• Quantitative Bio-Science
• /
• v.37 no.2
• /
• pp.133-141
• /
• 2018

Graphical lasso is one of the most popular methods to estimate a sparse precision matrix, which is an inverse of a covariance matrix. The objective function of graphical lasso imposes an ${\ell}_1$-penalty on the (vectorized) precision matrix, where a tuning parameter controls the strength of the penalization. The selection of the tuning parameter is practically and theoretically important since the performance of the estimation depends on an appropriate choice of tuning parameter. While information criteria (e.g. AIC, BIC, or extended BIC) have been widely used, they require an asymptotically unbiased estimator to select optimal tuning parameter. Thus, the biasedness of the ${\ell}_1$-regularized estimate in the graphical lasso may lead to a suboptimal tuning. In this paper, we propose a two-staged bias-correction procedure for the graphical lasso, where the first stage runs the usual graphical lasso and the second stage reruns the procedure with an additional constraint that zero estimates at the first stage remain zero. Our simulation and real data example show that the proposed bias correction improved on both edge recovery and estimation error compared to the single-staged graphical lasso.

• Journal of Korean Society of Forest Science
• /
• v.81 no.2
• /
• pp.146-155
• /
• 1992

The natural mixed stand in Jindong-Ri, according to a recent study, showed the possibility of selection cutting as a silvicultural system based on the stand structure such as DBH distribution and height distribution. However, volume structure per DBH class of this stand had not a mature stand of selection cutting. In this study, wherefore, the rate of increment for DBH and volume was used to predict the future stand structure including volume distribution per DBH class. The possibility of selection cutting was then discussed using the future stand structure. From the prediction of future stand structure for 30 years per every 10 years, it could be concluded that the stand will be induced to selection cutting forest because of enough number of trees in objective DBH class and above, total volume per hectare, and the volume of large DBH class which can be harvested every year. However, this stand still did not show the structure of typical selection cutting which has the rate of 1 : 2 : 7 in the number of trees per hectare and the volume rate of 5 : 3 : 2 for large, medium, and small DBH class. This problem could be improved by appropriate silvicultural treatments.

• The Journal of Fisheries Business Administration
• /
• v.38 no.1 s.73
• /
• pp.19-45
• /
• 2007

There have not been many studies which considered both quantitative and qualitative location factors on the issues of site selection problems for a fish farm. This study develops AHP(analytic hierarchy process) model to resolve site selection problem for a fish raising farm by using quantitative and qualitative factors. In order to evaluate the validity of the location factors found in the literature review, the study used advice from fish raising farmers and related academic experts. Four major factors have been selected as economic factors, social factors, natural environmental factors and infrastructures. An AHP structural diagram has developed by considering the factors and potential sites proposed for fish farming. Through the survey on the preference of factors and potential sites, pairwise comparison matrices have been estimated and used to calculated the relative weights of each potential site. The AHP model process shown in the study can be applied to resolve site selection problems for fish raising farmers.

• Journal of the Korean Statistical Society
• /
• v.21 no.2
• /
• pp.93-110
• /
• 1992

A model selection approach is used to find out whether the mean and the variance of a unique sample are different from the pre-specified values. Normal distribution is selected as an approximating model. Kullback-Leibler discrepancy comes out as a natural measure of discrepancy between the operating model and the approximating model. Several estimates of selection criterion are computed including AIC, TIC, and a coupleof bootstrap estimator of the selection criterion are considered according to the way of resampling. It is shown that a closed form expression is available for the parametric bootstrap estimated cirterion. A Monte Carlo study is provided to give a formal comparison when the operating family itself is normally distributed.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.983-984
• /
• 2008

This paper proposes a variable break that can offset prediction error as well as a pre-selection methods, based on the variable break, for enhanced unit selection. In Japanese, a sentence consists of several APs (Accentual phrases) and MPs (Major phrases), and the breaks between these phrases must predicted to realize text-to-speech systems. An MP also consists of several APs and plays a decisive role in making synthetic speech natural and understandable because short pauses appear at its boundary. The variable break is defined as a break that is able to change easily from an AP to an MP boundary, or from an MP to an AP boundary. Using CART (Classification and Regression Trees), the variable break is modeled stochastically, and then we pre-select candidate units in the unit-selection process. As the experimental results show, it was possible to complement a break prediction error and improve the naturalness of synthetic speech.

