• 한국시뮬레이션학회논문지
• /
• 제18권4호
• /
• pp.137-148
• /
• 2009

본 논문의 목적은 신뢰성 있는 선형회귀모델을 구축하기 위하여 후보독립변수 중 유효변수를 선택하는 알고리즘을 구현하는 것이다. 선형회귀모델을 구축하는데 있어서 데이터 상의 모든 후보독립변수를 포함하는 것은 모델의 통계적 유의성을 감소시킬 수 있으며, 차원의 저주(Curse of dimensionality)를 유발할 수 있고, 데이터의 개수보다 변수의 개수가 많을 경우 모델의 구축이 불가능한 문제점 등이 있다. 이와 같은 문제점을 해결하기 위하여 변수선택의 문제를 조합최적화의 문제로 보고 유전 알고리즘(Genetic Algorithm)을 활용하였다. 일반적으로 선형회귀모델의 통계적 유의성을 평가하는 대표적인 통계량으로는 종속변수에 대한 독립변수의 설명력을 나타내는 결정계수($R^2$), 회귀식의 통계적 유의성을 검정하는 F통계량, 회귀계수의 통계적 유의성을 검정하는 t통계량, 잔차의 표준오차 등이 있다. 모델의 통계적 유의성은 하나의 통계량으로 표현될 수 없으므로 다양한 기준을 고려한 다중목적식(Multi-objective function)을 가지는 유전 알고리즘을 설계하였다. 설계한 알고리즘의 성능평가를 위하여 다양한 조건을 가정한 시뮬레이션 데이터에 적용하였다. 그 결과 구축한 알고리즘이 유효변수를 판단함에 있어 기존의 대표적인 변수선택 알고리즘인 LARS(Least Angle Regression)에 비해 우수한 성능을 보임을 확인할 수 있었다. 또한, 주가 데이터를 이용한 포트폴리오 선택에 적용해 본 결과 우수한 응용문제 해결 능력이 있음을 확인할 수 있었다.

• Journal of Biosystems Engineering
• /
• 제31권3호
• /
• pp.194-202
• /
• 2006

Using a multi-variable linear regression technique and SUR(seemingly unrelated regression) model, the demand functions of tractor, combine and rice transplanter were estimated. The demand was regarded as an annual supply of each machine and modeled as a function of 11 independent variables which reflect the actual farmer's income, actual prices of farm machines, previous supply, previous stock, actual amount of available subsidy, actual amount of available loan, arable land, import of farm machines and rice price. The actual amount of available loan affects most significantly the demand functions. The actual farmer's income, actual farmer's asset, loan coverage, and rice price affect the demand positively while prices of farm machines and import negatively. The annual demands of tractor, combine and rice transplanter estimated using the demand functions were also presented over the next 4 years.

• Journal of Advanced Marine Engineering and Technology
• /
• 제40권2호
• /
• pp.138-145
• /
• 2016

This paper proposes an improved tabu search method for subset selection in multiple linear regression models. Variable selection is a vital combinatorial optimization problem in multivariate statistics. The selection of the optimal subset of variables is necessary in order to reliably construct a multiple linear regression model. Its applications widely range from machine learning, timeseries prediction, and multi-class classification to noise detection. Since this problem has NP-complete nature, it becomes more difficult to find the optimal solution as the number of variables increases. Two typical metaheuristic methods have been developed to tackle the problem: the tabu search algorithm and hybrid genetic and simulated annealing algorithm. However, these two methods have shortcomings. The tabu search method requires a large amount of computing time, and the hybrid algorithm produces a less accurate solution. To overcome the shortcomings of these methods, we propose an improved tabu search algorithm to reduce moves of the neighborhood and to adopt an effective move search strategy. To evaluate the performance of the proposed method, comparative studies are performed on small literature data sets and on large simulation data sets. Computational results show that the proposed method outperforms two metaheuristic methods in terms of the computing time and solution quality.

