• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.189-200
• /
• 2015

Stationary bootstrapping is applied to a Lagrangian multiplier (LM) test to test market microstructure noise (MMN) in financial asset prices. A Monte-Carlo experiment shows that the bootstrapping method improves the size of the original LM test which has some size distortion for conditional heteroscedastic models. The proposed test is illustrated for real data sets like KOSPI index and Won-Dollar exchange rate.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.9
• /
• pp.878-886
• /
• 2012

This paper investigates the implementation and flight test of realtime vision guided autopilot system based on virtual instrumentation platform. A graphical design process via virtual instrumentation platform is fully used for the image processing, communication between systems, vehicle dynamics control, and vision coupled guidance algorithms. A significatnt ojective of the algorithm is to achieve an environment robust autopilot despite wind and an irregular image acquisition condition. For a robust vision guided path tracking and hovering performance, the flight path guidance logic is combined in a multi conditional basis with the position estimation algorithm coupled with the vehicle attitude dynamics. An onboard flight test equipped with the developed realtime vision guided autopilot system is done using the rotary UAV system with full attitude control capability. Outdoor flight test demonstrated that the designed vision guided autopilot system succeeded in UAV's hovering on top of ground target within about several meters under geenral windy environment.

• The Korean Journal of Applied Statistics
• /
• v.15 no.1
• /
• pp.187-199
• /
• 2002

When the sample size is small, exact tests are often employed because the asymptotic distribution of the test statistic is in doubt. The advantage of exact tests is that it is guaranteed to bound the type I error probability to the nominal level. In this paper we review the methods of constructing exact tests, the algorithm and commercial software. We also examine the difference between exact p-values obtained from exact tests and true p-values obtained from the true underlying distribution.

• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.435-443
• /
• 2022

In this paper, using Covid-19 diagnostic data provided by the Korea Disease Control and Prevention Agency (KDCA), we examine the probability of confirmed cases and the probability of actually being confirmed when the rapid test is negative according to the sensitivity and specificity of the rapid diagnostic kit. When we know the conditional probability of confirmation given a positive test, we induce the relationship between sensitivity and specificity, and compute the actual sensitivity of the rapid diagnosis kit based on the data of KDCA.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.6
• /
• pp.173-178
• /
• 2008

With the discontinuation of analog broadcasting in 2012, the cable broadcasters are investing in the conversion to DCATV (Digital Cable TV). DCATV is providing various broadcast of high quality to audiences through paid broadcasting called PPV (Pay Per View). Such services are using various kinds of CASs (Conditional Access System) in order to verify the viewing rights of subscriber. In addition, to respond to the fast changing environment of digital broadcast, not only simple digitalization of broadcast but also services such as PVR (Personal Video Recorder) and VOD (Video On Demand) are provided to subscribers. Because these additional services have many difficult areas to cover with traditional CAS alone, a new plan has become necessary. With the improvement of related regulations in 2008, the test service of IPTV (Internet Protocol TV) which is a broadcast service through the internet started. Because like DCATV, IPTV also sets the real time broadcast and the VOD service as the basic services, the use of appropriate CAS is required. In this study, the CASs for DCATV and IPTV undergo comparative analysis, and the development direction which will benefit both subscribers and broadcasting companies is suggested.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.451-456
• /
• 2017

Semantic segmentation, which is the most basic and complicated problem in computer vision, classifies each pixel of an image into a specific object and performs a task of specifying a label. MRF and CRF, which have been studied in the past, have been studied as effective methods for improving the accuracy of pixel level labeling. In this paper, we propose a semantic partitioning method that combines CNN, a kind of deep running, which is in the spotlight recently, and CRF, a probabilistic model. For learning and performance verification, Pascal VOC 2012 image database was used and the test was performed using arbitrary images not used for learning. As a result of the study, we showed better partitioning performance than existing semantic partitioning algorithm.

• Fashion & Textile Research Journal
• /
• v.17 no.3
• /
• pp.392-404
• /
• 2015

This study investigated how the image exaggeration influence consumer attitude toward product in mobile shopping. Image exaggeration was manipulated by adding light effects on image and adjusting the width for slender mirror effect. Subjects were randomly allocated to four mock-mobile website stimuli. The overall results showed that the image exaggeration had negative effect on product attitude mediated by diagnositicity. First, the mediation effect of diagnositicity between exaggeration and product attitude was tested by bootstap method. The diagnositicity fully mediated between two variables and exaggeration had negative total effect on diagnositicity. The image exaggeration had no direct effect on product attitude. Second, to test the moderating effect of image congruence between the image exaggeration and diagnositicity, conditional indirect effect of diagnositicity was analyzed. As a result, the moderating effect of image congruence was significant. When consumers perceived high self-image congruence with picture image on mobile website, the exaggeration had no negative effect on product attitude. This indicates self-image congruence counteracts the negative effect of the exaggeration on diagositicity. And the moderating effect of image aesthetics between the image exaggeration and product attitude was examinated by the conditional direct effect model. The analysis found that image aesthetics had significant moderating effects particularly on high or low levels of aesthetics. When image aesthetics was perceived as high, image exaggeration had negative effect on product attitude, whereas image aesthetics was low, image exaggeration had positive effect on product attitude. This result indicated that the positive exaggeration effects existed when images were aesthetically appealing.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.22 no.51
• /
• pp.199-210
• /
• 1999

The number of car accident is Recently on the increase in Korea because of the explosive increase of cars, the poor road condition, the lack of safety facility, and others. The insurant with a accident has to decide whether receiving a insurance or not. In this paper, we represent a reasonable decision support material by calculating the approximate insurance fee based on the discount rate and premium additive rate, which is changed by the accident type and the accident expenditure. Practically, there is difference in the standard insurance rate and premium additive rate according to the accident type and the accident expenditure in Korea. The premium additive rate is assessed considering the number of accident, the pattern of accident, and the reason of accident for 3 years. In this paper, we represent a decision making method considering not only the first-time car accident but also the future car accident. For considering the repeated accident, we analyzed the real data accumulated until the year of 1996 from S Insurance Company, and estimated the probability density function between the first and the second-time accident, and executed the goodness of fit test using ARENA and STATISTICA software. Using this conditional PDF, we can calculate the insurance fee next 3 years and compare the insurance fee with the equivalent present value of cash flows. The program performing this analysis is represented, and written in VISUAL BASIC Language. We tried to suggest an accurate guideline for the insurant to decide the insurance coverage rationally, and tried to correct a wrong idea of dependence on the car insurance only by the amount of the accident expenditure. And we expect this study can generally be applied to many different accident types under the uncertain circumstances in our daily life.

• Journal of the Korean Society for Library and Information Science
• /
• v.52 no.4
• /
• pp.179-194
• /
• 2018

The purpose of this study is to discuss the application of the Latent Growth Model to measure the outcomes of public library. For outcome measurements, library circulation data were collected to identify longitudinal changes of library users' reading habit. The latent growth model was applied to statistically test the changes over time. The circulation data of 95,962 users registered in some public libraries in Seoul, ranged between 2010 and 2015, were analyzed using unconditional model, conditional model, and growth mixture model which all are called the latent growth model. The results show that the intercept of the model is 4.19 and the slop is 0.24 in the linear growth model. The gender difference in two latent variables including intercept and slop was a shade difference. The result from the growth mixture model analysis, additionally indicates that the number of books checked out by children under age 10 is rapidly increased. The application of the latent growth model in library fields is expected to widely spread out for the longitudinal data analysis.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.