• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.354-354
• /
• 2023

최근 기후변화로 인해 전 지구적인 기후 특성이 변화하고 있으며, 기후 특성의 변화는 수문순환에도 큰 영향을 미친다. IPCC (Intergorvernmental Panel on Climate Change) 6차 기후변화 평가 보고서(2022)에 의하면 AR5 (Assessment Report 5)와 비교해 AR6 (Assessment Report 6)에서는 높은 신뢰도로 기후변화 영향의 범위 및 규모는 보다 확대되었으며, 단기적인 리스크로 극한기후 현상의 빈도와 강도 및 기간이 증가할 것으로 예측하였다. 또한, 중장기적인 리스크로 하천 유량의 규모와 관련한 극한 현상의 변화에 따라 수자원 관리 측면에서 어려움을 겪을 것으로 전망하였다. 위와 같은 기후변화에 대응하기 위해 국내에서는 기후변화와 관련된 다양한 연구가 진행되고 있다. 국내 기후변화 관련 연구로는 ArcSWAT 모형을 활용한 RCP4.5, RCP8.5 시나리오 기반 미래 유출량 추정에 관한 연구와, SWAT, IHACRES, GR4J 모형을 이용한 용담댐 유역의 미래기간 유출량 변화 모의, SWAT과 VIC 모형을 활용한 미래 저유량 예측 시 관측 자료와 비교해 모형이 가지는 불확실성 평가 등 기후변화 영향을 평가 및 예측하기 위한 연구는 활발히 진행 중이다. 하지만, 최근 연구의 주요 동향은 유출 모형을 활용한 미래 유출량 모의에 초점이 맞추어져 있으며, 관측 자료를 통한 기후변화 평가 연구는 부족한 실정이다. 따라서 본 연구에서는 한반도 5대 수계(한강, 금강, 낙동강, 영산강, 섬진강) 유량 관측소의 실측 유량을 활용해 과거기간의 기후변화에 따른 유출특성의 변화와, 미래기후변화 시나리오 자료를 활용한 미래기간 유출특성의 변화를 분석하였다. 분석 인자로 연 유출량, 1일 최대 유출량, 상위 90%에 해당하는 유출량, 하위 10%에 해당하는 유출량 등을 연도별로 분석하였다. 분석 결과 연도별 총 유출량의 큰 변화는 없지만, 홍수 기간의 첨두유량이 증가하는 동시에 갈수 기간 또한 빈도와 규모가 증가하는 양극화 현상이 진행되고 있음을 확인하였다.

• The Korean Journal of Applied Statistics
• /
• v.12 no.2
• /
• pp.397-404
• /
• 1999

1997년말 발생한 외환위기 이후 불확실성의 증대로 시계열모형을 이용한 경제예측에 한계가 노정되고 있다. 이를 극복하기 위하여 경제주체의 기대(expectation)를 파악할수 있는 기업경기실사지수를 경제예측에 도입할 필요가 있다. 본고에서는 기업경기실사지수를 이용한 모형과 시계열모형을 추정하고 이들을 예측력 측면에서 비교, 분석해보았다. 분석결과 불확실성이 높았던 외환위기이후 기간에는 기업경기실사지수를 이용한 모형이 시계열모형보다 예측력면에서 우수한 것으로 나타났다.

• The Journal of Bigdata
• /
• v.4 no.1
• /
• pp.63-72
• /
• 2019

For power energy, optimal generation and distribution plans based on accurate demand forecasts are necessary because it is not recoverable after they have been delivered to users through power generation and transmission processes. Failure to predict power demand can cause various social and economic problems, such as a massive power outage in September 2011. In previous studies on forecasting power demand, ARIMA, neural network models, and other methods were developed. However, limitations such as the use of the national average ambient air temperature and the application of uniform criteria to distinguish seasonality are causing distortion of data or performance degradation of the predictive model. In order to improve the performance of the power demand prediction model, we divided Korea into five major regions, and the power demand prediction model of the linear regression model and the neural network model were developed, reflecting seasonal characteristics through regional characteristics and migration period learning techniques. With the proposed approach, it seems possible to forecast the future demand in short term as well as in long term. Also, it is possible to consider various events and exceptional cases during a certain period.

• 한국ITS학회:학술대회논문집
• /
• 2004.11a
• /
• pp.154-162
• /
• 2004

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1143-1154
• /
• 2021

The selection of activation function has a great influence on the groundwater level prediction performance of artificial neural network (ANN) model. In this study, five activation functions were applied to ANN model for two groundwater level observation wells in the middle mountainous area of the Pyoseon watershed in Jeju Island. The results of the prediction of the groundwater level were compared and analyzed, and the optimal activation function was derived. In addition, the results of LSTM model, which is a widely used recurrent neural network model, were compared and analyzed with the results of the ANN models with each activation function. As a result, ELU and Leaky ReLU functions were derived as the optimal activation functions for the prediction of the groundwater level for observation well with relatively large fluctuations in groundwater level and for observation well with relatively small fluctuations, respectively. On the other hand, sigmoid function had the lowest predictive performance among the five activation functions for training period, and produced inappropriate results in peak and lowest groundwater level prediction. The ANN-ELU and ANN-Leaky ReLU models showed groundwater level prediction performance comparable to that of the LSTM model, and thus had sufficient potential for application. The methods and results of this study can be usefully used in other studies.