• Clinics in Shoulder and Elbow
• /
• 제16권1호
• /
• pp.63-72
• /
• 2013

임상 의학의 연구에 사용되는 대표적 다변량 분석 방법은 다중 회귀 분석 방법인데, 이는 인과 관계를 토대로 여러 개의 변수에 의한 한꺼번에의 영향력을 분석하기 위한 방법이다. 다중 회귀 분석은 기본적으로 회귀 분석의 기본 가정을 만족해야 함은 물론, 여러 개의 독립 변수들이 포함되기 때문에 변수들을 모형에 포함시키는 방법 및 다중 공선성 문제에 대한 고려가 필요하다. 다중 회귀 분석 모형의 설명력은 결정 계수 $R^2$으로 표현되어 1에 가까울수록 설명력이 크며, 각 독립 변수들의 결과에의 영향력은 회귀 계수인 ${\beta}$값으로 표현된다. 다중 회귀 분석은 종속 변수의 형태에 따라 다중 선형 회귀 분석, 다중 로지스틱 회귀 분석, 콕스 회귀 분석으로 나눌 수 있다. 종속 변수가 연속 변수인 경우 다중 선형 회귀 분석, 범주형 변수인 경우 다중 로지스틱 회귀 분석, 시간의 영향을 고려한 상태 변수인 경우는 콕스 회귀 분석을 시행해야 하며, 각각 결과에의 영향력은 회귀 계수 ${\beta}$, 교차비, 위험비로 평가한다. 이러한 다변량 분석에 대한 이해는 연구를 계획하고 결과를 분석하고자 하는 임상 의사에게 있어 보다 효율적인 연구를 위해 필수적인 소양이라고 할 수 있다.

• 품질경영학회지
• /
• 제32권3호
• /
• pp.109-125
• /
• 2004

This paper deals with an optimal process control problem in production of hull structural steel plate with high defective rate. The main quality characteristic(dependent variable) is the internal quality(defect) of plates and is dependent on process parameters(independent variables). The dependent variable(quality characteristics) has three categorical ordinal data and there are 35 independent variables(29 continuous variables and 6 categorical variables). In this paper, we determine the main factors and to develop the mathematical model between internal quality predicted probabilities and the main factors. Secondly, we find out the optimal process condition of main factors through analysis of variance(ANOVA) using simulation. We consider three models to obtain the main factors and the optimal process condition: linear, quadratic, error models.

• 산경연구논집
• /
• 제12권3호
• /
• pp.7-19
• /
• 2021

Purpose: This study aims to examine customer experience toward repurchase intention in offline and online stores and discuss customer satisfaction as a mediator variable. Research design, data, and methodology: This study investigates customer experience that consists of product, customer service, staff service, shopping environment and shopping procedure toward customer satisfaction using Regression Linear. This study also measures customer satisfaction as a mediated variable in the relationship between customer experience and repurchase intention using Sobel Test. Results: Almost all of the customer experience hypothesis is significant toward customer satisfaction, shopping process experience in the context of the online channel to customer satisfaction is not significant. We also found that customer satisfaction can be mediated variable in customer experience toward repurchase intention. Conclusions: Retails who want to make customers feel satisfied to have to make sure that have good resources in improving the product, the customer service is easy to contact to find the solution over customer problem in purchasing product, also develop the staff member skill in functional product knowledge, presentations, and communicating with customers online or offline, the retailer has to create enjoyment and pleasurable customer emotion through the shopping environment and also give seamless shopping experience to their customer in two-channel.

• Imaging Science in Dentistry
• /
• 제40권2호
• /
• pp.63-68
• /
• 2010

Purpose : To compare the CT numbers on 3 cone-beam CT (CBCT) images with those on multi-detector CT (MDCT) image using CT phantom and to develop linear regressive equations using CT numbers to material density for all the CT scanner each. Materials and Methods : Mini CT phantom comprised of five 1 inch thick cylindrical models with 1.125 inches diameter of materials with different densities (polyethylene, polystyrene, plastic water, nylon and acrylic) was used. It was scanned in 3 CBCTs (i-CAT, Alphard VEGA, Implagraphy SC) and 1 MDCT (Somatom Emotion). The images were saved as DICOM format and CT numbers were measured using OnDemand 3D. CT numbers obtained from CBCTs and MDCT images were compared and linear regression analysis was performed for the density, $\rho$ ($g/cm^3$), as the dependent variable in terms of the CT numbers obtained from CBCTs and MDCT images. Results : CT numbers on i-CAT and Implagraphy CBCT images were smaller than those on Somatom Emotion MDCT image (p<0.05). Linear relationship on a range of materials used for this study were $\rho$=0.001H+1.07 with $R^2$ value of 0.999 for Somatom Emotion, $\rho$=0.002H+1.09 with $R^2$ value of 0.991 for Alphard VEGA, $\rho$=0.001H+1.43 with $R^2$ value of 0.980 for i-CAT and $\rho$=0.001H+1.30 with $R^2$ value of 0.975 for Implagraphy. Conclusion: CT numbers on i-CAT and Implagraphy CBCT images were not same as those on Somatom Emotion MDCT image. The linear regressive equations to determine the density from the CT numbers with very high correlation coefficient were obtained on three CBCT and MDCT scan.

