• 한국물환경학회지
• /
• 제36권5호
• /
• pp.353-363
• /
• 2020

Hydrologic models can be classified into two types: those for understanding physical processes and those for predicting hydrologic quantities. This study deals with how to use the model to predict today's stream flow based on the system's knowledge of yesterday's state and the model parameters. In this regard, for the model to generate accurate predictions, the uncertainty of the parameters and appropriate estimates of the state variables are required. In this study, a relatively simple hydrologic partitioning model is proposed that can explicitly implement the hydrologic partitioning process, and the posterior distribution of the parameters of the proposed model is estimated using the Markov chain Monte Carlo approach. Further, the application method of the ensemble Kalman filter is proposed for updating the normalized soil moisture, which is the state variable of the model, by linking the information on the posterior distribution of the parameters and by assimilating the observed steam flow data. The stochastically and recursively estimated stream flows using the data assimilation technique revealed better representation of the observed data than the stream flows predicted using the deterministic model. Therefore, the ensemble Kalman filter in conjunction with the Markov chain Monte Carlo approach could be a reliable and effective method for forecasting daily stream flow, and it could also be a suitable method for routinely updating and monitoring the watershed-averaged soil moisture.

• 스마트미디어저널
• /
• 제9권2호
• /
• pp.22-32
• /
• 2020

The hippocampal volume atrophy is known to be linked with neuro-degenerative disorders and it is also one of the most important early biomarkers for Alzheimer's disease detection. The measurements of hippocampal pure volumes from Magnetic Resonance Imaging (MRI) is a crucial task and state-of-the-art methods require a large amount of time. In addition, the structural brain development is investigated using MRI data, where brain morphometry (e.g. cortical thickness, volume, surface area etc.) study is one of the significant parts of the analysis. In this study, we have proposed a patch-based ensemble model of 3-D convolutional neural network (CNN) to measure the hippocampal pure volume from MRI data. The 3-D patches were extracted from the volumetric MRI scans to train the proposed 3-D CNN models. The trained models are used to construct the ensemble 3-D CNN model and the aggregated model predicts the pure volume in one-step in the test phase. Our approach takes only 5 seconds to estimate the volumes from an MRI scan. The average errors for the proposed ensemble 3-D CNN model are 11.7±8.8 (error%±STD) and 12.5±12.8 (error%±STD) for the left and right hippocampi of 65 test MRI scans, respectively. The quantitative study on the predicted volumes over the ground truth volumes shows that the proposed approach can be used as a proxy.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.382-382
• /
• 2020

과거 많은 연구에서 다수의 모형의 결과를 이용한 앙상블 방법론은 인공지능 모형 (artificial neural network)의 예측 능력에 향상을 갖고 온다 논하였다. 본 연구에서는 미계측유역의 저수량(low flow)의 예측을 위하여 Jittering을 기반으로 한 인공지능 모형을 제시하고자 한다. 기본적인 방법론은 설명변수들에게 백색 잡음(white noise)를 삽입하여 훈련되는 자료를 증가시키는 것이다. Jittering을 기반으로 한 인공지능 모형에 대한 효과를 검증하기 위하여 본 연구에서는 Multi-output neural network model을 기반으로 모형을 구축하였다. 다음으로 Jittering을 기반으로 한 앙상블 모형을 variable importance measuring algorithm과 결합시켜서 유역특성치와 예측되는 저수량의 특성치들의 관계를 추론하였다. 본 연구에서 사용되는 방법론들의 효용성을 평가하기 위해서 미동북부에 위치하고 있는 총 207개의 유역을 사용하였다. 결과적으로 본 연구에서 제시한 Jittering을 기반으로 한 인공지능 앙상블 모형은 단일예측모형 (single modeling approach)을 정확도 측면에서 우수한 것으로 확인되었다. 또한, 적은 숫자의 앙상블 모형에서도 그 정확성이 단일예측모형보다 우수한 것을 확인하였다. 마지막으로 본 연구에서는 유역특성치들의 효과가 살펴보고자 하는 저수량의 특성치들에 따라서 일관적으로 영향을 미치거나 그 중요도가 변화하는 것을 확인하였다.

• 한국농림기상학회지
• /
• 제25권3호
• /
• pp.129-141
• /
• 2023

작물 모형은 작물의 유전적 특성을 나타내는 품종모수를 요구하며, 품종모수는 작물의 개별 품종별로 추정되어야 한다. 품종모수의 추정에는 고품질의 많은 생육 자료가 요구되지만, 자료의 생산에 상당한 비용이 필요하다. 비교적 낮은 품질의 가용성이 높은 자료를 활용하는 대신, 대량의 랜덤 모수를 생성하고 이를 평가하여 품종모수를 추정할 수 있다. 본 연구에서는 SIMPLE 작물 모델의 불확도를 최소화하기 위해 품종모수 추정 방식을 비교하고, 두 앙상블 방식과 대한 비교를 하였다. 모수 추정을 위한 Metropolis-Hastings (MH) 알고리즘에 대한 목적함수로 로그 가능도(log-likelihood: LL)와 generic composite similarity measure (GCSM)를 사용하였다. 또한 품종모수의 평균값을 사용한 예측(E_pm)과 개별 모수들로부터 얻어진 추정값의 평균값(E_em)의 일치도를 분석하여 앙상블 방식에 따른 불확도 변화를 파악하였다. 국내에서 재배되는 사료용 벼 품종인 조우 벼와 영우 벼를 대상으로 품종모수를 추정하였다. 2013년, 2014년, 2016년에 대한 수원, 전주, 나주, 익산에 위치한 실험포장에서 얻은 수량 관측 자료를 사용하였다. 또한 2016년부터 2018년까지 수원에서 보고된 별도의 수량 관측 자료를 사용하였다. 목적함수에 따라 추정된 품종모수의 분포에 차이가 있었다. LL을 통해 얻은 품종모수는 GCSM으로 얻은 품종모수보다 좁은 범위에 분포하였다. 두 가지 앙상블 접근법은 통계적으로 유의한 차이가 나타나지 않음을 확인하였다. GCSM의 상대적으로 높은 불확도는 수용확률을 조정하여 낮출 수 있다고 사료되고, E_pm의 결과는 기존과 다른 앙상블 방식을 통해 적은 연산을 통해 불확도를 낮출 수 있음을 보인다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.287-287
• /
• 2023

