• 한국항해항만학회지
• /
• 제36권7호
• /
• pp.553-559
• /
• 2012

It is extremely important to predict the logistics requirements in a scientific and rational way. However, in recent years, the improvement effect on the prediction method is not very significant and the traditional statistical prediction method has the defects of low precision and poor interpretation of the prediction model, which cannot only guarantee the generalization ability of the prediction model theoretically, but also cannot explain the models effectively. Therefore, in combination with the theories of the spatial economics, industrial economics, and neo-classical economics, taking city of Erdos as the research object, the study identifies the leading industry that can produce a large number of cargoes, and further predicts the static logistics generation of the Erdos and hinterlands. By integrating various factors that can affect the regional logistics requirements, this study established a logistics requirements potential model from the aspect of spatial economic principles, and expanded the way of logistics requirements prediction from the single statistical principles to an new area of special and regional economics.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.125-130
• /
• 2020

At the end of 1997, the volatility of the exchange rate intensified as the nation's exchange rate system was converted into a free-floating exchange rate system. As a result, managing the exchange rate is becoming a very important task, and the need for forecasting the exchange rate is growing. The exchange rate prediction model using the existing exchange rate prediction method, statistical technique, cannot find a nonlinear pattern of the time series variable, and it is difficult to analyze the time series with the variability cluster phenomenon. And as the number of variables to be analyzed increases, the number of parameters to be estimated increases, and it is not easy to interpret the meaning of the estimated coefficients. Accordingly, the exchange rate prediction model using artificial neural network, rather than statistical technique, is presented. Using DNN, which is the basis of deep learning among artificial neural networks, and LSTM, a recurrent neural network model, the number of hidden layers, neurons, and activation function changes of each model found the optimal exchange rate prediction model. The study found that although there were model differences, LSTM models performed better than DNN models and performed best when the activation function was Tanh.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권5호
• /
• pp.161-168
• /
• 2020

스포츠 경기 결과예측은 전반적인 경기의 흐름과 승패에 영향을 미치는 변인들의 분석을 통해 팀의 전략 수립을 가능하게 해준다. 이와 같은 스포츠 경기결과 예측에 대한 연구는 주로 통계학적 기법과 기계학습 기법을 활용하여 진행되어 왔다. 승부예측 모델은 무엇보다 예측 성능이 가장 중요시된다. 그러나 최적의 성능을 보이는 예측 모델은 학습에 사용되는 데이터에 따라 다르게 나타나는 경향을 보였다. 본 논문에서는 이러한 문제를 해결하기 위해 데이터가 달라지더라도 해당 데이터에 대한 예측 시 가장 좋은 성능을 보이는 모델의 선택이 가능한 기존의 축구경기결과 예측에서 좋은 성능을 보여온 통계학적 모델과 기계학습 모델을 결합한 새로운 앙상블 모델을 제안한다. 본 논문에서 제안하는 앙상블 모델은 각 단일모델들의 경기 예측결과와 실제 경기결과를 병합한 데이터로부터 최종예측모델을 학습하여 경기 승부예측을 수행한다. 제안 모델에 대한 실험 결과, 기존 단일모델들에 비해 높은 성능을 보였다.

• Journal of the Korean Statistical Society
• /
• 제14권2호
• /
• pp.63-75
• /
• 1985

This paper considers a statistical calibration problem in which the standard as wel as the nonstandard measurement is subject to error. Since the classicla approach cannot handle this situation properly, a functional relationship model with additional feature of prediction is proposed. For the analysis of the problem four different approaches-two estimation techniques (ordinary and grouping least squares) combined with two prediction methods (classical and inverse prediction)-are considered. By Monte Carlo simulation the perromance of each approach is assessed in term of the probability of concentration. The simulation results indicate that the ordinary least squares with inverse prediction is generally preferred in interpolation while the grouping least squares with classical prediction turns out to be better in extrapolation.

• 항공우주시스템공학회지
• /
• 제14권2호
• /
• pp.50-56
• /
• 2020

In this study, we investigated whether long short-term memory (LSTM) can be used in the future to predict F10.7 index data; the F10.7 index is a space environment factor affecting atomic oxygen erosion. Based on this, we compared the prediction performances of LSTM, the Autoregressive integrated moving average (ARIMA) model (which is a traditional statistical prediction model), and the similar pattern searching method used for long-term prediction. The LSTM model yielded superior results compared to the other techniques in the prediction period starting from the max/min points, but presented inferior results in the prediction period including the inflection points. It was found that efficient learning was not achieved, owing to the lack of currently available learning data in the prediction period including the maximum points. To overcome this, we proposed a method to increase the size of the learning samples using the sunspot data and to upgrade the LSTM model.

