• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.498-509
• /
• 2023

Purpose: This paper proposes a method detecting the falling of a maintenance worker in the underground utility tunnel, by applying deep learning techniques using CCTV video, and evaluates the applicability of the proposed method to the worker monitoring of the utility tunnel. Method: Each rule was designed to detect the falling of a maintenance worker by using the inference results from pre-trained YOLOv5 and OpenPose models, respectively. The rules were then integrally applied to detect worker falls within the utility tunnel. Result: Although the worker presence and falling were detected by the proposed model, the inference results were dependent on both the distance between the worker and CCTV and the falling direction of the worker. Additionally, the falling detection system using YOLOv5 shows superior performance, due to its lower dependence on distance and fall direction, compared to the OpenPose-based. Consequently, results from the fall detection using the integrated dual deep learning model were dependent on the YOLOv5 detection performance. Conclusion: The proposed hybrid model shows detecting an abnormal worker in the utility tunnel but the improvement of the model was meaningless compared to the single model based YOLOv5 due to severe differences in detection performance between each deep learning model

• Journal of the Society of Disaster Information
• /
• v.19 no.2
• /
• pp.270-279
• /
• 2023

Purpose: The purpose of this study is to examine the new drugs that recently have shown rapid increase and provide solutions to eradicate them. Method: This study used the relevant preceding studies, statistics, and overseas materials to identify the new drug problems and suggest solutions. Result: Compared to the past, the numbers of criminals detected for the administration, distribution, and production of drugs are rapidly increasing. According to the statistical data on drugs in 2021, the number of drug-related cases decreased compared to the previous year. However, there are concerns because the amount of detected drugs increased more than three times, and the age group of drugrelated criminals are getting younger. Such results are largely affected by the spread of new drugs. In particular, it is deemed to be affected by the spread of new drugs, such as fentanyl, yaba, khat, kratom, etc., as well as the new psychoactive drugs and hemp-related materials. Conclusion: In response to spread of new drugs, this study suggests simplifying the temporary classification of drugs, enforcing control of foreign drug users, strengthening the cooperation with relevant institutions, such as Korea Customs Service and the Ministry of Food and Drug Safety, and intensifying the punishment on the drug users in order to strengthen the countermeasure against the new drugs.

• Journal of Wetlands Research
• /
• v.25 no.4
• /
• pp.345-352
• /
• 2023

Recently, the risk of snow disasters has been increasing South Korea. The damages of heavy snow were categorized into direct and indirect. Direct damage is usually the collapse of buildings as houses, greenhouse or barns. Indirect damage is various, for example, traffic congestion, traffic acident, drop damage, and so on. In South Korea, direct damage is severe in rural area, mosty collapse of greenhouse or barns. However, indirect damage such as traffic accident is mostly occurred in urban area. Therefore, the regional characteristics should be considered when vulnerability is evaluated. Therefore, in this study, the PSR and DPSIR method were applied by regional scale in South Korea. The PSR evaluation method is divided into pressure, state, and reaction index. however, the DPSIR evaluation method is divided into Driving force, Pressure, State, Impact, and Response index. the DPSIR evaluation method is divided into Driving force, Pressure, State, Impact, and Response index. Data corresponding to each indicator were collected, and the weight was calculated using the entropy method to calculate the snowfall vulnerability index by regional scale in South Korea. Calculated heavy snow damage vulnerabilities from the two methods were compared. The calculated vulnerabilities were validated using the recent snow damage in South Korea from 2018 to 2022. Snow vulnerability index calculated using the DPSIR method showed more reliable results. The results of this study could be utilized as an information to prepare the mitigation of heavy snow damage and to establish an efficient snow removal response system.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.826-833
• /
• 2023

Purpose: We suggest the need to utilize ESG in the safety field to prevent serious industrial accidents. Method: The Serious Accident Punishment Act, a strong serious accident prevention system, was reviewed through a review of previous research. And through comparative analysis of serious accident data from the United States and Korea, the main causes of accidents in the domestic chemical industry were derived. Result: It was determined that there was a need to induce voluntary safety management by companies through ESG management along with the Serious Accident Punishment Act, which aims to prevent corporate accidents. Through statistical analysis of accident data, it was confirmed that the scale of damage and number of deaths in domestic accidents was greater than in the United States. The reason was interpreted to be that there are many accidents caused by human causes in the country. Conclusion: In order to compensate for the lack of voluntariness in corporate safety management as well as the Serious Accident Punishment Act and encourage active safety management, the proportion of 'ESG safety evaluation' must be expanded. By using ESG as an indirect social sanction, we can expect companies to voluntarily and actively manage safety and expand safety investments in the safety field.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.2
• /
• pp.5-18
• /
• 2023

As the development of drones and sensors accelerates, new services and values are created by fusing data acquired from various sensors mounted on drone. However, the construction of spatial information through data fusion is mainly constructed depending on the image, and the quality of data is determined according to the specification and performance of the hardware. In addition, it is difficult to utilize it in the actual field because expensive equipment is required to construct spatial information of high-quality. In this study, super-resolution was performed by applying deep learning to low-resolution images acquired through RGB and THM cameras mounted on a drone, and quantitative evaluation and feature point extraction were performed on the generated high-resolution images. As a result of the experiment, the high-resolution image generated by super-resolution was maintained the characteristics of the original image, and as the resolution was improved, more features could be extracted compared to the original image. Therefore, when generating a high-resolution image by applying a low-resolution image to an super-resolution deep learning model, it is judged to be a new method to construct spatial information of high-quality without being restricted by hardware.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.329-338
• /
• 2024

