• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.155-166
• /
• 2002

Neural networks have been studied as a popular tool for classification and they are very flexible. Also, they are used for many applications of pattern classification and pattern recognition. This paper focuses on Bayesian approach to feed-forward neural networks with single hidden layer of units with logistic activation. In this model, we are interested in deciding the number of nodes of neural network model with p input units, one hidden layer with m hidden nodes and one output unit in Bayesian setup for fixed m. Here, we use the latent variable into the prior of the coefficient regression, and we introduce the 'sequential step' which is based on the idea of the data augmentation by Tanner and Wong(1787). The MCMC method(Gibbs sampler and Metropolish algorithm) can be used to overcome the complicated Bayesian computation. Finally, a proposed method is applied to a simulated data.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.6
• /
• pp.55-62
• /
• 2006

For the fault diagnosis of three-phase induction motors, we construct a experimental unit and then develop a diagnosis algorithm based on pattern recognition. The experimental unit consists of machinery module for induction motor drive and data acquisition module to obtain the fault signal. As the first step for diagnosis procedure, preprocessing is performed to make the acquired current simplified and normalized. To simplify the data, three-phase current is transformed into the magnitude of Concordia vector. As the next step, feature extraction is performed by kernel principal component analysis(KPCA) and linear discriminant analysis(LDA). Finally, we used the classifier based on radial basis function(RBF) network. To show the effectiveness, the proposed diagnostic system has been intensively tested with the various data acquired under different electrical and mechanical faults with varying load.

• Advances in aircraft and spacecraft science
• /
• v.9 no.6
• /
• pp.507-523
• /
• 2022

This study is aimed to accurately predict the vibration response of two types of functionally graded sandwich plates, one with FGM core and another with FGM face sheets. The gradation in FGM layer is quantified by exponential method. An efficient zig-zag theory is used and the zigzag impacts are established via a linear unit Heaviside step function. The present theory fulfills interlaminar transverse stress continuity at the interface and zero condition at the top and bottom surfaces of the plate for transverse shear stresses. Nine-noded C-0 FE having 8DOF/node is utilized throughout analysis. The present model is free from the obligation of any penalty function or post-processing technique and hence is computationally efficient. Numerical results have been presented on the free vibration behavior of sandwich FGM for different end conditions, lamination schemes and layer orientations. The applicability of present model is confirmed by comparing with published results. Several new results are also specified, which will serve as the benchmark for future studies.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.8
• /
• pp.889-897
• /
• 1999

This paper deals with a problem searching a target transfer function to meet the time-domain specifications for feedback system with given plant transfer function. For the Type I system, we first define three forms of transient response to unit step input, which are named by F, M, S-type. These are charaacterized as follows ; F-type has fast initial response and slow approach to the steady sate after reaching at 90% of the steady state value, S-type has slow initial response but fast approach to the steady state, and M-type is denoted by highly smooth response between F-type and S-type. Three prototypes corresponding to each form are proposed, time. For the order $n{\geq}4$, after determining admissible root structures of target characteristic polynomials empirically and expressing such polynomial coefficients by using special parameters ${\gamma}_i$ and $\epsilon$, the optimal prototypes that minimize the integral of the squared of the modified errors(ISME) have been obtained. Since the step responses of these prototypes have almost same wave forms irrespective to the order, the desired settling time or the rise time can be converted into the equibalent time constant $\tau$ and thus it is easy to obtain a target transfer function. It is shown through a design example that the present prototype is very useful for meeting the time-domain specifications and has been compared with different methods with a viewpoint of pertinence.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.26 no.1
• /
• pp.1-7
• /
• 1990

Theoretical evaluations of the vertical displacement at the epicenter on the circular glass plate have been carried out in the case of the unit point loading(1 dyne force strength) with the Heaviside step-function time dependency. Acoustic emission signals generated during pencil lead($\Phi$=0.5mm, HB) fracture on the soda-lime glass($\Phi$=22cm, thickness=2.8cm) were observed by the optical Michelson interferometer with the stabilized circuit, and then the source function of the observed acoustic emission signals was analyzed by the deconvolution method. The source function of acoustic emission during pencil lead fracture had a 'dip' of~0.7$\mu$sec duration time at the front portion and a step function of~0.5$\mu$sec rise time with a force strength of~4.5N.

