• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.91-92
• /
• 2021

최근 사물 인터넷 관련 해킹 우려 신고 건수가 증가하는 추세를 보이고 있다. 하지만 급격하게 늘어나는 IoT 환경에 따라서 관리자가 새로운 침입 탐지 공격패턴을 인식하는 것에 대한 어려움이 있으며, 대량의 공격이나 새로운 공격패턴이 등장할 경우 이에 맞는 특징을 재선정해야 할 경우도 발생한다. 본 논문에서는 운영 네트워크 상에 특정이상동작 파악 및 근원지 진단을 위한 목적을 가진 전반적인 네트워크 상태 분석 및 사용자 이슈 식별이 가능한 프레임워크를 설계하였다.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.5
• /
• pp.1119-1128
• /
• 2024

This study developed an anomaly detection algorithm for underground hydrogen pipelines using Distributed Acoustic Sensing (DAS) and Distributed Temperature Sensing (DTS) technologies. The LSTM-AE-based algorithm was tested in a real-world testbed, showing high performance in detecting third-party construction activities and gas leaks. The model achieved 99.86% accuracy, 100% precision, 99.74% recall, and a 99.87% F1 score for DAS data, and 99.95% accuracy, 100% precision, 95.24% recall, and a 97.44% F1 score for DTS data. These results demonstrate the algorithm's effectiveness in real-time monitoring and its potential to enhance the safety of hydrogen pipeline infrastructure. Future research will focus on optimizing the algorithm for broader applications.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.153-159
• /
• 2019

Respiration is one of the important vital signs to determine the condition of the patient. Especially during deep sedation, since the patient's apnea and hypopnea are difficult to detect without continuous monitoring, there is a need for a continuous respiration monitoring method that can accurately and simply determine the patient's respiratory condition. Currently, respiration monitoring methods using various devices have been developed, but these methods have not only late response time but also low reliability at the clinical stage. In this study, attachable sensor using PVDF(polyvinylidene fluoride) film and a monitoring device which could detect abnormal symptoms of breathing in early stage during deep sedation. The results of this study can be used in various medical fields including not only in the area of remote monitoring for respiration related sleep monitoring but also in routine monitoring during deep sedation.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.507-518
• /
• 2006

The radiation at $11{\mu}m$ absorbed more than at $12{\mu}m$ when aerosols is loaded in the atmosphere, whereas it will be the other way around when cloud is present. The difference of the two channels provides an opportunity to detect aerosols such as Yellow Sand even with the presence of clouds and at night. However problems associated with this approach arise because the difference can be affected by various atmospheric and surface conditions. In this paper, we has analyzed how the threshold and sensitivity of the brightness temperature difference between two channel (BTD) vary with respect to the conditions in detail. The important finding is that the threshold value for the BTD distinguishing between aerosols and cloud is $0.8^{\circ}K$ with the US standard atmosphere, which is greater than the typical value of $0^{\circ}K$. The threshold and sensitivity studies for the BTD show that solar zenith angle, aerosols altitude, surface reflectivity, and atmospheric temperature profile marginally affect the BTD. However, satellite zenith angle, surface temperature along with emissivity, and vertical profile of water vapor are strongly influencing on the BTD, which is as much as of about 50%. These results strongly suggest that the aerosol retrieval with the BTD method must be cautious and the outcomes must be carefully calibrated with respect to the sources of the error.

• Journal of Korea Water Resources Association
• /
• v.57 no.3
• /
• pp.181-193
• /
• 2024

