災難逃生是現代社會中相當重要的課題，優秀的逃生系統能夠幫助社會減少生命財產損失等憾事。而災難逃生可以被分為兩種，一種是室內的逃生，另一種則是大規模災難的逃生。室內逃生的特性是民眾在危險發生當下處於室內，此類的危險通常更加緊急，民眾需要快速地逃往安全地點。而大規模災難逃生通常擁有較充裕的逃生時間，其重點往往在於如何最大化節約交通與通訊資源的利用，以利救難隊進行下一步的行動。在這篇論文中，提出了兩個與災難逃生相關的系統，分別對應兩種的逃生情境，包括：(1) 用於室內火災逃生的安全路徑規劃方法、(2)基於資源節約的大規模災難庇護所選擇方法。
在為了幫助人們在室內火災中逃生，已經有許多研究提出了各種室內火災疏散方法。傳統方法重點是找到最近的出口並設計最直接的路線。然而，這種方法存在局限性，包括逃生路徑的不靈活和需要耗費大量計算時間去適應火災的動態。近年的方法利用了傳感器網絡提供的實時數據，動態地決定疏散出口和計算逃生路徑。而這些技術仍然存在缺陷，例如陷入局部最優解以及過度依賴可能在火災中受損的傳感器網絡。與其他方法相比，我們的提出的系統（用於室內火災逃生的安全路徑規劃方法）利用火災預測工具來確定安全的逃生路線，並且克服先前研究的缺點。我們的實驗中證明，本系統的計算時間只需要其他方法的十分之一，並且提高了約百分之十的逃生成功率。
大多數的大規模災害疏散策略都強調根據個人的逃生時間為他們選擇最合適的避難所。然而，我們觀察到許多人在安全抵達避難所後，仍然堅持與親人和熟人保持聯繫，甚至前往與他們相聚。這種行為占用了通信和交通資源，導致交通和網絡的擁堵。但是在災害期間，這些資源都是有限且相當寶貴的，應留待緊急情況使用。因此，我們提出了一種名為RCSA的基於資源節約的大規模災難庇護所選擇方法，該方法在分配避難所給人們時，同時考慮到他們的情感關係和座標位置。人們會被與他們關心的人分到同一避難所，以進一步保護災害救援工作的資源。此外，RCSA亦可以移動設備上獨立運行，以應對災難中不可避免的網絡故障。

Evacuation during disasters is a critical subject in contemporary society to minimize the loss of lives and property. Disaster evacuations can be classified into two types: indoor evacuations and large-scale disaster evacuations.　Indoor evacuation involves individuals being inside a building when the danger occurs. Indoor emergencies are typically more urgent, requiring people to quickly move to a safe location. On the other hand, large-scale disaster evacuations often allow for more time to evacuate, focusing on maximizing the efficient use of transportation and communication resources to facilitate subsequent rescue operations. In this dissertation, two evacuation-related systems are proposed, encompassing (1) a safe path planning method for indoor fire evacuations and (2) a resource conservation shelter-selection approach for large-scale area emergency.
A variety of indoor fire evacuation strategies have been developed to aid people in fleeing from fires. Conventional approaches focus on finding the nearest exit and devising the most direct route. However, such methods possess limitations, including inflexibility and a time-consuming adaptation process to the dynamic progression of fires. More advanced methods harness real-time data from sensor networks to dynamically determine evacuation exits and paths. These techniques, however, suffer from drawbacks such as producing locally optimal solutions and an overreliance on the sensor network, which may be damaged in fires. In contrast to earlier approaches, our study, a safe path planning method for indoor fire evacuations, employs fire prediction to identify the safest route. The survival rate and computation time are considered essential performance indicators for evaluating fire evacuation methods. Our simulations reveal that our safest path planning technique is 10 times more faster than alternative approaches and achieves a survival rate greater than 10% compared to previous methods.
The majority of large-scale disaster evacuation strategies emphasize selecting the most suitable shelters for individuals based on their escape time. However, it has been observed that many people persistently attempt to communicate with or travel to their loved ones and acquaintances after safely reaching shelters. This behavior occupies communication and transportation resources, leading to traffic congestion and network congestion. Resources during disasters are limited and should be preserved for emergency situations. Therefore, we propose an approach called a resource conservation shelter-selection approach for large-scale area emergency, RCSA, which allocates shelters to people by taking into account their relationships and locations. In essence, people are grouped with those they care about at the same shelter to optimize resource conservation for disaster relief efforts. Furthermore, RCSA is designed to function independently on mobile devices to address the inevitable network failures during disasters.

