• Journal of the Korean Data and Information Science Society
• /
• v.27 no.1
• /
• pp.111-120
• /
• 2016

In usual, the discontinuous variance function was estimated nonparametrically using a kernel type estimator with data sets split by an estimated location of the change point. Kang et al. (2000) proposed the Gasser-$M{\ddot{u}}ller$ type kernel estimator of the discontinuous regression function using the adjusted observations of response variable by the estimated jump size of the change point in $M{\ddot{u}}ller$ (1992). The adjusted observations might be a random sample coming from a continuous regression function. In this paper, we estimate the variance function using the Nadaraya-Watson kernel type estimator using the adjusted squared residuals by the estimated location of the change point in the discontinuous variance function like Kang et al. (2000) did. The rate of convergence of integrated squared error of the proposed variance estimator is derived and numerical work demonstrates the improved performance of the method over the exist one with simulated examples.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.2
• /
• pp.65-74
• /
• 2013

A research program for the roe deer (Capreolus pygargus) has been set up at the Jeju Experimental Forest of Warm-temperate and Subtropical Forest Research Center in Jeju Island. To explore the home range size and habitat environment, 3 males and 3 females have been captured and released with GPS-CDMA based telemetry since 24th April 2012. Among them 2 females were captured at Hannam Forest of Seoguipo, were pregnant and monitored by the tracking system. There are significantly different patterns in behavior around the parturition. After parturition they show recurrence behavior toward one point in the forest, while they have irregular patterns in moving before. To calculate the home range size, the MCP (minimum convex polygon) and Kernel Method are applied through the extension of ESRI ArcView GIS 3.2a. The pregnant female captured 9th May 2012 has the size of MCP=67ha and Kernel 95%=0.5ha and the pregnant female captured 12th July 2012 has the size of MCP=82ha and Kernel 95%=0.9ha. Although a fawn could move immediately just after the birth likely others to avoid any risks, they stay at very narrow space significantly, and the size become wider when more time goes by. Furthermore, they mainly have a home range away from human activity area such as forest tracking roads. The habitat environment for the parturition is summarized as 40years old cryptomeria forests with new sprouting shrubs for foods, which are the controlled forest through the thinning and removing shrubs 2 years ago. This means that forest works could cause positive results for the parturition and survival of young. The period of parturition is earlier than highland in Jeju Island, the size of home range is narrower than other countries, and the habitat environment of the shelter for a fawn is similar to previous research in other countries.

• Journal of Ecology and Environment
• /
• v.29 no.3
• /
• pp.253-257
• /
• 2006

The objectives of this paper are to estimate home range and core habitat area of wild bores in Jirisan National Park of Korea. A radio-telemetry study was carried out on 5 wild boar individuals (3 females and 2 males). Except one individual whose enough data could not be collected, the mean home range size of 4 individuals was $5.13km^2$ (95% kernel) and mean core habitat area was $1.18{\pm}0.31km^2$ (50% kernel). Home-range sizes of 2 females were $6.21km^2\;and\;5.45km^2$ each, and that of 2 males were $5.15km^2\;and\;3.72km^2$ each, which means home-ranges of female boars were larger than those of male boars in this research. This result is presumed to have been caused by the fact that the males were sub adult individuals weighing 40 kg and 19 kg when they were captured for this research.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.33 no.s01
• /
• pp.1-17
• /
• 1988

Rice Quality is considered to the five catagories ; the nutritional value: the characteristics of cooking. eating and processing: grain size, shape and appearance : milling yields: and storage characteristics. Because most rice is processed and consumed in whole-kernel form. the cooking and eating quality is of important and the physical properties of the intact kernel such as size, shape and general appearance are of particular significance in determining marketing quality. Eating Quality which can be directly evaluated by consumer's panel test is so complicate and variable, and thus the objective and simplified method of evaluation is required of using appropriate instruments. Even though many researches have been done to evaluate the eating quality in various aspects such as the texture of cooked rice kernels, amylogram analysis of rice powder, amylose content. gelatinization temperature. moisture absorption of rice kernel, and cooking characteristics, none of them is satisfied for the evaluation of eating quality. The improving eating quality should be also considered to many cultural factors. such as varieties, climatic and soil conditions, cultural method, handling after harvest. milling and storage conditions. In Korea, many researches in grain size. shape and appearance, and eating quality have been done with the varietal improvement mainly by rice breeders, but no effective method of evaluation was established. A few research have been done in the relationship between rice quality and cultural factors. In the future, research in rice quality should emphasize to establish the standard evaluation method in the physicochemical properties of rice kernels for application of varietal selection. and to develop cultural practices for the preserving quality characteristics of the varieties.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.30 no.4
• /
• pp.460-470
• /
• 1985

