• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.152-152
• /
• 2017

최근 지속적인 심한 가뭄의 발생은 사회적 이슈가 되고 있으므로 가뭄을 감시할 수 있는 가뭄 모니터링 뿐만 아니라 경감할 수 있는 가뭄전망이 되어야 한다. 이를 위해 우선적으로 우리나라 실정에 맞는 최적화된 가뭄지수의 선정 혹은 개선이 필요하며, 다음으로 개선된 가뭄지수를 기반으로 한 다양한 가뭄정보들이 수자원확보를 위한 관리와 정책에 활용되어야 한다. 이에 따라 본 연구에서는 국내 기존에 활용되고 있는 수문학적 가뭄지수인 MSWSI를 개선하였으며, 개선된 MSWSI를 이용하여 앙상블기법 기반의 확률론적 가뭄전망을 수행하였다. 대상 유역은 낙동강 유역을 선정하였으며, 연구내용을 살펴보면, 첫 번째로 MSWSI의 개선에 있어서는 (1) 유역 내 공식적으로 수집되는 모든 수문기상인자를 조사하여 중권역 유역별로 기존 MSWSI에서 적용한 4개 인자(강수량, 하천유량, 댐 유입량, 지하수량) 뿐만 아니라 사용 가능한 적합한 인자(댐 저수위, 댐 방류량)를 추가 선정하여 반영; (2) 각 수문인자들에 대해 기존에는 정규분포만 적용하였으나 본 연구에서는 각각 인자별 적합한 확률분포를 추정하였다. 두 번째로 극심한 가뭄이 발생한 2006년과 2014년을 대상으로 개선된 MSWSI를 이용한 앙상블기반 확률론적 가뭄전망을 수행하고 검증하였다. 분석 결과를 살펴보면, 개선된 MSWSI를 과거 실측 수문기상자료를 이용하여 검증한 결과 기존 MSWSI보다 개선된 MSWSI가 과거 발생한 가뭄현상을 더 잘 나타내어 개선된 MSWSI가 효용성이 있음을 확인하였다. 또한 앙상블 기반의 확률론적 가뭄 전망 결과, 기존보다 개선된 MSWSI를 이용한 가뭄전망이 우수한 결과를 나타냈다. 또한 대부분의 유역에서 실제 가뭄의 가뭄지수가 개선된 MSWSI를 이용한 가뭄전망 범위에 속하는 것으로 나타났다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.59-59
• /
• 2019

최근 기후변화로 인해 대류성 집중호우가 빈번하게 발생하고 있으며, 이러한 강우 특성은 산지지역에 위치한 소하천유역에 상당한 피해를 야기한다. 대류성 집중호우는 규모가 작고 속도가 빠르기 때문에 중규모 이상의 유역에서 부분적으로 상이한 강우특성을 보인다. 아울러 이러한 호우패턴의 변화는 일시적인 현상이 아닌 하나의 기상 특성으로 자리를 잡아가고 있기 때문에 이에 대한 대책마련이 더욱 필요한 실정이다. 돌발홍수 예경보시스템에 예측강우 자료는 예측 선행시간의 한계를 가진다. 즉, 예측강우 자료자체가 가지는 편의와 불확실성으로 인해 예측 선행시간이 3시간을 초과하면 신뢰도가 급격히 하락하게 된다. 이를 해결하기 위해 우리나라에서는 지상관측치와의 편의를 보정하거나 예측강우자료 자체의 품질을 개선하려는 노력을 지속하고 있다. 본 연구에서는 예측 선행시간을 확장하고자 순차적으로 생산되는 예측강우를 가중평균하여 앙상블 예측치를 모의하는 기법을 개발하였다. 각 선행시간별 예측강우자료를 앙상블 멤버로 인식하여 이들의 공분산 구조를 파악하고, 분산과 공분산 수치를 이용하여 가중치를 결정하였다. 1, 2, 3시간 예측 선행시간에 대한 확장 가능성을 확인하고자 하였고, 최적의 앙상블 멤버 개수를 결정하여 적용 및 평가하였다. 본 연구에서는 2016년과 2017년에 발생한 주요 호우사상을 선정하고, 우리나라 전역에 걸쳐 예측강우 앙상블 생성 방법론을 적용하였다. 그 결과, 가중평균 앙상블의 예측치가 예측강우장 1개, 단순평균 앙상블 예측치에 비해 좋은 품질의 예측 성능을 보였으며, 예측치의 분산 또한 감소하여 예측에 대한 불확실성이 줄어듦을 확인하였다.