• Journal of Internet Computing and Services
• /
• v.7 no.1
• /
• pp.75-89
• /
• 2006

This paper is concerned with analysing the bankruptcy prediction power of three models: Multivariate Discriminant Analysis(MDA), Logit Analysis, Neural Network. The research targeted the bankrupted companies after the foreign exchange crisis in 1997 to differentiate from previous research efforts, and all participating companies were randomly selected from the KSE listed companies belonging to manufacturing industry to improve prediction accuracy and validity of the model. In order to assure meaningful bankruptcy prediction, training data and testing data were not extracted within the corresponding period. The result is that prediction accuracy of neural networks is more excellent than that of logit analysis and MDA model when considering that execution of testing data was followed by execution of training data.

• Journal of Digital Convergence
• /
• v.15 no.12
• /
• pp.283-291
• /
• 2017

This Study analyzes the predictability of accounting information from mandatory K-IFRS adoption using the K-IFRS reconciliations information. We use the sample of 2,557 firm-year Korea listed companies belonging to non-financial corporate sector during 2010-2016. Specifically, we examine whether K-IFS reconciliation would improve or reduce the predicting power for future earnings after K-IFRS adoption. The results of empirical analyses show that reconciliation information from discretionary judgement tend to reduce the predicting power of K-IFRS based accounting earnings for future earnings. This result indicates that managers are likely to use the adjustments process to reconcile K-GAAP accounting numbers with corresponding K-IFRS as means to realize the various private utility. This study is expected to provide useful information by suggesting the need for more rigid screening schemes for the K-IFRS reconciliation process and also for adequate measures to be taken to ensure that the interests of the outside investors are properly protected.

• The Korean Journal of Financial Studies
• /
• v.5 no.1
• /
• pp.213-236
• /
• 1999

최근 우리 나라는 금융환경의 변화가 진전됨에 따라 보험산업에도 변화가 일어나기 시작했다. 이에 따라 보험산업은 지급능력 및 수익성에 관심을 갖게 되었다. 이에 본 연구에서는 국내 생명보험회사의 투자수익율이 재무제표에 나타난 요인에 의해 어떻게 결정되는가를 살펴봄으로써 수익률 결정요인을 찾는데 있다. 본 연구에서 사용한 자료는 생명보험회사 33개사 중에서 외국사를 제외한 29개사를 선택하여 수집하였다. 분석 기간은 1989년부터 1996년까지이며, 생명보험회사는 기존사, 지방사, 내국사, 합작사로 구분하였다. 분석결과, 시차별 분석에서는 결정계수가 기간이 짧을수록 높게 나타났고 예측된 부호는 잉여금, 사업비율이 반대로 나타났다. 그룹별 분석에서는 기존사, 내국사, 지방사, 합작사의 모델이 각각 유의수준 5%에서 유의하였고 결정계수는 높게 나타났다. 예측부호는 자산증가율과 사업비율, 수입보험료 증가율(기존사 제외), 부채/자본비율(기존사 제외)이 일치하지 않았다. 경영평가제도에 의한 분석에서는 결정계수가 높은 편이며, 유의수준 5%에서 유의하였다. 자본증가율은 예측된 부호와 일치하나 영향력이 거의 없는 것으로 나타났다. 유동성 비율은 신설사(내국사, 지방사, 합작사)가 예측부호와 반대의 경우로 나타났다. 또한 총자산은 투자수익율과 규모에 의해 결정되지 않은 것으로 나타났다. 모집인은 투자수익율에 유의적이나 직접적인 투자요인이 아닌 것으로 분석되었다. 기존연구와 비교해 볼 때, 한국 생명보험회사의 잉여금과 효력상실 해약율은 기존연구 모형과 예측부호가 일치하나 나머지 변수는 그룹간 다소 상이하게 나타났다. 결론적으로 본 연구의 분석 결과, 예측부호는 다소 차이가 있는 것으로 나타났고, 유의적인 변수는 없는 것으로 분석된다.

• Journal of the Society of Disaster Information
• /
• v.8 no.3
• /
• pp.234-241
• /
• 2012

The main objective of this research is to calibrate the performance prediction models for the growth of fatigue cracking in multi-layered asphalt concrete pavement systems. However, the calibration factors are dependent upon the prediction model, testing method, and the laboratory loading history. A detailed study on the field data has revealed that the performance of flexible pavements is affected by both the traffic loading and the environmental cycling which is related to the age of the pavements. Thus, a composite indicator was developed in this study which utilizes both the traffic and the age information with appropriate weighting factors. Using the proposed fatigue performance model the calibration factors were also estimated through the comparisons between the field performances on fatigue cracking and the laboratory-based fatigue life.

• Journal of Korea Water Resources Association
• /
• v.46 no.12
• /
• pp.1249-1263
• /
• 2013

In order to minimize the damages caused by long-term drought, appropriate drought management plans of the basin should be established with the drought forecasting technology. Further, in order to build reasonable adaptive measurement for future drought, the duration and severity of drought must be predicted quantitatively in advance. Thus, this study, attempts to forecast drought in Korea by using an Artificial Neural Network Model, and drought index, which are the representative statistical approach most frequently used for hydrological time series forecasting. SPI (Standardized Precipitation Index) for major weather stations in Korea, estimated using observed historical precipitation, was used as input variables to the MLP (Multi Layer Perceptron) Neural Network model. Data set from 1976 to 2000 was selected as the training period for the parameter calibration and data from 2001 to 2010 was set as the validation period for the drought forecast. The optimal model for drought forecast determined by training process was applied to drought forecast using SPI (3), SPI (6) and SPI (12) over different forecasting lead time (1 to 6 months). Drought forecast with SPI (3) shows good result only in case of 1 month forecast lead time, SPI (6) shows good accordance with observed data for 1-3 months forecast lead time and SPI (12) shows relatively good results in case of up to 1~5 months forecast lead time. The analysis of this study shows that SPI (3) can be used for only 1-month short-term drought forecast. SPI (6) and SPI (12) have advantage over long-term drought forecast for 3~5 months lead time.