• Journal of Korean Society of Rural Planning
• /
• v.2 no.1
• /
• pp.31-38
• /
• 1996

As a rational decision-making process of county-level area development, this study designed 3-step framework : function-giving(areal analysis) on unit planning area by decision matrix of land suitability, check of typical characteristics of each function area and formulation of its future development strategies. Two alternatives were suggested as the areal analysis method, of which one is equal ordering / valuing technique of checking indices for land suitability classfication and the other preferential weighting technique. And then, under the algorithm specially defined in this study, land suitability maps(Fig.2,3) of the case study area (Seungju-county area, Chonnam-province, Korea) were drawn from the areal analysis results. By use of land suitability classification results, unique characteristics of typical function areas were defined (on 7 types of alternative 1 , 8 types of II ) and their future development strategies were formulated in the case study area, According to the categorization criteria in this study, all the villages of the case area were classfied as a suitable type of function areas illustrated in this study.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.2
• /
• pp.57-62
• /
• 1999

Estimation of the point spread function (PSF) is one of the main research topic of image processing, because it determines the performance of the auto-focusing system. In this paper, a new algorithm for PSF estimation is proposed, and its application to image restoration is also presented. The procedure for complete realization of the auto-focusing system consists of two steps: PSF estimation based on edge classification, and image restoration using the estimated PSF. More specifically, we divide imput image into multiple small image or block, estimate unit step response and average them on the blocks which contain edge, and estimate 2-dimensional isotropic PSF from the 1 dimensional step response. Finally we obtain in-focused image by using image restoration based on the estimated PSF.

• Animal Bioscience
• /
• v.37 no.4
• /
• pp.576-590
• /
• 2024

Objective: The objective of this study was to identify genes associated with 305-day milk yield (MY) and fat yield (FY) that also influence the adaptability of the Thai multibreed dairy cattle population to tropical conditions. Methods: A total of 75,776 imputed and actual single nucleotide polymorphisms (SNPs) from 2,661 animals were used to identify genomic regions associated with MY and FY using the single-step genomic best linear unbiased predictions. Fixed effects included herd-year-season, breed regression, heterosis regression and calving age regression effects. Random effects were animal additive genetic and residual. Individual SNPs with a p-value smaller than 0.05 were selected for gene mapping, function analysis, and quantitative trait loci (QTL) annotation analysis. Results: A substantial number of QTLs associated with MY (9,334) and FY (8,977) were identified by integrating SNP genotypes and QTL annotations. Notably, we discovered 17 annotated QTLs within the health and exterior QTL classes, corresponding to nine unique genes. Among these genes, Rho GTPase activating protein 15 (ARHGAP15) and catenin alpha 2 (CTNNA2) have previously been linked to physiological traits associated with tropical adaptation in various cattle breeds. Interestingly, these two genes also showed signs of positive selection, indicating their potential role in conferring tolerance to trypanosomiasis, a prevalent tropical disease. Conclusion: Our findings provide valuable insights into the genetic basis of MY and FY in the Thai multibreed dairy cattle population, shedding light on the underlying mechanisms of tropical adaptation. The identified genes represent promising targets for future breeding strategies aimed at improving milk and fat production while ensuring resilience to tropical challenges. This study significantly contributes to our understanding of the genetic factors influencing milk production and adaptability in dairy cattle, facilitating the development of sustainable genetic selection strategies and breeding programs in tropical environments.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.8 no.5
• /
• pp.423-433
• /
• 2016

In this paper, we consider the cybersecurity issue of ship information system (SIS) from a new perspective which is called opacity. For a SIS, its confidential information (named as "secret") may be leaked through the working behaviors of each Distributed Control Unit (DCU) from an outside observer called an "intruder" which is able to determine ship's mission state by detecting the source of each data flow from the corresponding DCUs in SIS. Therefore we proposed a dual layer mechanism to enforce opacity by activating non-essential DCU during secret mission. This mechanism is calculated by two types of insertion functions: Safety-assured insertion function ($f_{IS}$) and Admissibility-assured insertion function ($f_{IA}$). Due to different objectives, $f_{IS}$ is designed to confuse intruder by constructing a non-secret behaviors from a unsafe one, and the division of $f_{IA}$ is to polish the modified output behaviors back to normal. We define the property of "$I_2$-Enforceability" that dual layer insertion functions has the ability to enforce opacity. By a given mission map of SIS and the marked secret missions, we propose an algorithm to select $f_{IS}$ and compute its matchable $f_{IA}$ and then the DCUs which should be activated to release non-essential data flow in each step is calculable.

• The KIPS Transactions:PartA
• /
• v.8A no.3
• /
• pp.279-286
• /
• 2001

This paper proposes a low power resource allocation and scheduling algorithm that minimized power consumption such as DSP circuit in high-level synthesis process. In this paper, we have used list-scheduling method for low power design in scheduling step. Also, it increase possibility to reuse input through resource sharing when assign resource. After scheduling, the resources allocation uses the power function in consideration of the result of calculating average hamming distances and switching activity between two input. First, it obtain switching activity about input value after calculate average hamming distances between two operator and find power value make use of bit pattern of the input value. Resource allocation process assign operator to minimize average hamming distance and power dissipation on all occasions which is allocated at each control step according to increase control step. As comparing the existed method, the execution time becomes fast according to number of operator and be most numberous control step. And in case of power that consume, there is decrease effect from 6% to 8% to be small.