• Journal of the Korean Society for information Management
• /
• v.36 no.2
• /
• pp.57-77
• /
• 2019

Random Forest (RF), a representative ensemble technique, was applied to automatic classification of journal articles in the field of library and information science. Especially, I performed various experiments on the main factors such as tree number, feature selection, and learning set size in terms of classification performance that automatically assigns class labels to domestic journals. Through this, I explored ways to optimize the performance of random forests (RF) for imbalanced datasets in real environments. Consequently, for the automatic classification of domestic journal articles, Random Forest (RF) can be expected to have the best classification performance when using tree number interval 100~1000(C), small feature set (10%) based on chi-square statistic (CHI), and most learning sets (9-10 years).

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.30 no.6
• /
• pp.319-325
• /
• 2018

This study conducted an experimental investigation on oscillatory behavior of the hydraulic jump roller. Based on the similarity of the hydraulic jump and tidal bore, the behavior of the front face of hydraulic jump with increasing downstream water depth was studied focusing on profile and fluctuation. In this study, for statistical approach, the ensemble averaging was applied to obtain relevant front profile and compared with the time averaging. The front profile gets mildly sloped and the fluctuation of the starting point of hydraulic jump decreases as the downstream water depth increases.

• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.27-33
• /
• 2021

The whole world now is dealing with Coronavirus, and it has turned to be one of the most widespread and long-lived pandemics of our times. Reports reveal that the infectious disease has taken toll of the almost 80% of the world's population. Amidst a lot of research going on with regards to the prediction on growth and transmission through Symptomatic carriers of the virus, it can't be ignored that pre-symptomatic and asymptomatic carriers also play a crucial role in spreading the reach of the virus. Classification Algorithm has been widely used to classify different types of COVID-19 carriers ranging from simple feature-based classification to Convolutional Neural Networks (CNNs). This research paper aims to present a novel technique using a Random Forest Machine learning algorithm with hyper-parameter tuning to classify different types COVID-19-carriers such that these carriers can be accurately characterized and hence dealt timely to contain the spread of the virus. The main idea for selecting Random Forest is that it works on the powerful concept of "the wisdom of crowd" which produces ensemble prediction. The results are quite convincing and the model records an accuracy score of 99.72 %. The results have been compared with the same dataset being subjected to K-Nearest Neighbour, logistic regression, support vector machine (SVM), and Decision Tree algorithms where the accuracy score has been recorded as 78.58%, 70.11%, 70.385,99% respectively, thus establishing the concreteness and suitability of our approach.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.17-28
• /
• 2022

The cable component of cable-stayed bridges is gradually impacted by weather conditions, vehicle loads, and material corrosion. The stayed cable is a critical load-carrying part that closely affects the operational stability of a cable-stayed bridge. Damaged cables might lead to the bridge collapse due to their tension capacity reduction. Thus, it is necessary to develop structural health monitoring (SHM) techniques that accurately identify damaged cables. In this work, a combinational identification method of three efficient techniques, including statistical analysis, clustering, and neural network models, is proposed to detect the damaged cable in a cable-stayed bridge. The measured dataset from the bridge was initially preprocessed to remove the outlier channels. Then, the theory and application of each technique for damage detection were introduced. In general, the statistical approach extracts the parameters representing the damage within time series, and the clustering approach identifies the outliers from the data signals as damaged members, while the deep learning approach uses the nonlinear data dependencies in SHM for the training model. The performance of these approaches in classifying the damaged cable was assessed, and the combinational identification method was obtained using the voting ensemble. Finally, the combination method was compared with an existing outlier detection algorithm, support vector machines (SVM). The results demonstrate that the proposed method is robust and provides higher accuracy for the damaged cable detection in the cable-stayed bridge.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.905-910
• /
• 2022

