• Journal of Korea Water Resources Association
• /
• v.50 no.12
• /
• pp.837-847
• /
• 2017

Land Surface Model (LSM) was developed for the Soyang river basin located in Korean Peninsula to clarify the spatio-temporal variability of hydrological weather parameters. Variable Infiltration Capacity (VIC) model was used as a LSM. The spatial resolution of the model was 10 km and the time resolution was 1 day. Based on the daily flow data from 2007 to 2010, the 7 parameters of the model were calibrated using the Isolated Particle Swarm Optimization algorithm and the model was verified using the daily flow data from 2011 to 2014. The model showed a Nash-Sutcliffe Coefficient of 0.90 and a correlation coefficient of 0.95 for both calibration and validation periods. The hydrometeorological variables estimated for the Soyang river basin reflected well the seasonal characteristics of summer rainfall concentration, the change of short and shortwave radiation due to temperature change, the change of surface temperature, the evaporation and vegetation increase in the cover layer, and the corresponding change in total evapotranspiration. The model soil moisture data was compared with in-situ soil moisture data. The slope of the trend line relating the two data was 1.087 and correlation coefficient was 0.723 for the Spring, Summer and Fall season. The result of this study suggests that the LSM can be used as a powerful tool in developing precise and efficient water resources plans by providing accurate understanding on the spatio-temporal variation of hydrometeorological variables.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.10
• /
• pp.1042-1049
• /
• 2009

Design and optimization of a broadband waveguide magic-T was performed for X-Band tracking radars. A multi-stepped conducting cylinder was used to enhance the bandwidth performance of the conventional waveguide magic-Ts. Particles swarm optimization in conjunction with genetic algorithm was employed to obtain the optimized geometrical parameters. The optimized design exhibits low reflection coefficient below -20 dB at all waveguide ports with frequency bandwidth of 12%. The transmission loss and difference are within 0.2 dB and 0.1 dB, respectively. Measured results are also shown to be in good agreement with the simulated results. Finally, the bandwidth performances for five and seven-stepped conducting cylinders are also investigated.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2007.05a
• /
• pp.229-232
• /
• 2007

In hot strip rolling, the work roll profile is one of the main factors in predicting and correcting the strip profile. Various studies concerning the wear profile and the thermal crown of work roll have been performed, and the results of these studies have shown that the work roll profile must be predicted accurately so as to efficiently control the strip qualities such as thickness, crown, flatness, and camber. Therefore, a precise prediction model of roll profile is called for in a perfect shape control system. In this paper, a genetic algorithm was applied to improve on the roll profile prediction model in hot strip rolling. In this approach, the optimal design problem is formulated on the basis of a numerical model so as to cover the diverse design variables and objective functions. A genetic algorithm was adopted for conducting design iteration for optimization to determine the coefficient of the numerical model for minimization of errors in the result of the calculated value and the measured data. A comparative analysis showed a satisfactory conformity between them..

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.6
• /
• pp.1060-1069
• /
• 2016

In this paper, we introduce the fingerprint recognition system based on Radial Basis Function Neural Network(RBFNN). Fingerprints are classified as four types(Whole, Arch, Right roof, Left roof). The preprocessing methods such as fast fourier transform, normalization, calculation of ridge's direction, filtering with gabor filter, binarization and rotation algorithm, are used in order to extract the features on fingerprint images and then those features are considered as the inputs of the network. RBFNN uses Fuzzy C-Means(FCM) clustering in the hidden layer and polynomial functions such as linear, quadratic, and modified quadratic are defined as connection weights of the network. Particle Swarm Optimization (PSO) algorithm optimizes a number of essential parameters needed to improve the accuracy of RBFNN. Those optimized parameters include the number of clusters and the fuzzification coefficient used in the FCM algorithm, and the orders of polynomial of networks. The performance evaluation of the proposed fingerprint recognition system is illustrated with the use of fingerprint data sets that are collected through Anguli program.

