• Journal of Korean Port Research
• /
• v.12 no.1
• /
• pp.55-64
• /
• 1998

Directed graphic algorithm was applied to an empirical analysis of traffic occupant fatalities based on a model by Crandall. In this paper, Crandall's data on U.S. traffic fatalities for the period 1947-1981 are focused and extended to include 1982-1993. Based on the 1947-1981 annual data, the directed graph algorithms reveal that occupant traffic deaths are directly caused by income, vehicle miles, and safety devices. Vehicle mileage is caused by income and rural driving. The estimation is conducted using three stage least squares regression. Those results show a difference between the traditional regression methodology and causal graphical analysis. It is also found that forecasts from the directed graph based model outperform forecasts from the regression-based models, in terms of mean squared forecasts error. Furthermore, it is demonstrates that there exists some latent variables between all explanatory variables and occupant deaths.

• The Korean Journal of Applied Statistics
• /
• v.25 no.3
• /
• pp.403-413
• /
• 2012

The modifications suggested in Uhm et al. (2011) are studied using a partly parametric version of Aalen's additive risk model. A follow-up time period is partitioned into intervals, and hazard functions are estimated as a piecewise constant in each interval. A maximum likelihood estimator by iteratively reweighted least squares and variance estimates are suggested based on the model as well as evaluated by simulations using mean square error and a coverage probability, respectively. In conclusion the modifications are needed when there are a small number of uncensored deaths in an interval to estimate the piecewise constant hazard function.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.69-72
• /
• 1999

In this paper, an efficient time domain equalization algorithm for discrete wavelet multitone(DWMT) data transmission is developed. In this algorithm, the time domain equalizer(TEQ) consists of two stages, i.e., the channel impulse response shortening equalizer(TEQ-S) in the first stage and the channel frequency flattening equalizer(TEQ-F) in the second stage. TEQ-S reduces the length of transmission channel impulse response to decrease intersymbol interference(ISI) followed by TEQ-F that enhances the channel frequency response characteristics to the level of an ideal channel, hence diminishes the bit error rate. TEQ-S is implemented using the least-squares(LS) method, while TEQ-F is designed by using the least mean-square(LMS) algorithm. Since DWMT system also requires of the frequency domain equalizer in order to further reduce ICI and ISI the hardware complexity is an another concern. However, by adopting an well designed and trained TEQ, the hardware complexity of the whole DWMT system can be greatly reduced.

• Communications for Statistical Applications and Methods
• /
• v.23 no.2
• /
• pp.105-117
• /
• 2016

In the paper, as a sequence of the first tutorial, we discuss sufficient dimension reduction methodologies used to estimate central subspace (sliced inverse regression, sliced average variance estimation), central mean subspace (ordinary least square, principal Hessian direction, iterative Hessian transformation), and central $k^{th}$-moment subspace (covariance method). Large-sample tests to determine the structural dimensions of the three target subspaces are well derived in most of the methodologies; however, a permutation test (which does not require large-sample distributions) is introduced. The test can be applied to the methodologies discussed in the paper. Theoretical relationships among the sufficient dimension reduction methodologies are also investigated and real data analysis is presented for illustration purposes. A seeded dimension reduction approach is then introduced for the methodologies to apply to large p small n regressions.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.4
• /
• pp.437-444
• /
• 2009

A bi-directional, multi-step numerical integrator is developed to determine the GPS (Global Positioning System) orbit based on a dynamic approach, which shows micrometer-level accuracy at GPS altitude. The acceleration due to the planets other than the Moon and the Sun is so small that it is replaced by the empirical forces in the Solar Radiation Pressure (SRP) model. The satellite orbit parameters are estimated with the least-squares adjustment method using both the integrated orbit and the published IGS (International GNSS Service) precise orbit. For this estimation procedure, the integration should be applied to the partial derivatives of the acceleration with respect to the unknown parameters as well as the acceleration itself. The accuracy of the satellite orbit is evaluated by the RMS (Root Mean Squares error) of the residuals calculated from the estimated orbit parameters. The overall RMS of orbit error during March 2009 was 5.2 mm, and there are no specific patterns in the absolute orbit error depending on the satellite types and the directions of coordinate frame. The SRP model used in this study includes only the direct and once-per-revolution terms. Therefore there is errant behavior regarding twice-per-revolution, which needs further investigation.

