• Journal of the Korean Society of Visualization
• /
• v.16 no.2
• /
• pp.23-30
• /
• 2018

The present study compares flow fields reconstructed by data assimilation method with different combinations of parameters. As a data assimilation method, Vortex-in-Cell-sharp (VIC#), which supplements additional constraints and multigrid approximation to Vortex-in-Cell-plus (VIC+), is used to reconstruct flow fields from scattered particle tracks. Two parameters, standard deviation of Gaussian radial basis function (RBF) and grid spacing, are mainly tested using artificial data sets which contain few particle tracks. Consequent flow fields are analyzed in terms of flow structure sizes. It is demonstrated that sizes of the flow structures are proportional to an actual scale of the standard deviation of RBF. It implies that a combination of larger grid spacing and smaller standard deviation which preserves the actual standard deviation is able to save computational resources in case of a low track density. In addition, a simple comparison using an experimental data filled with dense particle tracks is conducted.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.2
• /
• pp.416-424
• /
• 2017

In this study, we propose a design of digits recognition system based on RBFNNs through a comparative study of pre-processing algorithms in order to recognize digits in handwritten. Histogram of Oriented Gradient(HOG) is used to get the features of digits in the proposed digits recognition system. In the pre-processing part, a dimensional reduction is executed by using Principal Component Analysis(PCA) and (2D)2PCA which are widely adopted methods in order to minimize a loss of the information during the reduction process of feature space. Also, The architecture of radial basis function neural networks consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, the connection weights are used as the extended type of polynomial expression such as constant, linear, quadratic and modified quadratic. By using MNIST handwritten digit benchmarking database, experimental results show the effectiveness and efficiency of proposed digit recognition system when compared with other studies.

• Journal of Korea Water Resources Association
• /
• v.34 no.4
• /
• pp.303-316
• /
• 2001

In this study, Radial Basis Function(RBF) Neural Networks Model, a kind of Hybrid Neural Networks was applied to hydrological forecasting in a small watershed. RBF Neural Networks Model has four kinds of parameters in it and consists of unsupervised and supervised training patterns. And Gaussian Kernel Function(GKF) was used among many kinds of Radial Basis Functions(RBFs). K-Means clustering algorithm was applied to optimize centers and widths which ate the parameters of GKF. The parameters of RBF Neural Networks Model such as centers, widths weights and biases were determined by the training procedures of RBF Neural Networks Model. And, with these parameters the validation procedures of RBF Neural Networks Model were carried out. RBF Neural Networks Model was applied to Wi-Stream basin which is one of the IHP Representative basins in South Korea. 10 rainfall events were selected for training and validation of RBF Neural Networks Model. The results of RBF Neural Networks Model were compared with those of Elman Neural Networks(ENN) Model. ENN Model is composed of One Step Secant BackPropagation(OSSBP) and Resilient BackPropagation(RBP) algorithms. RBF Neural Networks shows better results than ENN Model. RBF Neural Networks Model spent less time for the training of model and can be easily used by the hydrologists with little background knowledge of RBF Neural Networks Model.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.6 no.3
• /
• pp.327-340
• /
• 1996

In this study, a series of $LiNbO_{3}$ crystals with different [Li]/[Nb] ratios, congruent $LiNbO_{3}$ crystals with doped Mg and with Mg and codoped with Mn were grown by the Czocharalski method. These were investigated by UV and IR spectrophotometry. Stoichiometry dependences of the UV absorption edge and the $OH^{-}$ absorption spectra were studied with different [Li]/[Nb] ratios. The position of the UV absorption edge adn the shape and peak point of the $OH^{-}$ absorption spectra changed monotonously upto a critical concentration of Mg ions. The mechanism of the incorporation of Mg ions changes at this concentration. The decomposition of the $OH^{-}$ absorption spectra using a Gaussian lineshape function showed that in Li-deficient crystals the absorption spectra consist of five components in contrast to more or less perfect stoichiometric crystals which reveal to three components. On the basis of these results, the intrinsic and the extrinsic defect structure models in $LiNbO_{3}$ crystals were examined. The behaviour of $\nu$ (OH) reflects the defect structure and supports the Li-site vacancy model as the intrinsic defect structure model and the corresponding extrinsic defect model. A brief discussion is also given of the behaviour of $\nu$ (OH) in $LiNbO_{3}$ crystals simultaneously doped with several kinds of impurity.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.3
• /
• pp.466-472
• /
• 2008

