• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.195-195
• /
• 2018

기상청에서는 영국 전지구기후모델인 HadGEM2-AO 기반의 영국 지역기후모델 HadGEM3-RA로부터 생산된 기후변화 시나리오를 기후변화예측을 위한 국가표준시나리오 자료로 제공하고 있다. 하지만, 기후모델의 특성상, 관측자료와 모의자료 간에는 통계적인 차이가 존재하며, 이러한 차이를 무시하고 원자료를 그대로 분석에 사용하는 것은 무의미 하다. 따라서 이러한 보정하기 위해서 주로 Quantile Mapping, Quantile Delta Mapping, Detrended Quantile Mapping 방법이 주로 사용된다. 하지만 어떠한 편의보정 방법이든 극값이 다수 존재하는 미래기간 모의자료를 보정할 때에는 외삽법(extrapolation)의 적용이 필요하다. 외삽법의 경우 constant correction 방법이 주로 적용된다. 본 연구에서는 기상청의 국가표준시나리오를 대상으로 이러한 편의보정 방법의 적용에 따른 미래 극한강우량의 차이를 분석하고자 하였다. 우선, 모의자료에서 우리나라 주요 기상관측지점에 해당하는 격자로부터 강우량자료를 추출하고 연최대강우시계열을 산정하였다. 그 후, 위의 세 가지 편의보정 방법을 이용하여 강우자료의 편의보정을 수행하였으며, constant correction 방법을 적용하여 이상치를 보정하였다. 그 후, 보정된 미래기간 모의자료의 추세를 분석하고, 이를 미래 확률강우량 산정방법인 scale-invariance 기법에 적용하여 미래 확률강우량을 산정하였다. 그 결과, 외삽법의 적용에 따라 편의보정 방법에 따라 미래 자료의 추세 또는 확률강우량의 변화패턴은 큰 차이를 나타내지 않았지만, 그 값 자체는 다소 차이가 있는 것으로 나타났다. 이러한 차이는 사용된 GCM과 RCM 조합으로 인한 오차와 더해져, 미래 예측결과의 불확실성으로 나타나기에 미래 극한강우량 예측을 위해서는 다수의 GCM, RCM 조합뿐만 아니라 다수의 편의보정 방법에 따른 결과도 함께 고려(ensemble)하여 결과를 나타내는 것이 필요할 것으로 판단된다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.693-698
• /
• 2003

Every baseball game generates various records and on the basis of those records, win/lose prediction about the next game is carried out. Researches on win/lose predictions of professional baseball games have been carried out, but there are not so good results yet. Win/lose prediction is very difficult because the choice of features on win/lose predictions among many records is difficult and because the complexity of a learning model is increased due to overlapping factors among the data used in prediction. In this paper, learning features were chosen by opinions of baseball experts and a heuristic function was formed using the chosen features. We propose a hybrid model by creating a new value which can affect predictions by combining multiple features, and thus reducing a dimension of input value which will be used for backpropagation learning algorithm. As the experimental results show, the complexity of backpropagation was reduced and the accuracy of win/lose predictions on professional baseball games was improved.

• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1159-1172
• /
• 2020

This study applied deep convolution neural network based on U-Net and SegNet using long period weather radar data to very short-term rainfall prediction. And the results were compared and evaluated with the translation model. For training and validation of deep neural network, Mt. Gwanak and Mt. Gwangdeoksan radar data were collected from 2010 to 2016 and converted to a gray-scale image file in an HDF5 format with a 1km spatial resolution. The deep neural network model was trained to predict precipitation after 10 minutes by using the four consecutive radar image data, and the recursive method of repeating forecasts was applied to carry out lead time 60 minutes with the pretrained deep neural network model. To evaluate the performance of deep neural network prediction model, 24 rain cases in 2017 were forecast for rainfall up to 60 minutes in advance. As a result of evaluating the predicted performance by calculating the mean absolute error (MAE) and critical success index (CSI) at the threshold of 0.1, 1, and 5 mm/hr, the deep neural network model showed better performance in the case of rainfall threshold of 0.1, 1 mm/hr in terms of MAE, and showed better performance than the translation model for lead time 50 minutes in terms of CSI. In particular, although the deep neural network prediction model performed generally better than the translation model for weak rainfall of 5 mm/hr or less, the deep neural network prediction model had limitations in predicting distinct precipitation characteristics of high intensity as a result of the evaluation of threshold of 5 mm/hr. The longer lead time, the spatial smoothness increase with lead time thereby reducing the accuracy of rainfall prediction The translation model turned out to be superior in predicting the exceedance of higher intensity thresholds (> 5 mm/hr) because it preserves distinct precipitation characteristics, but the rainfall position tends to shift incorrectly. This study are expected to be helpful for the improvement of radar rainfall prediction model using deep neural networks in the future. In addition, the massive weather radar data established in this study will be provided through open repositories for future use in subsequent studies.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.11-20
• /
• 2023

The cost of medical treatment for motor vehicle accidents is increasing every year. In this study, we created a model to predict long-term hospitalization(more than 18 days) among minor patients, which is the main item of increasing traffic accident medical expenses, using five algorithms such as decision tree, and analyzed the factors affecting long-term hospitalization. As a result, the accuracy of the prediction models ranged from 91.377 to 91.451, and there was no significant difference between each model, but the random forest and XGBoost models had the highest accuracy of 91.451. There were significant differences between models in the importance of explanatory variables, such as hospital location, name of disease, and type of hospital, between the long-stay and non-long-stay groups. Model validation was tested by comparing the average accuracy of each model cross-validated(10 times) on the training data with the accuracy of the validation data. To test of the explanatory variables, the chi-square test was used for categorical variables.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.5
• /
• pp.160-170
• /
• 2007

This study predicts Life Cycle Cost of RC Slab bridge case in maintenance and operation level and calculated economic efficiency by the avoidable costs of a bridge. This result of the study can be summarized as follow: (1) LCC analysis model on the bridge case is suggested. (2) Maintenance and operation level of a bridge have been divided, and LCC of the bridge case has been predicted at current maintenance and operation level and required maintenance and operation level. (3) Reduction costs is predicted by LCC of the bridge case, and its economic efficiency is calculated.

