• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.7 no.3
• /
• pp.51-58
• /
• 2007

The present study surveyed 750 graduate and undergraduate students who were living or not living in Gangwon province concerning the characteristics of disasters in Gangwon province, people's consciousness of disaster prevention, etc. According to the results of analysis, all the respondents thought that the possibility of disasters is higher in Gangwon province(74.0%) than in any other province. Compared to non-residents, Gangwon province residents tended to perceive that the possibility of storm and flood disasters and forest fires is high in Gangwon province. As to reasons for frequent disasters in Gangwon province, the respondents mentioned disadvantageous natural conditions, the shortage of disaster prevention facilities and local residents' low consciousness of disaster prevention. As to methods for enhancing people's consciousness of disaster prevention in Gangwon province, they considered essential the expansion of disaster prevention facilities and education on disaster prevention. In particular, 62.1% of the respondents did not have experiences in disaster education. This suggests the necessity for extending disaster education.

• Wind and Structures
• /
• v.28 no.2
• /
• pp.129-140
• /
• 2019

Accurately simulating the wind field of large-scale region, for instant urban areas, the locations of large span bridges, wind farms and so on, is very difficult, due to the complicated terrains or land surfaces. Currently, the regional wind field can be simulated through the combination of observation data and numerical model using observation-nudging in the Weather Research and Forecasting model (WRF). However, the main drawback of original observation-nudging method in WRF is the effects of observation on the surrounding field is fully mathematical express in terms of temporal and spatial, and it ignores the effects of terrain, wind direction and atmospheric circulation, while these are physically unreasonable for the turbulence. For these reasons, a spatial correlation-based observation-nudging method, which can take account the influence of complicated terrain, is proposed in the paper. The validation and comparation results show that proposed method can obtain more reasonable and accurate result than original observation-nudging method. Finally, the discussion of wind field along bridge span obtained from the simulation with spatial correlation-based observation-nudging method was carried out.

• Journal of Korean Society of Disaster and Security
• /
• v.16 no.1
• /
• pp.37-48
• /
• 2023

The possibility of a super-large disaster is increasing due to changes in national territory, urban space and social environment, extreme weather conditions due to climate change, and paralysis of national infrastructure due to natural disasters. In this study, in order to support the systematic establishment of national territorial disaster prevention strategies for future disasters, alternatives to intelligent national territorial disaster prevention policies for future disasters were considered. Changes in the national environment related to future disasters, domestic and foreign prior studies and policy trends related to national disaster prevention, and studies related to the national disaster management system were investigated, and institutional and technical policy alternatives were derived. As a policy alternative, it was suggested that the creation of a self-adapting national territory for future disasters should be systematized and continuously supported through a technically intelligent decision-making support system.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.6
• /
• pp.590-596
• /
• 2019

Numerous deaths and substantial property damage have occurred recently due to frequent disasters of the highest intensity according to the abnormal climate, which is caused by various problems, such as global warming, all over the world. Such large-scale disasters have become an international issue and have made people aware of the disasters so they can implement disaster-prevention measures. Extensive information on disaster prevention actively has been announced publicly to support the natural disaster reduction measures throughout the world. In Japan, diverse developmental studies on disaster prevention systems, which support hazard map development and flood control activity, have been conducted vigorously to estimate external forces according to design frequencies as well as expected maximum frequencies from a variety of areas, such as rivers, coasts, and ports based on broad disaster prevention data obtained from several huge disasters. However, the current reduction measures alone are not sufficiently effective due to the change of the paradigms of the current disasters. Therefore, in order to obtain the synergy effect of reduction measures, a study of the establishment of an integrated system is required to improve the various disaster prevention technologies and the current disaster prevention system. In order to develop a similar typhoon search system and establish a disaster prevention infrastructure, in this study, techniques will be developed that can be used to forecast typhoons before they strike by using artificial intelligence (AI) technology and offer primary disaster prevention information according to the direction of the typhoon. The main function of this model is to predict the most similar typhoon among the existing typhoons by utilizing the major typhoon information, such as course, central pressure, and speed, before the typhoon directly impacts South Korea. This model is equipped with a combination of AI and DNN forecasts of typhoons that change from moment to moment in order to efficiently forecast a current typhoon based on similar typhoons in the past. Thus, the result of a similar typhoon search showed that the quality of prediction was higher with the grid size of one degree rather than two degrees in latitude and longitude.

