• Journal of Korean Society for Atmospheric Environment
• /
• v.32 no.5
• /
• pp.513-525
• /
• 2016

To propose an effective ensemble methods in predicting $PM_{10}$ concentration, six experiments were designed by different ensemble average methods (e.g., non-weighted, single weighted, and cluster weighted methods). The single weighted method was calculated the weighted value using both multiple regression analysis and singular value decomposition and the cluster weighted method was estimated the weighted value based on temperature, relative humidity, and wind component using multiple regression analysis. The effects of ensemble average methods were significantly better in weighted average than non-weight. The results of ensemble experiments using weighted average methods were distinguished according to methods calculating the weighted value. The single weighted average method using multiple regression analysis showed the highest accuracy for hourly $PM_{10}$ concentration, and the cluster weighted average method based on relative humidity showed the highest accuracy for daily mean $PM_{10}$ concentration. However, the result of ensemble spread analysis showed better reliability in the single weighted average method than the cluster weighted average method based on relative humidity. Thus, the single weighted average method was the most effective method in this study case.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.

• Journal of Korean Society of Water and Wastewater
• /
• v.28 no.4
• /
• pp.377-389
• /
• 2014

In recent years, Smart Water Grid (SWG) concept has globally emerged over the last decade and also gained significant recognition in South Korea. Especially, there has been growing interest in water demand forecast and this has led to various studies regarding energy saving and improvement of water supply reliability. In this regard, this study aims to develop a nonlinear ensemble model for hourly water demand forecasting which allow us to estimate uncertainties across different model classes. The concepts was demonstrated through application to observed from water plant (A) in the South Korea. Various statistics (e.g. the efficiency coefficient, the correlation coefficient, the root mean square error, and a maximum error rate) were evaluated to investigate model efficiency. The ensemble based model with an cross-validate prediction procedure showed better predictability for water demand forecasting at different temporal resolutions. In particular, the performance of the ensemble model on hourly water demand data showed promising results against other individual prediction schemes.

• Journal of Korean Society on Water Environment
• /
• v.37 no.5
• /
• pp.335-343
• /
• 2021

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-ob servation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

• Journal of the korean Society of Automotive Engineers
• /
• v.14 no.6
• /
• pp.39-47
• /
• 1992

The engine combustion is one of the most important process affecting performance and emissions. One effective way to improve the engine combustion is to control motion of the charge inside a cylinder by means of optimum induction system design, because the flame speed is mainly determined by the turbulence in a gasoline engine. This paper describes the measurement and characterization of mean velocity and turbulence intensity inside the cylinder of a 4-valve gasoline engine using laser Doppler velocimeter(LDV) under motoring(non-firing) conditions. Since the measured LDV data in each cycle show small cycle variation during compression stroke in the tested engine, the mean velocity and turbulence intensity are calculated by ensemble averaging method neglecting cycle variation effects. In the ensemble averaging method, the effects of the calculation window, in which velocities are assumed as the same crank angle, on mean velocity and turbulence intensity are fully investigated. In addition, the effects of measuring point on the flow characteristics are studied. With large calculation window, the mean velocity is shown to be less sensitive with respect to crank angle and turbulence intensity decrease in its absolute amplitude. When the piston approch to the top dead center of compression, the turbulence intensity is found to be homogeneous in the cylinder.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.7
• /
• pp.595-601
• /
• 2001

We applied PIV method to obtain instantaneous and ensemble averaged velocity fields from the first row to the fifth row of a staggered tube bundle. The Reynolds number based on the tube diameter and the maximum velocity was set to be 4,000. Remarkably different natures are observed in the developing bundle flow. Such differences are depicted in the mean recirculating bubble length and the vorticity distributions. The jet-like flow seems to be a dominant feature after the second row and usually skew. However, the ensemble averaged fields show symmetric profiles and the flow characteristics between the third and fourth measuring planes are not so different. comparison between the PIV data and the RANS simulation yields severe disagreement in spite of the same Reynolds number. It can be explained that the distinct jet-like unsteady motions are not to be accounted in th steady numerical analysis.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.3
• /
• 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.

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.587-607
• /
• 2020

Soil moisture is essential information for meteorological and hydrological analyses. To date, many efforts have been made to achieve the two goals for soil moisture data, i.e., the improvement of accuracy and resolution, which is very challenging. We presented an ensemble downscaling method for quality improvement of gridded soil moisture data in terms of the accuracy and the spatial resolution by the integration of BMA (Bayesian model averaging) and ATPRK (area-to-point regression kriging). In the experiments, the BMA ensemble showed a 22% better accuracy than the data sets from ESA CCI (European Space Agency-Climate Change Initiative), ERA5 (ECMWF Reanalysis 5), and GLDAS (Global Land Data Assimilation System) in terms of RMSE (root mean square error). Also, the ATPRK downscaling could enhance the spatial resolution from 0.25° to 0.05° while preserving the improved accuracy and the spatial pattern of the BMA ensemble, without under- or over-estimation. The quality-improved data sets can contribute to a variety of local and regional applications related to soil moisture, such as agriculture, forest, hydrology, and meteorology. Because the ensemble downscaling method can be applied to the other land surface variables such as temperature, humidity, precipitation, and evapotranspiration, it can be a viable option to complement the accuracy and the spatial resolution of satellite images and numerical models.

• Atmosphere
• /
• v.27 no.3
• /
• pp.301-316
• /
• 2017

This study analyzes the spatio-temporal variability of terrestrial carbon flux and the response of land carbon sink with climate factors to improve of understanding of the variability of land-atmosphere carbon exchanges accurately. The coupled carbon-climate models of CMIP5 (the fifth phase of the Coupled Model Intercomparison Project) and CT (CarbonTracker) are used. The CMIP5 multi-model ensemble mean overestimated the NEP (Net Ecosystem Production) compares to CT and GCP (Global Carbon Project) estimates over the period 2001~2012. Variation of NEP in the CMIP5 ensemble mean is similar to CT, but a couple of models which have fire module without nitrogen cycle module strongly simulate carbon sink in the Africa, Southeast Asia, South America, and some areas of the United States. Result in comparison with climate factor, the NEP is highly affected by temperature and solar radiation in both of CT and CMIP5. Partial correlation between temperature and NEP indicates that the temperature is affecting NEP positively at higher than mid-latitudes in the Northern Hemisphere, but opposite correlation represents at other latitudes in CT and most CMIP5 models. The CMIP5 models except for few models show positive correlation with precipitation at $30^{\circ}N{\sim}90^{\circ}N$, but higher percentage of negative correlation represented at $60^{\circ}S{\sim}30^{\circ}N$ compare to CT. For each season, the correlation between temperature (solar radiation) and NEP in the CMIP5 ensemble mean is similar to that of CT, but overestimated.