• 교육시설
• /
• 제15권3호
• /
• pp.4-16
• /
• 2008

BTL(Build-Transfer-Lease) Project for Education Facilities is contracted as a package which consists of several education facilities and its maintenance period is 20 years. Thus, total cost variation largely depends on the accuracy of the maintenance cost forecasting in the early stage in the life cycle of the BTL Projects. This research develops a method using complete linkage algorithm and branch & bound algorithm to help in finding optimal bundling combination. The result of this research suggests more reasonable and effective forecasting method for the maintenance bundle in BTL projects.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.210-218
• /
• 2023

The author presents a simple data-driven intraday technical indicator trading approach based on Genetic Programming (GP) for return forecasting in the Bitcoin market. We use five trend-following technical indicators as input to GP for developing trading rules. Using data on daily Bitcoin historical prices from January 2017 to February 2020, our principal results show that the combination of technical analysis indicators and Artificial Intelligence (AI) techniques, primarily GP, is a potential forecasting tool for Bitcoin prices, even outperforming the buy-and-hold strategy. Sensitivity analysis is employed to adjust the number and values of variables, activation functions, and fitness functions of the GP-based system to verify our approach's robustness.

• 기술혁신연구
• /
• 제30권2호
• /
• pp.1-27
• /
• 2022

최근 급격한 변화를 겪고 있는 자율주행 자동차 분야의 미래 기술 및 시장 전망 예측에 대한 요구와 관심이 집중되고 있다. 자동차 산업의 특성상, 복합적 요인의 상관관계가 미치는 영향력이 크고 요인 간의 복잡도가 높으므로, 체계적인 미래 예측 방법론 적용을 통한 미래 전망분석 및 전략 수립이 시급하다. 본 연구에서는 자동차 분야에 적합한 미래 예측 방법론 중 필드 변칙 완화기법(Field Anomaly Relaxation)과 다중관점 개념 기법(Multiple Perspective Concept)을 복합적으로 적용하여, 자율주행 자동차 분야의 핵심기술 및 산업 동향에 관한 미래 시나리오들을 개발하여 실증하였다. 도출된 3개의 시나리오는 전문가 평가 체크리스트를 통하여 타당성을 검증하였다. 본 연구 결과는 자율주행 자동차 산업과 같은 다양한 변동성이 존재하는 분야의 미래 예측 방법 중 한 가지로 적용될 수 있다는 점에 의의가 있다.

• 응용통계연구
• /
• 제35권3호
• /
• pp.385-393
• /
• 2022

본 논문에서는 시계열 예측 분야에서 잘 알려져 있는 단변량 시계열 모형들을 이용하여, 그들의 단순 조합이 어떤 예측력을 보여주는지 연구한다. 고려된 단변량 시계열 모형으로는, 지수평활 및 ARIMA(autoregressive integrated moving average) 모형들과 그들의 확장된 형태인 모형들 그리고 예측의 벤치마크 모형으로 자주 사용되는 비계절 및 계절 랜덤워크 모형이다. 단순 조합의 방법은 중앙값과 평균을 이용하였으며, 검증을 위하여 사용된 데이터셋은 3,003개의 시계열 자료로 구성된 M3-competition 자료이다. 예측 성능을 sMAPE(symmetric mean absolute percentage error)와 MASE(mean absolute scaled error)로 평가한 결과, 단변량 시계열 모형들의 단순 조합이 아주 우수한 예측력을 가지고 있음을 확인하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.136-136
• /
• 2021

In this study, a deep convolutional neural network (DCNN) model is proposed for short-term precipitation forecasting using weather radar-based images. The DCNN model is a combination of convolutional neural networks, autoencoder neural networks, and U-net architecture. The weather radar-based image data used here are retrieved from competition for rainfall forecasting in Korea (AI Contest for Rainfall Prediction of Hydroelectric Dam Using Public Data), organized by Dacon under the sponsorship of the Korean Water Resources Association in October 2020. This data is collected from rainy events during the rainy season (April - October) from 2010 to 2017. These images have undergone a preprocessing step to convert from weather radar data to grayscale image data before they are exploited for the competition. Accordingly, each of these gray images covers a spatial dimension of 120×120 pixels and has a corresponding temporal resolution of 10 minutes. Here, each pixel corresponds to a grid of size 4km×4km. The DCNN model is designed in this study to provide 10-minute predictive images in advance. Then, precipitation information can be obtained from these forecast images through empirical conversion formulas. Model performance is assessed by comparing the Score index, which is defined based on the ratio of MAE (mean absolute error) to CSI (critical success index) values. The competition results have demonstrated the impressive performance of the DCNN model, where the Score value is 0.530 compared to the best value from the competition of 0.500, ranking 16^th out of 463 participating teams. This study's findings exhibit the potential of applying the DCNN model to short-term rainfall prediction using weather radar-based images. As a result, this model can be applied to other areas with different spatiotemporal resolutions.

