous system model used to develop the existing IMM algorithm. The difference lies in the modeling of the mode switching time. Performance of the proposed algorithm is compared numerically with that of the existing IMM algorithm for noisy system identification. Based on the numerical analysis, the proposed algorithm is applied to target tracking with a large sampling period for performance comparison with the existing IMM.

• Communications for Statistical Applications and Methods
• /
• 제6권3호
• /
• pp.801-812
• /
• 1999

Change-point hazard rate models arise for example in applying "burn-in" techniques to screen defective items and in studing times until undesirable side effects occur in clinical trials. Sometimes in screening defectives it might be sensible to model two stages of burn-in. In a clinical trial there might be an initial hazard rate for a side effect which after a period of time changes to an intermediate hazard rate before settling into a long term hazard rate. In this paper we consider the multiple change points hazard rate model. The classical approach's asymptotics can be poor for the small to all moderate sample sizes often encountered in practice. We propose a Bayesian approach avoiding asymptotics to provide more reliable inference conditional only upon the data actually observed. The Bayesian models can be fitted using simulation methods. Model comparison is made using recently developed Bayesian model selection criteria. The above methodology is applied to a generated data and to a generated data and the Lawless(1982) failure times of electrical insulation.