• Korean Journal of Remote Sensing
• /
• v.19 no.6
• /
• pp.465-478
• /
• 2003

This paper presents two methods for automatic estimation of threshold values in unsupervised change detection of multi-temporal remote sensing images. The proposed methods consist of two analytical steps. The first step is to compute the parameters of a 3-component Gaussian mixture model from difference or ratio images. The second step is to determine a threshold value using Bayesian rule for minimum error. The first method which is an extended version of Bruzzone and Prieto' method (2000) is to apply an Expectation-Maximization algorithm for estimation of the parameters of the Gaussian mixture model. The second method is based on an iterative thresholding algorithm that successively employs thresholding and estimation of the model parameters. The effectiveness and applicability of the methods proposed here were illustrated by two experiments and one case study including the synthetic data sets and KOMPSAT-1 EOC images. The experiments demonstrate that the proposed methods can effectively estimate the model parameters and the threshold value determined shows the minimum overall error.

• Composites Research
• /
• v.22 no.6
• /
• pp.18-22
• /
• 2009

In this paper, we examined impact force and impact behavior through low velocity impact tests of composite laminates. And through c-scan as nondestructive inspection, explored the damaged area being difficult to examine with the visual inspection. Through CAI tests, we also measured the compression strength of composite laminates subjected to low velocity impact. To examine the characteristics of impact behavior measured from low velocity impact test, nondestructive inspection, and CAI test, the simulated data are generated from the test data using Monte-Carlo simulation, then represented it by probability distribution. The testing results using visible stochastic distribution were examined and compared.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.2
• /
• pp.94-106
• /
• 2010

Understanding of the amount of energy resources and site selection are required prior to develop Ocean Thermal Energy (OTE). It is necessary to calculate the appearance probability of difference of seawater temperature(${\Delta}T$) between sea surface layer and underwater layers. This research mainly aimed to calculate the appearance probability of ${\Delta}T$ using frequency analysis(FA) and harmonic analysis(HA), and compare the advantages and weaknesses of those methods which has used in the South Sea of Korea. Spatial scale for comparison of two methods was divided into local and global scales related to the estimation of energy resources amount and site selection. In global scale, the Probability Differences(PD) of calculated ${\Delta}T$ from using both methods were created as spatial distribution maps, and compared areas of PD. In local scale, both methods were compared with not only the results of PD at the region of highest probability but also bimonthly probabilities in the regions of highest and lowest PD. Basically, the strong relationship(pearson r=0.96, ${\alpha}$=0.05) between probabilities of two methods showed the usefulness of both methods. In global scale, the area of PD more than 10% was less than 5% of the whole area, which means both methods can be applied to estimate the amount of OTE resources. However, in practice, HA method was considered as a more pragmatic method due to its capability of calculating under various ${\Delta}T$ conditions. In local scale, there was no significant difference between the high probability areas by both methods, showing difference under 5%. However, while FA could detect the whole range of probability, HA had a disadvantage of inability of detecting probability less than 10%. Therefore it was analyzed that the HA is more suitable to estimate the amount of energy resources, and FA is more suitable to select the site for OTE development.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.3
• /
• pp.431-444
• /
• 2013

Widespread use of smartphones and wireless LAN accompany a threat called rogue AP. When a user connects to a rogue AP, the rogue AP can mount the man-in-the-middle attack against the user, so it can easily acquire user's private information. Many researches have been conducted on how to detect a various kinds of rogue APs, and in this paper, we are going to propose an algorithm to identify and detect a rogue AP that impersonates a regular AP by showing a regular AP's SSID and connecting to a regular AP. User is deceived easily because the rogue AP's SSID looks the same as that of a regular AP. To detect this type of rogue APs, we use a machine learning algorithm called SVM(Support Vector Machine). Our algorithm detects rogue APs with more than 90% accuracy, and also adjusts automatically detection criteria. We show the performance of our algorithm by experiments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.4
• /
• pp.11-17
• /
• 2017

Organizations are experiencing an ever-growing concern of how to prevent confidential information leakage from internal employees. Those who have authorized access to organizational data are placed in a position of power that could well be abused and could cause significant damage to an organization. In this paper, we investigate the task of detecting such insider through a method of modeling a user's normal behavior in order to detect anomalies in that behavior which may be indicative of an data leakage. We make use of Hidden Markov Models to learn what constitutes normal behavior, and then use them to detect significant deviations from that behavior. Experiments have been made to determine the optimal HMM parameters and our result shows detection capability of 20% false positive and 80% detection rate.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1231-1235
• /
• 2017

Given the network structure in online social network, it is important to determine a way to distinguish spam accounts from the network features. In online social network, the service provider attempts to detect social spamming to maintain their service quality. However the spammer group changes their strategies to avoid being detected. Even though the spammer attempts to act as legitimate users, certain distinguishable structural features are not easily changed. In this paper, we investigate a way to generate meaningful network structure features, and suggest spammer detection method using recursive structural features. From a result of real-world dataset experiment, we found that the proposed algorithm could improve the classification performance by about 8%.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.8
• /
• pp.661-669
• /
• 2017