• Smart Media Journal
• /
• v.7 no.1
• /
• pp.16-23
• /
• 2018

In this paper, we used the Deep Neural Network (DNN) to predict the number of daily spectators of Gwangju - KIA Champions Field in order to provide marketing data for the team and related businesses and for managing the inventories of the facilities in the stadium. In this study, the DNN model, which is based on an artificial neural network (ANN), was used, and four kinds of DNN model were designed along with dropout and batch normalization model to prevent overfitting. Each of four models consists of 10 DNNs, and we added extra models with ensemble model. Each model was evaluated by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The learning data from the model randomly selected 80% of the collected data from 2008 to 2017, and the other 20% were used as test data. With the result of 100 data selection, model configuration, and learning and prediction, we concluded that the predictive power of the DNN model with ensemble model is the best, and RMSE and MAPE are 15.17% and 14.34% higher, correspondingly, than the prediction value of the multiple linear regression model.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2007.05a
• /
• pp.190-197
• /
• 2007

외환위기 이후 우리나라 금융기관은 상대적으로 위험성이 높은 기업대출보다, 높은 수익성을 가지는 가계 대출에 관심을 기울이게 되었다. 가계대출이 증가함에 따라 개인신용평가의 중요성이 부각되고, 이에 많은 신용평가시스템이 개발되어 왔다. 하지만 기존의 신용평가시스템은 대출 신청 당시의 데이터 및 과거의 데이터를 가지고 개인의 신용을 평가하기 때문에, 미래 상황에 대한 예측은 고려하지 못한다. 시스템 다이나믹스는 시간의 흐름에 따른 각 요인의 변화를 살펴봄으로써 미래 상황에 대한 예측이 가능한 분석 방법이다. 이에 본 연구에서는 시스템 다이나믹스 방법론을 활용하여 개인 신용 상태에 대한 미래의 동태적인 변화를 예측하여, 그 결과를 반영한 신용평가모델을 개발하고자 한다. 이를 위하여, 먼저 신용평점 영향을 주는 변수들을 선정하고, 이 변수들 간의 인과관계를 밝혀낸 후, 인과관계를 토대로 분석 모델을 구축한 뒤, 컴퓨터 시뮬레이션을 실행함으로써, 대출 희망자의 미래의 신용상태 변화 모양을 예측해 본다. 이러한 시뮬레이션 결과를 신용평가에 반영하게 되면, 금융기관의 신용 대출의 위험을 줄이는 데 기여할 것으로 기대된다.

• Journal of Environmental Health Sciences
• /
• v.27 no.4
• /
• pp.99-105
• /
• 2001

도로교통소음은 많은 지역에 산재해 있으며 특히 주도로변에 거주하는 사람들에게 환경과 관련하여 매우 중요하다. 도로교통으로부터 소음수준을 계산하는데 몇가지 다른 방법들이 이용되고 있다. 이 방법들은 계산방법과 그래프식 그리고 컴퓨터 모델링 기술 등이다. 교통과 교통소음의 영향으로부터 소음을 계산하는 간단한 기술의 예측방법은 여기에 나타내었다. 이 TNS (traffic Noise Screening) 방법은 서로 다른 도로유형에 대한 일련의 도로교통소음레벨의 예측그래프로 전개된 것이다. 이 그래프는 Federal Highway Administration (FHWA) STAMINA 2.0을 이용하여 다양한 시나리오에 대한 소음 예측모델을 계산한 결과를 기초하였다. TNS에 도로의 기하학적 형태, 교통량 주행속도 그리고 도로중앙선의 거리등의 데이터를 입력시킨다. TNS 그래프는 소음영향과 연관된 교통소음예측에서 사용하는 경우 교통소음레벨의 계산을 쉽게 한다. 이 TNS 방법은 STAMINA 2.0과 같은 상세 모델링을 대신하지는 못하지만 상세 모델을 필요로 할 때 도움을 주는 도구이다 만약 소음계산들이 중요하거나 또는 시나리오가 보다 복잡하고 부가된다면 보다 상세한 모델링이 수행되어져 스크린 결과들이 나타난다.

• Journal of the Korean Solar Energy Society
• /
• v.31 no.5
• /
• pp.19-26
• /
• 2011

복잡지형에서의 풍력단지 CFD 모델링을 통한 시뮬레이션 결과가 이 논문에 주어졌다. 이 연구를 위하여 작은 산(오름)들로 둘러싸인 제주도 성산 풍력단지가 선택되었고, 두 개의 주풍향에 대하여 ANSYS CFX로 시뮬레이션 하였다. 격자생성을 위하여 실제 지형데이터가 사용되었고, 풍력발전기와 복잡지형으로부터 발생하는 후류효과를 예측하기 위하여 SST 난류모델 및 액추에이터 디스크 모델이 적용되었다. 그 결과, 성산 풍력단지 주변에 있는 작은 산 및 풍력발전기에서 발생하는 후류의 영향은 3~7 km 계속된다고 예측되었다. 또한 그 후류는 풍속 및 난류강도에 상당한 영향을 미치고 있다고 예측되었다.