• Atmosphere
• /
• v.28 no.3
• /
• pp.247-261
• /
• 2018

The objective of this paper is to compare probabilistic temperature forecasts from different regional and global ensemble prediction systems over PyeongChang area. A statistical post-processing method is used to take into account combination and calibration of forecasts from different numerical prediction systems, laying greater weight on ensemble model that exhibits the best performance. Observations for temperature were obtained from the 30 stations in PyeongChang and three different ensemble forecasts derived from the European Centre for Medium-Range Weather Forecasts, Ensemble Prediction System for Global and Limited Area Ensemble Prediction System that were obtained between 1 May 2014 and 18 March 2017. Prior to applying to the post-processing methods, reliability analysis was conducted to identify the statistical consistency of ensemble forecasts and corresponding observations. Then, ensemble model output statistics and bias-corrected methods were applied to each raw ensemble model and then proposed weighted combination of ensembles. The results showed that the proposed methods provide improved performances than raw ensemble mean. In particular, multi-model forecast based on ensemble model output statistics was superior to the bias-corrected forecast in terms of deterministic prediction.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.665-675
• /
• 2019

In this paper, we compare and analyze the classification performance of deep learning algorithm Convolutional Neural Network(CNN) ac cording to ensemble generation and combining techniques. We used several CNN models(VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, GoogLeNet) to create 10 ensemble generation combinations and applied 6 combine techniques(average, weighted average, maximum, minimum, median, product) to the optimal combination. Experimental results, DenseNet169-VGG16-GoogLeNet combination in ensemble generation, and the product rule in ensemble combination showed the best performance. Based on this, it was concluded that ensemble in different models of high benchmarking scores is another way to get good results.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.3944-3951
• /
• 2021

Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.55-71
• /
• 2013

The prediction model is the main factor affecting the performance of a knowledge-based system for bankruptcy prediction. Earlier studies on prediction modeling have focused on the building of a single best model using statistical and artificial intelligence techniques. However, since the mid-1980s, integration of multiple techniques (hybrid techniques) and, by extension, combinations of the outputs of several models (ensemble techniques) have, according to the experimental results, generally outperformed individual models. An ensemble is a technique that constructs a set of multiple models, combines their outputs, and produces one final prediction. The way in which the outputs of ensemble members are combined is one of the important issues affecting prediction accuracy. A variety of combination schemes have been proposed in order to improve prediction performance in ensembles. Each combination scheme has advantages and limitations, and can be influenced by domain and circumstance. Accordingly, decisions on the most appropriate combination scheme in a given domain and contingency are very difficult. This paper proposes a confidence-based selection approach as part of an ensemble bankruptcy-prediction scheme that can measure unified confidence, even if ensemble members produce different types of continuous-valued outputs. The present experimental results show that when varying the number of models to combine, according to the creation type of ensemble members, the proposed combination method offers the best performance in the ensemble having the largest number of models, even when compared with the methods most often employed in bankruptcy prediction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1147-1151
• /
• 2009

In this study, we address the problem of producing probability forecasts of summer seasonal rainfall, on the basis of Hindcast experiments from a ensemble of GCMs(cwb, gcps, gdaps, metri, msc_gem, msc_gm2, msc_gm3, msc_sef and ncep). An advanced Hierarchical Bayesian weighting scheme is developed and used to combine nine GCMs seasonal hindcast ensembles. Hindcast period is 23 years from 1981 to 2003. The simplest approach for combining GCM forecasts is to weight each model equally, and this approach is referred to as pooled ensemble. This study proposes a more complex approach which weights the models spatially and seasonally based on past model performance for rainfall. The Bayesian approach to multi-model combination of GCMs determines the relative weights of each GCM with climatology as the prior. The weights are chosen to maximize the likelihood score of the posterior probabilities. The individual GCM ensembles, simple poolings of three and six models, and the optimally combined multimodel ensemble are compared.

• Korean Journal of Human Ecology
• /
• v.10 no.1
• /
• pp.37-48
• /
• 2007

The purpose of this study was to investigate the proper combination of ensemble suit details for the body silhouette of elderly women. In this study, the principal component analysis was used to search for the proper combination of suit details for covering defects of body which has been changed unbalanced. The designs of evaluated suits were manipulated in 18 different kinds by the essential elements such as collars, neckline(round neckline, shirt collar, tailored collar), types of one-piece dress(pleats type, gather type, flare type), and opening(opened, closed). The data evaluated by a multiple ranking test was analyzed by mean, paired t-test, ANOVA and Duncan's multiple ranged test. The results were summarized as follows: In case of normal body type, it had complementary effects for upper body with closed round neckline jacket or shirt collar jacket, and for lower and the whole body with a combination of closed tailored collar jacket or shirt collar jacket with pleats or gored type one piece dress. The visual effect for elderly women's body shape was different in opened or closed jacket. And that enhanced by Jacket with collar.

• Atmosphere
• /
• v.25 no.1
• /
• pp.67-83
• /
• 2015

Predicting the location and intensity of precipitation still remains a main issue in numerical weather prediction (NWP). Resolution is a very important component of precipitation forecasts in NWP. Compared with a lower resolution model, a higher resolution model can predict small scale (i.e., storm scale) precipitation and depict convection structures more precisely. In addition, an ensemble technique can be used to improve the precipitation forecast because it can estimate uncertainties associated with forecasts. Therefore, NWP using both a higher resolution model and ensemble technique is expected to represent inherent uncertainties of convective scale motion better and lead to improved forecasts. In this study, the limited area ensemble prediction system for the convective-scale (i.e., high resolution) operational Unified Model (UM) in Korea Meteorological Administration (KMA) was developed and evaluated for the ensemble forecasts during August 2012. The model domain covers the limited area over the Korean Peninsula. The high resolution limited area ensemble prediction system developed showed good skill in predicting precipitation, wind, and temperature at the surface as well as meteorological variables at 500 and 850 hPa. To investigate which combination of horizontal resolution and ensemble member is most skillful, the system was run with three different horizontal resolutions (1.5, 2, and 3 km) and ensemble members (8, 12, and 16), and the forecasts from the experiments were evaluated. To assess the quantitative precipitation forecast (QPF) skill of the system, the precipitation forecasts for two heavy rainfall cases during the study period were analyzed using the Fractions Skill Score (FSS) and Probability Matching (PM) method. The PM method was effective in representing the intensity of precipitation and the FSS was effective in verifying the precipitation forecast for the high resolution limited area ensemble prediction system in KMA.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• Atmosphere
• /
• v.31 no.5
• /
• pp.511-523
• /
• 2021

This study explores the optimal ensemble size to improve the prediction performance of the Korea Meteorological Administration's operational climate prediction system, global seasonal forecast system version 5 (GloSea5). The GloSea5 produces an ensemble of hindcast data using the stochastic kinetic energy backscattering version2 (SKEB2) and timelagged ensemble. An experiment to increase the hindcast ensemble from 3 to 14 members for four initial dates was performed and the improvement and effect of the prediction performance considering Root Mean Square Error (RMSE), Anomaly Correlation Coefficient (ACC), ensemble spread, and Ratio of Predictable Components (RPC) were evaluated. As the ensemble size increased, the RMSE and ACC prediction performance improved and more significantly in the high variability area. In spread and RPC analysis, the prediction accuracy of the system improved as the ensemble size increased. The closer the initial date, the better the predictive performance. Results show that increasing the ensemble to an appropriate number considering the combination of initial times is efficient.

• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2011

In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including 'without compensation') and five feature enhancement methods (including 'without enhancement'). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).