Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost
Older pedestrians are vulnerable on the streets and at significant risk of injury or death when involved in crashes. Pedestrians’ safety is critical for roadway agencies to consider and improve, especially older pedestrians aged greater than 65 years old. To better protect the older pedestrian group...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Sustainability |
Subjects: | |
Online Access: | https://www.mdpi.com/2071-1050/13/2/926 |
id |
doaj-4fcfa4e152484e478d4d41104c4447bf |
---|---|
record_format |
Article |
spelling |
doaj-4fcfa4e152484e478d4d41104c4447bf2021-01-19T00:02:42ZengMDPI AGSustainability2071-10502021-01-011392692610.3390/su13020926Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoostManze Guo0Zhenzhou Yuan1Bruce Janson2Yongxin Peng3Yang Yang4Wencheng Wang5Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Ministry of Transport, Beijing Jiaotong University, P.O. Box 173364, Beijing 100044, ChinaKey Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Ministry of Transport, Beijing Jiaotong University, P.O. Box 173364, Beijing 100044, ChinaDepartment of Civil Engineering, University of Colorado Denver, P.O. Box 173364, Denver, CO 80217-3364, USAZachry Department of Civil and Environmental Engineering, Texas A&M University, P.O. Box 3135, TAMU, College Station, TX 77843-3135, USAKey Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Ministry of Transport, Beijing Jiaotong University, P.O. Box 173364, Beijing 100044, ChinaBeijing Municipal Institute of City Planning & Design, Beijing 100045, ChinaOlder pedestrians are vulnerable on the streets and at significant risk of injury or death when involved in crashes. Pedestrians’ safety is critical for roadway agencies to consider and improve, especially older pedestrians aged greater than 65 years old. To better protect the older pedestrian group, the factors that contribute to the older crashes need to be analyzed deeply. Traditional modeling approaches such as Logistic models for data analysis may lead to modeling distortions due to the independence assumptions. In this study, Extreme Gradient Boosting (XGBoost), is used to model the classification problem of three different levels of severity of older pedestrian traffic crashes from crash data in Colorado, US. Further, Shapley Additive explanations (SHAP) are implemented to interpret the XGBoost model result and analyze each feature’s importance related to the levels of older pedestrian crashes. The interpretation results show that the driver characteristic, older pedestrian characteristics, and vehicle movement are the most important factors influencing the probability of the three different severity levels. Those results investigate each severity level’s correlation factors, which can inform the department of traffic management and the department of road infrastructure to protect older pedestrians by controlling or managing some of those significant features.https://www.mdpi.com/2071-1050/13/2/926older pedestrian traffic safetypedestrian traffic crashesmachine learningcrashes severitySHAPXGBoost |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Manze Guo Zhenzhou Yuan Bruce Janson Yongxin Peng Yang Yang Wencheng Wang |
spellingShingle |
Manze Guo Zhenzhou Yuan Bruce Janson Yongxin Peng Yang Yang Wencheng Wang Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost Sustainability older pedestrian traffic safety pedestrian traffic crashes machine learning crashes severity SHAP XGBoost |
author_facet |
Manze Guo Zhenzhou Yuan Bruce Janson Yongxin Peng Yang Yang Wencheng Wang |
author_sort |
Manze Guo |
title |
Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost |
title_short |
Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost |
title_full |
Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost |
title_fullStr |
Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost |
title_full_unstemmed |
Older Pedestrian Traffic Crashes Severity Analysis Based on an Emerging Machine Learning XGBoost |
title_sort |
older pedestrian traffic crashes severity analysis based on an emerging machine learning xgboost |
publisher |
MDPI AG |
series |
Sustainability |
issn |
2071-1050 |
publishDate |
2021-01-01 |
description |
Older pedestrians are vulnerable on the streets and at significant risk of injury or death when involved in crashes. Pedestrians’ safety is critical for roadway agencies to consider and improve, especially older pedestrians aged greater than 65 years old. To better protect the older pedestrian group, the factors that contribute to the older crashes need to be analyzed deeply. Traditional modeling approaches such as Logistic models for data analysis may lead to modeling distortions due to the independence assumptions. In this study, Extreme Gradient Boosting (XGBoost), is used to model the classification problem of three different levels of severity of older pedestrian traffic crashes from crash data in Colorado, US. Further, Shapley Additive explanations (SHAP) are implemented to interpret the XGBoost model result and analyze each feature’s importance related to the levels of older pedestrian crashes. The interpretation results show that the driver characteristic, older pedestrian characteristics, and vehicle movement are the most important factors influencing the probability of the three different severity levels. Those results investigate each severity level’s correlation factors, which can inform the department of traffic management and the department of road infrastructure to protect older pedestrians by controlling or managing some of those significant features. |
topic |
older pedestrian traffic safety pedestrian traffic crashes machine learning crashes severity SHAP XGBoost |
url |
https://www.mdpi.com/2071-1050/13/2/926 |
work_keys_str_mv |
AT manzeguo olderpedestriantrafficcrashesseverityanalysisbasedonanemergingmachinelearningxgboost AT zhenzhouyuan olderpedestriantrafficcrashesseverityanalysisbasedonanemergingmachinelearningxgboost AT brucejanson olderpedestriantrafficcrashesseverityanalysisbasedonanemergingmachinelearningxgboost AT yongxinpeng olderpedestriantrafficcrashesseverityanalysisbasedonanemergingmachinelearningxgboost AT yangyang olderpedestriantrafficcrashesseverityanalysisbasedonanemergingmachinelearningxgboost AT wenchengwang olderpedestriantrafficcrashesseverityanalysisbasedonanemergingmachinelearningxgboost |
_version_ |
1724332713317498880 |