• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.1
• /
• pp.87-94
• /
• 2017

Reliability analysis(RA) and Reliability-based design optimization(RBDO) require statistical modeling of input random variables, which is parametrically or nonparametrically determined based on experimental data. For the parametric method, goodness-of-fit (GOF) test and model selection method are widely used, and a sequential statistical modeling method combining the merits of the two methods has been recently proposed. Kernel density estimation(KDE) is often used as a nonparametric method, and it well describes a distribution function when the number of data is small or a density function has multimodal distribution. Although accurate statistical models are needed to obtain accurate RA and RBDO results, accurate statistical modeling is difficult when the number of data is small. In this study, the accuracy of two statistical modeling methods, SSM and KDE, were compared according to the number of data. Through numerical examples, the RA results using the input models modeled by two methods were compared, and appropriate modeling method was proposed according to the number of data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.75-88
• /
• 2008

This paper presents a spatial-level nonparametric multi-focus image fusion technique based on kernel estimates of input image blocks' underlying class-conditional probability density functions. Image fusion is approached as a classification task whose posterior class probabilities, P($wi{\mid}Bikl$), are calculated with likelihood density functions that are estimated from the training patterns. For each of the C input images Ii, the proposed method defines i classes wi and forms the fused image Z(k,l) from a decision map represented by a set of $P{\times}Q$ blocks Bikl whose features maximize the discriminant function based on the Bayesian decision principle. Performance of the proposed technique is evaluated in terms of RMSE and Mutual Information (MI) as the output quality measures. The width of the kernel functions, ${\sigma}$, were made to vary, and different kernels and block sizes were applied in performance evaluation. The proposed scheme is tested with C=2 and C=3 input images and results exhibited good performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.407-410
• /
• 2009

본 논문에서는 개선된 mean shift를 이용한 컬러 영상 분할을 소개한다. Mean shift는 Yizong Cheng에 의해 재조명되고 Dorin Comaniciu 등에 의해 정리되어 영상 필터링(image filtering), 영상 분할(image segmentation), 물체 추적(object tracking) 등 여러 응용 분야에 널리 활용되고 있다. 커널을 이용해 밀도를 추정하고 밀도가 가장 높은 점으로 커널을 연속적으로 이동함으로써 지역적으로 주요한 위치로 데이터 값을 갱신시킨다. 그러나 영상에 포함된 모든 화소에 대해 mean shift를 수행해야하기 때문에 연산 시간이 많이 소요되는 단점이 있다. 본 논문에서는 mean shift 필터링 과정을 분석하고 참조수렴방법과 강제수렴방법을 이용해 소요 시간을 단축시켰다. 모든 점에 대해 mean shift를 수행하는 대신 특정 조건을 만족하는 픽셀은 이웃 픽셀의 수렴 값을 참조하고, mean shift 과정에 진동 또는 미미한 이동을 계속하는 픽셀은 강제 수렴을 실시하였다. 개선된 방법과 기존의 mean shift 방식을 적용하여 영상 필터링과 영상 분할에 적용한 실험에서 결과 영상에는 차이가 적고 기존의 방법에 비해 수행 시간이 24% 정도 소요됨을 확인하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.531-536
• /
• 2022

This paper compared the performance of the parametric method and the nonparametric method when estimating the distribution for the tail of the distribution with heavy tails. For the parametric method, the generalized extreme value distribution and the generalized Pareto distribution were used, and for the nonparametric method, the kernel density estimation method was applied. For comparison of the two approaches, the results of function estimation by applying the block maximum value model and the threshold excess model using daily fine dust public data for each observatory in Seoul from 2014 to 2018 are shown together. In addition, the area where high concentrations of fine dust will occur was predicted through the return level.

• Communications for Statistical Applications and Methods
• /
• v.15 no.2
• /
• pp.283-292
• /
• 2008

Smoothing parameter or bandwidth plays a key role in nonparametric classification based on kernel density estimation. We consider choosing smoothing parameter in nonparametric classification, which optimize the Bayes risk. Hall and Kang (2005) clarified the theoretical properties of smoothing parameter in terms of minimizing Bayes risk and derived the optimal order of it. Bootstrap method was used in their exploring numerical properties. We compare cross-validation and bootstrap method numerically in terms of optimal order of bandwidth. Effects on misclassification rate are also examined. We confirm that bootstrap method is superior to cross-validation in both cases.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.124-132
• /
• 2011

In a modern electronic warfare, radar signal environments become more denser and complex. Therefor the capability of reliable signal analysis techniques is required for ES(Electronic warfare Support) system to identify and analysis individual emitter signals from received signals. In this paper, we propose the new signal grouping algorithm to ensure the reliable signal analysis and to reduce the cost of the signal processing steps in the ES. The proposed grouping algorithm uses KDE(Kernel Density Estimator) and its CDF(Cumulative Distribution Function) to compose windows considering the statistical distribution characteristics based on the radar frequency modulation type. Simulation results show the good performance of the proposed technique in the signal grouping.

• Environmental and Resource Economics Review
• /
• v.18 no.1
• /
• pp.105-138
• /
• 2009

This study investigates the spatial distribution of the degree of water pollutants in Han River using data obtained by the water pollution observation stations. This study estimates a non -parametric kernel density function for each water pollutants, and tests a significant difference between two estimated distribution functions. Next, Generalized Entropy inequality indices are evaluated and this research tests difference of inequality indices between two years using bootstrapping method. Lastly in a dynamic of view, it is analyzed that there are significant changes in the ranking of water pollution level. Estimation results show that the degree of inequality in spatial distribution of water pollution tends to be stable or decreasing for last 15 years in a great part of water pollutants, and ranking of water pollution level hardly changes in Han River.

• Journal of the Korean Data and Information Science Society
• /
• v.3 no.1
• /
• pp.25-31
• /
• 1992

Some results relating to $C_{0}(R)\;and\;L^{1}(R)$ spaces with application to kernel density estimators will be introduced. First, random elements in $C_{0}(R)\;and\;L^{1}(R)$ are discussed. Then, complete convergence limit theorems are given to show that these results can be used in establishing uniformly consistency and $L^{1}$ consistency.

• Communications for Statistical Applications and Methods
• /
• v.18 no.2
• /
• pp.245-255
• /
• 2011

There are two nonparametric methods that use empirical distribution functions and probability density estimators for the test of the distribution change of data. In this paper we investigate the two methods precisely and summarize the results of previous research. We assume several probability models to make a simulation study of the change point analysis and to examine the finite sample behavior of the two methods. Empirical powers are compared to verify which is better for each model.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.1-11
• /
• 2023

Deep-learning-based image segmentation is one of the most widely employed lane detection approaches, and it requires a post-process for extracting the key points on the lanes. A general approach for key-point extraction is using a fixed threshold defined by a user. However, finding the best threshold is a manual process requiring much effort, and the best one can differ depending on the target data set (or an image). We propose a novel key-point extraction algorithm that automatically adapts to the target image without any manual threshold setting. In our adaptive key-point extraction algorithm, we propose a line-level normalization method to distinguish the lane region from the background clearly. Then, we extract a representative key point for each lane at a line (row of an image) using a kernel density estimation. To check the benefits of our approach, we applied our method to two lane-detection data sets, including TuSimple and CULane. As a result, our method achieved up to 1.80%p and 17.27% better results than using a fixed threshold in the perspectives of accuracy and distance error between the ground truth key-point and the predicted point.