Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study
There have been numerous studies on traffic accidents and their severity, particularly in relation to weather conditions and road geometry. In these studies, traditional statistical methods have been employed, such as linear regression, logistic regression, and negative binomial regression modeling,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/1/129 |
| _version_ | 1818016262967525376 |
|---|---|
| author | Jonghak Lee Taekwan Yoon Sangil Kwon Jongtae Lee |
| author_facet | Jonghak Lee Taekwan Yoon Sangil Kwon Jongtae Lee |
| author_sort | Jonghak Lee |
| collection | DOAJ |
| description | There have been numerous studies on traffic accidents and their severity, particularly in relation to weather conditions and road geometry. In these studies, traditional statistical methods have been employed, such as linear regression, logistic regression, and negative binomial regression modeling, which are the most common linear and non-linear regression analysis methods. In this research, machine learning architecture was applied to this problem using the random forest, artificial neural network, and decision tree techniques to ascertain the strengths and weaknesses of these methods. Three data sets were used: road geometry data, precipitation data, and traffic accident data over nine years corresponding to the Naebu Expressway, which is located in Seoul, Korea. For the model evaluation, three measures were employed: the out-of-bag estimate of error rate (OOB), mean square error (MSE), and root mean square error (RMSE). The low mean OOB, MSE, and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy. |
| first_indexed | 2024-04-14T07:10:55Z |
| format | Article |
| id | doaj.art-f26fba02585c4be5a44de7c39b325899 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-14T07:10:55Z |
| publishDate | 2019-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f26fba02585c4be5a44de7c39b3258992022-12-22T02:06:27ZengMDPI AGApplied Sciences2076-34172019-12-0110112910.3390/app10010129app10010129Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City StudyJonghak Lee0Taekwan Yoon1Sangil Kwon2Jongtae Lee3Transportation Pollution Research Center, National Institute of Environmental Research, (Environmental Research Complex), Hwangyeong-ro 42 Seo-gu, Incheon 22689, KoreaSmart Infrastructure Center, Korea Research Institute for Human Settlements, 5 Gukchaegyeonguwon-ro, Sejong-si 30149, KoreaTransportation Pollution Research Center, National Institute of Environmental Research, (Environmental Research Complex), Hwangyeong-ro 42 Seo-gu, Incheon 22689, KoreaTransportation Pollution Research Center, National Institute of Environmental Research, (Environmental Research Complex), Hwangyeong-ro 42 Seo-gu, Incheon 22689, KoreaThere have been numerous studies on traffic accidents and their severity, particularly in relation to weather conditions and road geometry. In these studies, traditional statistical methods have been employed, such as linear regression, logistic regression, and negative binomial regression modeling, which are the most common linear and non-linear regression analysis methods. In this research, machine learning architecture was applied to this problem using the random forest, artificial neural network, and decision tree techniques to ascertain the strengths and weaknesses of these methods. Three data sets were used: road geometry data, precipitation data, and traffic accident data over nine years corresponding to the Naebu Expressway, which is located in Seoul, Korea. For the model evaluation, three measures were employed: the out-of-bag estimate of error rate (OOB), mean square error (MSE), and root mean square error (RMSE). The low mean OOB, MSE, and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy.https://www.mdpi.com/2076-3417/10/1/129machine learning architecturerandom forest modelartificial neural networkdecision tree algorithmaccident severity levelroad surface conditionroad hazard zone forecasting |
| spellingShingle | Jonghak Lee Taekwan Yoon Sangil Kwon Jongtae Lee Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study Applied Sciences machine learning architecture random forest model artificial neural network decision tree algorithm accident severity level road surface condition road hazard zone forecasting |
| title | Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study |
| title_full | Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study |
| title_fullStr | Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study |
| title_full_unstemmed | Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study |
| title_short | Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study |
| title_sort | model evaluation for forecasting traffic accident severity in rainy seasons using machine learning algorithms seoul city study |
| topic | machine learning architecture random forest model artificial neural network decision tree algorithm accident severity level road surface condition road hazard zone forecasting |
| url | https://www.mdpi.com/2076-3417/10/1/129 |
| work_keys_str_mv | AT jonghaklee modelevaluationforforecastingtrafficaccidentseverityinrainyseasonsusingmachinelearningalgorithmsseoulcitystudy AT taekwanyoon modelevaluationforforecastingtrafficaccidentseverityinrainyseasonsusingmachinelearningalgorithmsseoulcitystudy AT sangilkwon modelevaluationforforecastingtrafficaccidentseverityinrainyseasonsusingmachinelearningalgorithmsseoulcitystudy AT jongtaelee modelevaluationforforecastingtrafficaccidentseverityinrainyseasonsusingmachinelearningalgorithmsseoulcitystudy |