• Communications for Statistical Applications and Methods
• /
• v.27 no.2
• /
• pp.255-268
• /
• 2020

A mixture of multivariate canonical fundamental skew t-distribution (CFUST) has been of interest in various fields. In particular, interest in the unsupervised learning society is noteworthy. However, fitting the model via EM algorithm suffers from significant processing time. The main cause is due to the calculation of many multivariate t-cdfs (cumulative distribution functions) in E-step. In this article, we provide an approximate, but fast calculation method for the in univariate fashion, which is the product of successively conditional univariate t-cdfs with Taylor's first order approximation. By replacing all multivariate t-cdfs in E-step with the proposed approximate versions, we obtain the admissible results of fitting the model, where it gives 85% reduction time for the 5 dimensional skewness case of the Australian Institution Sport data set. For this approach, discussions about rough properties, advantages and limits are also presented.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.333-351
• /
• 2022

The skew-t distribution is an attractive family of asymmetrical heavy-tailed densities that includes the normal, skew-normal and Student's-t distributions as special cases. In this work, we propose an EM-type algorithm for computing the maximum likelihood estimates for skew-t linear regression models with censored response. In contrast with previous proposals, this algorithm uses analytical expressions at the E-step, as opposed to Monte Carlo simulations. These expressions rely on formulas for the mean and variance of a truncated skew-t distribution, and can be computed using the R library MomTrunc. The standard errors, the prediction of unobserved values of the response and the log-likelihood function are obtained as a by-product. The proposed methodology is illustrated through the analyses of simulated and a real data application on Letter-Name Fluency test in Peruvian students.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.36.3-37
• /
• 2020

Recent observation of the neutron star merger event, GW170817, through both gravitational wave (GW) and electromagnetic wave (EM) observations opened a new way of exploring the universe, namely, multi-messenger astronomy (MMA). One of the keys to the success of MMA is a rapid identification of EM counterpart. We will introduce GW follow-up observation project in Korea for hunting GW EM counterpart rapidly and its strategy for prioritization of GW source host galaxy candidates. Our method relies on recent simulation results regarding plausible properties of GW source host galaxies and the low latency localization map from LIGO/Virgo. We will show a test result for both binary neutron star merger events using previous event and describe observing strategy with our facilities for GW events during the ongoing LIGO/Virgo O3 run. Finally, we report the results of optical/NIR follow-up observation of GW190425, the first neutron.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.20 no.4
• /
• pp.243-250
• /
• 2000

Selection of oat variety according to cultivation period is an important to increase productivity of forage crop. To investigate the growth characters and dry matter productivity of oats according to cultivation period, early-maturing oat(EM0) and medium-maturing oat(MM0) variety were sown in spring and autumn at central district of Korea. When oats were cultivated in spring, MMO variety was longer 8 cm in leaf length and wider 5 mm in leaf width than 25 cm and 12 mm of EM0 variety, rexpectively. but in autumn, those were not different between maturities of oat varieties. Plant length of MMO variety was longer 7 cm than that of EM0 Variety in spring cultivation, but in autumn, plant length of EM0 variety was longer 14 cm than that of MMO variety. Heading dates were 20th to 22th May in EM0 variety, and 30th May to 10th June in MMO variety in spring cultivation, and ear of EM0 variety emerged 30th Oct. to loth Nov. but that of MMO variety did not emerge at harvesting day in autumn cultivation. In Spring cultivation, dry matter(DM) yield of EM0 variety was 7,349 kg/ha that was less 56% than 11,466 kg/ha of MMO variety, but In Autumn, was more 15% than 6,575 kg/ha of MMO variety. In conclusion, selection of oat variety in spring and autumn cultivation can be different with cropping system of forage crop, and this trial is suggesting that oat variety could be sown MMO variety in spring and EM0 variety in autumn at central district of Korea. (Key words : Oat variety, Productivity, Cultivation season)

• The Korean Journal of Zoology
• /
• v.39 no.1
• /
• pp.1-11
• /
• 1996

The SR 95531, a GABA antagonist was microinjected into either the pretectum nuclei (nucleus Superficialis Synencephali nSS) or the nBOR (nucleus Ectomammilaris nEM) of chickens. Monocular optokinetic nystagmus (01(N) was reorded by the search coil technique before and after unilateral intracerebral drug administration. Unilateral microinjections of SR 95531 into either the nSS or nEM induce a reversible increase of gain in OKN directed by contralateral eye for both directions of stimulation. The administration into the nSS increased directional asymmetry by increasing the T~ component velocity gain more strongly than the N-T component velocity gain. On the other hand, the unilateral administration of the drug into the nEM suppressed the diretional O1(N asymmetry by increasing the N-T component velocity gain more strongly than the T-N component velocity gain. The nSS seems especially involved in monocular OKN in response to a T-N stimulation, while the nEM seems more involved in the OKN response to N-T stimulation. These results indicate that the drug suppresses GABAergic inhibition at the mesencephalic level. The increase in gain of OKN directed by the ipsilateral eye to microinjeded nuclei could account for the strong interactions existing between these two mesencephalic structures responsible for horizontal OKN.

• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.795-804
• /
• 2003

In this article, a tomography for the estimation of the origin-destination(OD) traffic intensities in dynamic routing network is considered. Vardi(1996)'s approach based on fixed route is not directly applicable to dynamic routing protocols, which arises from the fact that we cannot access the route at every observation time. While it uses link-wise traffics as the observations, the proposed method considers the triple of ingress/outgress/relayed traffics data at each node so that we can transform the problem into a routing-independent tomography. An EM algorithm for implementation and some simulated experiments are provided.

• Journal of Biomedical Engineering Research
• /
• v.19 no.2
• /
• pp.133-142
• /
• 1998

In Bayesian SPECT reconstruction, the incorporation of elaborate forms of priors can lead to improved quantitative performance in various statistical terms, such as bias and variance. In particular, the use of higher-order smoothing priors, such as the thin-plate prior, is known to exhibit improved bias behavior compared to the conventional smoothing priors such as the membrane prior. However, the bias advantage of the higher-order priors is effective only when the hyperparameters involved in the reconstruction algorithm are properly chosen. In this work, we further investigate the quantitative performance of the two representative smoothing priors-the thin plate and the membrane-by observing the behavior of the associated hyperparameters of the prior distributions. In our experiments we use Monte Carlo noise trials to calculate bias and variance of reconstruction estimates, and compare the performance of ML-EM estimates to that of regularized EM using both membrane and thin-plate priors, and also to that of filtered backprojection, where the membrane and thin plate models become simple apodizing filters of specified form. We finally show that the use of higher-order models yields excellent "robustness" in quantitative performance by demonstrating that the thin plate leads to very low bias error over a large range of hyperparameters, while keeping a reasonable variance. variance.

• Proceedings of the KIEE Conference
• /
• 1998.11a
• /
• pp.13-15
• /
• 1998

EM(Electro Magnetic) pump is used for the purpose of transporting liquid sodium coolant with electrical conductivity in the LMR(Liquid Metal Reactor). In the present study. pilot EM pump has been designed by using of equivalent circuit method which is commonly employed to analyze linear induction machines for the test of removal of residual heat. The length and diameter of the pump have fixed values of 840 mm and 101.6 mm each by taking account of geometrical size of circulation loop for the installation of EM pump. Flowrate versus developing pressure is related from Laithwaite's standard design formula and the characteristic analyses of developing force and efficiency are carried out according to change of input frequency. From the characteristic curve, input frequency of 13 Hz is determined as the design frequency. On the other hand, The annular air gap size of 6.05 mm is selected not to bring about too much hydraulic loss. Resultantly design analysis makes pump have the electrical input of 604 VA and the hydrodynamical capacity of 1.3 bars and 40 l/min.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.34D no.9
• /
• pp.21-27
• /
• 1997

Square spiral inductors are designed with EM program in accordance with the inner diameter and the metal thickness which is 0.2.mu.m and 20.mu.m respectively. We propose a parameter extraction method based on the S-parameter. Lumped equivalent circuits of spiral inductors are analyed with reflection coefficient S$_{11}$, of witch freqency rnage is 1~10GHz. When metal thickness is 0.2.mu.m, S$_{11}$ with EM simulation is not the same as S$_{11}$ that of SPICE simulation. So we suggests a new lumped equivalent circuits which compensate circuits. Te new lumped equivalent circuits are adequate for other inductor with small scale at high frequencies.ncies.

• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.349-353
• /
• 2008

In this paper, the EM wave absorber was designed and fabricated for preventing Reader Interference of RFID communication system in UHF band We fabricated several samples in different composition ratios of Amorphous and CPE(Chlorinated Polyethylene). Absorption abilities were simulated in accordance with different thicknesses of the prepared absorbers and changed complex relative permittivity and permeability due to composition ratio. The mixing ratio of Amorphous and CPE was searched as 80 : 20 wt.% by experiments and simulation. Then the EM wave absorber was fabricated and tested using the simulated data. As a result, the developed EM wave absorber has a thickness of 4 mm and absorption ability was over 20 dB in frequency range of $860\;MHz{\sim}960\;MHz$. Therefore, it was confirmed that the developed absorber can be used for suppressing RFID reader interference in UHF band.