• 대기
• /
• 제25권2호
• /
• pp.249-260
• /
• 2015

The changes in thermodynamic and dynamic aspects on near (2025~2049) and long-term (2075~2099) future climate changes between the historical run (1979~2005) and the Representative Concentration Pathway (RCP) 4.5 run with 20 coupled models which employed in the phase five of Coupled Model Inter-comparison Project (CMIP5) over East Asia (EA) and the Korean Peninsula are investigated as an extended study for Moon et al. (2014) study noted that the 20 models' multi-model ensemble (MME) and best five models' multi-model ensemble (B5MME) have a different increasing trend of precipitation during the boreal winter and summer, in spite of a similar increasing trend of surface air temperature, especially over the Korean Peninsula. Comparing the MME and B5MME, the dynamic factor (the convergence of mean moisture by anomalous wind) and the thermodynamic factor (the convergence of anomalous moisture by mean wind) in terms of moisture flux convergence are analyzed. As a result, the dynamic factor causes the lower increasing trend of precipitation in B5MME than the MME during the boreal winter and summer over EA. However, over the Korean Peninsula, the dynamic factor causes the lower increasing trend of precipitation in B5MME than the MME during the boreal winter, whereas the thermodynamic factor causes the higher increasing trend of precipitation in B5MME than the MME during the boreal summer. Therefore, it can be noted that the difference between MME and B5MME on the change in precipitation is affected by dynamic (thermodynamic) factor during the boreal winter (summer) over the Korean Peninsula.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2008년도 학술발표회 논문집
• /
• pp.299-303
• /
• 2008

In this study, an uncertainty assessment for surface air temperature(T2m) and precipitation(PCP) over East Asia is carried out. The data simulated by the intergovermental Panel on Climate Change (IPCC) Fourth Assessment Report (AR4) Atmosphere-Ocean coupled general circulation Model (AOGCM) are used to assess the uncertainty. Examination of the seasonal uncertainty of T2m and PCP variabilities shows that spring-summer cold bias and fall warm bias of T2m are found over both East Asia and the Korea peninsula. In contrast, distinctly summer dry bias and winter-spring wet bias of PCP over the Korea peninsula is found. To investigate the PCP seasonal variability over East Asia, the cyclostationary empirical orthogonal function(CSEOF) analysis is employed. The CSEOF analysis can extract physical modes (spatio-temporal patterns) and their undulation (PC time series) of PCP, showing the evolution of PCP. A comparison between spatio-temporal patterns of observed and modeled PCP anomalies shows that positive PCP anomalies located in northeastern China (north of Korea) of the multi-model ensemble(MME) cannot explain properly the contribution to summer monsoon rainfalls across Korea and Japan. The uncertainty of modeled PCP indicates that there is disagreement between observed and MME anomalies. The spatio-temporal deviation of the PCP is significantly associated with lower- and upper-level circulations. In particular, lower-level moisture transports from the warm pool of the western Pacific and corresponding moisture convergence significantly contribute to summer rainfalls. These lower- and upper-level circulations physically consistent with PCP give a insight of the reason why differences between modeled and observed PCP occur.

• 한국IT서비스학회지
• /
• 제11권4호
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• The Korean Journal of Legal Medicine
• /
• 제41권2호
• /
• pp.32-40
• /
• 2017

In addition to identifying genetic differences between target populations, it is also important to determine the impact of genetic differences with regard to the respective target populations. In recent years, there has been an increasing number of cases where this approach is needed, and thus various statistical methods must be considered. In this study, genetic data from populations of Southeast and Southwest Asia were collected, and several statistical approaches were evaluated on the Y-chromosome short tandem repeat data. In order to develop a more accurate and practical classification model, we applied gradient boosting and ensemble techniques. To infer between the Southeast and Southwest Asian populations, the overall performance of the classification models was better than that of the decision trees and regression models used in the past. In conclusion, this study suggests that additional statistical approaches, such as data mining techniques, could provide more useful interpretations for forensic analyses. These trials are expected to be the basis for further studies extending from target regions to the entire continent of Asia as well as the use of additional genes such as mitochondrial genes.

