A two-step machine learning method for casualty prediction under emergencies
Casualty prediction is meaningful to the emergency management of natural hazards and human-induced disasters. In this study, a two-step machine learning method, including classification step and regression step, is proposed to predict the number of casualties under emergencies. In the classification...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-09-01
|
| Series: | Journal of Safety Science and Resilience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666449622000160 |
| _version_ | 1798036641010417664 |
|---|---|
| author | Xiaofeng Hu Jinming Hu Miaomiao Hou |
| author_facet | Xiaofeng Hu Jinming Hu Miaomiao Hou |
| author_sort | Xiaofeng Hu |
| collection | DOAJ |
| description | Casualty prediction is meaningful to the emergency management of natural hazards and human-induced disasters. In this study, a two-step machine learning method, including classification step and regression step, is proposed to predict the number of casualties under emergencies. In the classification step, whether there are casualties under an incident is firstly predicted, then in the regression step, samples predicted to have casualties are used to further predict the exact number of the casualties. Using an open-source dataset, this two-step method is validated. The results show that the two-step model performs better than the original regression models. Back propagation(BP) neural network combined with Random Forest performs the best in terms of the death toll and the number of injuries. Among all the two-step models, the lowest mean absolute error (MAE) for the death toll is 1.67 while that for the number of injuries is 4.13, which indicates that this method can accurately predict the number of casualties under emergencies. This study's results are expected to provide support for decision-making on rapid resource allocation and other emergency responses. |
| first_indexed | 2024-04-11T21:15:41Z |
| format | Article |
| id | doaj.art-42d86b531fed4a2a8b7f9a0ed1d82954 |
| institution | Directory Open Access Journal |
| issn | 2666-4496 |
| language | English |
| last_indexed | 2024-04-11T21:15:41Z |
| publishDate | 2022-09-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Safety Science and Resilience |
| spelling | doaj.art-42d86b531fed4a2a8b7f9a0ed1d829542022-12-22T04:02:49ZengKeAi Communications Co., Ltd.Journal of Safety Science and Resilience2666-44962022-09-0133243251A two-step machine learning method for casualty prediction under emergenciesXiaofeng Hu0Jinming Hu1Miaomiao Hou2Corresponding author.; School of Information Technology and Cyber Security, People's Public Security University of China, Beijing 100038, ChinaSchool of Information Technology and Cyber Security, People's Public Security University of China, Beijing 100038, ChinaSchool of Information Technology and Cyber Security, People's Public Security University of China, Beijing 100038, ChinaCasualty prediction is meaningful to the emergency management of natural hazards and human-induced disasters. In this study, a two-step machine learning method, including classification step and regression step, is proposed to predict the number of casualties under emergencies. In the classification step, whether there are casualties under an incident is firstly predicted, then in the regression step, samples predicted to have casualties are used to further predict the exact number of the casualties. Using an open-source dataset, this two-step method is validated. The results show that the two-step model performs better than the original regression models. Back propagation(BP) neural network combined with Random Forest performs the best in terms of the death toll and the number of injuries. Among all the two-step models, the lowest mean absolute error (MAE) for the death toll is 1.67 while that for the number of injuries is 4.13, which indicates that this method can accurately predict the number of casualties under emergencies. This study's results are expected to provide support for decision-making on rapid resource allocation and other emergency responses.http://www.sciencedirect.com/science/article/pii/S2666449622000160EmergenciesMachine learningCasualty predictionTwo-step method |
| spellingShingle | Xiaofeng Hu Jinming Hu Miaomiao Hou A two-step machine learning method for casualty prediction under emergencies Journal of Safety Science and Resilience Emergencies Machine learning Casualty prediction Two-step method |
| title | A two-step machine learning method for casualty prediction under emergencies |
| title_full | A two-step machine learning method for casualty prediction under emergencies |
| title_fullStr | A two-step machine learning method for casualty prediction under emergencies |
| title_full_unstemmed | A two-step machine learning method for casualty prediction under emergencies |
| title_short | A two-step machine learning method for casualty prediction under emergencies |
| title_sort | two step machine learning method for casualty prediction under emergencies |
| topic | Emergencies Machine learning Casualty prediction Two-step method |
| url | http://www.sciencedirect.com/science/article/pii/S2666449622000160 |
| work_keys_str_mv | AT xiaofenghu atwostepmachinelearningmethodforcasualtypredictionunderemergencies AT jinminghu atwostepmachinelearningmethodforcasualtypredictionunderemergencies AT miaomiaohou atwostepmachinelearningmethodforcasualtypredictionunderemergencies AT xiaofenghu twostepmachinelearningmethodforcasualtypredictionunderemergencies AT jinminghu twostepmachinelearningmethodforcasualtypredictionunderemergencies AT miaomiaohou twostepmachinelearningmethodforcasualtypredictionunderemergencies |