• 한국태양에너지학회 논문집
• /
• 제36권1호
• /
• pp.27-37
• /
• 2016

A simple but practical Ensemble Prediction System(EPS) for wind power forecasting was developed and evaluated using the measurement of the offshore meteorological tower, HeMOSU-1(Herald of Meteorological and Oceanographic Special Unite-1) installed at the Southwest Offshore in South Korea. The EPS developed by the Korea Institute of Energy Research is based on a simple ensemble mean of two Numerical Weather Prediction(NWP) models, WRF-NMM and WRF-ARW. In addition, the Kalman Filter is applied for real-time quality improvement of wind ensembles. All forecasts with EPS were analyzed in comparison with the HeMOSU-1 measurements at 97 m above sea level during Typhoon Bolaven episode in August 2012. The results indicate that EPS was in the best agreement with the in-situ measurement regarding (peak) wind speed and cut-out speed incidence. The RMSE of wind speed was 1.44 m/s while the incidence time lag of cut-out wind speed was 0 hour, which means that the EPS properly predicted a development and its movement. The duration of cut-out wind speed period by the EPS was also acceptable. This study is anticipated to provide a useful quantitative guide and information for a large-scale offshore wind farm operation in the decision making of wind turbine control especially during a typhoon episode.

• 지능정보연구
• /
• 제21권4호
• /
• pp.93-110
• /
• 2015

기존의 협업필터링 추천시스템 연구는 상품에 대한 고객의 평점(rating)이나 구매 여부 데이터로부터 하나의 프로파일을 생성하고 이를 기반으로 추천 성능을 향상시킬 수 있는 새로운 알고리즘을 개발하는 위주로 진행되어 왔다. 그러나 빅데이터 환경이 도래하면서 기업이 수집할 수 있는 고객 데이터가 풍부해지고 다양해짐에 따라, 보다 정확하게 고객의 선호도나 행태를 파악하는 것이 가능하게 되었고 이러한 데이터, 즉 퍼스널 빅데이터(personal big data)를 추천시스템에 활용하는 연구의 필요성이 대두되고 있다. 본 연구에서는 마케팅의 시장세분화 이론에 근거하여 퍼스널 빅데이터로부터 고객의 선호도나 행태를 다양한 관점에서 표현할 수 있는 5종의 다중 프로파일(multimodal profile)을 개발하고, 이를 활용하여 협업필터링 추천시스템의 성능을 개선하고자 한다. 제안하는 5종의 다중 프로파일은 프로파일 통합 유사도, 개별 프로파일 유사도 평균, 개별 프로파일 유사도 가중 평균이라는 세 가지 앙상블 기법을 통해 협업필터링의 이웃(neighborhood) 탐색과정에 적용된다. 실제 퍼스널 빅데이터에 본 연구에서 제안하는 방법론을 적용한 결과, 단일 프로파일을 사용하는 협업필터링 알고리즘보다 추천 성능이 상당히 개선되었으며 앙상블 방법 중에서는 개별 프로파일 유사도 가중 평균 기법이 가장 높은 추천 성능을 보여주었다. 본 연구는 빅데이터 환경에서 추천시스템을 개발하고자 할 때, 어떠한 성격의 데이터로부터 고객의 특성을 규명하는 프로파일을 만들고 이를 어떻게 결합하여 사용하는 것이 효과적인 지 처음으로 제안하였다는 점에서 그 의의가 있다.

• 전기학회논문지
• /
• 제58권8호
• /
• pp.1638-1643
• /
• 2009

Uroflowmetry is a convenient clinical test to screen the benign prostatic hyperplasia(BPH) common in the aged men. A load cell is located beneath the urine container to measure the weight of urine. However, it is sensitive to the impact applied on the bottom of the container by the urine stream, which could be a noise source lowering the reliability of the system. With this aim, our study proposed a noise reduction technique by computing ensemble average of the weighted signals that were acquired from three-load cells forming a regular triangle beneath the urine container. Simulated urination experiment was performed with three different collection methods, all of which demonstrated significant noise reduction by ensemble averaging. Furthermore, the best results can be obtained without any special urine collection devices. Thus, our novel method can be usefully applied to uroflowmetry for enhancing measurement in terms of accuracy and reliability.

• Journal of Positioning, Navigation, and Timing
• /
• 제9권3호
• /
• pp.261-272
• /
• 2020

A Kalman filter algorithm is used for the generation of an ensemble timescale with three hydrogen masers maintained in KRISS. Allan deviation curves of three pairs of clocks were obtained by a three-cornered hat method and were used as reference curves for determination of parameters of the Kalman filter-based timescale. The ensemble timescale equation of a 3-clock system was established, and the clocks' phases estimated by the Kalman filter were used as the prediction time of each clock in the equation. The weight of each clock was determined inversely proportional to the Allan variance calculated with the clocks' phases. The Allan deviation of the weighted mean was 1.2×10^-16 at the averaging time of 57,600 s. However when we made fine adjustments of the clocks' weight, the minimum Allan deviation of 2×10^-17 was obtained. To find out the reason of the great improvement in the frequency stability, additional researches are in progress theoretically and experimentally.

• Computers and Concrete
• /
• 제32권3호
• /
• pp.313-326
• /
• 2023

The seismic safety of the shear wall structure can be assessed through seismic fragility analysis, which requires high computational costs in estimating seismic demands. Accordingly, machine learning methods have been applied to such fragility analyses in recent years to reduce the numerical analysis cost, but it still remains a challenging task. Therefore, this study uses the ensemble machine learning method to present an improved framework for developing a more accurate seismic demand model than the existing ones. To this end, a rank-based selection method that enables determining an excellent model among several single machine learning models is presented. In addition, an index that can evaluate the degree of overfitting/underfitting of each model for the selection of an excellent single model is suggested. Furthermore, based on the selected single machine learning model, we propose a method to derive a more accurate ensemble model based on the bagging method. As a result, the seismic demand model for which the proposed framework is applied shows about 3-17% better prediction performance than the existing single machine learning models. Finally, the seismic fragility obtained from the proposed framework shows better accuracy than the existing fragility methods.