• Journal of Biosystems Engineering
• /
• v.33 no.6
• /
• pp.430-437
• /
• 2008

Optical diffuse reflectance sensing in visible and near-infrared wavelength ranges is one approach to rapidly quantify soil properties for site-specific management. The objectives of this study were to investigate effects of preprocessing of reflectance data and determine the accuracy of the reflectance approach for estimating physical and chemical properties of selected Missouri and Illinois, USA surface soils encompassing a wide range of soil types and textures. Diffuse reflectance spectra of air-dried, sieved samples were obtained in the laboratory. Calibrations relating spectra to soil properties determined by standard methods were developed using partial least squares (PLS) regression. The best data preprocessing, consisting of absorbance transformation and mean centering, reduced estimation errors by up to 20% compared to raw reflectance data. Good estimates ($R^2=0.83$ to 0.92) were obtained using spectral data for soil texture fractions, organic matter, and CEC. Estimates of pH, P, and K were not good ($R^2$ < 0.7), and other approaches to estimating these soil chemical properties should be investigated. Overall, the ability of diffuse reflectance spectroscopy to accurately estimate multiple soil properties across a wide range of soils makes it a good candidate technology for providing at least a portion of the data needed in site-specific management of agriculture.

• Korean Journal of Poultry Science
• /
• v.20 no.4
• /
• pp.197-201
• /
• 1993

The objective of this study was to investigate the effects of hatch and sex on the body weight and shank length of growing pheasant. Least squares means of body weight at the age of 0, 4, 8, 12, 16 and 20 wks were 17.9, 96.0, 296.4, 563.4, 709.0 and 757.4 g for female, and 18.3, 104.4, 349.1, 728.5, 1001.4 and 1101.6 g for male, respectively. The hatch effect on body weight was significant at the age of 4, 8, 12 and 16 wks (P＜0.05), but the effects on shank length were significant at the age of birth and 8 wks only. There was no significant hatch effect on both the body weight and shank length at the age of 20 wks(P＞0.05). Least squares mean differences between female and male were significant(P＜0.01) over all wks of age except at hatch.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3
• /
• pp.38-44
• /
• 1997

In this study, wer derived LMF-Sato, LMSF-Sato complex blind equalization algorithms for complex data. And then, the convergence rates, the convergence characteristics at the steady state and the stability of the proposed LMF and LMSF blind equalization algorithms are compared with those of LMS-Sato blind equalization algorithm. In simulations with 16-QAM data, LMF-Sato and LMSF-Sato algorithms showed better performance comparing with LMS-Sato algorithm generally. When the initial estimation errors of the weights of the equalizer are large, LMF-Sato algorithm showed ill characteristic in stability. However, LMSF-Sato algorithm has good covergence characteristics and preserves robustness.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5C
• /
• pp.673-682
• /
• 2004

The adaptive beam-forming is promising approach for noise reduction in hearing aids. This approach has come in the focus of interest only recently, because of the availability of new and powerful digital signal processors. The adaptation U using usually a Least Mean Squares algorithm, updates the weight vector. In this Paper, we propose a fast wavelet based adaptive algorithm using variable step size algorithm which varies adaptive constant by the change of signal environment. We compared the performance of the proposed algorithm with the known adaptive algorithm using computer simulation of multi channel adaptive bemformer in hearing aids. As the result the proposed algorithm is suitable for adaptive signal processing area using hearing aids and has advantages reducing computational complexity. And we show the beam-forming system using proposed algorithm converges stably in a sudden change of system environment.

• Korean Management Science Review
• /
• v.11 no.2
• /
• pp.133-146
• /
• 1994

This study compares the performance of neural networks and ordinary least squares regression with quality-control processes. We examine the applicability of neural networks because they do not require any assumptions regarding either the functional from of the underlying process or the distribution of errors. The coefficient of determination($R^2$), mean absolute deviation(MAD), and the mean squared error(MSE) metrics indicate that neural networks are a viable and can be a superior technique. We also demonstrate that an assessment of the magnitude of the neural notwork input layer cumulative weights can be used to determine the relative importance of predictor variables.