• 대기
• /
• 제29권2호
• /
• pp.149-164
• /
• 2019

The purpose of this study is to introduce the improvement of current operational climate prediction system of KMA and to compare previous and improved that. Whereas the previous system is based on GloSea5GA3, the improved one is built on GloSea5GC2. GloSea5GC2 is a fully coupled global climate model with an atmosphere, ocean, sea-ice and land components through the coupler OASIS. This is comprised of component configurations Global Atmosphere 6.0 (GA6.0), Global Land 6.0 (GL6.0), Global Ocean 5.0 (GO5.0) and Global Sea Ice 6.0 (GSI6.0). The compositions have improved sea-ice parameters over the previous model. The model resolution is N216L85 (~60 km in mid-latitudes) in the atmosphere and ORCA0.25L75 ($0.25^{\circ}$ on a tri-polar grid) in the ocean. In this research, the predictability of each system is evaluated using by RMSE, Correlation and MSSS, and the variables are 500 hPa geopotential height (h500), 850 hPa temperature (t850) and Sea surface temperature (SST). A predictive performance shows that GloSea5GC2 is better than GloSea5GA3. For example, the RMSE of h500 of 1-month forecast is decreased from 23.89 gpm to 22.21 gpm in East Asia. For Nino3.4 area of SST, the improvements to GloSeaGC2 result in a decrease in RMSE, which become apparent over time. It can be concluded that GloSea5GC2 has a great performance for seasonal prediction.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2016년도 학술발표회
• /
• pp.516-516
• /
• 2016

기후변화는 농업생산량 감소와 식량 안보 문제와 같이 농업에 심각한 영향을 미칠 수 있다. 또한 기존의 농업수리 및 관개배수 시설 운영에 영향을 줄 수 있다. 따라서 지속가능한 농업 수자원 관리를 위해서는 기후변화의 영향을 고려한 장기적인 계획 수립이 필요하다. 따라서 본 연구에서는 논벼 지역의 설계용수량의 확률론적 분석을 통한 논벼 필요수량 및 설계용수량에 대한 기후변화영향 평가를 실시하였다. 이를 위해서 본 연구에서는 23개 GCM의 36개 산출물을 활용하여 Multi-model ensemble 구축하였다. 먼저 GCM별 증발산량과 유효우량을 산정한 결과 중부지역에서는 IPSL-CM5A 모델의 기후변화자료를 활용할 경우 증발산량과 유효우량이 타 GCM 모델들과 비하여 크게 산정되었다. 남부지역에서는 CanESM2 모델을 적용할 경우 가장 많은 증발산량과 유효우량이 모의되는 것으로 나타났다. 이처럼 GCM별로 다양한 결과가 모의되기 때문에 농업시설 설계에 적용되는 설계용수량의 경우 안전성을 위하여 Multi-GCM models을 활용할 필요가 있다. Multi-model ensemble의 RCP 4.5와 RCP 8.5 시나리오를 적용한 결과, 모든 경우에서 1995s(1981-2014)에 비해 설계용수량은 점차적으로 증가하는 것으로 나타났다. 평균 증가율은 RCP 4.5에서 중부지역이 9.4%, 남부지역이 6.0% 증가하는 것으로 나타난 반면, RCP 8.5에서는 중부지역이 11.1%, 남부지역이 8.2% 증가하는 것으로 나타났다. 또한 여러 GCM 산출물간의 불확실성은 RCP 4.5보다는 RCP 8.5 시나리오가, 중부 지역보다는 남부 지역이, 논벼 증발산량 보다는 유효우량이 더 큰 것으로 분석되었다. 본 연구는 향후 미래 가뭄 위험성을 최소화하기 위한 농업 수자원관리 전략수립에 활용될 수 있을 것이다. 또한 본 연구결과는 기후변화 영향 평가에 있어서 적합한 GCM 자료를 선택하는데 있어, 불확실성을 가늠할 수 있는 유용한 척도로 이용될 수 있을 것으로 기대된다.

• 한국환경복원기술학회지
• /
• 제25권5호
• /
• pp.1-13
• /
• 2022

The damages caused by landslides are increasing worldwide due to climate change. In Korea, damages from landslides occur frequently, making it necessary to develop the effective response strategies. In particular, there is a lack of countermeasures against landslides in cultural heritage areas. The purpose of this study was to spatially analyze the relationship between Buyeo-gun's cultural heritage and landslide susceptible areas in Buyeo-gun, Chungcheongnam-do, which has a long history. Nine spatial distribution models were used to evaluate the landslide susceptibility, and the ensemble method was applied to reduce the uncertainty of individual model. There were 17 cultural heritages belonging to the landslide susceptible area. As a result of calculating the area ratio of the landslide susceptible area for cultural heritages, the cultural heritages with 100% of the area included in the landslide susceptible area were "Standing statue of Maae in Hongsan Sangcheon-ri" and "Statue of King Seonjo." More than 35% of "Jeungsanseong", "Garimseong", and "Standing stone statue of Maitreya Bodhisattva in Daejosa Temple" belonged to landslide susceptible areas. In order to effectively prevent landslide damage, the application of landslide prevention measures should be prioritized according to the proportion belonging to the landslide susceptible area. Since it is very difficult to restore cultural properties once destroyed, preventive measures are required before landslide damage occurs. The approach and results of this study provide basic data and guidelines for disaster response plans to prevent landslides in Buyeo-gun.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2030-2052
• /
• 2023