• 한국산업융합학회 논문집
• /
• 제26권6_3호
• /
• pp.1205-1213
• /
• 2023

This study delves into methods for enhancing the power efficiency of air compressor systems, with the primary objective of significantly impacting industrial energy consumption and environmental preservation. The paper scrutinizes Shinhan Airro Co., Ltd.'s power efficiency optimization technology and employs machine learning ensemble models to simulate power efficiency optimization. The results indicate that Shinhan Airro's optimization system led to a notable 23.5% increase in power efficiency. Nonetheless, the study's simulations, utilizing machine learning ensemble techniques, reveal the potential for a further 51.3% increase in power efficiency. By continually exploring and advancing these methodologies, this research introduces a practical approach for identifying optimization points through data-driven simulations using machine learning ensembles.

• 한국컴퓨터정보학회논문지
• /
• 제27권3호
• /
• pp.33-43
• /
• 2022

본 논문에서는 기존의 스마트폰 카메라 센서를 사용하여 비접촉식 손바닥 기반 사용자 식별 시스템을 구축하기 위해 Attention U-Net 모델과 사전 훈련된 컨볼루션 신경망(CNN)이 있는 다채널 손바닥 이미지를 이용한 앙상블 모델을 제안한다. Attention U-Net 모델은 손바닥(손가락 포함), 손바닥(손바닥 미포함) 및 손금을 포함한 관심 영역을 추출하는 데 사용되며, 이는 앙상블 분류기로 입력되는 멀티채널 이미지를 생성하기 위해 결합 된다. 생성된 데이터는 제안된 손바닥 정보 기반 사용자 식별 시스템에 입력되며 사전 훈련된 CNN 모델 3개를 앙상블 한 분류기를 사용하여 클래스를 예측한다. 제안된 모델은 각각 98.60%, 98.61%, 98.61%, 98.61%의 분류 정확도, 정밀도, 재현율, F1-Score를 달성할 수 있음을 입증하며, 이는 저렴한 이미지 센서를 사용하고 있음에도 불구하고 제안된 모델이 효과적이라는 것을 나타낸다. 본 논문에서 제안하는 모델은 COVID-19 펜데믹 상황에서 기존 시스템에 비하여 높은 안전성과 신뢰성으로 대안이 될 수 있다.

• 한국지능시스템학회논문지
• /
• 제13권5호
• /
• pp.545-551
• /
• 2003

본 논문은 전통적인 지문분류 모델인 헨리식 분류방법으로는 적용이 어려운 현대의 자동화된 지문인식 시스템에서 대용량 데이터베이스 운용시 정합속도를 향상시키기 위한 융선 기울기의 변화량을 이용한 앙상블 지문분류 알고리즘을 적용한다. 기존의 분류체계인 헨리분류체계는 중심점과 삼각점을 모두 획득하는 회전낙인의 경우에 사용 가능한 분류방법이나 현대의 자동화된 지문인식 시스템에서는 입력센서의 크기 및 입력방법의 문제로 인하여, 헨리식 분류방법을 적용할 수 없다. 본 논문에서 제안하는 앙상블 지문분류 시스템 알고리즘은 융선 기울기의 변화량을 이용하여 삼각점을 획득하지 못한 영상에서도 기존의 헨리식 분류체계에 의해 분류된 5개의 문양을 분류할 수 있다. 이와 같은 방법으로 지문분류론 수행한 후 정합을 실행하면 정합 대상이 되는 데이터의 양이 줄어들게 되어 인식 시스템의 정합속도를 향상시킬 수 있다.

• 농촌지도와개발
• /
• 제16권4호
• /
• pp.939-965
• /
• 2009

The Machine Learning has been identified as a promising approach to knowledge-based system development. This study aims to examine the ability of machine learning techniques for farmer's decision making and to develop the reference model for using pig farm data. We compared five machine learning techniques: logistic regression, decision tree, artificial neural network, k-nearest neighbor, and ensemble. All models are well performed to predict the sow's productivity in all parity, showing over 87.6% predictability. The model predictability of total litter size are highest at 91.3% in third parity and decreasing as parity increases. The ensemble is well performed to predict the sow's productivity. The neural network and logistic regression is excellent classifier for all parity. The decision tree and the k-nearest neighbor was not good classifier for all parity. Performance of models varies over models used, showing up to 104% difference in lift values. Artificial Neural network and ensemble models have resulted in highest lift values implying best performance among models.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2008년도 학술발표회 논문집
• /
• pp.1388-1392
• /
• 2008

Water resources management depends on dealing inherent uncertainties stemming from climatic and hydrological inputs and models. Dealing with these uncertainties remains a challenge. Streamflow forecasts basically contain uncertainties arising from model structure and initial conditions. Recent enhancements in climate forecasting skill and hydrological modeling provide an breakthrough for delivering improved streamflow forecasts. However, little consideration has been given to methodologies that include coupling both multiple climate and multiple hydrological models, increasing the pool of streamflow forecast ensemble members and accounting for cumulative sources of uncertainty. The approach here proposes integration and coupling of global climate models (GCM), multiple regional climate models, and numerous hydrological models to improve streamflow forecasting and characterize system uncertainty through generation of ensemble forecasts.