Evaluation of PSO Algorithm Considering Obstacle Avoidance in Evacuation Guidance

Year 2022, , 318 - 335, 30.09.2022

Tomofumi Matsuzawa , Akiyoshi Ishii

https://doi.org/10.31197/atnaa.1095309

Abstract

In recent years, IoT has been expected to provide support during natural disasters, and studies focusing on ant colony optimization (ACO) have been conducted for providing evacuation routes for evacuees.
We previously proposed a modified algorithm for ACO that improved on the slow convergence of ACO, but the problem with ACO-based evacuation is the time it takes the evacuees to reach a safe zone.

In this study, we proposed a route suggestion algorithm that improves particle swarm optimization (PSO) to reduce the time required for ACO evacuation, and compared the performance of ACO and the proposed PSO. We also proposed a method that combines ACO and PSO and evaluated its performance.

Keywords

ACO, PSO, Evacuation guidance, Natural disaster

References

• 1] Erick Mas, Anawat Suppasri, Fumihiko Imamura, and Shunichi Koshimura. Agent-based simulation of the 2011 great east japan earthquake/tsunami evacuation: An integrated model of tsunami inundation and evacuation. Journal of Natural Disaster Science, 34(1):41-57, 2012.
• [2] Nobuhisa Komatsu, Masahiro Sasabe, Jun Kawahara, and Shoji Kasahara. Automatic evacuation guiding scheme based on implicit interactions between evacuees and their mobile nodes. Geoinformatica, 22:127-141, 2018.
• [3] Shohei Taga, Tomofumi Matsuzawa, Munehiro Takimoto, and Yasushi Kambayashi. Multi-agent base evacuation support system considering altitude. In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 1: HAMT,, pages 299-306. INSTICC, SciTePress, 2019.
• [4] J. Kennedy and R. Eberhart. Particle swarm optimization. In Proceeding of IEEE Int. Conf. Neural Networks, volume 4, pages 1942-1948, 1995.
• [5] Dorigo Marco, Maniezzo Vittorio, and Colorni Alberto. Ant system: Optimization by a colony of cooperating agents. In Proceeding of IEEE Transaction on System, volume 26, pages 29-41, 1996.
• [6] Asuka Ohta, Tomofumi Matsuzawa, and Masayuki Takeda. Information exchange on manet for efficient evacuation. Inter- national Journal of Communications, Network and System Sciences, 10(8):187-197, 2017.
• [7] Hirotaka Goto, Asuka Ohta, Tomofumi Matsuzawa, Munehiro Takimoto, Yasushi Kambayashi, and Masayuki Takeda. A guidance system for wide-area complex disaster evacuation based on ant colony optimization. In Proceedings of the 8th International Conference on Agents and Arti?cial Intelligence - Volume 1: ICAART,, pages 262-268. INSTICC, SciTePress, 2016.
• [8] Asuka Ohta, Hirotaka Goto, Tomofumi Matsuzawa, Munehiro Takimoto, Yasushi Kambayashi, and Masayuki Takeda. An improved evacuation guidance system based on ant colony optimization. In Proceedings of the 19th Asia Pacific Symposium on Intelligent and Evolutionary Systems, volume 5, pages 15-27, 2016.
• [9] Kaiyu Suzuki, Tomofumi Matsuzawa, Munehiro Takimoto, and Yasushi Kambayashi. Vector quantization to visualize the detection process. In Proceedings of the 13th International Conference on Agents and Arti?cial Intelligence - Volume 1: SDMIS,, pages 553-561. INSTICC, SciTePress, 2021.