A machine learning based study on pedestrian movement dynamics under emergency evacuation
Knowledge of evacuees' movement dynamics is crucial to building safety design and evacuation management. Although it is recognized that stepwise movement is the fundamental element to construct the whole evacuation process, movement pattern and its influencing factors are still not well underst...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143390 |
| _version_ | 1811682251092525056 |
|---|---|
| author | Wang, Ke Shi, Xiupeng Goh, Algena Pei Xuan Qian, Shunzhi |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Wang, Ke Shi, Xiupeng Goh, Algena Pei Xuan Qian, Shunzhi |
| author_sort | Wang, Ke |
| collection | NTU |
| description | Knowledge of evacuees' movement dynamics is crucial to building safety design and evacuation management. Although it is recognized that stepwise movement is the fundamental element to construct the whole evacuation process, movement pattern and its influencing factors are still not well understood. In this study, we explored the potential of adopting machine learning methods to study evacuees' stepwise movement1 dynamics based on two videos of quasi-emergency evacuation experiments. The movement patterns were categorized through Two-step Cluster Analysis and principal influencing factors were identified through Principal Component Analysis. The relationship between the movement patterns and the principal components were investigated using different modeling methods: traditional method (Multinomial Logit Model, MLM) and machine learning methods (Decision Tree, Support Vector Machine, K-Nearest Neighbor, and Artificial Neural Network). Results from two experimental videos showed reasonable consistency and the main findings are: (1) Distance to the target exit has the most pronounced effect on a single evacuee's stepwise movement pattern. (2) Surrounding evacuees' actions also have significant and complex influence on a single evacuee's stepwise movement pattern. (3) MLM showed comparable prediction accuracy with machine learning methods when the scenario is simple. The superiority of machine learning became apparent when the scenario was more complex, with a maximum enhancement of 13.25% in prediction accuracy. Each machine learning method demonstrated distinct features and advantages in different aspects. |
| first_indexed | 2024-10-01T03:53:52Z |
| format | Journal Article |
| id | ntu-10356/143390 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:53:52Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1433902021-01-28T08:45:28Z A machine learning based study on pedestrian movement dynamics under emergency evacuation Wang, Ke Shi, Xiupeng Goh, Algena Pei Xuan Qian, Shunzhi School of Civil and Environmental Engineering Engineering::Civil engineering Emergency Evacuation Movement Dynamics Knowledge of evacuees' movement dynamics is crucial to building safety design and evacuation management. Although it is recognized that stepwise movement is the fundamental element to construct the whole evacuation process, movement pattern and its influencing factors are still not well understood. In this study, we explored the potential of adopting machine learning methods to study evacuees' stepwise movement1 dynamics based on two videos of quasi-emergency evacuation experiments. The movement patterns were categorized through Two-step Cluster Analysis and principal influencing factors were identified through Principal Component Analysis. The relationship between the movement patterns and the principal components were investigated using different modeling methods: traditional method (Multinomial Logit Model, MLM) and machine learning methods (Decision Tree, Support Vector Machine, K-Nearest Neighbor, and Artificial Neural Network). Results from two experimental videos showed reasonable consistency and the main findings are: (1) Distance to the target exit has the most pronounced effect on a single evacuee's stepwise movement pattern. (2) Surrounding evacuees' actions also have significant and complex influence on a single evacuee's stepwise movement pattern. (3) MLM showed comparable prediction accuracy with machine learning methods when the scenario is simple. The superiority of machine learning became apparent when the scenario was more complex, with a maximum enhancement of 13.25% in prediction accuracy. Each machine learning method demonstrated distinct features and advantages in different aspects. Nanyang Technological University Accepted version This study is conducted under the financial support from NTU (Nanyang Technological University) Research Scholarship. The authors thank Mr. Sarvi's research group (University of Melbourne) for their generous sharing of the video records. We also thank Mr. Yushu Chen (National University of Singapore) for critical discussion and comments on the manuscript. 2020-08-31T00:56:56Z 2020-08-31T00:56:56Z 2019 Journal Article Wang, K., Shi, X., Goh, A. P. X., & Qian, S. (2019). A machine learning based study on pedestrian movement dynamics under emergency evacuation. Fire Safety Journal, 106, 163-176. doi:10.1016/j.firesaf.2019.04.008 0379-7112 https://hdl.handle.net/10356/143390 10.1016/j.firesaf.2019.04.008 2-s2.0-85065502238 106 163 176 en Fire Safety Journal © 2019 Elsevier Ltd. All rights reserved. This paper was published in Fire Safety Journal and is made available with permission of Elsevier Ltd. application/pdf |
| spellingShingle | Engineering::Civil engineering Emergency Evacuation Movement Dynamics Wang, Ke Shi, Xiupeng Goh, Algena Pei Xuan Qian, Shunzhi A machine learning based study on pedestrian movement dynamics under emergency evacuation |
| title | A machine learning based study on pedestrian movement dynamics under emergency evacuation |
| title_full | A machine learning based study on pedestrian movement dynamics under emergency evacuation |
| title_fullStr | A machine learning based study on pedestrian movement dynamics under emergency evacuation |
| title_full_unstemmed | A machine learning based study on pedestrian movement dynamics under emergency evacuation |
| title_short | A machine learning based study on pedestrian movement dynamics under emergency evacuation |
| title_sort | machine learning based study on pedestrian movement dynamics under emergency evacuation |
| topic | Engineering::Civil engineering Emergency Evacuation Movement Dynamics |
| url | https://hdl.handle.net/10356/143390 |
| work_keys_str_mv | AT wangke amachinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT shixiupeng amachinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT gohalgenapeixuan amachinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT qianshunzhi amachinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT wangke machinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT shixiupeng machinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT gohalgenapeixuan machinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation AT qianshunzhi machinelearningbasedstudyonpedestrianmovementdynamicsunderemergencyevacuation |