Purpose: This study verified the safety of the improved box-type girder behavior by comparing and evaluating the bending behavior results of a full-scale specimen based on the analytical behavior of the splice element PSC U-shaped girder with integrated tensioning systems. Method: Based on the results of the service and strength limit state design using the bridge design standard(limit state design method), the applied load of a 40m full-scale specimen was calculated and a static loading experiment using the four-point loading method was performed. Result: When the design load, crack load, and ultimate load were applied, the specimen deflection occurred at 97.1%, 98.5%, and 79.0% of the analytical deflection value. When the design load, crack load, and ultimate load were applied, the crack gauge was measured at 0.009~0.035mm, 0.014~0.050mm, and 6.383~5.522mm at each connection. Conclusion: The specimen behaved linear-elastically until the crack load was applied, and after cracks occurred, it showed strainhardening up to the ultimate load, and it was confirmed that the resistance of bending behavior was clearly displayed against the applied load. The cracks in the dry joints were less than 25% of grade B based on the evaluation of facility condition standard. The final residual deformation after removing the ultimate load was 0.114mm, confirming the stable behavior of the segment connection.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.369-378
• /
• 2024

Purpose: This study aims to verify structural stability by manufacturing a 40m full-scale specimen composed of a segmental U-shaped PSC girder with integrated tensioning systems and a concrete slab, proceeding dynamic behavior tests, and compare the results of the tests with the results of numerical analysis. Method: Dynamic behavior tests were conducted on a full-scale, undamaged specimen using an impact hammer, and the natural frequency and damping ratio were measured and compared with numerical analysis techniques and the general damping ratio of the facilities. Result: The natural frequency of the numerical analysis model consisting of a girder and slab composite section was calculated to be 2.561Hz, the natural frequency of the full-scale specimen was measured to be 2.670Hz, and the damping ratio was calculated to be 0.42~0.68%. Conclusion: The natural frequency of the full-scale specimen was found to be 4.3% larger than that of the numerical analysis model. Since the masses of the full-scale specimen and the numerical analysis model are the same as 99.97%, it can be derived that the stiffness of the full-scale specimen has secured structural safety and stability. As a result, the dynamic behavior stability of the specimen was verified. The measured damping ratio of 0.42~0.68% was found to be a stable dynamic behavior compared to the PSC structures damping ratio of 0.5~1.0% in the elastic region.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.2
• /
• pp.149-160
• /
• 2024

Severe casualties and property damage are occurring due to urban floods caused by extreme rainfall. However, there is a lack of research on preparedness, appropriate estimation of flood damages, assessment of losses, and compensation. Particularly, the flood damage estimation methods used in the USA and Japan show significant differences from the domestic situation, highlighting the need for methods tailored to the Korean context. This study addresses these issues by developing an optimized flood damage estimation technique based on the building characteristics. Utilizing the flood prediction solution developed by the Korea Institute of Science and Technology Information (KISTI), we have established an optimal flood damage estimation technology. We introduced a methodology for flood damage estimation by incorporating vulnerability curves based on the inventory of structures and apply this technique to real-life cases. The results show that our approach yields more realistic outcomes compared to the flood damage estimation methods employed in the USA and Japan. This research can be practically applied to procedures for flood damage in urban basement residences, and it is expected to contribute to establishing appropriate response procedures in cases of public grievances.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.5
• /
• pp.1105-1115
• /
• 2015

Big data analysis for disaster have been recently started especially to text data such as social media. Social data usually supports for the final two stages of disaster management, which consists of four stages: prevention, preparation, response and recovery. Otherwise, big data analysis for meteorologic data can contribute to the prevention and preparation. This motivated us to review big data technologies dealing with non-text data rather than text in natural disaster area. To this end, we first explain the main keywords, big data, data mining and machine learning in sec. 2. Then we introduce the state-of-the-art machine learning techniques in meteorology-related field sec. 3. We show how the traditional machine learning techniques have been adapted for climatic data by taking into account the domain specificity. The application of these techniques in natural disaster response are then introduced (sec. 4), and we finally conclude with several future research directions.

• Korean Security Journal
• /
• no.20
• /
• pp.45-69
• /
• 2009

This study is to present effective and rational strategies by comparing and analyzing plans of some nations such as the United States, Britain, Germany and Japan against terrorism. Nations mentioned above have made alliance to prevent the possible terrorism after 9.11 attack and performed various tasks efficiently. The result of this study is summarized as follows. First, it is required that there should be an integrated system which works properly. Each nation has not distinguished natural disaster from man-made one based on the damage and the abilities of authorities to deal with. On the other hand, South Korea tells two disasters according to causes and runs distributed systems in which each government division performs its duties to manage each disaster. Accordingly, in economic terms, it is much more effective to provide integrated counter terrorism, not distributed one. Second, information sharing must be stimulated. To take actions quickly when an accident occurs, the government needs to have united and integrative systems, which make it prepare for various types of terrorism well. In addition, it is necessary for a government-related organization to tie up with other channels for collecting, analyzing and sharing information. For this, integrative systems for terrorism should be taken into consideration.