An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data
It is of great significance to identify dangerous driving behavior by extracting vehicle trajectory through video monitoring to ensure highway traffic safety. At present, there is no suitable method to identify dangerous driving vehicles accurately based on trajectory data. This paper aims to develo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/10/1557 |
| _version_ | 1797500316910878720 |
|---|---|
| author | Shengxue Zhu Chongyi Li Kexin Fang Yichuan Peng Yuming Jiang Yajie Zou |
| author_facet | Shengxue Zhu Chongyi Li Kexin Fang Yichuan Peng Yuming Jiang Yajie Zou |
| author_sort | Shengxue Zhu |
| collection | DOAJ |
| description | It is of great significance to identify dangerous driving behavior by extracting vehicle trajectory through video monitoring to ensure highway traffic safety. At present, there is no suitable method to identify dangerous driving vehicles accurately based on trajectory data. This paper aims to develop a detection algorithm for identifying dangerous driving behavior based on the road scene, which is mainly composed of imbalanced dangerous driver detection and labeling, extraction of driving behavior characteristics and the establishment of a recognition model about dangerous driving behavior. Firstly, this paper defines the risk index of the vehicle related to five types of dangerous driving behavior: dangerous following, lateral deviation, frequent acceleration and deceleration, frequent lane change, and forced insertion. Then, a variety of methods, including K-means clustering, local factor anomaly algorithm, isolation forest and OneClassSVM, are used to carry out anomaly detection on the risk indicators of drivers, and the optimal method is proposed to identify dangerous drivers. Then, the speed and acceleration of each vehicle are Fourier transformed to obtain the characteristics of the driver’s driving behavior. Finally, considering the imbalanced characteristic of the analyzed dataset with a very small proportion of dangerous drivers, this paper compares a variety of imbalanced classification algorithms to optimize the recognition performance of dangerous driving behavior. The results show that the OneClassSVM detection algorithm can be effectively applied to the identification of dangerous driving behavior. The improved Xgboost algorithm performs best for the extremely imbalanced data of dangerous drivers. |
| first_indexed | 2024-03-10T03:00:10Z |
| format | Article |
| id | doaj.art-948343b8346345249b3cd15ec967ec58 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:00:10Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-948343b8346345249b3cd15ec967ec582023-11-23T10:46:55ZengMDPI AGElectronics2079-92922022-05-011110155710.3390/electronics11101557An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced DataShengxue Zhu0Chongyi Li1Kexin Fang2Yichuan Peng3Yuming Jiang4Yajie Zou5Jiangsu Key Laboratory of Traffic and Transportation Security, Huaiyin Institute of Technology, Huaian 223003, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 200092, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 200092, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 200092, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 200092, ChinaKey Laboratory of Road and Traffic Engineering of Ministry of Education, Tongji University, Shanghai 200092, ChinaIt is of great significance to identify dangerous driving behavior by extracting vehicle trajectory through video monitoring to ensure highway traffic safety. At present, there is no suitable method to identify dangerous driving vehicles accurately based on trajectory data. This paper aims to develop a detection algorithm for identifying dangerous driving behavior based on the road scene, which is mainly composed of imbalanced dangerous driver detection and labeling, extraction of driving behavior characteristics and the establishment of a recognition model about dangerous driving behavior. Firstly, this paper defines the risk index of the vehicle related to five types of dangerous driving behavior: dangerous following, lateral deviation, frequent acceleration and deceleration, frequent lane change, and forced insertion. Then, a variety of methods, including K-means clustering, local factor anomaly algorithm, isolation forest and OneClassSVM, are used to carry out anomaly detection on the risk indicators of drivers, and the optimal method is proposed to identify dangerous drivers. Then, the speed and acceleration of each vehicle are Fourier transformed to obtain the characteristics of the driver’s driving behavior. Finally, considering the imbalanced characteristic of the analyzed dataset with a very small proportion of dangerous drivers, this paper compares a variety of imbalanced classification algorithms to optimize the recognition performance of dangerous driving behavior. The results show that the OneClassSVM detection algorithm can be effectively applied to the identification of dangerous driving behavior. The improved Xgboost algorithm performs best for the extremely imbalanced data of dangerous drivers.https://www.mdpi.com/2079-9292/11/10/1557dangerous driver identificationanomaly detectionimbalanced datavehicle trajectoryOneClassSVM algorithm |
| spellingShingle | Shengxue Zhu Chongyi Li Kexin Fang Yichuan Peng Yuming Jiang Yajie Zou An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data Electronics dangerous driver identification anomaly detection imbalanced data vehicle trajectory OneClassSVM algorithm |
| title | An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data |
| title_full | An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data |
| title_fullStr | An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data |
| title_full_unstemmed | An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data |
| title_short | An Optimized Algorithm for Dangerous Driving Behavior Identification Based on Unbalanced Data |
| title_sort | optimized algorithm for dangerous driving behavior identification based on unbalanced data |
| topic | dangerous driver identification anomaly detection imbalanced data vehicle trajectory OneClassSVM algorithm |
| url | https://www.mdpi.com/2079-9292/11/10/1557 |
| work_keys_str_mv | AT shengxuezhu anoptimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT chongyili anoptimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT kexinfang anoptimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT yichuanpeng anoptimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT yumingjiang anoptimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT yajiezou anoptimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT shengxuezhu optimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT chongyili optimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT kexinfang optimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT yichuanpeng optimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT yumingjiang optimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata AT yajiezou optimizedalgorithmfordangerousdrivingbehavioridentificationbasedonunbalanceddata |