The paper concerns Fuzzy C-Means clustering based fuzzy neural networks (FCM-FNN) and the optimization of the network is carried out by means of hierarchal fair competition-based parallel genetic algorithm (HFCPGA). FCM-FNN is the extended architecture of Radial Basis Function Neural Network (RBFNN). FCM algorithm is used to determine centers and widths of RBFs. In the proposed network, the membership functions of the premise part of fuzzy rules do not assume any explicit functional forms such as Gaussian, ellipsoidal, triangular, etc., so its resulting fitness values directly rely on the computation of the relevant distance between data points by means of FCM. Also, as the consequent part of fuzzy rules extracted by the FCM-FNN model, the order of four types of polynomials can be considered such as constant, linear, quadratic and modified quadratic. Since the performance of FCM-FNN is affected by some parameters of FCM-FNN such as a specific subset of input variables, fuzzification coefficient of FCM, the number of rules and the order of polynomials of consequent part of fuzzy rule, we need the structural as well as parametric optimization of the network. In this study, the HFCPGA which is a kind of multipopulation-based parallel genetic algorithms(PGA) is exploited to carry out the structural optimization of FCM-FNN. Moreover the HFCPGA is taken into consideration to avoid a premature convergence related to the optimization problems. The proposed model is demonstrated with the use of two representative numerical examples.

• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.526-534
• /
• 2010

This paper describes an algorithm which merges two HDR pictures taken under different exposure time to display on the LDR devices such as LCD or CRT. The proposed method does not generate the radiance map, but directly merges using the weights computed from the input images. The weights are firstly produced on the pixel basis, and then blended with a Gaussian function. This process prevents some possible sparkle noises caused by radical change of the weights and contributes to smooth connection between 2 image informations. The chrominance informations of the images are merged on the weighted averaging scheme using the deviations of RGB average and their differences. The algorithm is characterized by the feature that it represents well the unsaturated area of 2 original images and the connection of the image information is smooth. The proposed method uses only 2 input images and automatically tunes the whole internal process according to them, thus autonomous operation is possible when it is included in HDR cameras which use double shuttering scheme or double sensor cells.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.45-52
• /
• 2017

Drifter is an equipment for observing the characteristics of seawater in the ocean, and it can be used to predict effluent oil diffusion and to observe ocean currents. In this paper, we design models or the prediction of drifter trajectory using machine learning. We propose methods for estimating the trajectory of drifter using support vector regression, radial basis function network, Gaussian process, multilayer perceptron, and recurrent neural network. When the propose mothods were compared with the existing MOHID numerical model, performance was improve on three of the four cases. In particular, LSTM, the best performed method, showed the imporvement by 47.59% Future work will improve the accuracy by weighting using bagging and boosting.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.1-8
• /
• 2017

Accurate forecasting enables to effectively prepare for future phenomenon. Especially, meteorological phenomenon is closely related with human life, and it can prevent from damage such as human life and property through forecasting of weather and disaster that can occur. To respond quickly and effectively to oil spill accidents, it is important to accurately predict the movement of oil spills and the weather in the surrounding waters. In this paper, we selected four representative machine learning techniques: support vector machine, Gaussian process, multilayer perceptron, and radial basis function network that have shown good performance and predictability in the previous studies related to oil spill detection and prediction in meteorology such as wind, rainfall and ozone. we suggest the applicability of oil spill prediction model based on machine learning.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.17-24
• /
• 2014

This paper proposes a fault detection method for low-speed rolling element bearings of an induction motor using acoustic emission signals and histogram modeling. The proposed method performs envelop modeling of the histogram of normalized fault signals. It then extracts and selects significant features of each fault using partial autocorrelation coefficients and distance evaluation technique, respectively. Finally, using the extracted features as inputs, the support vector regression (SVR) classifies bearing's inner, outer, and roller faults. To obtain optimal classification performance, we evaluate the proposed method with varying an adjustable parameter of the Gaussian radial basis function of SVR from 0.01 to 1.0 and the number of features from 2 to 150. Experimental results show that the proposed fault identification method using 0.64-0.65 of the adjustable parameter and 75 features achieves 91% in classification performance and outperforms conventional fault diagnosis methods as well.

• 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.