• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.216-218
• /
• 2022

Natural disasters caused by abnormal climates are continuously increasing, and the types of natural disasters that cause the most damage are flood damage caused by heavy rains and typhoons. Therefore, in order to reduce flood damage, this paper proposes a system that can predict the water level, a major parameter of flood, in real time using LSTM and GRU. The input data used for flood prediction are upstream and downstream water levels, temperature, humidity, and precipitation, and real-time prediction is performed through the pre-trained LSTM-GRU model. The input data uses data from the past 20 hours to predict the water level for the next 3 hours. Through the system proposed in this paper, if the risk determination function can be added and an evacuation order can be issued to the people exposed to the flood, it is thought that a lot of damage caused by the flood can be reduced.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.3
• /
• pp.231-238
• /
• 2017

Using 3D based BIM(Building Information Modeling) enables a variety of construction simulations. The is no case to simulate BIM demonstration experiment on deeply immersed virtual reality environment in korea. This paper develops a multi screen based simulation system to enable 3D based immersed environment to diverse decision making and virtual construction simulation. In a developed simulation laboratory, we can carry out BIM drawing review, disaster evacuation simulation, constructability review on wild land and design urban planning using haptic device on 3-side space with 4K resolution . Also, It can review large amount of drawings without data conversion because of compatibility with BIM software.

• Journal of the Society of Disaster Information
• /
• v.9 no.1
• /
• pp.78-86
• /
• 2013

Caused by the Cheonanham attack and the Yeonpyeongdo bombardment occurred a few years ago, and the recent North Korea's nuclear test, the war crisis between South and North Korea has been increasing. Accordingly, an interest in obtaining a temporary residential space, for the case of the outbreak of war, where people can reside safely over a period of time has been escalating. However, in the disaster relief planning guidelines of the National Emergency Management Agency, the standards on the temporary residential spaces in preparation for storm and flood or earthquake are included, but the standards on the ones in responding to war are not yet equipped. In particular, the standards on the underground temporary residential spaces that can accommodate massive victims should be developed in preparation. In this study, through a requirements analysis based on the survey of war victims and a comparative analysis between disaster-related laws and regulations, the direction of relevant system improvement for the utilization of temporary residential spaces in responding to war is established.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.97-102
• /
• 2019

Disaster accidents at industrial sites have been increasing every year. In shipyards there are countless enclosed spaces causing issues like harmful-toxic gases stuck in those sealed areas. And due to such special and complicated structures of the working places with many layers of walls separating each other, there exist more issues of communication with workers trapped inside when accidents happen. Under this circumstance there must be a huge difficulty to evacuate or rescue the workers in case of any disaster. Therefore, in this paper, We would like to introduce the "integrated safety system" to more effectively deal with the problems and prevent such disasters in tough working environments. The suggested integrated safety system can prevent accidents in advance because it can control the data on the location of the workers in real time and the numerical values such as gas, oxygen, and carbon dioxide generated in the workplace in real time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.491-493
• /
• 2022

Flood damage due to torrential rains and typhoons is occurring in many parts of the world. In this paper, we propose a water level prediction model using water level, precipitation, and humidity data, which are key parameters for flood prediction, as input data. Based on the LSTM and GRU models, which have already proven time-series data prediction performance in many research fields, different input datasets were constructed using the ASOS(Automated Synoptic Observing System) data and AWS(Automatic Weather System) data provided by the Korea Meteorological Administration, and performance comparison experiments were conducted. As a result, the best results were obtained when using ASOS data. Through this paper, a performance comparison experiment was conducted according to the input data, and as a future study, it is thought that it can be used as an initial study to develop a system that can make an evacuation decision in advance in connection with the flood risk determination model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.571-579
• /
• 2019

To minimize the damage from chemical accidents, a risk management plan (RMP) has been implemented since 2015. According to this regulation, operators who handle more than the designated quantity of the accident preparedness chemicals should provide emergency response information to the public within the affected areas of accidents. The information, including chemicals, affected areas and evacuation instructions should be provided to the public in advance so that they can evacuate immediately in the event of a chemical accident. Currently, the information notification can be provided in various methods by being registered in the notification system, sent with written documents or delivered directly to the public. To examine the status of the operation method, this study analyzed similar cases overseas, investigated the degree of awareness of providing information through the number of the annual visitor of the Information Provision System, and obtained survey results from some residents. This current operation method are problems because the public, who do not have sufficient information about chemicals, do not understand the emergency information properly or it is difficult to recognize where the residents should find this information because of the convenient operation based on the information provider. In this study, measures were proposed to minimize the damage by making it easier for the public to understand the emergency information and the information communicated appropriately in advance by dividing them into an information providing method and post management.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.656-664
• /
• 2023

