Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model
Safety of drivers in freeway work zones has been a problem. Real-time crash prediction helps prevent crashes before they happen. This paper looks at real-time crash prediction in freeway work zones by using machine learning approaches. Both the Convolutional Neural Network and the Binary Logistic Re...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2022-09-01
|
Series: | International Journal of Transportation Science and Technology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2046043021000514 |
_version_ | 1797760565784870912 |
---|---|
author | Junhua Wang Hao Song Ting Fu Molly Behan Lei Jie Yingxian He Qiangqiang Shangguan |
author_facet | Junhua Wang Hao Song Ting Fu Molly Behan Lei Jie Yingxian He Qiangqiang Shangguan |
author_sort | Junhua Wang |
collection | DOAJ |
description | Safety of drivers in freeway work zones has been a problem. Real-time crash prediction helps prevent crashes before they happen. This paper looks at real-time crash prediction in freeway work zones by using machine learning approaches. Both the Convolutional Neural Network and the Binary Logistic Regression model are introduced. For training and testing the models, crash data and traffic data from several freeways in D7 zone, Los Angeles, California, were used. Crash data were collected from California Highway Patrol Incident System, and traffic data were obtained from the Caltrans Performance Measurement System. Data processing and matching were conducted. Both the two models were trained and tested. Results show that the Convolutional Neural Network performed slightly better over the Binary Logistic Regression model in predicting crashes with a global accuracy of 79.50%. Despite this, the main merit of the Binary Logistic Regression model is that it is able estimate the impact of affecting variables on the probability of crashes and can help identify the factors related to risks in work zones. Machine learning approaches applied in this study perform well in crash prediction. In general, machine learning techniques and reliable real-time crash prediction applications can be promising in helping drivers and transportation engineers make timely responses to potential crashes on freeways. |
first_indexed | 2024-03-12T19:01:21Z |
format | Article |
id | doaj.art-7e144ed3ef634f2dbb12b02ab970bc20 |
institution | Directory Open Access Journal |
issn | 2046-0430 |
language | English |
last_indexed | 2024-03-12T19:01:21Z |
publishDate | 2022-09-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | International Journal of Transportation Science and Technology |
spelling | doaj.art-7e144ed3ef634f2dbb12b02ab970bc202023-08-02T06:39:03ZengKeAi Communications Co., Ltd.International Journal of Transportation Science and Technology2046-04302022-09-01113484495Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression modelJunhua Wang0Hao Song1Ting Fu2Molly Behan3Lei Jie4Yingxian He5Qiangqiang Shangguan6Engineering Research Center of Road Traffic Safety and Environment, Ministry of Education, Shanghai, China; College of Transportation Engineering, Tongji University, 4800 Cao’an Highway, Shanghai, ChinaEngineering Research Center of Road Traffic Safety and Environment, Ministry of Education, Shanghai, China; College of Transportation Engineering, Tongji University, 4800 Cao’an Highway, Shanghai, ChinaEngineering Research Center of Road Traffic Safety and Environment, Ministry of Education, Shanghai, China; College of Transportation Engineering, Tongji University, 4800 Cao’an Highway, Shanghai, China; Corresponding author at: 4800 Cao’an Highway, Shanghai, China.Department of Civil Engineering and Applied Mechanics, McGill University, Quebec H3A 0C3, CanadaHangjinqu Branch of Zhejiang Communications Investment Group CO., LTD, Hangzhou, Zhejiang, ChinaEngineering Research Center of Road Traffic Safety and Environment, Ministry of Education, Shanghai, China; College of Transportation Engineering, Tongji University, 4800 Cao’an Highway, Shanghai, ChinaEngineering Research Center of Road Traffic Safety and Environment, Ministry of Education, Shanghai, China; College of Transportation Engineering, Tongji University, 4800 Cao’an Highway, Shanghai, ChinaSafety of drivers in freeway work zones has been a problem. Real-time crash prediction helps prevent crashes before they happen. This paper looks at real-time crash prediction in freeway work zones by using machine learning approaches. Both the Convolutional Neural Network and the Binary Logistic Regression model are introduced. For training and testing the models, crash data and traffic data from several freeways in D7 zone, Los Angeles, California, were used. Crash data were collected from California Highway Patrol Incident System, and traffic data were obtained from the Caltrans Performance Measurement System. Data processing and matching were conducted. Both the two models were trained and tested. Results show that the Convolutional Neural Network performed slightly better over the Binary Logistic Regression model in predicting crashes with a global accuracy of 79.50%. Despite this, the main merit of the Binary Logistic Regression model is that it is able estimate the impact of affecting variables on the probability of crashes and can help identify the factors related to risks in work zones. Machine learning approaches applied in this study perform well in crash prediction. In general, machine learning techniques and reliable real-time crash prediction applications can be promising in helping drivers and transportation engineers make timely responses to potential crashes on freeways.http://www.sciencedirect.com/science/article/pii/S2046043021000514Work zoneFreeway safetyReal-time crash predictionMachine learningConvolutional Neural NetworkBinary Logistic Regression |
spellingShingle | Junhua Wang Hao Song Ting Fu Molly Behan Lei Jie Yingxian He Qiangqiang Shangguan Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model International Journal of Transportation Science and Technology Work zone Freeway safety Real-time crash prediction Machine learning Convolutional Neural Network Binary Logistic Regression |
title | Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model |
title_full | Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model |
title_fullStr | Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model |
title_full_unstemmed | Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model |
title_short | Crash prediction for freeway work zones in real time: A comparison between Convolutional Neural Network and Binary Logistic Regression model |
title_sort | crash prediction for freeway work zones in real time a comparison between convolutional neural network and binary logistic regression model |
topic | Work zone Freeway safety Real-time crash prediction Machine learning Convolutional Neural Network Binary Logistic Regression |
url | http://www.sciencedirect.com/science/article/pii/S2046043021000514 |
work_keys_str_mv | AT junhuawang crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel AT haosong crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel AT tingfu crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel AT mollybehan crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel AT leijie crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel AT yingxianhe crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel AT qiangqiangshangguan crashpredictionforfreewayworkzonesinrealtimeacomparisonbetweenconvolutionalneuralnetworkandbinarylogisticregressionmodel |