• 한국해양공학회지
• /
• 제23권6호
• /
• pp.71-76
• /
• 2009

This paper describes a statistical analysis method for predicting a coast fishing boat's effective horsepower. The EHP estimation method for small coast fishing boats was developed, based on a statistical regression analysis of model test results in a circulating water channel. The statistical regression formula of a fishing boat's effective horsepower is determined from the regression analysis of the resistance test results for 15 actual coast fishing boats. This method was applied to the effective horsepower prediction of a G/T 4 ton class coast fishing boat. From the estimation of the effective horsepower using this regression formula and the experimental model test of the G/T 4 ton class coast fishing boat, the estimation accuracy was verified under 10 percent of the design speed. However, the effective horsepower prediction method for coast fishing boats using the regression formula will be used at the initial design and hull-form development stage.

• 디지털콘텐츠학회 논문지
• /
• 제19권4호
• /
• pp.685-692
• /
• 2018

본 연구는 통계분석을 이용한 중년 성인의 고혈압 예측모델 개발이 목적이다. 국민건강영양조사자료(2013년-2016년)를 사용하여 통계분석과 예측모델을 개발하였다. 이진 로지스틱 회귀분석으로 통계적 유의한 고혈압 위험인자를 제시하였으며, Wrapper 변수선택기법을 적용한 로지스틱회귀와 나이브베이즈 알고리즘을 이용하여 예측모델을 개발하였다. 통계분석에서 고혈압에 가장 높은 연관성을 갖는 인자는 남성에서 WHtR (p<0.0001, OR = 2.0242), 여성에서 AGE(p<0.0001, OR = 3.9185)로 나타났다. 예측모델의 성능평가에서, 로지스틱 회귀 모델이 남성(AUC = 0.782)과 여성(AUC = 0.858)에서 가장 좋은 예측력을 보였다. 우리의 연구 결과는 고혈압에 대한 대규모 스크리링 도구를 개발하는데 중요한 정보를 제공하며, 고혈압 연구에 대한 기반정보로 활용할 수 있다.

• Asia-Pacific Journal of Atmospheric Sciences
• /
• 제54권4호
• /
• pp.563-573
• /
• 2018

An Expert Seasonal Prediction System for operational Seasonal Outlook (ESPreSSO) is developed based on the APEC Climate Center (APCC) Multi-Model Ensemble (MME) dynamical prediction and expert-guided statistical downscaling techniques. Dynamical models have improved to provide meaningful seasonal prediction, and their prediction skills are further improved by various ensemble and downscaling techniques. However, experienced scientists and forecasters make subjective correction for the operational seasonal outlook due to limited prediction skills and biases of dynamical models. Here, a hybrid seasonal prediction system that grafts experts' knowledge and understanding onto dynamical MME prediction is developed to guide operational seasonal outlook in Korea. The basis dynamical prediction is based on the APCC MME, which are statistically mapped onto the station-based observations by experienced experts. Their subjective selection undergoes objective screening and quality control to generate final seasonal outlook products after physical ensemble averaging. The prediction system is constructed based on 23-year training period of 1983-2005, and its performance and stability are assessed for the independent 11-year prediction period of 2006-2016. The results show that the ESPreSSO has reliable and stable prediction skill suitable for operational use.

• 한국콘텐츠학회논문지
• /
• 제22권2호
• /
• pp.545-558
• /
• 2022

본 연구의 목적은 전통적인 통계과 기계학습(Machine Learning)을 통해 중국 문화산업 기업의 재무적 곤경을 정확하게 예측하는 분석 모형을 탐색하는 데 있다. 예측모형을 구축하기 위하여 중국 128개 문화산업상장 기업의 데이터를 수집하였다. 25개 설명변수로 이뤄진 데이터베이스를 토대로 판별분석과 로지스틱 회귀(Logistic) 등 전통적인 통계 방법과 서포트 벡터 기계(SVM), 결정 트리(Decision Tree)와 랜덤 포레스트(Random Forest) 등 기계학습을 이용한 예측모형을 구축하고 각 모형의 성능 평가를 위해 Python 소프트웨어를 사용한다. 분석 결과, 예측 성능이 가장 좋은 모형은 랜덤 포레스트(Random Forest) 모형으로 95%의 정확도를 보였다. 그 다음은 서포트 벡터 기계(SVM) 모형으로 93%의 정확도를 보였다. 그 다음은 결정 트리(Decision Tree) 모형으로 92%의 정확도를 보였다. 그 다음은 판정분석 모형으로 89%의 정확도를 보였다. 예측 효과가 가장 낮은 모형은 로지스틱 회귀(Logistic) 모형으로 88%의 정확도를 보였다. 이는 중국 문화산업 기업의 재무적 곤경을 예측하면서 기계학습 모형이 전통적인 통계 모형보다 더 좋은 예측 효과를 얻을 수 있음을 설명한다.

• Communications for Statistical Applications and Methods
• /
• 제17권1호
• /
• pp.99-106
• /
• 2010

In this paper, we present two methods for obtaining prediction intervals for the times to failure of units censored in multiple stages in a progressively censored sample from proportional hazard rate models. A numerical example and a Monte Carlo simulation study are presented to illustrate the prediction methods.