• Journal of Environmental Impact Assessment
• /
• v.28 no.6
• /
• pp.580-591
• /
• 2019

This study analyzed roadkill hotspots in Yeongju, Mungyeong-si Andong-si and Cheongsong-gun to compare the method of searching the area of the spatial cluster for selecting the roadkill hotspots. The local spatial autocorrelation index Getis-Ord Gi* statistics were calculated by different units of analysis, drawing hotspot areas of 9% from 300 m and 14% from 1 km on the basis of the total road area. The rating of Z-score in the 1km hotspot area showed the highest Z-score in the 28th National Road section on the border between Yecheon-gun and Yeongj-si. The kernel density method performed general kernel density estimation and network kernel density estimation analysis, both of which made it easier to visualize roadkill hotspots than district unit analysis, but there were limitations that it was difficult to determine statistically significant priority. As a result, local hotspot areas were found to be different according to the cluster analysis method, and areas that are in common need of reduction measures were found to be the hotspot of 28th National Road through Yeongju-si and Yecheon-gun. It is deemed that the results of this study can be used as basic data when identifying roadkill hotspots and establishing measures to reduce roadkill.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.4
• /
• pp.765-775
• /
• 2012

The cross-validation is a popular method to select bandwidth in all types of kernel estimation. The maximum likelihood cross-validation, the least squares cross-validation and biased cross-validation have been proposed for bandwidth selection in kernel density estimation. In the case that the probability density function has a discontinuity point, Huh (2012) proposed a method of bandwidth selection using the maximum likelihood cross-validation. In this paper, two forms of cross-validation with the one-sided kernel function are proposed for bandwidth selection to estimate the location and jump size of the discontinuity point of density. These methods are motivated by the least squares cross-validation and the biased cross-validation. By simulated examples, the finite sample performances of two proposed methods with the one of Huh (2012) are compared.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.3
• /
• pp.173-181
• /
• 2019

To estimate probabilistic distribution function from experimental data, kernel density estimation(KDE) is mostly used in cases when data is insufficient. The estimated distribution using KDE depends on bandwidth selectors that smoothen or overfit a kernel estimator to experimental data. In this study, various bandwidth selectors such as the Silverman's rule of thumb, rule using adaptive estimates, and oversmoothing rule, were compared for accuracy and conservativeness. For this, statistical simulations were carried out using assumed true models including unimodal and multimodal distributions, and, accuracies and conservativeness of estimating distribution functions were compared according to various data. In addition, it was verified how the estimated distributions using KDE with different bandwidth selectors affect reliability analysis results through simple reliability examples.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.3
• /
• pp.221-230
• /
• 2016

To establish objective criteria for high pedestrian accident zones, we combined Getis-ord Gi* and Kernel Density Estimation to select high pedestrian accident zones for 54,208 pedestrian accidents in Seoul from 2009 to 2013. By applying Getis-ord Gi* and considering spatial patterns where pedestrian accident hot spots were clustered, this study identified high pedestrian accident zones. The research examined the microscopic distribution of accidents in high pedestrian accident zones, identified the critical hot spots through Kernel Density Estimation, and analyzed the inner distribution of hot spots by identifying the areas with high density levels.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.135-142
• /
• 2016

Visual analysis of spatiotemporal data has focused on a variety of techniques for analyzing and exploring the data. The goal of these techniques is to explore the spatiotemporal data using time information, discover patterns in the data, and analyze spatiotemporal data. The overall trend flow patterns help users analyze geo-referenced temporal events. However, it is difficult to extract and visualize overall trend flow patterns using data that has no trajectory information for movements. In order to visualize overall trend flow patterns, in this paper, we estimate continuous distributions of discrete events over time using KDE, and we extract vector fields from the continuous distributions using the gravity model. We then apply our technique on twitter data to validate techniques.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.561-566
• /
• 2021

The optimum kernel size for error-distribution estimation with given error samples cannot be used in the weight adjustment of minimum Euclidean distance between error distributions (MED) algorithms. In this paper, a new adaptive kernel estimation method for convergence enhancement of MED algorithms is proposed. The proposed method uses the average rate of change in error power with respect to a small interval of the kernel width for weight adjustment of the MED learning algorithm. The proposed kernel adjustment method is applied to experiments in communication channel compensation, and performance improvement is demonstrated. Unlike the conventional method yielding a very small kernel calculated through optimum estimation of error distribution, the proposed method converges to an appropriate kernel size for weight adjustment of the MED algorithm. The experimental results confirm that the proposed kernel estimation method for MED can be considered a method that can solve the sensitivity problem from choosing an appropriate kernel size for the MED algorithm.

• Journal of IKEEE
• /
• v.13 no.4
• /
• pp.1-7
• /
• 2009

A video segmentation algorithm, which can extract objects even with non-stationary backgrounds, is proposed in this work. The proposed algorithm is composed of three steps. First, we perform an initial segmentation interactively to build the probability density functions of colors per each macro block via kernel density estimation. Then, for each subsequent frame, we construct a coherence strip, which is likely to contain the object contour, by exploiting spatio-temporal correlations. Finally, we perform the segmentation by minimizing an energy function composed of color, coherence, and smoothness terms. Experimental results on various test sequences show that the proposed algorithm provides accurate segmentation results.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.426-428
• /
• 2022

해상 교통량을 정량적으로 평가하고 추출하기 위한 방법으로 선박 AIS 데이터 기반의 밀집도 분석을 활용하고 있다. 밀집도는 단위시간 당 단위면적에 분포하는 선박 통항량을 계산한 것으로, 일반적으로 그리드 셀 내에 존재하는 선박 항적 포인트 개수, 항적도 라인 길이, 선박 척수 등을 계산한 밀집도 분석 방법과 커널 밀도 추정(Kernel Density Estimation) 방법 등이 있다. 하지만, AIS 데이터의 특징상 선박 속력에 따라 수신 주기가 다르기 때문에 항적이 등간격으로 나타나지 않는 문제점이 있으며, 선박의 이동과 시간의 속성으로 인해 각각의 밀집도 분석 방법은 한계점이 존재한다. 따라서 본 연구에서는 실측 AIS 데이터를 이용하여 다양한 방법의 선박 밀집도 분석을 수행하고 이를 비교하였다. 그 결과, 항적도 라인 길이에 의한 밀집도 분석이 가장 정량적인 방법으로 나타났으며 이를 통항 척수로 변환할 수 있는 선박 밀집도 분석을 개선방안으로 제안한다.

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.6-13
• /
• 2024

This paper proposes an approach to detect abnormal data in automotive controller area network (CAN) using an unsupervised learning model, i.e. autoencoder and Gaussian kernel density estimation function. The proposed autoencoder model is trained with only message ID of CAN data frames. Afterwards, by employing the Gaussian kernel density estimation function, it effectively detects abnormal data based on the trained model characterized by the optimally determined number of frames and a loss threshold. It was verified and evaluated using four types of attack data, i.e. DoS attacks, gear spoofing attacks, RPM spoofing attacks, and fuzzy attacks. Compared with conventional unsupervised learning-based models, it has achieved over 99% detection performance across all evaluation metrics.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.