Purpose: The Ministry of Employment and Labor manages disasters based on the standard manual for risk management of large-scale human accidents in workplaces when large-scale disasters such as fires and collapses occur in workplaces. We are going to check the standard manual currently in operation and suggest improvement plans for the insufficient items. Method: Accordingly, the standard manual was checked together with internal and external experts in the disaster management manual and disaster management staff at headquarters and local government offices, and items to be improved were identified with priority. Result: In case of a collapse accident, it is necessary for the Ministry of Public Administration and Security to accurately present the selection criteria in order to eliminate the controversy over the selection of the disaster management department. In addition, it seems necessary to supplement the details of the disaster safety communication network operation and evacuation guidelines. Conclusion: In the future, in order to improve the disaster management system that meets the public's eye level, it is expected to prepare a standard manual for risk management of large-scale human accidents in workplaces that guarantees the lives and safety of workers through the collection of opinions from experts in the relevant field, disaster management personnel, and the general public.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.195-195
• /
• 2016

Kon - Ha Thanh River basin is the largest and the most important river basin in Binh Dinh, a province in the South Central Coast of Vietnam. In the lower rivers, frequent flooding and inundation caused by heavy rains, upstream flood and or uncontrolled flood released from upstream reservoirs, are very serious, causing damage to agriculture, socio-economic activity, human livelihood, property and lives. The damage is expected to increase in the future as a result of climate change. An advanced flood warning system could provide achievable non-structural measures for reducing such damages. In this study, we applied a modelling system which intergrates a 1-D river flow model and a 2-D surface flow model for simulating hydrodynamic flows in the river system and floodplain inundation. In the model, exchange of flows between the river and surface floodplain is calculated through established links, which determine the overflow from river nodes to surface grids or vice versa. These occur due to overtopping or failure of the levee when water height surpasses levee height. A GIS based comprehensive raster database of different spatial data layers was prepared and used in the model that incorporated detailed information about urban terrain features like embankments, roads, bridges, culverts, etc. in the simulation. The model calibration and validation were made using observed data in some gauging stations and flood extents in the floodplain. This research serves as an example how advanced modelling combined with GIS data can be used to support the development of efficient strategies for flood emergency and evacuation but also for designing flood mitigation measures.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.175-185
• /
• 2023

Recently, novel viral infections such as COVID-19 have spread and pose a serious public health problem. In particular, these diseases have a fatal effect on the elderly, threatening life and causing serious social and economic losses. Accordingly, applications such as telemedicine, healthcare, and disease prevention using the Internet of Things (IoT) and artificial intelligence (AI) have been introduced in many industries to improve disease detection, monitoring, and quarantine performance. However, since existing technologies are not applied quickly and comprehensively to the sudden emergence of infectious diseases, they have not been able to prevent large-scale infection and the nationwide spread of infectious diseases in society. Therefore, in this paper, we try to predict the spread of infection by collecting various infection information with regional limitations through a virus disease information collector and performing AI analysis and severity matching through an AI broker. Finally, through the Korea Centers for Disease Control and Prevention, danger alerts are issued to the elderly, messages are sent to block the spread, and information on evacuation from infected areas is quickly provided. A realistic elderly support system compares the location information of the elderly with the information of the infected area and provides an intuitive danger area (infected area) avoidance function with an augmented reality-based smartphone application. When the elderly visit an infected area is confirmed, quarantine management services are provided automatically. In the future, the proposed system can be used as a method of preventing a crushing accident due to sudden crowd concentration in advance by identifying the location-based user density.

• Journal of Satellite, Information and Communications
• /
• v.10 no.4
• /
• pp.28-31
• /
• 2015

The elevator is extreme important due to the large size of the building and public facilities. In particular, it occurs bottleneck phenomenon in a elevator in case of using a theater. So, in this paper, we suggests technology of removing the traffics of visitors' movement and increase the efficiency of the use of elevator. Configuration of the proposed technique is divided parts of the processing unit, the movement route of the mobile cover to help viewers to create a route to collect sensor and the sensed data to detect state and a waiting elevator. This was the design and verification of technical performance and implementation.