• Smart Structures and Systems
• /
• v.33 no.6
• /
• pp.449-463
• /
• 2024

Automated crack detection is crucial for structural health monitoring and post-earthquake rapid damage detection. However, realizing high precision automatic crack detection in the absence of corresponding manual labeling presents a formidable challenge. This paper presents a novel crack segmentation transfer learning method and a novel crack segmentation model called Swin-CrackFormer. The proposed method facilitates efficient crack image style transfer through a meticulously designed data preprocessing technique, followed by the utilization of a GAN model for image style transfer. Moreover, the proposed Swin-CrackFormer combines the advantages of Transformer and convolution operations to achieve effective local and global feature extraction. To verify the effectiveness of the proposed method, this study validates the proposed method on three unlabeled crack datasets and evaluates the Swin-CrackFormer model on the METU dataset. Experimental results demonstrate that the crack transfer learning method significantly improves the crack segmentation performance on unlabeled crack datasets. Moreover, the Swin-CrackFormer model achieved the best detection result on the METU dataset, surpassing existing crack segmentation models.

• Journal of Korean Society of Forest Science
• /
• v.110 no.3
• /
• pp.419-430
• /
• 2021

This study investigated spatiotemporal trends of sediment-related disasters in North Korea from 1960 to 2019 and post-disaster recovery cases based on a literature review and satellite images. Results showed that occurrence status of sediment-related disasters was initially externally reported in 1995 (during the Kim Jongil era); their main triggering factor was heavy summer rainfall. Furthermore, forest degradation rate was positively correlated with population density (R² = 0.4347, p = 0.02) and occurrence number of sediment-related disasters was relatively high on the west coast region, where both variables showed high values. This indicates that human activity was a major cause of forest degradation and thus, significantly affected sediment-related disasters in mountain regions. Finally, sediment- related disasters due to shallow landslides, debris flow, and slow-moving landslides were observed in undisturbed forest regions and human-impacted forest regions, including terraced fields, opencast mines, forest roads, and post-wildfire areas, via satellite image analysis. These disaster-hit areas remained mostly abandoned without any recovery works, whereas hillside erosion control work (e.g., treeplanting with terracing) or torrent erosion control work (e.g., check dam, debris flow guide bank) were implemented in certain areas. These findings can provide reference information to expand inter-Korean exchange and cooperation in forest rehabilitation and erosion control works of North Korea.

• Geomechanics and Engineering
• /
• v.14 no.5
• /
• pp.459-466
• /
• 2018

By conducting uniaxial loading cycle tests on the coal rock with outburst proneness, the dilatation characteristics at different loading rates were investigated. Under uniaxial loading and unloading, the lateral deformation of coal rock increased obviously before failure, leading to coal dilatation. Moreover, the post-unloading recovery of the lateral deformation was rather small, suggesting the onset of an accelerated failure. As the loading rate increased further, the ratio of the stress at the dilatation critical point to peak-intensity increased gradually, and the pre-peak volumetric deformation decreased with more severe post-peak damage. Based on the laboratory test results, the lateral deformation of the coals at different depths in the #1302 isolated coal pillars, Yangcheng Coal Mine, was monitored using wall rock displacement meter. The field monitoring result indicates that the coal lateral displacement went through various distinct stages: the lateral displacement of the coals at the depth of 2-6 m went through an "initial increase-stabilize-step up-plateau" series. When the coal wall of the working face was 24-18 m away from the measuring point, the coals in this region entered the accelerated failure stage; as the working face continued advancing, the lateral displacement of the coals at the depth over 6 m increased steadily, i.e., the coals in this region were in the stable failure stage.

• Journal of Korean Association for Spatial Structures
• /
• v.15 no.2
• /
• pp.79-86
• /
• 2015

This study investigated the embedded depth of guardrail posts through 3-D soil material model and carried out evaluation of the dynamic performance of guard rail. In order to calculate for embedded depth of sloping ground, displacement of guardrail posts is analyzed according to the embedded depth of experiment variables. Through the static test of guardrail posts, the maximum deflection was found to decrease the interval. By performing the dynamic test using the Bogie Car, that is confirmed the elastic modulus of the soil occuring the maximum deflection. Guardrail posts is considered to need for further reinforcement in the larger slope than the plains. This study researched about maximum displacement and deviation velocity through dynamic performance of guardrail system and conducted analysis about protection performance evaluation of passenger.

