• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.459-460
• /
• 2021

본 논문에서는 BEGAN을 활용한 한국인 얼굴 데이터 생성을 위한 최적의 Hyper Parameter를 제안한다. 연구에서는 GAN의 발전된 모델인 BEGAN을 이용한다. 위의 모델을 작성하기 위하여 본 논문에서는 Anaconda 기반의 Jupyter Notebook에서 Python Tensorflow 모델을 작성하여 테스트하고, 만들어진 모델을 FID를 통해 모델의 성능을 비교한다. 본 연구에서는 제안하는 방법들을 통해서 만들어진 모델을 이용해 한국인 얼굴 데이터를 구하고, 생성된 이미지에 대한 정량적인 평가를 진행한다.

• Journal of Electrical Engineering and Technology
• /
• v.1 no.4
• /
• pp.455-460
• /
• 2006

This paper presents the convergency property of the Auxiliary Problem Principle when it is applied to large-scale Optimal Power Flow problems with Distributed or Parallel computation features. The key features and factors affecting the convergence ratio and solution stability of APP are also analyzed.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.425-436
• /
• 2016

In this paper, a parameter optimization based iterative learning control strategy is presented for permanent magnet synchronous motor control. This paper analyzes the mechanism of iterative learning control suppressing PMSM torque ripple and discusses the impact of controller parameters on steady-state and dynamic performance of the system. Based on the analysis, an optimization problem is constructed, and the expression of the optimal controller parameter is obtained to adjust the controller parameter online. Experimental research is carried out on a 5.2kW PMSM. The results show that the parameter optimization based iterative learning control proposed in this paper achieves lower torque ripple during steady-state operation and short regulating time of dynamic response, thus satisfying the demands for both steady state and dynamic performance of the speed regulating system.

• Smart Structures and Systems
• /
• v.19 no.1
• /
• pp.21-31
• /
• 2017

To control the stochastic vibration of a vibration-sensitive instrument supported on a beam, the beam is designed as a sandwich structure with magneto-rheological visco-elastomer (MRVE) core. The MRVE has dynamic properties such as stiffness and damping adjustable by applied magnetic fields. To achieve better vibration control effectiveness, the optimal bounded parametric control for the MRVE sandwich beam with supported mass under stochastic and deterministic support motion excitations is proposed, and the stochastic and shock vibration suppression capability of the optimally controlled beam with multi-mode coupling is studied. The dynamic behavior of MRVE core is described by the visco-elastic Kelvin-Voigt model with a controllable parameter dependent on applied magnetic fields, and the parameter is considered as an active bounded control. The partial differential equations for horizontal and vertical coupling motions of the sandwich beam are obtained and converted into the multi-mode coupling vibration equations with the bounded nonlinear parametric control according to the Galerkin method. The vibration equations and corresponding performance index construct the optimal bounded parametric control problem. Then the dynamical programming equation for the control problem is derived based on the dynamical programming principle. The optimal bounded parametric control law is obtained by solving the programming equation with the bounded control constraint. The controlled vibration responses of the MRVE sandwich beam under stochastic and shock excitations are obtained by substituting the optimal bounded control into the vibration equations and solving them. The further remarkable vibration suppression capability of the optimal bounded control compared with the passive control and the influence of the control parameters on the stochastic vibration suppression effectiveness are illustrated with numerical results. The proposed optimal bounded parametric control strategy is applicable to smart visco-elastic composite structures under deterministic and stochastic excitations for improving vibration control effectiveness.

• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.17-26
• /
• 2017

CPV system is composed with CPV cells, modules, PCS(power conditioning system), solar tracker, system installation and balance of systems(BOS). Mention about modelling method which is applied for CPV system simulation and evaluation system analysis. This paper focuses on CPV system modeling and optimal design of the electric energy production analysis through the development of proposed optimal CPV system simulation. Calculated simulation results of the generalized CPV system in regard to loss parameter calculation method can make out optimal configuration of CPV system with high reliability and stability. The loss parameter calculation method establish a mathematical modeling for the purposed of simulation and utilization various data for economical analysis of the CPV system design.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.2
• /
• pp.284-292
• /
• 2003