Experiments were carried out to evaluate the standard gravity in determining potential kernel size and to determine the effective sampling way by analyzing intra - and inter - plant variations for some source and sink characters using eleven semi-dwarf indica and three japonica cultivars including four semi-dwarf indica nearisogenic lines. Also, additional experiments were conducted to understand yearly variation and variety x year interaction effects for ten characters related to source and sink and to characterize the varietal difference of pre- and post-heading self-competition employing three parental varieties and their F$\sub$5/ progenies in 1982 and 1983. It is desirable to determine the potential kernel size by average kernel wight of rice grains showing above 1.15 specific gravity. There was significant difference in leaf area per tiller, spikelets and sink capacity per panicle among vigorous, intermediate and inferior tillers classified by differentiated order and vigorousness. Although it was difficult to find out any significant difference in grain-fill ratio, ratio of perfectly ripened grain, potential kernel size and sink/source ratio between vigorous and intermediate tillers, there was big difference between them and inferior one. The coefficients of variation within each tiller-group for some characters related to source and sink were larger with the order of vigorous tillers < intermediate one '||'&'||'lt; inferior one, and the average heritability of all characters, evaluated by the ratio of varietal variance (equation omitted) to total variance (equation omitted), were higher with the order of inferior tillers '||'&'||'lt; intemediate one '||'&'||'lt; superior one. Therefore, it is desirable to sample the vigorous tillers to represent the varietal difference of these traits. '82-'83 year variations of three parental cultivars were significant for all traits except for leaf area/tiller, panicles/hill, leaf area index and rough rice yield. The characters showing highly significant variance of variety x year interaction were growth duration from transplanting to heading, leaf area/tiller, sink/source ratio, sink capacity/panicle and grain yield. Generalized yearly response of three parental varieties (Suweon 264, Raegyeong, IR1317-70-l) and their F$\sub$5/ progenies on the 1st and 2nd principal components extracted from ten source and sink characters generally exhibited reduction in both source and sink. However, there were diverse variety x year interactions such as progenies showing similar reaction with their parents and intermediate or recombinational yearly response with little or considerable yearly movement on the four-dimensional planes of the two upper principal components between 1982 and 1983. Sink characters revealing highly significant border effect were grain-fill ratio, spikelets and sink capacity per panicle. Among them the latter two especially showed significant variety x border effect interaction. Self-competition characterized by relative weakness of inside plant's sink characters compared to the border one was more severe during the reproductive stage before heading than maturing stage. Though the larger sink capacity per panicle generally disclosed the severer self-competition, some lines (like Suweon 264) revealed severe self-competition with small sink capacity while a few others showed tender self-competition in spite of big sink capacity per panicle.

• Journal of radiological science and technology
• /
• v.30 no.1
• /
• pp.1-6
• /
• 2007

This study is to decrease compound noise in x-ray films. This study compared Signal to noise ratio(SNR), Peak signal to noise ratio(PSNR), Mean square error(MSE) to surface of the earth. In addition, we evaluated noise elimination effect according to the kernel size of Median filter. This experiments show that some filters are useful by finding image that is near in circle image comparing circle picture with each processed picture. In noise power value, when cutoff frequency was compared with other filters of cutoff frequency. Cutoff frequency of $2/3\pi{\sim}3/4\pi$ is good and it shows good SNR and PSNR. Therefore, it can display high filter effect. As Median Filter's Kernel size grows SNR value gets bigger, which shows better filter effect. Most pictures are distorted after filter application in medical treatment image. It is important to keep spatial resolution in most medical images. Visual estimation as well as quantitative indicators should be necessary for a better image.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.11a
• /
• pp.103-108
• /
• 2002

We consider an estimation of discontinuous variance function in nonparametric heteroscedastic random design regression model. We first propose estimators of a change point and jump size in variance function and then construct an estimator of entire variance function. We examine the rates of convergence of these estimators and give results on their asymptotics. Numerical work reveals that the effectiveness of change point analysis in variance function estimation is quite significant.

• Journal of the Korean Mathematical Society
• /
• v.43 no.3
• /
• pp.635-658
• /
• 2006

This paper is concerned with giving some rather weak size conditions implying the $L^P$ boundedness of the multiple Marcin-kiewicz integrals for some fixed $1\;<\;p\;<\;{\infty}$, which essentially improve and extend some known results.

• Spatial Information Research
• /
• v.16 no.2
• /
• pp.237-247
• /
• 2008

Statistical analysis of the coordinate information is regarded as one of the major GIS functions. Among them, one of the most fundamental analysis is density analysis of point features. For analyzing the density appropriately, determining the search radius, kernel radius, has critical importance. In this study, using L-index, known as its usefulness for choosing the kernel radius in previous researches, radius for density analysis of various point features are estimated, and the behavior of L-index is studied based on the estimated results. As results, L-index is not suitable to determine the search radius for the point features that are evenly distributed with small clusters, because the pattern of the L-index is depends on the size of the study area. But for the point features with small number of highly clustered areas, L-index is suitable, because the pattern of the L-index is not affected by the size of study area.

• The Journal of Information Technology
• /
• v.6 no.3
• /
• pp.65-73
• /
• 2003

The evaluation AP embedded Linux board is implemented. The board is made of IBM 405 GP processor, PPCBoot-1.2.1 boot loader, Linux-2.4.21 kernel and root file system. The evaluation board has two flash memories, boot flash and application flash of size 512Kbyte and 16Mbyte, respectively. And it supports IEEE 802.11a which provide the maximum throughput of 54Mbps in the 5.2GHz frequency band. MTD(Memory Technology Device) and JFFS2(Journalling Flash File System version 2) technologies are adopted to optimally package the system software, boot loader, kernel and root file system. And in order to optimize root file system, busybox package and tiny login are used. Linux kernel and root file system is combined together with mkimage utility.