• The Journal of the Korea Contents Association
• /
• v.16 no.9
• /
• pp.12-21
• /
• 2016

The emergency evacuation support system supports evacuation assistance when an urgent disaster occurs. We have implemented evacuation route search algorithm to assist people's escape when a disaster occurs such as fires or terrorism in the building. The algorithm will guide the escape route at the fastest emergency exit of each region at the emergency state. The algorithm calculates the escape route by applying the weighting factor of age groups and population density around the emergency exit and of other regions. So the system helps escape to bypass the crowded emergency exit and the disaster area, and reduces the congestion of emergency exit and overloading of evacuation route.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.132-133
• /
• 2023

The safe evacuation of people during disasters is of utmost importance. Various life safety evacuation simulation tools have been developed and implemented, with most relying on algorithms that analyze maps to extract the shortest path and guide agents along predetermined routes. While effective in predicting evacuation routes in stable disaster conditions and short timeframes, this approach falls short in dynamic situations where disaster scenarios constantly change. Existing algorithms struggle to respond to such scenarios, prompting the need for a more adaptive evacuation route algorithm that can respond to changing disasters. Artificial intelligence technology based on reinforcement learning holds the potential to develop such an algorithm. As a fundamental step in algorithm development, this study aims to evaluate whether an evacuation algorithm developed by reinforcement learning satisfies the performance conditions of the evacuation simulation tool required by IMO MSC.1/Circ1533.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.69-70
• /
• 2017

As the industry develops, the size of buildings and ships are getting bigger and more complicated. In such a complex space, emergency evacuation systems are required because of the possibility of casualties when an accident situation occurs. However, because present systems are composed of basic devices, such as alarms, emergency exit signs, and announcement regarding the situation and inform only the least information to evacuees, evacuees are not able to judge objectively. To solve these problems, various evacuation algorithms have been proposed. However, these studies aim to search evacuation routes based on specific risk factors or to model the effects of bottlenecks in evacuation situations. Therefore, there is a limit to apply to real systems. Therefore, we propose algorithms to search the optimal evacuation route considering various risk factors such as fire and bottleneck in evacuation situations and to be applicable in actual situation in this paper. Performance evaluation using computer simulations showed that the proposed scheme is effective.

• Fire Science and Engineering
• /
• v.25 no.6
• /
• pp.156-167
• /
• 2011

The number of buildings is growing at a rapid pace in Korea. It is driven by significant economic improvements, the rapid population growth and urban centralization. Such being this case, some city are underway to building enlargement, Manhattanization. To Solve these problem and ensure the safety of live, fire Evacuation Simulation system is used for safe check of buildings. Forecasting an egress behavior in building fire is so important in order to construct a safe and reliable environment. But, currently most of the fire evacuation simulation system used in practice are foreign software that is not reflect korean conditions. Thus, This study focus on objectives that develop a fire evacuation system considering Korean Characteristics and create 3D space-based topology. so the system calculate evacuation path. This system developed as a result of research can be used by architectural designer in practice due to it is based 3D spatial information modeling.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.628-629
• /
• 2018

Recently, residential spaces in urban areas have changed into multi - family residential spaces. There is a feature that smoke is charged when a fire occurs here. Also, the evacuation route and the direction of the outflow of smoke are the same, and the possibility of inhaling the smoke of the evacuees is very high. When fighting fire in a narrow residential space such as a dwelling in a downtown area, exploration is the most important. For this purpose, we implement EO / IR sensor which can be mounted on firefighter 's helmet and can be used for fire detection. By using the EO / IR operation test, we can derive the results that can be used for research and development of the fire search sensor.

• Fire Science and Engineering
• /
• v.32 no.5
• /
• pp.46-51
• /
• 2018

The purpose of this study was to assess the evacuation route in a disaster information map to evacuate people to a shelter quickly and precisely during a disaster situation. For this purpose, this study examined the current status of domestic and international disaster information maps and related laws and conducted experiments to derive effective types of intersecting routes. The problems of the disaster information map were obtained through the first preliminary experiment and a survey. Based on these problems, experiments for each type were conducted to provide effective indication information for a disaster information map. To investigate the gait characteristics according to the number of crossing paths, the reduction rate in the crossing path was derived for each type by comparing the previous speed and passing speed. This will enable suggestions to judge the route quickly and accurately when determining the intersecting route in the search for an evacuation route. In conclusion, the experiment of this paper aims to make rapid and accurate evacuations using the disaster information map in response to disasters, and provide guidelines to citizens to contribute to a reduction of casualties.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.7
• /
• pp.870-874
• /
• 2018

In the worst maritime accidents, people should abandon ship, but ship structures are narrow and complex and operation takes place on rough seas, so escape is not easy. In particular, passengers on cruise ships are untrained and varied, making evacuation prospects worse. In such a case, the evacuation management of the crew plays a very important role. If a rescuer enters a ship at distress and conducts rescue activities, which zones represent the most effective entry should be examined. Generally, crew and rescuers take the shortest route, but if an accident occurs along the shortest route, it is necessary to select the second-best alternative. To solve this situation, this study aims to calculate evacuation routes using Q-Learning of Reinforcement Learning, which is a machine learning technique. Reinforcement learning is one of the most important functions of artificial intelligence and is currently used in many fields. Most evacuation analysis programs developed so far use the shortest path search method. For this reason, this study explored optimal paths using reinforcement learning. In the future, machine learning techniques will be applicable to various marine-related industries for such purposes as the selection of optimal routes for autonomous vessels and risk avoidance.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.4D
• /
• pp.459-467
• /
• 2008

Because of the insufficiency of ground space, the utilization of underground is getting more and more in these days. Moreover, underground space is being used not only buildings but multipurpose space for movement, storage and shopping. However, ground space has vital weakness for fire compared to ground space. Especially in case of underground shopping center, there are various stuffs to burn and poisonous gas can be exposed on this count when the space is burned. A large number of casualties can be also occurred from conflagration as underground space has closed structures that prevent rapid evacuation and access. Therefore, this research proposes the guidance methodology for evacuation from conflagration in large-sized underground facilities. In addition, suggested methodology uses high technology wireless sensor information from up-to-date ubiquitous sensor networks. Fire information collected by sensors is integrated with existing underground facilities information and this is sent to guidance systems by inducing process. In the end, this information is used for minimum time paths finding algorithm considering the passageway capacity and distance. Also, usefulness and inadequacies of proposed methodology is verified by a case study.