• Journal of the Korean Wood Science and Technology
• /
• v.45 no.4
• /
• pp.399-408
• /
• 2017

Research on the rapid and accurate prediction of physical properties of wood using near-infrared (NIR) spectroscopy has attracted recent attention. In this study, partial least squares analysis was performed between NIR spectra and air-dried specific gravity of five domestic conifer species including larch (Larix kaempferi), Korean pine (Pinus koraiensis), red pine (Pinus densiflora), cedar (Cryptomeria japonica), and cypress (Chamaecyparis obtusa). Fifty different lumbers per species were purchased from the five National Forestry Cooperative Federations of Korea. The air-dried specific gravity of 100 knot- and defect-free specimens of each species was determined by NIR spectroscopy in the range of 680-2500 nm. Spectral data preprocessing including standard normal variate, detrend and forward first derivative (gap size = 8, smoothing = 8) were applied to all the NIR spectra of the specimens. Partial least squares analysis including cross-validation (five groups) was performed with the air-dried specific gravity and NIR spectra. When the performance of the regression model was expressed as $R^2$ (coefficient of determination) and root mean square error of calibration (RMSEC), $R^2$ and RMSEC were 0.63 and 0.027 for larch, 0.68 and 0.033 for Korean pine, 0.62 and 0.033 for red pine, 0.76 and 0.022 for cedar, and 0.79 and 0.027 for cypress, respectively. For the calibration model, which contained all species in this study, the $R^2$ was 0.75 and the RMSEC was 0.37.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.159-168
• /
• 2008

Since the term structure of interest rates (TSIR) has longitudinal data, we should consider as input variables both time left to maturity and time simultaneously to get a more useful and more efficient function estimation. However, since the resulting data set becomes very large, we need to develop a fast and reliable estimation method for large data set. Furthermore, it tends to overestimate TSIR because data are correlated. To solve these problems we propose a mixture of weighted least squares support vector machines. We recognize that the estimate is well smoothed and well explains effects of the third stock market crash in USA through applying the proposed method to the US Treasury bonds data.

• Asian-Australasian Journal of Animal Sciences
• /
• v.18 no.10
• /
• pp.1475-1478
• /
• 2005

Statistical analysis was conducted on sow stillbirth traits of three genotypes with 2,400 litters including the Erhualian, Large White and the $F_1$ cross of these two breeds. Number of stillborn piglets per litter in the Erhualian, Large White and the $F_1$ averaged 0.85, 0.31 and 0.70, and percentage born alive averaged 95.0%, 97.0% and 95.5%, respectively. Erhualian sows with a greater litter size also had a higher stillbirth rate. Results of analysis of variance indicated that genotype, parity, farrowing year${\times}$farrowing season interaction and total number born had highly significant effects on both number of stillborn piglets per litter and percentage born alive in sows (p<0.0001). Farrowing year had no significant effect on number of stillborn piglets per litter (p>0.05), and highly significant effect on percentage born alive (p<0.01). Farrowing season had highly significant effects on both number of stillborn piglets per litter and percentage born alive (p<0.01). From parity one to parity ten, least squares means for number of stillborn piglets per litter progressively increased with increasing parity and least squares means for percentage born alive progressively decreased with increasing parity. Sows that farrowed in winter had the highest number of stillborn piglets per litter and the lowest percentage born alive, sows that farrowed in autumn had the lowest number of stillborn piglets per litter and the highest percentage born alive. With increasing total number born, least squares means for number of stillborn piglets per litter markedly increased and least squares means for percentage born alive markedly decreased. Results from analysis of paternal half sibs indicated that the heritabilities for number of stillborn piglets per litter and percentage born alive were 0.110 and 0.124, and the genetic, phenotypic and environmental correlations between them were -0.989, -0.951 and -0.948, respectively. These results indicated that number of stillborn piglets per litter and percentage born alive were traits with the similar genetic background.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2005.05a
• /
• pp.227-232
• /
• 2005

Least squares (${\ell}^2-norm$) solutions of seismic inversion tend to be very sensitive to data points with large errors. The ${\ell}^p-norm$ minimization for $1{\le}p<2$ gives more robust solutions, but usually with higher computational cost. Iteratively reweighted least squares (IRLS) gives efficient approximate solutions of these ${\ell}^p-norm$ problems. I propose a simple way to implement the IRLS method for a hybrid ${\ell}^1/{\ell}^2$ minimization problem that behaves as ${\ell}^2$ fit for small residual and ${\ell}^1$ fit for large residuals. Synthetic and a field-data examples demonstrates the improvement of the hybrid method over least squares when there are outliers in the data.

• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.97-110
• /
• 2006

Since it is well-established that even high quality data tend to contain outliers, one would expect fat? greater reliance on robust regression techniques than is actually observed. But most of all robust regression estimators suffers from the computational difficulties and the lower efficiency than the least squares under the normal error model. The weighted self-tuning estimator (WSTE) recently suggested by Lee (2004) has no more computational difficulty and it has the asymptotic normality and the high break-down point simultaneously. Although it has better properties than the other robust estimators, WSTE does not have full efficiency under the normal error model through the weighted least squares which is widely used. This paper introduces a new approach as called the reweighted WSTE (RWSTE), whose scale estimator is adaptively estimated by the self-tuning constant. A Monte Carlo study shows that new approach has better behavior than the general weighted least squares method under the normal model and the large data.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.228-236
• /
• 2014

Towed array SONAR is deformed because it operates in fluid such as an ocean. It especially undergoes significant change in shape as a towing vessel takes a turn. In this case, beam pattern synthesis of the line array is limited, resulting in degradation in quality such as signal-to-noise ratio. This paper presents a modified two-step least squares algorithm based on the two-step least squares method. The shape of the sea-operated line array formation with the towing vessel changing course(angle) was modeled and the algorithm was subsequently applied. While changing course and location of the main lobe in beam pattern was altered, signal-to-noise ratio of steering beam pattern synthesis was analyzed by algorithm (proposed and others). As a result, the proposed algorithm presented improvement in performance by 2dB compared to other algorithms while forming relatively constant beam pattern.

• Geophysics and Geophysical Exploration
• /
• v.8 no.2
• /
• pp.170-176
• /
• 2005

Recently the velocity stack inversion is having many attentions as an useful way to perform various seismic data processing. In order to be used in various seismic data processing, the inversion method used should have properties such as robustness to noise and parsimony of the velocity stack result. The IRLS (Iteratively Reweighted Least-Squares) method that minimizes ${L_1}-norm$ is the one used mostly. This paper introduce another method, CGG (Conjugate Guided Gradient) method, which can be used to achieve the same goal as the IRLS method does. The CGG method is a modified CG (Conjugate Gradient) method that minimizes ${L_1}-norm$. This paper explains the CGG method and compares the result of it with the one of IRSL methods. Testing on synthetic and real data demonstrates that CGG method can be used as an inversion method f3r minimizing various residual/model norms like IRLS methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.8
• /
• pp.1485-1492
• /
• 1994

In this paper, we design and implement the Combline Bandpass Filters for the satellite transponder by using the least-squares curve-fitting method. The Combline Bandpass Filters are located front of the mixer and behind of it, which is the component of down converter. Comparing with the filters which have $\lambda$/4 resonance length. Combline Filter has wide range of stop-band by using $\lambda$/8. So, it is useful to the satellite transponder owing to its low mass and small size. The filters described are realized as coupled rectangular coaxial transmission lines. The choice of this type is due to the ease of machining and wide variations in coupling coefficients rather than the use of the round rod resonators. We determine 800 MHz bandwidths for the combline bandpass filters. By using Chebyshev filter function, we design and implement 4-pole combline filters.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.12 no.5
• /
• pp.31-38
• /
• 2008

Recently the necessity of time history analyses is increasing for the seismic analyses of a structure, and the seismic design provisions of IBC2003, ASCE and KBC2005 require the use of a minimum of seven earthquake records for the time history analyses. Earthquake records for the time history analyses could be selected from the database of the field-measured earthquake records having similar site conditions with the designed site, or from simulated sites satisfying the design spectrum. However, in this study seven earthquake records were generated using 50 earthquake records, classified as records measured at the rock, in the database of the Pacific Earthquake Research Center (PEER). Seven earthquake records were first selected by the least squares fitting method comparing the scaling factored response spectra with the specified design spectrum, and a family of seven artificial time history earthquake records was ultimately generated by multiplying scaling factors, which were calculated by the least squares fitting method and the SRSS averaging method, to the corresponding selected earthquake records.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.4
• /
• pp.739-748
• /
• 2012

In this paper we propose a mixed effects least squares support vector machine (LS-SVM) for the censored data which are observed from different groups. We use weights by which the randomly right censoring is taken into account in the nonlinear regression. The weights are formed with Kaplan-Meier estimates of censoring distribution. In the proposed model a random effects term representing inter-group variation is included. Furthermore generalized cross validation function is proposed for the selection of the optimal values of hyper-parameters. Experimental results are then presented which indicate the performance of the proposed LS-SVM by comparing with a standard LS-SVM for the censored data.