The increasing atmospheric imbalance caused by climate change leads to an elevation in precipitation, resulting in a heightened frequency of flooding. Consequently, there is a growing need for technology to detect and monitor these occurrences, especially as the frequency of flooding events rises. To minimize flood damage, continuous monitoring is essential, and flood areas can be detected by the Synthetic Aperture Radar (SAR) imagery, which is not affected by climate conditions. The observed data undergoes a preprocessing step, utilizing a median filter to reduce noise. Classification techniques were employed to classify water bodies and non-water bodies, with the aim of evaluating the effectiveness of each method in flood detection. In this study, the Otsu method and Support Vector Machine (SVM) technique were utilized for the classification of water bodies and non-water bodies. The overall performance of the models was assessed using a Confusion Matrix. The suitability of flood detection was evaluated by comparing the Otsu method, an optimal threshold-based classifier, with SVM, a machine learning technique that minimizes misclassifications through training. The Otsu method demonstrated suitability in delineating boundaries between water and non-water bodies but exhibited a higher rate of misclassifications due to the influence of mixed substances. Conversely, the use of SVM resulted in a lower false positive rate and proved less sensitive to mixed substances. Consequently, SVM exhibited higher accuracy under conditions excluding flooding. While the Otsu method showed slightly higher accuracy in flood conditions compared to SVM, the difference in accuracy was less than 5% (Otsu: 0.93, SVM: 0.90). However, in pre-flooding and post-flooding conditions, the accuracy difference was more than 15%, indicating that SVM is more suitable for water body and flood detection (Otsu: 0.77, SVM: 0.92). Based on the findings of this study, it is anticipated that more accurate detection of water bodies and floods could contribute to minimizing flood-related damages and losses.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.922-929
• /
• 2022

Purpose: The purpose of this paper is to develop a deep learning model to detect fire extinguishers in images taken from CCTVs in underground utility tunnels. Method: Various fire extinguisher images were collected for detection of fire extinguishers in the running-based underground utility tunnel, and a model applying the One-stage Detector method was developed based on the CNN algorithm. Result: The detection rate of fire extinguishers photographed within 10m through CCTV video in the underground common area is over 96%, showing excellent detection rate. However, it was confirmed that the fire extinguisher object detection rate drops sharply at a distance of 10m or more, in a state where it is difficult to see with the naked eye. Conclusion: This paper develops a model for detecting fire extinguisher objects in underground common areas, and the model shows high performance, and it is judged that it can be used for underground common area digital twin model synchronizing.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.247-252
• /
• 2007

오늘날 컴퓨팅 환경은 점차 복잡해지고 있으며, 복잡한 환경을 관리하는 이 점차 중요해 지고 있다. 이러한 관리를 위해 어플리케이션의 내부 구조를 드러내지 않은 상태에서 환경에 적응하는 자가치유에 관한 연구가 중요한 이슈가 되고 있다. 우리의 이전 연구에서는 자가 적응 모듈의 성능 향상을 위해 스위치를 사용하여 컴포넌트의 동작 유무를 결정하였다. 그러나 바이러스와 같은 외부 상황에 의해 자가 적응 모듈이 정상적으로 동작하지 않을 수 있으며 다수의 파일을 전송할 때 스위치가 꺼진 컴포넌트들은 메모리와 같은 리소스를 낭비한다. 본 연구에서는 이전 연구인 성능 개선 자가 적응 모듈에서 발생할 수 있는 문제점을 해결하기 위한 방법을 제안한다. 1) 컴포넌트의 동작 여부를 결정하는 스위치를 확인하여 비정상 상태인 컴포넌트를 찾아 치유를 하고, 2) 현재 단계에서 사용하지 않는 컴포넌트를 다른 작업에서 재사용한다. 이러한 제안 방법론을 통해 파일 전송이 않은 상황에서도 전체 컴포넌트의 수를 줄일 수 있으며 자가 적응 제어 모듈을 안정적으로 작동할 수 있도록 한다. 본 논문에서는 명가를 위하여 비디오 회의 시스템 내의 파일 전송 모듈에 제안 방법론을 적용하여 이전 연구의 모듈과 제안 방법론을 적용한 모듈이 미리 정한 상황들에서 정상적으로 적응할 수 있는지를 비교한다. 또한 파일 전송이 많은 상황에서 제안 방법론을 적용하였을 때 이전 연구 방법론과의 컴포넌트 수를 비교한다. 이를 통해 이전 연구의 자가 적응 모듈의 비정상 상태를 찾아낼 수 있었고, 둘 이상의 파일 전송이 이루어 질 때 컴포넌트의 재사용을 통해 리소스의 사용을 줄일 수 있었다.위해 잡음과 그림자 영역을 제거한다. 잡음과 그림자 영역을 제거하면 구멍이 발생하거나 실루엣이 손상되는 문제가 발생한다. 손상된 정보는 근접한 픽셀이 유사하지 않을 때 낮은 비용을 할당하는 에너지 함수의 스무드(smooth) 항에 의해 에지 정보를 기반으로 채워진다. 결론적으로 제안된 방법은 스무드 항과 대략적으로 설정된 데이터 항으로 구성된 에너지 함수를 그래프 컷으로 전역적으로 최소화함으로써 더욱 정확하게 목적이 되는 영역을 추출할 수 있다.능적으로 우수한 기호성, 즉석에서 먹을 수 있는 간편성, 장기저장에 의한 식품 산패, 오염 및 변패 미생물의 생육 등이 발생하지 않는 우수한 생선가공, 저장방법, 저가 생선류의 부가가치 상승 등 여러 유익한 결과를 얻을 수 있는 효과적인 가공방법을 증명하였다.의 평균섭취량에도 미치지 못하는 매우 저조한 영양상태를 보여 경제력, 육체적 활동 및 건강상태 등이 매우 열악한 이들 집단에 대한 질 좋은 영양서비스의 제공이 국가적 차원에서 시급히 재고되어야 할 것이다. 연구대상자 특히 배달급식 대상자의 경우 모집의 어려움으로 인해 적은 수의 연구대상자의 결과를 보고한 것은 본 연구의 제한점이라 할 수 있다 따라서 본 연구결과를 바탕으로 좀 더 많은 대상자를 대상으로 한 조사 연구가 계속 이루어져 가정배달급식 프로그램의 개선을 위한 유용한 자료로 축적되어야 할 것이다.상범주로 회복함을 알수 있었고 실험결과 항암제 투여후 3 일째 피판 형성한 군에서 피판치유가 늦어진 것으로 관찰되어 인체에서 항암 투여후 수술시기는 인체면역계가 회복하는 시기를 3주이상 경과후 적어도 4주째 수술시기를 정하는 것이 유리하리라 생각되