This paper describes an MMTI(Maritime Moving Target Indicator) for periscope detection in airborne radar. Firstly, we analyze the characteristics of sea clutter, sea targets. Secondly, we study the differences between GMTI(Ground Moving Target Indicator) and MMTI. This paper proposes an optimal MMTI operating environment and method. We also suggest a signal processing algorithm using STAP(Space-Time Adaptive Processing) for detecting small RCS target moving low speed. The detection probability for moving target with MDV(Minimum Detectable Velocity) is simulated under various RCS and multi-channel system. Finally, we analyze the major performance for range, velocity and azimuth accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.482-482
• /
• 2023

상수도관은 사용년수가 경과함에 따라 노후화가 진행되며, 노후화된 상수관은 내부적으로 부식, 이물질 퇴적, 균열 등의 현상이 발생하게 되고, 이는 결국 수질문제로 연결되어, 탁수사고 발생 확률증가의 주요 원인이 되고 있다. 국내 상수도관의 경우 매설년수의 증가로 인해 내구연한이 도래한 상수관망의 비중이 점차 증가하고 있으며, 2019년 서울시 문래동 수질사고, 2019년 인천 붉은 수돗물 사고, 2022년 안양 동안구 탁수사고, 2022년 여수시 웅천 탁수사고 등 관의 노후화로인한 탁수 사고가 빈번하게 발생되고 있어 수도 사용자에게 불편함을 끼치고 있다. 현재 정수장 및 상수관망에 설치된 탁도계를 통해 수질에 대한 감시를 진행하고 있지만, 경제적인 문제로 인해 모든 상수도관에 탁도계를 설치하기에는 현실적으로 불가능하며, 제한적인 탁도계의 개수를 통해 수질에 대한 감시 및 관리를 진행하고 있는 실정이다. 이러한 상황으로 인해 탁수사고 발생 시 발생 원인분석 및 최초 발생위치 결정이 쉽지 않으며, 보수 보강을 통한 상수도관의 정상화까지 오랜 시간이 걸리게 된다. 이에 본 연구에서는 상수관망에서 탁수 발생 시 최초 발생 위치를 결정할 수 있는 기법을 개발하였으며, 이를 실제 상수도관망에 적용하여 탁수발생 파이프를 탐지하였다. 탁수사고 발생 시 실측된 수질 데이터의 부족으로 인해 임의의 파이프에서 탁수가 발생하였다고 가상의 탁수 발생시나리오를 가정하였으며, 완전혼합농도식을 통해 관망에 설치된 탁도계의 NTU(Nethelometric Paultity Unit) 농도를 계산하여 가상의 탁수발생 시나리오를 상수도관망에 적용하였다. 이후, 역추적 계산기법을 통해 파이프의 초기 NTU 농도를 변화시켜주며 관망내 설치된 탁도계의 NTU 농도를 계산하였으며, 가상 시나리오를 적용하여 계산된 탁도계의 NTU 농도와 역추적 계산법을 적용하여 계산된 탁도계의 NTU 농도의 Percentage Error를 비교/분석하여 탁수 발생 파이프를 탐지하였다. 분석결과, 가상 시나리오의 최초 탁수발생 파이프와 역추적 계산법을 적용하여 탐지한 최초 탁수발생 파이프의 위치가 일치하는 것으로 나타났다. 본 연구에서 개발된 역추적계산을 통한 탁수발생 파이프 탐지기법을 실제 관로 교체사업에 활용한다면 파이프의 개선 우선순위를 보다 명확하게 판단할 수 있으며, 더 나아가 상수도 관망의 유지관리에 활용하여 경제적이고 효율적인 상수관망 시스템관리를 할 수 있을 것으로 판단된다.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.57-64
• /
• 2022

If the inside of a building collapses due to a disaster such as fire, collapse, or natural disaster, the physical security inside the building is likely to become ineffective. Here, physical security is needed to minimize the human casualties and physical damages in the collapsed building. Therefore, this paper proposes an algorithm to minimize the damage in a disaster situation by fusing existing research that detects obstacles and collapsed areas in the building and a deep learning-based object detection algorithm that minimizes human casualties. The existing research uses a single camera to determine whether the corridor environment in which the robot is currently located has collapsed and detects obstacles that interfere with the search and rescue operation. Here, objects inside the collapsed building have irregular shapes due to the debris or collapse of the building, and they are classified and detected as obstacles. We also propose a method to detect rescue requesters-the most important resource in the disaster situation-and minimize human casualties. To this end, we collected open-source disaster images and image data of disaster situations and calculated the accuracy of detecting rescue requesters in disaster situations through various deep learning-based object detection algorithms. In this study, as a result of analyzing the algorithms that detect rescue requesters in disaster situations, we have found that the YOLOv4 algorithm has an accuracy of 0.94, proving that it is most suitable for use in actual disaster situations. This paper will be helpful for performing efficient search and rescue in disaster situations and achieving a high level of physical security, even in collapsed buildings.