In this paper, we carried out the numerical examination of the initial value setting-up method to extend the range of optimal step parameter in a adaptive system which is controlled by LMS algorithm. For initial value setting-up methods, the general method which select the initial value randomly and the other method which applies the approximate value obtained from the direct method to initial value, were used. And then, we compared to the ranges of step parameter setting, the convergence speeds of mean-square-error, and the stabilities during the convergence process when the initial values were applied to the optimal directivity synthesis problem. According to the numerical simulation results, the initial value setting-up method by means of the direct method provides wider range for the step parameter, more efficient capability for convergence and stability, and more error correction ability than the general method.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.1
• /
• pp.47-57
• /
• 1996

This paper on planning constant accelerated life test is assumed that parameters for a lognormal life distribution are depended on changes of stresses. The proposed test plans are optimum in that they minimize the asymptotic variance of maximum likelihood estimator of a specified quantile at the design stress. The optimal amount of low stress level ${\xi}_{L}$ and optimal sample proportion ${\pi}$ to be allocated at low stress level are obtained when the ratio of scales at high stress level and design stress level is unknown.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.1
• /
• pp.79-88
• /
• 2015

In this paper, it is investigated that the limitation due to the asymmetry of optical power and chromatic dispersion with respect to optical phase conjugator (OPC) for compensating optical signal distortion in WDM system is overcomed by using OPC position offset and optimal dispersion coefficients of fiber sections, which depend on OPC position offset. It is confirmed that overall WDM channels are efficiently compensated by applying the optimal parameter values obtained from the proposed method into 24 channels ${\times}40$ Gbps WDM system with non zero - dispersion shifted fiber (NZ-DSF) of 1, 000 km, such as power penalties of inter-channel are reduce to almost 3.5 dB from the infinite value. It is also confirmed that the flexible design of WDM system with OPC is possible by using the optimal parameters, in which OPC is placed at ${\pm}15km$ from 500 km for efficiently compensating overall channels. Thus, the methods proposed in this research will be expected to alternate with the method of making a symmetrical distribution of power and local dispersion in real optical link which generates a serious problem if it was not made but it is the condition in the case of applying the OPC into multi-channels WDM system.

• IE interfaces
• /
• v.9 no.1
• /
• pp.13-24
• /
• 1996

Quality of injection molded parts is dependent on both mold design and processing conditions. From the mold design point of view, an optimal shrinkage should be used to compensate the shrinkage of molded parts. From the processing point of view, it is important to analyze the priority of processing conditions because a number processing conditions affect the quality of molded parts. Processing analysis employing the design of experiment was performed, and the shrinkage of molded part was considered as a characteristic parameter to improve the quality. As the result of the analysis of variance on SN ratio of a characteristic value, injection speed and bolding pressure were selected as two effective process parameters. Regression analysis on shrinkage and processing conditions was carried out, and an optimal processing condition was obtained by the response surface analysis. Shrinkage at the optimal condition could be used to reduce the number of try-cut at the step of mold making. The ranges of indirect control parameter, such as maximum cavity pressure or weight, measured at the optimal processing condition were used for monitoring the quality of molded parts in process.

• Journal of information and communication convergence engineering
• /
• v.5 no.1
• /
• pp.17-22
• /
• 2007

In this paper, the optimal value of optical phase conjugator (OPC) position and the optimal values of dispersion coefficients of fiber sections for the best compensation of the distorted WDM signals with frequency chirp of -1 are induced to alternate with the symmetrical distributions of power and local dispersion with respect to OPC, which is difficult to form in real optical link due to fiber attenuation in mid-span spectral inversion (MSSI) technique. It is confirmed that the Q-factors of total channels of -18.5 dBm launching light power exceed 16.9 dB, which value corresponds to 10-12 BER, by applying the induced optimal parameter values into 16 channels ${\times}$ 40 Gbps WDM system, on the other hand the Q-factors of only 9 channels exceed that value in WDM system with the conventional MSSI technique. Thus, it is expected to expand the availability of OPC in WDM system through the using of the optimal parameter values that are induced by the proposed method in this paper, without the symmetrical distributions of power and local dispersion.