• Journal of Korean Society of Rural Planning
• /
• v.3 no.2
• /
• pp.81-89
• /
• 1997

Still today, many streams are channelized and embanked in Korea. On the other hand, some urban streams are being restored to their natural shapes by landscape planners. It would be better to improve rural streams in a way that would not require restoration in later days. Then, one important question is what kind of embankments the residents prefer for what reasons. Five simulated photos showing from very natural to artificial embankments were used in surveying 90 residents of three villages. Major findings are ; 1. Residents regard safety(from flooding) is the most critical factor to be considered in selection of stream bank materials. 2. They think ideal materials are natural stones or concrete blocks as they look tidy. Concrete retaining walls or vegetated natural slopes are not regarded good. 3. The most preferred material is concrete retaining wall, and the least preferred is vegetated natural slope. They prefer concrete retaining wall which they do not think an ideal material, because it will make a safe bank. 4. Natural stone bank is most preferred for its apperance, and vegetated natural slpoe is most disliked as it may collapse and as it does not look clean.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.176.3-176
• /
• 2001

Hydraulic servo system has the characteristic of high power in itself, as combining its characteristics with excellent electro equipment that comes from the development of electronics, electro-hydraulic servo system is widely used in industry that are requested high precision and power Electro-hydraulic servo system is characteristic of very strong non-linearity in itself and it is mainly applied the field of the inner or outer fluctuating load or disturbance in industry. Evolutionary computation based on the natural evolutionary process may solve many engineering problems. Algorithms can represent the natural selection in crossovers, mutations, production of the offspring, selection, etc. Nature has already shown is the superiority through ...

• Journal of KSNVE
• /
• v.5 no.2
• /
• pp.163-168
• /
• 1995

A criterion for the selection of spindle motor speeds in a hard disk drive (HDD) is investigated to guarantee stability and reduce nonrepeatable runout of a spining disk. Since the natural frequencies of the spining disk and the forced frequencies generated from the spindle motor depend on the rotating speed, careful consideration should be taken to avoid the resonance between the disk and motor. To do this, the natural frequencies of the spining disk are calculated and they are compared with the forced frequencies from the spindle motor.

• Structural Engineering and Mechanics
• /
• v.42 no.3
• /
• pp.425-448
• /
• 2012

In this paper, a new damage detection and quantification method has been presented to perform detection and quantification of structural damage under ambient vibration loadings. To extract modal properties of the structural system under ambient excitation, natural excitation technique (NExT) and eigensystem realization algorithm (ERA) are employed. Sensitivity matrices of the dynamic residual force vector have been derived and used in the parameter subset selection method to identify multiple damaged locations. In the sequel, the steady state genetic algorithm (SSGA) is used to determine quantified levels of the identified damage by minimizing errors in the modal flexibility matrix. In this study, performance of the proposed damage detection and quantification methodology is evaluated using a finite element model of a truss structure with considerations of possible experimental errors and noises. A series of numerical examples with five different damage scenarios including a challengingly small damage level demonstrates that the proposed methodology can efficaciously detect and quantify damage under noisy ambient vibrations.

• Korean Journal of Plant Resources
• /
• v.17 no.1
• /
• pp.54-57
• /
• 2004

These studies were carried out to develop native Calanthe in Korea. Calanthe native to southern islands in Korea has beautiful flowers with various color and sweet fragrance, and it has been reported to have very good ornamental value. According to the morphological characteristics of leaves and flower color, 57 horticultural lines of Calanthe collected in natural crossing group were investigated. And the selected orchid was given a name of horticultural cultivar to ‘Narai’. In its color of flower, sepal was deep purplish red, petal was yellow and lip was white. And also, ‘Narai’ had strong fragrance and shape of blooming was flat-blooming type.