• Proceedings of the KIPE Conference
• /
• 1998.10a
• /
• pp.346-351
• /
• 1998

In design of a digital current controller for a 3-phase (3 ) voltage-source (VS) PWM converter, its conventional model, i.e., stationary or synchronous reference frame model, is used in obtaining its discretized version. It introduces, however, inherent errors since the following practical problems are not taken into consideration: the characteristics of the space vector-based pulse-width modulation (SVPWM) and the time delays in the process of sampling and computation. In this paper, the new hybrid reference frame model of the 3 VS PWM converter is proposed considering these problems. In addition, the direct digital current controller based on this model is designed without any prediction or extrapolation algorithm to compensate the time delay. So the control algorithm is made very simple. It represents no steady-state error in input current control and has the optimized transient responses. The validity of the proposed algorithm is proved by the computer simulation and experimental results.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.4
• /
• pp.251-258
• /
• 2005

Automatic document classification may differ significantly according to the characteristics of documents that are subject to classification, as well as classifier's performance. This research identifies e-mail document's characteristics to apply a three-step preprocessing algorithm that can minimize e-mail document's atypical characteristics. In the first 5go, uncertain based sampling algorithm that used Mean Absolute Deviation(MAD), is used to address the question of selection learning document for the rule generation at the time of classification. In the subsequent stage, Weighted vlaue assigning method by attribute is applied to increase the discriminating capability of the terms that appear on the title on the e-mail document characteristic level. in the third and last stage, accuracy level during classification by each category is increased by using Naive Bayesian Presumptive Algorithm's Dynamic Threshold. And, we implemented an E-Mail Recommendtion System using a three-step preprocessing algorithm the enable users for direct and optimal classification with the recommendation of the applicable category when a mail arrives.

• Communications for Statistical Applications and Methods
• /
• v.24 no.5
• /
• pp.457-480
• /
• 2017

We develop a random partition procedure based on a Dirichlet process prior with Laplace distribution. Gibbs sampling of a Laplace mixture of linear mixed regressions with a Dirichlet process is implemented as a random partition model when the number of clusters is unknown. Our approach provides simultaneous partitioning and parameter estimation with the computation of classification probabilities, unlike its counterparts. A full Gibbs-sampling algorithm is developed for an efficient Markov chain Monte Carlo posterior computation. The proposed method is illustrated with simulated data and one real data of the energy efficiency of Tsanas and Xifara (Energy and Buildings, 49, 560-567, 2012).

• Smart Structures and Systems
• /
• v.12 no.6
• /
• pp.641-659
• /
• 2013

In this paper is studied the influence of the uncertain mass distribution over the floors on the choice of the optimal parameters of a hybrid control system for tall buildings subjected to wind load. In particular, an optimization procedure is developed for the robust design of a hybrid control system that is based on an enhanced Monte Carlo simulation technique and the genetic algorithm. The large computational effort inherent in the use of a MC-based procedure is reduced by the employment of the Latin Hypercube Sampling. With reference to a tall building modeled as a multi degrees of freedom system, several numerical analyses are carried out varying the parameters influencing the floors' masses, like the coefficient of variation of the distribution and the correlation between the floors' masses. The procedure allows to obtain optimal designs of the control system that are robust with respect to the uncertainties on the distribution of the dead and live loads.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.658-663
• /
• 1987

The new controller developed here, which is the facility with only one measurement, is a new concept for the level controller of the existing nuclear steam generator. A MACS (Microcomputer-based Adaptive Control System of a Steam Generator) is quite practical and efficient, and has also simple structure and higher flexibility in the installment for actual plant. A key ingredient of this system is adaptive regulator which can calculate adaptive, optimal valve position in response to changes in the dynamics of the process and the disturbances. In spite of many difficulties in the steam generator water level control at low power, it can be concluded from the experimental and simulation results, that the MACS can provide optimal, robust steam generator level control from zero to full power. The amount of the control input effort can be reduced by adjusting the weighting factor. However, the steady state water level errors are generated. To avoid the steady errors, the different adaptive algorithm should be investigated in the future. The 3 second sampling time is acceptable for this system. However, action should be taken to shorten the sampling time for better digital control.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.595-602
• /
• 2020

We propose a generative probabilistic model with Dirichlet prior distribution for topic modeling and text similarity analysis. It assigns a topic and calculates text correlation between documents within a corpus. It also provides posterior probabilities that are assigned to each topic of a document based on the prior distribution in the corpus. We then present a Gibbs sampling algorithm for inference about the posterior distribution and compute text correlation among 50 abstracts from the papers published by IEEE. We also conduct a supervised learning to set a benchmark that justifies the performance of the LDA (Latent Dirichlet Allocation). The experiments show that the accuracy for topic assignment to a certain document is 76% for LDA. The results for supervised learning show the accuracy of 61%, the precision of 93% and the f1-score of 96%. A discussion for experimental results indicates a thorough justification based on probabilities, distributions, evaluation metrics and correlation coefficients with respect to topic assignment.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.899-903
• /
• 2019

In networked control systems, time-varying delay of the transmitting signal is inevitable. If the transmission delay is longer than the fixed sampling time, the system will be unstable. To solve this problem, this paper proposes the method to predict the delay using logic-based fuzzy neural networks, and the predicted time delay will be used as a sampling time in the networked control systems. To verify the effectiveness of the proposed method, the delay data collected from the real system are used to train and test the logic-based fuzzy neural networks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.8
• /
• pp.1356-1362
• /
• 2008

In this paper. we propose a novel auto white balance algorithm which is one of the representative functions on cameras. White balance is the process of removing unrealistic color casts, which will make the captured white objects appear white. For white balance, we employ $CIEL^*a^*b^*$ color space which is the most complete color model available and is conventionally used to describe all the colors visible to the human eye and estimate the color difference on white objects with distribution of the image which is called the reference white estimation. For accuracy, we form groups or sets of pixels that are altered by the light sources and other elements. Moreover, Standard group is decided by judgment of specific-case images with the information of groups. Then, the reference white estimation is performed by the color sampling which is to choose all the accumulated pixels contained within the standard group. The color gain for image compensation by considering the color saturation is also computed. the proposed algorithm provides a significant performance.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.534-542
• /
• 2019

In active SONAR, several different methods are used to detect range-Doppler information of the target. Compressive sensing based method is more accurate than conventional methods and shows superior performance. There are several compressive sensing algorithms for range-Doppler estimation of active sonar. The ability of each algorithm depends on algorithm type, mutual coherence of sensing matrix, and signal to noise ratio. In this paper, we compared and analyzed computational performance and accuracy of various compressive sensing algorithms for range-Doppler estimation of active sonar. The performance of OMP (Orthogonal Matching Pursuit), CoSaMP (Compressive Sampling Matching Pursuit), BPDN (CVX) (Basis Pursuit Denoising), LARS (Least Angle Regression) algorithms is respectively estimated for varying SNR (Signal to Noise Ratio), and mutual coherence. The optimal compressive sensing algorithm is presented according to the situation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.5015-5038
• /
• 2018

In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.