• Journal of Korea Spatial Information System Society
• /
• v.12 no.1
• /
• pp.57-65
• /
• 2010

In this study, disaster damage investigation system was developed using high resolution satellite images and GIS technique to afford effective damage investigation system for widely disaster damaged area. Study area was selected in Bonghwa, Gyungsangbukdo where high magnitude of damages from torrential rain has occurred at July in 2008. GIS DB was built using 1:5,000 topographic map, cadastral map, satellite image and aerial photo to apply for investigation algorithm. Disaster damage investigation system was developed using VB NET languages, ArcObject component and MS-SQL DBMS for effective management of damage informations. The system can finding damaged area comparing pre- and post-disaster images and drawing damaged area according to the damage item unit. Extracted object was saved in Shape file format and overlayed with background GIS DB for obtaining detail information of damaged area. Disaster damage investigation system using high resolution spatial images can extract damage information rapidly and highly reliably for widely disaster areas. This system can be expected to highly contributing to enhance the disaster prevention capabilities in national level field investigation supporting and establishing recovery plan etc. This system can be utilized at the plan of disaster prevention through digital damage information and linked in national disaster information management system. Further studies are needed to better improvement in system and cover for the linkage of damage information with digital disaster registry.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.375-378
• /
• 2014

Marine disaster, such as 'the sinking of the Sewol ferry', on the ocean needs emergency communication with land post and Rescue services. Especially, It needs of emergency comomunication system has increased in Korea peninsula with the sea on three side. The system will be more fully equipped to deal with disasters linked to communication so alone sailing ship is at sea. Research is needed on communication links to submarines operated by submarine to sink a ship, as well as immersion in the sea with. And it is necessary in the study of the land in preparation for the emergency disaster ship and submarine communication links for offshore and subsea oil and associated communication systems. Will be studied in preparation for the communication protocols and emergency and disaster location and land the plane or for a career in the satellite systems are linked through this. It is necessary for this purpose is research on the integrated emergency disaster communication ecosystem.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.6
• /
• pp.81-92
• /
• 2014

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.77-77
• /
• 2016

최근 기후변화로 인한 수문기상학적인 극한 사상들은 점점 대형화되고 있고, 그 발생빈도 또한 잦아지고 있다. 인구의 증가와 급격한 도시화, 자산 가치의 증가 등으로 물과 관련된 재해로 인한 피해는 점점 더 규모가 커지고 있다. 홍수와 가뭄, 허리케인, 쓰나미와 같이 물과 관련된 재해는 그 영향을 받는 사람들의 수로 본다면 지구상의 재해 중 90%를 차지하고 있을 만큼 그 규모가 크다 할 수 있으며, 전세계적으로 물관련 재해로 인한 재산상의 피해를 약 1,000억 달러 규모로 추산하고 있는데, 2030년에는 그 현재의 두 배가 될 것으로 예측하고 있다. 이와 같은 재해로 인한 피해는 개도국이나 최빈국뿐만 아니라 관련 인프라가 잘 구축되어 있는 선진국 또한 예외는 아니다. 2015년 9월 UN 세계지속가능 정상 회의에서 각국의 수반들 또한 17개의 "지속가능개발목표(Sustainable Development Goals; SDGs)"를 채택함으로서 post-2015 아젠다가 세계를 지속가능하고 균형 있게 바꾸어 나가기 위해서 취해야 하는 가장 시급하고 필요한 과감한 혁신적인 조치임을 인식하였다. 재해경감과 지속가능개발은 2005년 채택된 "효고프레임웍(Hyogo Framework for Action) 2005-2015"에서 도 중요하게 다루어 졌다. 2015년 3월 제3차 세계재해경감대회에서 채택된 "센다이 프레임웍(Sendai Framework for Disaster Risk Reduction) 2015-2030"은 Post-2015 개발의제의 첫 번째 합의 결의안이라 할 수 있으며, 인명피해의 실질적인 감소와 재해에 의한 영향으로 피해 보는 사람들의 수를 줄이고, 경제적 손실과 대형 인프라 피해의 경감을 주요 타겟으로 하고 있다. 이와 같은 리질리언스의 중요성은 SDGs의 Goal 11인 "안전하고 지속가능한 도시와 정주지 조성(Make cities and human settlements inclusive, safe, resilient and sustainable)"에서 강조되고 있을 뿐만 아니라 다양한 골에서 재해로 부터의 리질리언스 확보에 대한 필요성을 강조하고 있다. 재해 위험을 경감시키기 위해서 국제적으로, 지역적으로 또는 국경을 넘어서는 협력 관계의 구축이 중앙정부나 지방정부를 비롯한 국가적으로 절대적으로 필요한 노력이라 할 수 있다. 특히나, Post-2015 개발 아젠다에 대한 기후변화와 재해경감을 위한 금융지원을 포함한 최빈국, 개도국, 군소 도서국가들과 중견국 선진국들의 양자간이나 다자간 협력 채널을 통한 역량 강화가 필요하다.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.17 no.2
• /
• pp.11-21
• /
• 2018

This study suggests desirable disaster safety education curriculum through analyzing the operational status of the school disaster safety management training course and demand survey of school staff. First, the problem of the disaster safety training course of the school is not connected with the lack of law and system and the school disaster safety job. Second, improvement of law and system and variety of training should be made to acquire professional knowledge. Third, it is necessary to divide curriculum into the following four categories, according to educational needs of public officials ; Educational administration officers course focused on facility safety, maintenance and disaster countermeasure. Educational officials in technical post course addressing approval and permission of school facility projects, seismic reinforcement of school building, etc. Educational supervisors course covering roles and responsibilities of the school safety supervisors in the event of disaster. Teaching staffs course focused on safety instructions for students. Fourth, it is found that lectures and experiential learning methods are the most desirable methods of teaching and learning, and the major ranks are earthquake disaster, fire, gas, typhoon, school road, and electrical safety.