[1] 中華民國內政部消防署，「110年全國火災統計分析」，2022。
[2] Dohi, M., Nemoto, M., Yamano, N., Shima, H., & Matsuoka, N. U.S. Patent No. 6,960,987. Washington, DC: U.S. Patent and Trademark Office, 2005.
[3] Ishii, H., & Ono, T.. U.S. Patent No. 4,871,999. Washington, DC: U.S. Patent and Trademark Office, 1989.
[4] Kates, L.. U.S. Patent No. 7,102,505. Washington, DC: U.S. Patent and Trademark Office, 2006
[5] 盧以霖，「以 FDS 模擬分析火災延燒」。國立交通大學機械工程系所，新竹市，2016。取自https：//hdl.handle.net/11296/94nu62
[6] 賴建豪，「以FDS模擬分析材料及熱釋放面積對延燒之影響」。國立交通大學機械工程系所，新竹市，2015。取自https：//hdl.handle.net/11296/7bx38s
[7] Thunderhead Engineering. PyroSim： A Model Construction Tool for Fire Dynamics Simulator, in PyroSim User Manual. Manhattan, USA： Thunderhead Eng, 2017.
[8] Hung-Yun, C., Pei-Hsuan, T. “A Speedup Fire Prediction for Online Evacuation Planning System”, 2021, https://thesis.lib.ncku.edu.tw/thesis/detail/a5246ef66aa15806e8a71a6b89c363b8/
[9] H. Y. Chen and P. H. Tsai, " A Speedup Simulation-based Fire Prediction for Online Evacuation Planning," International Computer Symposium, ICS 2020. Institute of Electrical and Electronics Engineers Inc. p. 73-78, 2020.
[10] Zenghao Chai, Chun Yuan, Zhihui Lin, Yunpeng Bai, “CMS-LSTM: ContextEmbedding and Multi-Scale Spatiotemporal-Expression LSTM for Video Prediction,” arXiv:2102.03586, 2021.
[11] PARASHAR, Manish; BROWNE, James C. On partitioning dynamic adaptive grid hierarchies. In: Proceedings of HICSS-29: 29th Hawaii International Conference on System Sciences. IEEE. p. 604-613, 1996.
[12] W. Zeng and R. L. Church, “Finding shortest paths on real road networks: the case for A*.” International journal of geographical information science 23.4, pp. 531-543, 2009.
[13] Filippoupolitis, A., & Gelenbe, E. An emergency response system for intelligent buildings. In Sustainability in Energy and Buildings (pp. 265-274). Springer, Berlin, Heidelberg, 2012.
[14] Mirahadi, F., & McCabe, B. Y. EvacuSafe: A real-time model for building evacuation based on Dijkstra's algorithm. Journal of Building Engineering, 34, 101687. 2021.
[15] Jingya Liu, Roberto Rojas-Cessa, and Ziqian Dong, “Sensing, calculating, and disseminating evacuating routes during an indoor fire using a sensor and diffusion network.” 2016 IEEE 13th International Conference on Networking, Sensing, and Control (ICNSC), IEEE. 2016.
[16] Ji, J., Ma, Z., He, J., Xu, Y., & Liu, Z. Research on Risk Evaluation and Dynamic Escape Path Planning Algorithm Based on Real-Time Spread of Ship Comprehensive Fire. Journal of Marine Science and Engineering, 8(8), 602, 2020.
[17] Kuan-Ting, Y., Pei-Hsuan, T. “An Evacuation Algorithm for Digital Twin Building Fire System”, 2019. https://hdl.handle.net/11296/8ujkjx
[18] Hu, X., Chen, L., Tang, B., Cao, D., & He, H. Dynamic path planning for autonomous driving on various roads with avoidance of static and moving obstacles. Mechanical Systems and Signal Processing, 100, 482-500, 2018.
[19] Hu, Y., & Liu, X. Optimization of grouping evacuation strategy in high-rise building fires based on graph theory and computational experiments. IEEE/CAA journal of automatica sinica, 5(6), 1104-1112, 2018.
[20] Wang, T., Bu, L., Yang, Z., Yuan, P., & Ouyang, J. A new fire detection method using a multi-expert system based on color dispersion, similarity and centroid motion in indoor environment. IEEE/CAA Journal of Automatica Sinica, 7(1), 263-275, 2019.
[21] Tian, G., Ren, Y., & Zhou, M. Dual-objective scheduling of rescue vehicles to distinguish forest fires via differential evolution and particle swarm optimization combined algorithm. IEEE Transactions on intelligent transportation systems, 17(11), 3009-3021, 2016.