Surface water-groundwater interaction (SWGI) is an important hydrological process that influences both the quantity and quality of water resources. However, regional scale SWGI model calibration and uncertainty analysis have been a challenge because integrated models inherently carry a vast number of parameters, modeling assumptions, and inputs, potentially leaving little time and budget to explore questions related to model performance and forecasting. In this study, we have proposed the application of iterative ensemble smoother (IES) for uncertainty analysis and calibration of the widely used integrated surface-subsurface model, SWAT-MODFLOW. SWAT-MODFLOW integrates Soil and Water Assessment Tool (SWAT) and a three-dimensional finite difference model (MODFLOW). The model was calibrated using a parameter estimation tool (PEST). The major advantage of the employed IES is that the number of model runs required for the calibration of an ensemble is independent of the number of adjustable parameters. The pilot point approach was followed to calibrate the aquifer parameters, namely hydraulic conductivity, specific storage, and specific yield. The parameter estimation process for the SWAT model focused primarily on surface-related parameters. The uncertainties both in the streamflow and groundwater level were assessed. The work presented provides valuable insights for future endeavors in coupled surface-subsurface modeling, data collection, model development, and informed decision-making.

• 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.

• Structural Engineering and Mechanics
• /
• 제39권6호
• /
• pp.813-831
• /
• 2011

This paper presents an efficient version of Hilbert-Huang transform for nonlinear non-stationary systems analyses. An ensemble empirical mode decomposition (EEMD) is introduced to alleviate the problem of mode mixing between intrinsic mode functions (IMFs) decomposed by EMD. Yet the problem has not been fully resolved when a signal of a similar scale resides in different IMF components. Instead of using a trial and error method to select the "best" outcome generated by EEMD, a hybrid algorithm based on EEMD and EMD is proposed for multi-mode signal processing. The developed approach comprises the steps from a bandpass filter design for regrouping modes of the IMFs obtained from EEMD, to the mode extraction using EMD, and to the assessment of each mode in the marginal spectrum. A simulated two-mode signal is tested to demonstrate the efficiency and robustness of the approach, showing average relative errors all equal to 1.46% for various noise levels added to the signal. The developed approach is also applied to a real bridge structure, showing more reliable results than the pure EMD. Discussions on the mode determination are offered to explain the connection between modegrouping form on the one hand, and mode-grouping performance on the other.

• Interaction and multiscale mechanics
• /
• 제4권3호
• /
• pp.173-185
• /
• 2011

A multiscale modeling scheme that addresses the influence of the nanoparticle size in nanocomposites consisting of nano-sized spherical particles embedded in a polymer matrix is presented. A micromechanics-based constitutive model for nanoparticle-reinforced polymer composites is derived by incorporating the Eshelby tensor considering the interface effects (Duan et al. 2005a) into the ensemble-volume average method (Ju and Chen 1994). A numerical investigation is carried out to validate the proposed micromechanics-based constitutive model, and a parametric study on the interface moduli is conducted to investigate the effect of interface moduli on the overall behavior of the composites. In addition, molecular dynamics (MD) simulations are performed to determine the mechanical properties of the nanoparticles and polymer. Finally, the overall elastic moduli of the nanoparticle-reinforced polymer composites are estimated using the proposed multiscale approach combining the ensemble-volume average method and the MD simulation. The predictive capability of the proposed multiscale approach has been demonstrated through the multiscale numerical simulations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• Smart Structures and Systems
• /
• 제29권2호
• /
• pp.321-336
• /
• 2022

Model uncertainty is a key factor that could influence the accuracy and reliability of numerical model-based analysis. It is necessary to acquire an appropriate updating approach which could search and determine the realistic model parameter values from measurements. In this paper, the Bayesian model updating theory combined with the transitional Markov chain Monte Carlo (TMCMC) method and K-means cluster analysis is utilized in the updating of the structural model parameters. Kriging and polynomial chaos expansion (PCE) are employed to generate surrogate models to reduce the computational burden in TMCMC. The selected updating approaches are applied to three structural examples with different complexity, including a two-storey frame, a ten-storey frame, and the national stadium model. These models stand for the low-dimensional linear model, the high-dimensional linear model, and the nonlinear model, respectively. The performances of updating in these three models are assessed in terms of the prediction uncertainty, numerical efforts, and prior information. This study also investigates the updating scenarios using the analytical approach and surrogate models. The uncertainty quantification in the Bayesian approach is further discussed to verify the validity and accuracy of the surrogate models. Finally, the advantages and limitations of the surrogate model-based updating approaches are discussed for different structural complexity. The possibility of utilizing the boosting algorithm as an ensemble learning method for improving the surrogate models is also presented.