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.31 no.1
• /
• pp.54-62
• /
• 1995

In order to telemeter the behavior and distribution of fishes. the telesounder was manufactured and it was examined to verify its performance and effects in the gape nets with wings located around Gokunsan islands. Yellow Sea. on August 8. 18~19 and September 8~9, 1994. The behavior of fish entering the net was observed with the buoy station at sea which was installed at the entrance of the gape nets with wing and its echosignal was transmitted remotely to the base station on ship at distance of about 1 km away from the buoy station at sea. The fishes catched by the gape nets with wings were 12 species and Anchovy(Engraulis japonica), Beka squid(Loligo beka), Herring(Harengula zunasi) was 95% of total catches. The images of color display monitor at the base station on ship were very well coincident with the records of fish finder from the buoy station located at sea. When the current velocity was less than 0.6 kt and slight fluctuation, the fishes entered into the gape net were much more in comparision with over 1.0kt and heavy fluctuation, and then the average swimming depth was about 4 m. The catches per one hauling was about 10~30 kg and when the current velocity was too weak and the current direction did not coincident with the direction of net or the current velocity was too strong, the catches was a few. It is concluded that telesounder system is very useful for investigating the distribution and the swimming behavior of fishes entering in the gape nets with wings.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.465-480
• /
• 2014

In this study, we analyzed the spatio-temporal variations of satellite imagery for the two heavy rainfall cases (21 September, 2010, 9 August, 2011) occurred in the Korean Peninsula. In general, the possibility of strong convection can be increased when the region with plenty of moisture at the lower layer overlapped with the boundary between dark and bright area in the water vapor imagery. And the merging of convective cells caused by the difference in the moving velocities of two cells resulted in the intensification of convective activity and rainfall intensity. The rainfall intensity is more closely linked with the minimum cloud top temperature than the mean cloud top temperature. Also the spatio-temporal variations of rainfall intensity are impacted by the existence of merging processes. The merging can be predicted by the animation of satellite imagery but earlier detection of convective cells is almost impossible by using the infrared and water vapor imagery.