[22] An-Fong L., Pei-Hsuan T., and Chia-Wei L. “A Map Segmentation Approach to Speedup Parallel Evacuation Planning,” in Proceedings of 2020 International Computer Symposium (ICS2020), Tainan, National Cheng Kung University, TAIWAN, December 17-19, 2020.
[23] J. R. Gilbert, G. L. Miller, and S. H. Teng, “Geometric mesh partitioning: Implementation and experiments,” SIAM J. Sci. Comput. vol. 19, pp. 2091-2110, 1998.
[24] S. L. Bezrukov, and B. Rovan, “On partitioning grids into equal parts,” Comput. Inform. vol. 16, pp. 153-165, 1997.
[25] M. Ye , J. Wang , J. Huang, S. Xu and Z. Chen. "Methodology and its application for community-scale evacuation planning against earthquake disaster." Natural hazards 61.3: 881-892, 2012.
[26] H. Zheng, Y.-C. Chiu, P. Mirchandani, and M. Hickman. "Modeling of evacuation and background traffic for optimal zone-based vehicle evacuation strategy." Transportation Research Record: Journal of the Transportation Research Board 2196: 65-74, 2010.
[27] Z. Alazawi, S. Altowaijri, R. Mehmood, and M. B. Abdljabar. "Intelligent disaster management system based on cloud-enabled vehicular networks." ITS Telecommunications (ITST), 2011 11th International Conference on. IEEE, 2011.
[28] A. Fujihara and H. Miwa. "Effect of traffic volume in real-time disaster evacuation guidance using opportunistic communications." Intelligent Networking and Collaborative Systems (INCoS), 2012 4th International Conference on. IEEE, 2012.
[29] V. E.G. Campos, P. A.L. da Silva, and P. O.B. Netto. "Evacuation transportation planning: A method of identify optimal independent routes." WIT Transactions on The Built Environment 44, 1970.
[30] E. Gelenbe and G. Gorbil. "Wireless networks in emergency management." Proceedings of the first ACM international workshop on Practical issues and applications in next generation wireless networks. ACM, 2012.
[31] W. Song, L. Zhu, Q. Li, X.D. Wang, Y. Liu, and Y.C. Dong. "Evacuation model and application for emergency events." Computer Sciences and Convergence Information Technology, 2009. ICCIT'09. Fourth International Conference on. IEEE, 2009.
[32] M. Min and J. Lee. "Maximum throughput flow-based contraflow evacuation routing algorithm." Pervasive Computing and Communications Workshops (PERCOM Workshops), 2013 IEEE International Conference on. IEEE, 2013.
[33] R.J. Szczerba, P. Galkowski, I.S. Glicktein, and N. Ternullo. "Robust algorithm for real-time route planning." IEEE Transactions on Aerospace and Electronic Systems 36.3: 869-878, 2000.
[34] Y. Wang, Y. He, Z. Liu, and J. Shi. "An integrated shelter location and route planning approach for emergent evacuation in transportation networks." Informative and Cybernetics for Computational Social Systems (ICCSS), 2014 International Conference on. IEEE, 2014.
[35] K. Kinoshita, K. Iizuka, and Y. Iizuka. "Effective disaster evacuation by solving the distributed constraint optimization problem." Advanced Applied Informatics (IIAIAAI), 2013 IIAI International Conference on. IEEE, 2013.
[36] Y. Iizuka, K. Yoshida, and K. Iizuka. "An effective disaster evacuation assist system utilized by an ad-hoc network." International Conference on Human-Computer Interaction. Springer, Berlin, Heidelberg, 2011.
[37] A. C.Y. Li, L. Nozick, N. Xu, and R. Davidson. "Shelter location and transportation planning under hurricane conditions." Transportation Research Part E: Logistics and Transportation Review 48.4: 715-729, 2012.
[38] Tanaka T, Matsuda Y, Fujimoto M, Suwa H, Yasumoto K. “Evacuation Shelter Decision Method Considering Non-Cooperative Evacuee Behavior to Support the Disaster Weak.” Sustainability; 13(9):5106, 2021.
[39] Rajkumar, R., Lee, I., Sha, L., & Stankovic, J. Cyber-physical systems: the next computing revolution. In Design automation conference (pp. 731-736). IEEE, 2010.
[40] Aqib, M., Mehmood, R., Albeshri, A., & Alzahrani, A. Disaster management in smart cities by forecasting traffic plan using deep learning and GPUs. In International Conference on Smart Cities, Infrastructure, Technologies and Applications (pp. 139-154). Springer, Cham, 2017.