• Journal of Korea Water Resources Association
• /
• v.39 no.12 s.173
• /
• pp.997-1012
• /
• 2006

We have presented a nonparametric stochastic approach for the SOI(Southern Oscillation Index) series that used nonlinear methodology called Nonlinear AutoRegressive(NAR) based on conditional kernel density function and CAFPE(Corrected Asymptotic Final Prediction Error) lag selection. The fitted linear AR model represents heteroscedasticity, and besides, a BDS(Brock - Dechert - Sheinkman) statistics is rejected. Hence, we applied NAR model to the SOI series. We can identify the lags 1, 2 and 4 are appropriate one, and estimated conditional mean function. There is no autocorrelation of residuals in the Portmanteau Test. However, the null hypothesis of normality and no heteroscedasticity is rejected in the Jarque-Bera Test and ARCH-LM Test, respectively. Moreover, the lag selection for conditional standard deviation function with CAFPE provides lags 3, 8 and 9. As the results of conditional standard deviation analysis, all I.I.D assumptions of the residuals are accepted. Particularly, the BDS statistics is accepted at the 95% and 99% significance level. Finally, we split the SOI set into a sample for estimating themodel and a sample for out-of-sample prediction, that is, we conduct the one-step ahead forecasts for the last 97 values (15%). The NAR model shows a MSEP of 0.5464 that is 7% lower than those of the linear model. Hence, the relevance of the NAR model may be proved in these results, and the nonparametric NAR model is encouraging rather than a linear one to reflect the nonlinearity of SOI series.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.985-986
• /
• 2008

In this paper, we introduce a novel variant of LDA for face renition. The proposed method is derived by regularizing the eigenvalue of nonlinear LDA. We evaluated the proposed method using AR face database, and it showed outstanding and stable performance over the preceding LDA variants.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.9A
• /
• pp.2333-2344
• /
• 1998

We present a two step approach for estimating the motionand sturcture parameters from region orrespondences in two frames. Given four or more region corresondences on the same planar surface, the motion and planar orientation parameters are first linearly estimated based on second-order approximation of the displacement field of the image plane. Then, using this linear estimate as an initial guess, a nonlinear estimate is obtained by iteratively minimizing an objective function using the exact experession of the displacement field. The objective function involves the centroids of corresponding regions and relationships among low-order moments. Through simulations, we show that the two-step region-based approach gives robust estimates. The performance of nonlinear region-based estimation is compared with that of linear region-based and point-based methods. Experimental results for two image pairs, on esynthetic and one real, ar epresented to show the practical applicability of our approach.

• ETRI Journal
• /
• v.31 no.6
• /
• pp.675-679
• /
• 2009

$Ti_xSi_{1-x}O_y$ (TSO) thin films are fabricated using plasma-enhanced atomic layer deposition. The Ti content in the TSO films is controlled by adjusting the sub-cycle ratio of $TiO_2$ and $SiO_2$. The refractive indices of $SiO_2$ and $TiO_2$ are 1.4 and 2.4, respectively. Hence, tailoring of the refractivity indices from 1.4 to 2.4 is feasible. The controllability of the refractive index and film thickness enables application of an antireflection coating layer to TSO films for use as a thin film solar cell. The TSO coating layer on an Si wafer dramatically reduces reflectivity compared to a bare Si wafer. In the measurement of the current-voltage characteristics, a nonlinear coefficient of 13.6 is obtained in the TSO films.

• Journal of the Korean Statistical Society
• /
• v.30 no.1
• /
• pp.31-39
• /
• 2001

For estimating parameters of possibly nonlinear and/or non-stationary seasonal autoregressive(AR) processes, we introduce a new instrumental variable method which use the direction vector of the regressors in the same period as an instrument. On the basis of the new estimator, we propose new seasonal random walk tests whose limiting null distributions are standard normal regardless of the period of seasonality and types of mean adjustments. Monte-Carlo simulation shows that he powers of he proposed tests are better than those of the tests based on ordinary least squares estimator(OLSE).

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.2
• /
• pp.62-66
• /
• 1986

Ion beam etching of silicon with N2 and Ar gas has been found to cause the band edge to bend downward near the surface in p-type silicon. Rectifying, rather than ohmic contacts are obtained on the structures formed by evaporation of gold and titanium onto ion-bean-etched p-type silicon. The 1/C2 versus V relationship measured at 1MHz is found to be nonlinear for small voltages indicating alteration of the effective doping colse to the silicon surface.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.04a
• /
• pp.583-586
• /
• 2000

In this paper, the embedded crack approach that crack is modeled by discontinuous line inside finite element is applied for localized progressive fracture analyses. The algorithm for progressive fracture analyses of concrete structure are enhanced by introducing nonlinear softening curve and unloading algorithm of tension-softening curve which can simulate localized fracture of concrete. The failure analysis results ar compared with existing test results for varification.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.821-830
• /
• 2006

This paper develops support vector based fuzzy linear and nonlinear regression models and applies it to forecasting the exchange rate. We use the result of Tanaka(1982, 1987) for crisp input and output. The model makes it possible to forecast the best and worst possible situation based on fewer than 50 observations. We show that the developed model is good through real data.

• Journal of Korean Elementary Science Education
• /
• v.40 no.1
• /
• pp.22-35
• /
• 2021

In order to investigate the trends in science education research using AR (Augmented Reality) and derive implications for elementary science education, we analyzed 71 research articles on AR application in science education published in both Korea and abroad from 2010 to August 2020. In quantitative aspects, the number of published articles has steadily increased. For domestic researches, the number of papers targeting for elementary school students was higher than that of middle & high school students. In the research method aspects, qualitative methods were most frequently used. In particular, papers regarding the development of AR program and verification of its effectiveness were most frequently published. The researches using mixed method in domestic field were smaller in number than that of the research in abroad. There were similar trends in research targeting elementary school students. In the aspects of the contents, more researches were performed on biology and earth science areas than others. In case of researches for elementary school students, the proportion of researches on biology and earth science was even higher. Domestically the proportion of studies on the convergence of science and non-science subjects was higher than that of foreign studies. The number of researches exploring the effectiveness on 'non-scientific attitude domain', 'cognitive domain', and 'program domain' were relatively higher than that on 'inquiry & practice domain' and 'science-related attitude domain'. For types of AR contents, 'observation manipulation type' was mostly studied, followed by 'experimental activity type', and 'learning guide type'. In case of studies on elementary school students, the ratio of 'observation manipulation type' contents was higher than that of others, whereas studies on 'field problem solving type' were relatively less reported than others. In addition, studies on 'simple interaction' were most frequently reported. Particularly, there were relatively few studies on 'linear and nonlinear interactions' in domestic field. As a result of analyzing key words, we found that the key words related to the characteristics and implementation of AR frequently occurred, and the key words related to elementary education and the merits of AR had many direct connections with other key words.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).