Research on the influence factors of accident severity of new energy vehicles based on ensemble learning
With the deepening of the concept of green, low-carbon, and sustainable development, the continuous growth of the ownership of new energy vehicles has led to increasing public concerns about the traffic safety issues of these vehicles. In order to conduct research on the traffic safety of new energy...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1329688/full |
| _version_ | 1797449184559759360 |
|---|---|
| author | Zixuan Zhang Zhenxing Niu Yan Li Xuejun Ma Shaofeng Sun |
| author_facet | Zixuan Zhang Zhenxing Niu Yan Li Xuejun Ma Shaofeng Sun |
| author_sort | Zixuan Zhang |
| collection | DOAJ |
| description | With the deepening of the concept of green, low-carbon, and sustainable development, the continuous growth of the ownership of new energy vehicles has led to increasing public concerns about the traffic safety issues of these vehicles. In order to conduct research on the traffic safety of new energy vehicles, three sampling methods, namely, Synthetic Minority Over-sampling Technique (SMOTE), Edited Nearest Neighbours (ENN), and SMOTE-ENN hybrid sampling, were employed, along with cost-sensitive learning, to address the problem of imbalanced data in the UK road traffic accident dataset. Three algorithms, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost), were selected for modeling work. Lastly, the evaluation criteria used for model selection were primarily based on G-mean, with AUC and accuracy as secondary measures. The TreeSHAP method was applied to explain the interaction mechanism between accident severity and its influencing factors in the constructed models. The results showed that LightGBM had a more stable overall performance and higher computational efficiency. XGBoost demonstrated a balanced combination of computational efficiency and model performance. CatBoost, however, was more time-consuming and showed less stability with different datasets. Studies have found that people using fewer protective means of transportation (bicycles, motorcycles) and vulnerable groups such as pedestrians are susceptible to serious injury and death. |
| first_indexed | 2024-03-09T14:22:10Z |
| format | Article |
| id | doaj.art-01b99c28e3cd46f49886cc3e0a26c073 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-03-09T14:22:10Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-01b99c28e3cd46f49886cc3e0a26c0732023-11-28T09:48:47ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-11-011110.3389/fenrg.2023.13296881329688Research on the influence factors of accident severity of new energy vehicles based on ensemble learningZixuan Zhang0Zhenxing Niu1Yan Li2Xuejun Ma3Shaofeng Sun4School of Transportation Engineering, Chang’an University, Xi’an, Shaanxi, ChinaKey Laboratory of Highway Engineering in Special Region of Ministry of Education, Chang’an University, Xi’an, Shaanxi, ChinaKey Laboratory of Highway Engineering in Special Region of Ministry of Education, Chang’an University, Xi’an, Shaanxi, ChinaJiaoke Transport Consultants Ltd., Beijing, ChinaSchool of Transportation Engineering, Chang’an University, Xi’an, Shaanxi, ChinaWith the deepening of the concept of green, low-carbon, and sustainable development, the continuous growth of the ownership of new energy vehicles has led to increasing public concerns about the traffic safety issues of these vehicles. In order to conduct research on the traffic safety of new energy vehicles, three sampling methods, namely, Synthetic Minority Over-sampling Technique (SMOTE), Edited Nearest Neighbours (ENN), and SMOTE-ENN hybrid sampling, were employed, along with cost-sensitive learning, to address the problem of imbalanced data in the UK road traffic accident dataset. Three algorithms, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost), were selected for modeling work. Lastly, the evaluation criteria used for model selection were primarily based on G-mean, with AUC and accuracy as secondary measures. The TreeSHAP method was applied to explain the interaction mechanism between accident severity and its influencing factors in the constructed models. The results showed that LightGBM had a more stable overall performance and higher computational efficiency. XGBoost demonstrated a balanced combination of computational efficiency and model performance. CatBoost, however, was more time-consuming and showed less stability with different datasets. Studies have found that people using fewer protective means of transportation (bicycles, motorcycles) and vulnerable groups such as pedestrians are susceptible to serious injury and death.https://www.frontiersin.org/articles/10.3389/fenrg.2023.1329688/fullgreen transportationtraffic engineeringensemble learningtraffic accidentsnew energy vehicles |
| spellingShingle | Zixuan Zhang Zhenxing Niu Yan Li Xuejun Ma Shaofeng Sun Research on the influence factors of accident severity of new energy vehicles based on ensemble learning Frontiers in Energy Research green transportation traffic engineering ensemble learning traffic accidents new energy vehicles |
| title | Research on the influence factors of accident severity of new energy vehicles based on ensemble learning |
| title_full | Research on the influence factors of accident severity of new energy vehicles based on ensemble learning |
| title_fullStr | Research on the influence factors of accident severity of new energy vehicles based on ensemble learning |
| title_full_unstemmed | Research on the influence factors of accident severity of new energy vehicles based on ensemble learning |
| title_short | Research on the influence factors of accident severity of new energy vehicles based on ensemble learning |
| title_sort | research on the influence factors of accident severity of new energy vehicles based on ensemble learning |
| topic | green transportation traffic engineering ensemble learning traffic accidents new energy vehicles |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1329688/full |
| work_keys_str_mv | AT zixuanzhang researchontheinfluencefactorsofaccidentseverityofnewenergyvehiclesbasedonensemblelearning AT zhenxingniu researchontheinfluencefactorsofaccidentseverityofnewenergyvehiclesbasedonensemblelearning AT yanli researchontheinfluencefactorsofaccidentseverityofnewenergyvehiclesbasedonensemblelearning AT xuejunma researchontheinfluencefactorsofaccidentseverityofnewenergyvehiclesbasedonensemblelearning AT shaofengsun researchontheinfluencefactorsofaccidentseverityofnewenergyvehiclesbasedonensemblelearning |