• 대한산업공학회지
• /
• 제30권4호
• /
• pp.267-276
• /
• 2004

Much of previous attention on researches of the decision tree focuses on the splitting criteria and optimization of tree size. Nowadays the quantity of the data increase and relation of variables becomes very complex. And hence, this comes to have plenty number of unnecessary node and leaf. Consequently the confidence of the explanation and forecasting of the decision tree falls off. In this research report, we propose some decision tree algorithms considering the interaction of predictor variables. A generic algorithm, the k-1 Algorithm, dealing with the interaction with a combination of all predictor variable is presented. And then, the extended version k-k Algorithm which considers with the interaction every k-depth with a combination of some predictor variables. Also, we present an improved algorithm by introducing control parameter to the algorithms. The algorithms are tested by real field credit card data, census data, bank data, etc.

• 한국융합학회논문지
• /
• 제11권11호
• /
• pp.257-267
• /
• 2020

본 연구는 우리나라 수출 분야의 산업별 고용비중을 다양한 머신러닝 기법을 활용하여 예측하고, 예측성능을 높이기 위하여 머신러닝 기법 예측값들에 예측조합 기법을 적용하였다. 특히, 본 연구에서는 각 머신러닝 기법 예측값들에 부여되는 가중치의 합을 1로 설정하는 제약하의 예측조합 기법을 사용하여 예측의 정확성과 안정성을 확보하고자 하였다. 또한, 본 연구는 산업별 고용비중에 영향을 주는 다양한 변수를 고려하기 위하여 재귀적특성제거 방법을 사용하여 주요 변수를 선별한 후, 머신러닝 기법에 적용함으로써 예측과정 상에서의 효율성을 높였다. 분석결과, 예측조합 방법에 따른 예측값은 머신러닝 기법의 예측값들보다 실제의 산업 고용비중에 근접한 것으로 나타났으며, 머신러닝 기법의 예측값들이 큰 변동성을 보이는 것과 달리 제약하의 예측조합 기법은 안정적인 예측값을 나타내었다.

• Water Engineering Research
• /
• 제5권2호
• /
• pp.101-109
• /
• 2004

Aggregating information by combining forecasts from two or more forecasting methods is an alternative to using forecasts from just a single method to improve forecast accuracy. This paper describes the development and use of a monthly inflow forecast model based on an optimal linear combination (OLC) of forecasts derived from naive, persistence, and Ensemble Streamflow Prediction (ESP) forecasts. Using the cross-validation technique, the OLC model made 1-month ahead probabilistic forecasts for the Chungju multi-purpose dam inflows for 15 years. For most of the verification months, the skill associated with the OLC forecast was superior to those drawn from the individual forecast techniques. Therefore this study demonstrates that OLC can improve the accuracy of the ESP forecast, especially during the dry season. This study also examined the value of the OLC forecasts in reservoir operations. Stochastic Dynamic Programming (SDP) derived the optimal operating policy for the Chungju multi-purpose dam operation and the derived policy was simulated using the 15-year observed inflows. The simulation results showed the SDP model that updated its probability from the new OLC forecast provided more efficient operation decisions than the conventional SDP model.

• 대기
• /
• 제32권2호
• /
• pp.149-162
• /
• 2022

This study investigated the prediction skill of the Asian dust seasonal forecasting model (GloSea5-ADAM) on the Asian dust and meteorological variables related to the dust generation for the period of 1991~2016. Additionally, we evaluated the prediction skill of those variables depending on the combination of the initial dates in the sub-seasonal scale for the dust source region affecting South Korea. The Asian dust and meteorological variables (10 m wind speed, 1.5 m relative humidity, and 1.5 m air temperature) from GloSea5-ADAM were compared to that from Synoptic observation and European Centre for medium range weather forecasts reanalysis v5, respectively, based on Mean Bias Error (MBE), Root Mean Square Error (RMSE), and Anomaly Correlation Coefficient (ACC) as evaluation criteria. In general, the Asian dust and meteorological variables in the source region showed high ACC in the prediction scale within one month. For all variables, the use of the initial dates closest to the prediction month led to the best performances based on MBE, RMSE, and ACC, and the performances could be improved by adjusting the number of ensembles considering the combination of the initial date. ACC was as high as 0.4 in Spring when using the closest two initial dates. In particular, the GloSea5-ADAM shows the best performance of Asian dust generation with an ACC of 0.60 in the occurrence frequency of Asian dust in March when using the closest initial dates for initial conditions.

• Advances in Computational Design
• /
• 제5권4호
• /
• pp.445-465
• /
• 2020

This paper presents a study conducted with the aim of developing a model of tendering based on a technique of artificial intelligence by managing and controlling the factors of success or failure of construction projects through the evaluation of the process of invitation to tender. Aiming to solve this problem, analysis of the current environment based on SWOT (Strengths, Weaknesses, Opportunities, and Threats) is first carried out. Analysis was evaluated through a case study of the construction projects in Algeria, to bring about the internal and external factors which affect the process of invitation to tender related to the construction projects. This paper aims to develop a mean to identify threats-opportunities and strength-weaknesses related to the environment of various national construction projects, leading to the decision on whether to continue the project or not. Following a SWOT analysis, novel artificial intelligence models in forecasting the project status are proposed. The basic principal consists in interconnecting the different factors to model this phenomenon. An artificial neural network model is first proposed, followed by a model based on fuzzy logic. A third model resulting from the combination of the two previous ones is developed as a hybrid model. A simulation study is carried out to assess performance of the three models showing that the hybrid model is better suited in forecasting the construction project status than RNN (recurrent neural network) and FL (fuzzy logic) models.