• Journal of Korean Society on Water Environment
• /
• v.28 no.3
• /
• pp.359-366
• /
• 2012

Accurate predictions about the water quality of a river have great importance in identifying in-stream flow and water supply requirements and solving relevant environmental problems. In this study, the effect of water release from upstream dam on the downstream water quality has been investigated by applying a hydological model combined with QUAL2E to Geum River basin. The ESP (Ensemble Stream Prediction) method, which has been validated and verified by lots of researchers, was used to predict reservoir and tributary inflow. The input parameters for a combined model to predict both hydrological characteristics and water quality were identified and optimized. In order to verify the model performance, the simulated result at Gongju station, located at the downstream from Daecheong Dam, has been compared with measured data in 2008. As a result, it was found that the proposed model simulates well the values of BOD, T-N, and T-P with an acceptable reliability.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.45-50
• /
• 2020

With the development of deep learning, studies using artificial neural networks based on deep learning in recommendation systems are being actively conducted. Especially, the recommendation system based on RNN (Recurrent Neural Network) shows good performance because it considers the sequential characteristics of data. This study proposes a travel route recommendation system using GRU(Gated Recurrent Unit) and Session-based Parallel Mini-batch which are RNN-based algorithm. This study improved the recommendation performance through an ensemble of top1 and bpr(Bayesian personalized ranking) error functions. In addition, it was confirmed that the RNN-based recommendation system considering the sequential characteristics in the data makes a recommendation reflecting the meaning of the travel destination inherent in the travel route.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.83-89
• /
• 2013

An adaptive blind equalization is a technique using to minimize the Inter-symbol Interference occurred on a communication channel in the transmission of the high speed digital data. In this paper, we propose a blind equalization more improving performance of the conventional MSAGF-MMA adaptive blind equalization algorithm by applying a multiple step size. This algorithm apply a LMS algorithm with a several step size according to each region divided by absolute values of decision-directed error to MSAGF-MMA. By computer simulation, it is confirmed that the proposed algorithm has a performance highly enhanced in terms of a convergence speed, a residual ISI and a residual error and an ensemble averaged MSE in a steady status compared with MMA and MSAGF-MMA.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.4
• /
• pp.197-204
• /
• 2020

The ImageNet dataset is a large scale dataset and contains various natural scene images. In this paper, we propose a convolutional neural network (CNN)-based weighted ensemble technique for the ImageNet classification task. First, in order to fuse several models, our technique uses weights for each model, unlike the existing average-based ensemble technique. Then we propose an algorithm that automatically finds the coefficients used in later ensemble process. Our algorithm sequentially selects the model with the best performance of the validation set, and then obtains a weight that improves performance when combined with existing selected models. We applied the proposed algorithm to a total of 13 heterogeneous models, and as a result, 5 models were selected. These selected models were combined with weights, and we achieved 3.297% Top-5 error rate on the ImageNet test dataset.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.52 no.1
• /
• pp.13-18
• /
• 2010

In this study the validities of runoff prediction methods are reviewed around ESP (Ensemble Streamflow Prediction) techniques. The improvements of runoff predictions on Yongdam river basin are evaluated by the comparison of different prediction methods including ESP incorporated with qualitative meteorological outlooks provided by meteorological agency as well as the runoff forecasting based on the analysis of the historical rainfall scenarios. As a result it is assessed that runoff predictions with ESP may give rise to more accurate results than the ordinary historical average runoffs. In deed the latter gave the mean of yearly absolute error as to be 60.86 MCM while the errors of the former ones amounted to 44.12 MCM (ESP) and 42.83 MCM (ESP incorporated with qualitative meteorological outlooks) respectively. In addition it is confirmed that ESP incorporated with qualitative meteorological outlooks could improve the accuracy of the results more and more. Especially the degree of improvement of ESP with meteorological outlooks shows rising by 10.8% in flood season and 8% in drought season. Therefore the methods of runoff predictions with ESP can be further used as the basic forecasting information tool for the purpose of the effective watershed management.

• Journal of Korean Association for Spatial Structures
• /
• v.19 no.2
• /
• pp.101-108
• /
• 2019

In this paper, the characteristic of intrinsic mode function(IMF) and its orthogonalization of ensemble empirical mode decomposition(EEMD), which is often used in the analysis of the non-linear or non-stationary signal, has been studied. In the decomposition process, the orthogonal IMF of EEMD was obtained by applying the Gram-Schmidt(G-S) orthogonalization method, and was compared with the IMF of orthogonal EMD(OEMD). Two signals for comparison analysis are adopted as the analytical test function and El Centro seismic wave. These target signals were compared by calculating the index of orthogonality(IO) and the spectral energy of the IMF. As a result of the analysis, an IMF with a high IO was obtained by GSO method, and the orthogonal EEMD using white noise was decomposed into orthogonal IMF with energy closer to the original signal than conventional OEMD.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.1
• /
• pp.109-115
• /
• 2021