• Journal of Environmental Science International
• /
• v.14 no.6
• /
• pp.613-619
• /
• 2005

Recently, we are suffered enormous loss from a natural disaster and making an effort to prepare measures for dealing with disasters. This study shows the major causes of natural disasters and stricken area with the analysis of meteorological data based on the Korean Meteorological Administration and the Central Disaster Relief Center records during 1987-2003 and classifies natural disasters according to the causes and damaged conditions. In this study, the most damaged area were Gangwon, Gyeongnam and Gyeongi province as a result of a typhoon and a localized heavy rain. To establish an effective disaster measure for these area, detailed prevention plans should be established by its causes after investigating precise regional damage data analysis.

• Journal of Environmental Science International
• /
• v.22 no.11
• /
• pp.1529-1538
• /
• 2013

Disasters like mountain landslides and collapse in cutting areas claim many a life and cause economic losses, involving much effort and expenses for their recovery. This study has surveyed and analyzed incident of disasters that had occurred on the sloping sides in Korea for the past 13 years in an effort to relieve damage caused by disasters on the sloping sides. The analysis confirms that while the major cause of disasters on the sloping side was storms in the past, frequency of disasters on sloping sides caused by local downpour is steadily on the rise. In addition, while disasters were concentrated in Gangwon Province, a mountainous region of the country, frequency of disasters occurring on the sloping sides is steadily increasing recently on the sloping sides in downtown areas in Seoul, Gyeonggi-do and so forth, attributing a large percentage of disasters to sloping sides. Data surveyed and analyzed in this study are thought to be applicable as basic data for the establishment of effective measures for the prevention of disasters occurring on the sloping sides in the days to come.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.7 no.3
• /
• pp.41-49
• /
• 2007

In order to reduce the amount of damage from natural disasters and perform the natural disaster mitigation program, the prevention activities and forecasting based on meteorological parameters and disaster datas are required. In addition, it is necessary to process prevention meteorological information for prevention activities in advance. For this, we have analyzed four data, such as Statistical yearbook of calamities and Statistics Yearbook issued by the Ministry of Government Administration and Human affairs. And Annual Climatological Report issued by the Korea Meteorological Administration and Recently 10 years for natural disaster damage from the Central Disaster and Safety Countermeasures Headquarters. We analyzed the causes, elements, occurrence frequencies, and vulnerable areas of natural disaster, using the 4 disaster datas, but these datas was not consistent with their terminology and items. Through the analysis of a kind and damage of disaster, we have selected the disaster variables, such as causes and elements, the amount of damage, vulnerable areas of natural disaster, etc and made a database. This database will be used to assess the natural disasters and develop the risk model and natural disasters mitigation plan.

• Journal of Environmental Science International
• /
• v.15 no.11
• /
• pp.1003-1010
• /
• 2006

It is very difficult to forecast accurately a damage from the natural disasters which occurs frequently. If the significant weather event was forecasted one or two days ago, we will be able to minimize a damage from the severe weather event through the suitable prevention activities. It said that 2000's our country's total damages from the meteorological disasters was several trillion won(Park et al, a, b, 2005). Therefore, we analyzed the Korea Meteorological Administration(KMA) and television broadcasting's reports, information contents, and transmission system, an ex post facto valuation about typhoon Nabi which struck the Korean peninsula from September 5 to 7, 2005. Through these investigations, we want to present the basic data to rises the application effect of disaster prevention meteorological information. We think KMA must present many information report to promote a citizen's understanding about the meteorological information and the serious disaster situation. And also we think the KMA and television broadcasting must present an advisable reports, the contents which is suitable to disaster response stages. And we must grasp the problem of disaster prevention meteorological information through an ex post facto examination, improve it effectively.

• 한국방재학회:학술대회논문집
• /
• 2008.02a
• /
• pp.309-312
• /
• 2008

In Korea, although the damage from disaster (flood and storm) is increasing, the early stage warning and countermeasure are not in operation rapidly. The research areas of transportation engineering arenot diverse, so once the road is flooded and interrupted, drivers, the system operators and managers are in panic, and nearby roads are in terrible traffic congestion. In case of Korea, the research of evacuation is highly needed, because it is very necessary and easy to apply in real field. In this paper, we establish the concept of transportation disaster prevention system and suggest the directions of it. In addition, based on this research, we choose one example of disasters and establish an example of the transportation disaster prevention system. Our goal is to make steps; prevention, preparation, countermeasure and restoration in the view of minimizing on social chaos and damages emphasizing aspect of transportation countermeasure. This research will be the good precedent of approach, analysis and countermeasure when the disasters are occurred, and a basis of transportation disaster prevention system and manual in Korea.