Drowsy driving requires a lot of social attention because it increases the incidence of traffic accidents and leads to fatal accidents. The number of accidents caused by drowsy driving is increasing every year. Therefore, in order to solve this problem all over the world, research for measuring various biosignals is being conducted. Among them, this paper focuses on non-contact biosignal analysis. Various noises such as engine, tire, and body vibrations are generated in a running vehicle. To measure the driver's heart rate and respiration rate in a driving vehicle with a piezoelectric sensor, a sensor plate that can cushion vehicle vibrations was designed and noise generated from the vehicle was reduced. In addition, we developed a system for classifying whether the driver is sleeping or not by extracting the model using the CNN-LSTM ensemble learning technique based on the signal of the piezoelectric sensor. In order to learn the sleep state, the subject's biosignals were acquired every 30 seconds, and 797 pieces of data were comparatively analyzed.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.381-381
• /
• 2020

자료동화(Data Assimilation) 기법은 실시간 수문학적 예측에 있어 정확도 향상을 위해 필수적인 과정이다. 가장 대중적으로 사용되는 기법들 중 하나가 모델 상태변수와 매개변수를 동시에 업데이트할 수 있는 이중 앙상블 칼만 필터(Dual Ensemble Kalman Filter)이다. 이 방법은 정확도 개선 및 적용의 용이성 때문에 많은 연구 분야에서 사용되어져 왔지만, 앙상블을 생성하는 과정에서 상당시간이 소요되는 단점이 존재한다. 본 연구에서는 상태변수와 매개변수를 동시에 업데이트 하면서 홍수 예측의 정확성을 보장할 뿐만 아니라, 앙상블 생성에 있어 계산 효율을 크게 향상시킬 수 있는 기법을 제안한다. Polynomial Chaos Expansion(PCE) 기법을 사용하여 앙상블 칼만 필터를 모방(mimic)할 수 있는 새로운 대체필터(Surrogate Filter)를 개발하는 것을 목표로 한다. 구체적으로 대체필터를 구성하기 위한 다양한 필터를 설계하였다. 첫째 시간에 대해서 PCE가 변화하지 않는 '불변 필터'(즉, 전체 예측기간에 대해 하나의 필터를 사용하여 자료동화할 수 있는 대체필터)와, 매 시간마다 PCE가 변화하는 '시변 필터'(즉, 예측하는 매 시간마다 새로운 필터를 생성해야 하는 대체필터)를 설계하여 적용성, 정확성, 예측성 등을 비교하였다. 또한, PCE의 하이퍼 매개변수를 최적화하기 위한 최적의 프레임 워크가 제안되어, 대체필터를 구축하는 데 효율을 높이고 PCE의 과적합(overfitting) 현상을 피할 수 있도록 하였다. 본 연구에서 제안된 기법은 기존 단일 및 이중 앙상블 칼만 필터(EnKF)의 결과와 비교 검증하였으며, 그 결과는 다음과 같다. (1) 대체필터의 대부분은 원래 EnKF와 비슷한 정도의 불확실성을 설명할 수 있음; (2) 모든 대체 필터는 선행시간이 짧은 경우의 예측에 있어 우수한 결과를 제공하며, 시변 필터가 불변 필터보다 더 정확한 예측 결과를 제공함; (3) 대체필터는 원래 앙상블 칼만필터보다 최대 500배 빠른 속도로 성능을 향상시킬 수 있음. 제안된 대체필터는 자료동화를 수행하는 기존필터와 비슷한 정도의 정확성, 매우 향상된 효율성을 보장함을 확인할 수 있었다.