The number of freshmen at universities is decreasing due to the recent decline in the school-age population, and the survival of many universities is threatened. To overcome this situation, universities are seeking ways to use big data within the school to improve the quality of education. A study on the prediction of dropout students is a representative case of using big data in universities. The dropout prediction can prepare a systematic management plan by identifying students who will drop out of school due to reasons such as dropout or expulsion. In the case of actual on-campus data, a large number of missing values are included because it is collected and managed by various departments. For this reason, it is necessary to construct a model by effectively reflecting the missing values. In this study, we propose a university student dropout prediction model based on eXtreme Gradient Boost that can be applied to data with many missing values and shows high performance. In order to examine the practical applicability of the proposed model, an experiment was performed using data from C University in Chungbuk. As a result of the experiment, the prediction performance of the proposed model was found to be excellent. The management strategy of dropout students can be established through the prediction results of the model proposed in this paper.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.17-24
• /
• 2023

Based on the problem of 'Tatanic - Machine Learning from Disaster', a representative competition of Kaggle that presents challenges related to data science and solves them, we want to see how data preprocessing and model construction affect prediction accuracy and score. We compare and analyze the features by selecting seven top-ranked solutions with high scores, except when using redundant models or ensemble techniques. It was confirmed that most of the pretreatment has unique and differentiated characteristics, and although the pretreatment process was almost the same, there were differences in scores depending on the type of model. The comparative analysis study in this paper is expected to help participants in the kaggle competition and data science beginners by understanding the characteristics and analysis flow of the preprocessing methods of the top score participants.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.101-101
• /
• 2023

지난 수십 년 동안 다양한 딥러닝 방법이 개발되고 있으며 수문 분야에서는 이러한 딥러닝 모형이 기존의 수문모형의 역할을 대체하여 사용할 수 있다는 가능성이 제시되고 있다. 본 연구에서는 딥러닝 모형 중에 트랜스포머 모형에 다중 인코더를 사용하여 중장기 기간 (1 ~ 10일)의 리드 타임에 대한 한국의 유출량 예측 전망의 가능성을 확인하고자 하였다. 트랜스포머 모형은 인코더와 디코더 구조로 구성되어 있으며 어텐션 (attention) 기법을 사용하여 기존 모형의 정보를 손실하는 단점을 보완한 모형이다. 본 연구에서 사용된 다중 인코더 기반의 트랜스포머 모델은 트랜스포머의 인코더와 디코더 구조에서 인코더를 하나 더 추가한 모형이다. 그리고 결과 비교를 위해 기존에 수문모형을 활용한 스태킹 앙상블 모형 (Stacking ensemble model) 기반의 예측모형을 추가로 구축하였다. 구축된 모형들은 남한 전체를 총 469개의 대규모 격자로 나누어 각 격자의 유출량을 비교하여 평가하였다. 결과적으로 수문모형보다 딥러닝 모형인 다중 인코더 기반의 트랜스포머 모형이 더 긴 리드 타임에서 높은 성능을 나타냈으며 이를 통해 수문모형의 역할을 딥러닝 모형이 어느 정도는 대신할 수 있고 높은 성능을 가질 수 있는 것을 확인하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.217-217
• /
• 2023

상수도관망은 사용자에게 고품질의 물을 안정적으로 공급하는 것을 목적으로 하며, 이를 평가하기 위한 지표 중 하나로 압력을 활용한다. 최근 스마트 센서의 설치가 확장됨에 따라 기계학습기법을 이용한 실시간 데이터 기반의 분석이 활발하다. 따라서 어디에서 데이터를 수집하느냐에 대한 센서 위치 결정이 중요하다. 본 연구는 eXtreme Gradient Boosting(XGBoost) 모델을 활용하여 대규모 상수도관망 내 센서 위치를 최적화하는 방법론을 제안한다. XGBoost 모델은 여러 의사결정 나무(decision tree)를 활용하는 앙상블(ensemble) 모델이며, 오차에 따른 가중치를 부여하여 성능을 향상시키는 부스팅(boosting) 방식을 이용한다. 이는 분산 및 병렬 처리가 가능해 메모리리소스를 최적으로 사용하고, 학습 속도가 빠르며 결측치에 대한 전처리 과정을 모델 내에 포함하고 있다는 장점이 있다. 모델 구현을 위한 독립 변수 결정을 위해 압력 데이터의 변동성 및 평균압력 값을 고려하여 상수도관망을 대표하는 중요 절점(critical node)를 선정한다. 중요 절점의 압력 값을 예측하는 XGBoost 모델을 구축하고 모델의 성능과 요인 중요도(feature importance) 값을 고려하여 센서의 최적 위치를 선정한다. 이러한 방법론을 기반으로 상수도관망의 특성에 따른 경향성을 파악하기 위해 다양한 형태(예를 들어, 망형, 가지형)와 구성 절점의 수를 변화시키며 결과를 분석한다. 본 연구에서 구축한 XGBoost 모델은 추가적인 전처리 과정을 최소화하며 대규모 관망에 간편하게 사용할 수 있어 추후 다양한 입출력 데이터의 조합을 통해 센서 위치 외에도 상수도관망에서의 성능 최적화에 활용할 수 있을 것으로 기대한다.