• 한국대기환경학회지
• /
• 제10권4호
• /
• pp.224-232
• /
• 1994

A new neural network model has been developed to predict short-term air pollution concentration. In addition, a multiple regression model widely used in statistical analysis was tested. These models were applied for prediction of daily maximum ozone concentration in Seoul during the summer season of 1991. The time periods between May and September 1989 and 1990 were utilized to train set of learning patterns in neural network model, and to estimate multiple regression model. To evaluate the results of the different models, several Performance indices were used. The results indicated that the multiple regression model tended to underpredict the daily maximum ozone concentration with small r$^{2}$(0.38). Also, large errors were found in this model; 21.1 ppb for RMSE, 0.324 for NMSE, and -0.164 for MRE. On the other hand, the results obtained from the neural network model were very promising. Thus, we can know that this model has a prominent efficiency in the adaptive control for the non-linear multi- variable systems such as photochemical oxidants. Also, when the recent new information was added in the neural network model, prediction accuracy was increased. From the new model, the values of RMSE, NMSE and r$^{2}$ were 13.2ppb, 0.089, 0.003 and 0.55 respectively.

• 수산해양기술연구
• /
• 제57권3호
• /
• pp.236-245
• /
• 2021

In this study, a drifting test using a experimental vessel (2,966 tons) in the northern waters of Jeju was carried out for the first time in order to obtain the fundamental data for drift. During the test, it was shown that the average leeway speed and direction by GPS position were 0.362 m/s and 155.54° respectively and the leeway rate for wind speed was 8.80%. The analysis of linear regression modes about leeway speed and direction of the experimental vessel indicated that wind or current (i.e. explanatory variable) had a greater influence upon response variable (e.g. leeway speed or direction) with the speed of the wind and current rather than their directions. On the other hand, the result of multiple regression model analysis was able to predict that the direction was negative, and it was demonstrated that predicted values of leeway speed and direction using an experimental vessel is to be more influential by current than wind while the leeway speed through variance and covariance was positive. In terms of the leeway direction of the experimental vessel, the same result of the leeway speed appeared except for a possibility of the existence of multi-collinearity. Then, it can be interpreted that the explanatory variables were less descriptive in the predicted values of the leeway direction. As a result, the prediction of leeway speed and direction can be demonstrated as following equations. Ŷ₁= 0.4031-0.0032X₁+0.0631X₂-0.0010X₃+0.4110X₄ Ŷ₂= 0.4031-0.6662X₁+27.1955X₂-0.6787X₃-420.4833X₄ However, many drift tests using actual vessels and various drifting objects will provide reasonable estimations, so that they can help search and rescue fishing gears as well.

• 해양환경안전학회지
• /
• 제27권1호
• /
• pp.13-21
• /
• 2021

본 연구의 목적은 Neural Network Regression 모델을 활용하여 선박의 가치평가 모델을 개발하는 것이다. 가치평가의 대상은 중고 VLCC선이며, 선행연구를 통해 선박의 가치 변화를 유발하는 주요 요인들을 선별하여 변수를 설정하고, 2000년 1월부터 2020년 8월까지의 해당 데이터를 확보하였다. 변수의 안정성을 판단하기 위해 다중 공선성 검사를 수행하여 최종적으로 6개의 독립변수와 1개의 종속변수를 선정하고 연구 구조를 설계하였다. 이를 바탕으로 Linear Regression, Neural Network Regression, Random Forest Algorithm을 활용하여 총 9개의 시뮬레이션 모델을 설계하였다. 또한 각 모델간의 비교검증을 통해 평가결과의 정확성을 제고시켰다. 평가 결과, VLCC실제값과의 비교를 통해 2층으로 구성된 Hidden Layer의 Neural Network Regression 모델이 가장 정확도가 높은 것으로 나타났다. 본 연구의 시사점은 첫째, 기존 정형화된 평가기법에서 벗어나 기계학습기반 모델을 선박가치평가에 적용하였다는 점이다. 둘째, 해운시장 변화요인을 동태적 관점에서 분석하고 예측함으로써 연구결과의 객관성을 제고시켰다고 할 수 있다.