Analysis of a bipartite (two-mode) network is a significant research area to understand the formation of social communities, economic systems, drug side effect topology, etc. in complex information systems. Most of the previous works talk about a projection-based model or latent feature model, which predicts the link based on singular similarity. The projection-based models suffer from the loss of structural information in the projected network and the latent feature is hardly present. This work proposes a novel method for link prediction in the bipartite network based on an ensemble of composite similarities, overcoming the issues of model-based and latent feature models. The proposed method analyzes the structure, neighborhood nodes as well as latent attributes between the nodes to predict the link in the network. To illustrate the proposed method, experiments are performed with five real-world data sets and compared with various state-of-art link prediction methods and it is inferred that this method outperforms with ~3% to ~9% higher using area under the precision-recall curve (AUC-PR) measure. This work holds great significance in the study of biological networks, e-commerce networks, complex web-based systems, networks of drug binding, enzyme protein, and other related networks in understanding the formation of such complex networks. Further, this study helps in link prediction and its usability for different purposes ranging from building intelligent systems to providing services in big data and web-based systems.

• 스마트미디어저널
• /
• 제12권11호
• /
• pp.1-9
• /
• 2023

스트레스는 감당하기 어려운 외부 또는 내부 요인으로부터 유발되는 것으로 현대 사회의 주요한 문제 중 하나이다. 높은 스트레스가 장기적으로 지속되면 만성적으로 발전할 수 있으며, 건강 및 생활 전반에 큰 악영향을 초래할 수 있다. 그러나 만성적인 스트레스를 겪는 사람들은 자신이 스트레스를 받고 있는지 알아차리기 어렵기 때문에 사전에 스트레스를 인지하고 관리하는 것이 중요하다. 웨어러블 기기로부터 측정된 생체 신호를 이용하여 스트레스를 탐지한다면, 스트레스를 효율적으로 관리할 수 있을 것이다. 그러나 생체 신호를 이용하는 데에는 두 가지 문제점이 있다. 첫째로 생체 신호에서 수작업 특징을 추출하는 것은 바이어스를 발생시킬 수 있으며, 두 번째는 실험 주체에 따라 분류 모델 성능의 변이가 클 수 있다는 것이다. 본 논문에서는 데이터의 핵심적인 특징을 표현할 수 있는 합성곱 오토인코더를 이용해 바이어스를 줄이고 앙상블 학습 중 하나인 소프트 보팅을 이용해 일반화 능력을 높여 성능의 변이를 줄이는 모델을 제안한다. 모델의 일반화 성능을 확인하기 위하여 LOSO 교차 검증 방법을 이용하여 성능을 평가한다. 본 논문에서 제안한 모델은 WESAD 데이터셋을 이용하여 높은 성능을 보여주었던 기존의 연구들보다 우수한 정확도를 보임을 확인하였다.

• 대한토목학회논문집
• /
• 제38권4호
• /
• pp.579-586
• /
• 2018

단기 통행속도 예측을 위해 데이터 기반 비모수적 기법들을 활용한 다양한 연구들이 수행되고 있다. 그럼에도 교통신호 및 교차로로 인한 복잡한 동적 특성을 가지는 도시부의 예측 연구는 상대적으로 부족한 실정이다. 본 연구는 도시부 통행 속도를 예측하기 위해 앙상블 경험적 모드 분해법(EEMD)과 인공신경망(ANN)을 이용한 하이브리드 접근법을 제안하는 것을 목적으로 한다. EEMD는 통행속도의 시계열 자료를 고유모드함수(IMF)와 오차항으로 분해한다. 분해된 IMF는 시간단위의 국지적 특성을 반영하며, ANN을 통해 개별적으로 예측된다. IMF는 원본데이터가 가진 비선형성, 비정상성, 진동 등의 복잡성을 완화하기 때문에, 원래의 통행속도에 비하여 더 정확하게 예측될 수 있다. 예측된 IMF들은 합산되어 예측 통행속도를 표현한다. 본 연구에서 제시된 방법을 검증하기 위하여 대구시의 DSRC로부터 구득된 통행속도 데이터가 활용된다. 성능평가는 도시부 링크 중 특히 예측이 어려운 지점에 대해 수행되었으며, 분석 결과 제시된 모형은 15분 후 예측에 대해 각각 평상시 10.41%, 와해상태시 25.35%의 오차율을 가지며, 단순 ANN 기법에 비하여 우수한 성능을 보이는 것으로 확인된다. 본 연구에서 개발된 모형은 도시교통관리체계의 신뢰성 있는 교통정보를 제공하는 데에 기여할 수 있을 것으로 기대된다.