• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.5
• /
• pp.1311-1318
• /
• 2008

This study aims at proposing a method to guide people to the most efficient route in an emergency through addressing the limitations of the existing research and providing a solution. Most of the existing intelligent guidance system tend to guide people to the shortest-distance path to the exit. A problem lies to the fact that the shortest-distance path doest not gurantee the most efficient way of evacuation. Rather than taking the shortest-distance path, this research proposes a way of taking the shortest-time path by introducing a real time loop sensor.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.2
• /
• pp.617-626
• /
• 2014

Lately, losses and damage from natural disasters have been increasing. Researchers across various fields in Korea are trying to come up with a response plan, but research for evacuation plans is still far from satisfactory. Hence this paper proposes a model that could find an optimized evacuation route for when disasters occur over wide areas. Development of the model used methods including the Dijkstra shortest path algorithm, feasible path method, genetic algorithm, and pareto efficiency. Computations used parallel computing (SPMD) for high performance. In addition, the developed model is applied to a virtual network to check the validity. Finally the adaptability of the model is verified on a real network by computating for Gumi 1stNational Industrial Complex. Computation results proved that this model is valid and applicable by comparison of the fitness values for before optimization and after optimization. This research can contribute to routing for responder vehicles as well as planning for evacuation by objective when disasters occur.

• Journal of the Society of Disaster Information
• /
• v.12 no.2
• /
• pp.130-135
• /
• 2016

In this paper, the trend of evacuation path providing or guidance systems for safety on disaster situation is analyzed. For trend analysis, 31 papers of domestic and international, 29 patents of domestic, and the finished 9 national funded projects, which have been performed for recent 15 years are analysed. As the results of analysis, the previous researches were performed in the view of the guidance systems, but there is no study that can be used for peoples in dangerous situation until now. Also it has technical limitations in using indoor positioning technology for peoples. In this paper, therefore, we propose to use the indoor positioning technology for developing a novel evacuation guidance system for peoples in dangerous situation. It can be utilized to develop a novel evacuation guidance system which is considered indoor disaster situations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.219-221
• /
• 2022

In recent summer, as it is concentrated, even in mountainous areas, flooding and flooding cause casualties in pedestrian evacuation situations. To compensate for this, a system that detects the occurrence of flooding and allows pedestrians to evacuate safely is required. Therefore, in this paper, we propose a research on pedestrian path search based on the shortest distance algorithm using Map API. The pedestrian route search system outputs a map using the T Map API, selects nearby buildings as shelters, and stores data. A shelter close to the pedestrian's current location is selected, and the shortest route is output and the distance and time are provided. If there is a problem with the current route during evacuation, another shelter route is provided from the current location. Therefore, it is thought that the pedestrian route search evacuation system proposed in this paper will prevent accidents during evacuation.

• Proceedings of the KOR-KST Conference
• /
• 2007.05a
• /
• pp.681-690
• /
• 2007

• Journal of KIBIM
• /
• v.6 no.3
• /
• pp.15-23
• /
• 2016

The purpose of this study is to present the possibility of adopting beacons to implement the fire evacuation guidance system in order to reduce the evacuation time for a fire in complex buildings. A beacon-based evacuation system can quickly detect a fire's origin, optimal path of evacuation involved with the exits and the location of evacuees using information collected by the proposed system. The assessment is conducted by integrating different scenario models including fire simulation. Based on the research result, beacon is an effective tool to warn potential hazards or to provide early detection and a safe escape.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5525-5533
• /
• 2012

Because of ultra-high buildings or deeper underground space, recent buildings have the potential that people who have lack of physical strength collapse before arriving at the emergency exits when catastrophes occur. In case of fire, the way to escape is that first, people take the stairs of the adjacent areas and then use the elevator to the remaining distance by road to escape notice or be safe. For this reason, the skyscrapers guidelines of Seoul for information on the elevator for evacuation has been established. Nevertheless, when designing buildings to install a elevator for evacuation separately is not effective, so passenger elevators installation according to the criteria are encouraged to use as evacuation elevators. However, this does not include detailed design guidelines so far. Therefore, this study was to investigate design method to use the passenger elevator for evacuation according to the domestic law and international installation criteria, and to calculated number of lifts and refuge to use the elevator using by the ELVAC+ and PathFinder evacuation program.

• Journal of the Korean Institute of Rural Architecture
• /
• v.10 no.4
• /
• pp.9-16
• /
• 2008

The purpose of this study is to compare and seize the type of the path of flow for nurses and living assistant, of the path of flow for evacuation and walking practice by analysis plan for the care facilities in the out-of-home service. It supposed many problem for living in the care facilities for the aged get down activity, especially their relates with difficulty in walking. And services of nurses and living assistant get mixed properties by that problem for the aged with difficulty in walking. It classified into T type, L type, H type, ${\Box}$ type, - type all the path of flow for nurses and living assistant on the longest from nursing station to each bedroom, the path of flow for evacuation from each room to exit, the path of flow for walking practice on the corridor and lobby. The three path of flow are influenced by an inner court, especially passable court is the important primary factor in the communication between the aged, a course and time required of flow.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1661-1670
• /
• 2016

In this paper, we present a risk prediction system and customized evacuation pathfinding algorithm in fire scenarios. For the risk prediction, we apply a multi-level clustering mechanism using collected temperature at sensor nodes throughout the network in order to predict the temperature at the time that users actually evacuate. Based on the predicted temperature and its reliability, we suggest an evacuation pathfinding algorithm that finds a suitable evacuation path from a user's current location to the safest exit. Simulation results based on FDS(Fire Dynamics Simulator) of NIST for a wireless sensor network consisting of 47 stationary nodes for 1436.41 seconds show that our proposed prediction system achieves a higher accuracy by a factor of 1.48. Particularly for nodes in the most reliable group, it improves the accuracy by a factor of up to 4.21. Also, the customized evacuation pathfinding based on our prediction algorithm performs closely with that of the ground-truth temperature in terms of the ratio of safe nodes on the selected path, while outperforming the shortest-path evacuation with a factor of up to 12% in terms of a safety measure.