• Transactions of Materials Processing
• /
• v.16 no.4 s.94
• /
• pp.250-253
• /
• 2007

In hot strip rolling, the work roll profile is one of the main factors in predicting and correcting the strip profile. Various studies concerning the wear profile and the thermal crown of work roll have been performed, and the results of these studies have shown that the work roll profile must be predicted accurately so as to efficiently control the strip qualities such as thickness, crown, flatness, and camber. Therefore, a precise prediction model of roll profile is called for in a perfect shape control system. In this paper, a genetic algorithm was applied to improve on the roll profile prediction model in hot strip rolling. In this approach, the optimal design problem is formulated on the basis of a numerical model so as to cover the diverse design variables and objective functions. A genetic algorithm was adopted for conducting design iteration for optimization to determine the coefficient of the numerical model for minimization of errors in the result of the calculated value and the measured data. A comparative analysis showed a satisfactory conformity between them.

• Journal of Korean Society on Water Environment
• /
• v.30 no.2
• /
• pp.159-165
• /
• 2014

Vegetative Filter Strip (VFS) is one of effective Best Management Practices (BMPs) to prevent sediment-laden water problem, is installed at the edge of source area such agricultural area so that sediment occurred in source area is trapped by VFS before it flow into stream or river. Appropriate scale of it needs to be simulated before it is installed, considering various field conditions. In this study, a model using VFSMOD-w model and Genetic Algorithm to determine effective VFS length was developed, it is available to calibrate input parameter related to source area sediment yield through thousands of VFSMOD-w simulations. Useful DBs, moreover, are stored in the model so that very specific input parameters can be used with reasonable values. Compared simulated values to observed data values for calibration, R2 and Nash-Stucliffe model efficiency coefficient were 0.74 and 0.65 in flow comparison, and 0.89 and 0.79 in sediment comparison. The model determined 1.0 m of Filter Length, 0.18 of Filter Slope, and 0.2 cm of Filter Media Spacing to reduce 80% of sediment by VFS. The model has not only Auto-Calibration module also DBs for specific input parameters, thus, the model is expected to be used for effective VFS scale.

• Structural Engineering and Mechanics
• /
• v.83 no.5
• /
• pp.671-680
• /
• 2022

The shear capacity of beams is an essential parameter in designing beams carrying shear loads. Precise estimation of the ultimate shear capacity typically requires comprehensive calculation methods. For steel fiber reinforced concrete (SFRC) beams, traditional design methods may not accurately predict the interaction between different parameters affecting ultimate shear capacity. In this study, artificial neural network (ANN) modeling was utilized to predict the ultimate shear capacity of SFRC beams using ten input parameters. The results demonstrated that the ANN with 30 neurons had the best performance based on the values of root mean square error (RMSE) and coefficient of determination (R²) compared to other ANN models with different neurons. Analysis of the ANN model has shown that the clear shear span to depth ratio significantly affects the predicted ultimate shear capacity, followed by the reinforcement steel tensile strength and steel fiber tensile strength. Moreover, a Genetic Algorithm (GA) was used to optimize the ANN model's input parameters, resulting in the least cost for the SFRC beams. Results have shown that SFRC beams' cost increased with the clear span to depth ratio. Increasing the clear span to depth ratio has increased the depth, height, steel, and fiber ratio needed to support the SFRC beams against shear failures. This study approach is considered among the earliest in the field of SFRC.

• Earthquakes and Structures
• /
• v.19 no.5
• /
• pp.347-359
• /
• 2020

The Mega-Sub Controlled Structure System (MSCSS), an innovative vibration passive control system for building structures, is improved by adding lead rubber bearings (LRBs) on top of the substructure. For the new system, a genetic algorithm is used to optimize the dynamic parameters and distributions of dampers and LRBs. The program uses various seismic performance indicators as optimization objectives, and corresponding results are compared. It is found that the optimization procedure for maximizing the energy dissipation ratio yields the best solutions, and optimized models have consistent seismic performances under different earthquakes. Seismic performances of optimized MSCSS models with and without LRBs, as well as the traditional Mega-Sub Structure model, are evaluated and compared under El Centro wave, Taft wave and 20 other artificial waves. In both elastic and plastic analysis, the model with LRBs shows significantly smaller story drift and horizontal acceleration than those of the other two models, and fewer plastic hinges are developed during severe earthquakes. Energy analysis also shows that LRBs installed in proper locations increase the deformation and energy dissipation of dampers, thereby significantly reduce the kinetic, potential, and hysteretic energy in the structure. However, LRBs do not have to be mounted on all the additional columns. It is also demonstrated that LRBs at unfavorable locations can decrease the energy dissipation for dampers. After LRBs are installed, the optimal damping coefficient and the optimal damping exponent of dampers are reduced to produce the best damping effect.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.1
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.