Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry

Ma, Yongfeng; Li, Wenlu; Tang, Kun; Zhang, Ziyu; Chen, Shuyan

doi:10.1016/j.aap.2021.106096

Cited by 53 publications

(20 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen that the six parameter values of Type A are the largest, the parameter values of Type B are in the middle, and the parameter values of Type C are the smallest. This result is similar to the results of [ 17 , 36 ] and proves the reliability of our results. The proportions of aggressive drivers, normal drivers, and cautious drivers were 19%, 54%, and 27%, respectively.…”

Section: Resultssupporting

confidence: 93%

“…First, velocity is one of the most frequently selected parameters as a driver feature from trajectory data [ 5 , 19 , 20 , 36 , 42 , 43 ]. In the same driving environment, if a driver tends to drive at a faster speed, then the driving style will be considered more aggressive [ 44 ].…”

Section: Methodsmentioning

confidence: 99%

“…For example, refs. [ 5 , 36 ] believed that 7:00 a.m.–10:00 a.m. is a peak period. However, as shown in the speed curve in Figure 2 , this division of time does not fit this dataset.…”

Section: Methodsmentioning

confidence: 99%

“…Ref. [ 36 ] analyzed the driving styles of car-hailing drivers in different driving tasks (defined as cruising, ride requests, and drop-off). However, the in-depth analysis of the driving styles for temporal and spatial distributions needs to be supplemented.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver’s Driving Style: A Case Study in China

Liu

2022

IJERPH

View full text Add to dashboard Cite

Monitoring the driving styles of ride-hailing drivers is helpful for providing targeted training for drivers and improving the safety of the service. However, previous studies have lacked analyses of the temporal variation as well as spatial variation characteristics of driving styles. Understanding the variations can also help authorities formulate driver management policies. In this study, trajectory data are used to analyze driving styles in various temporal and spatial scenarios involving 34,167 drivers. The k-means method is used to cluster sample drivers. In terms of driving style time-varying, we found that only 31.79% of drivers could maintain a stable driving style throughout the day. Spatially, we divided the research area into two parts, namely, road segments and intersections, to analyze the spatial driving characteristics of drivers with different styles. The speed distribution, the acceleration and deceleration distributions are analyzed, results indicated that aggressive drivers display more aggressive driving styles in road segments, and conservative drivers exhibit more conservative driving styles at intersections. The findings of this study provide an understanding of temporal and spatial driving behavior factors for ride-hailing drivers and offer valuable contributions to ride-hailing driver training and road safety management.

show abstract

Section: Resultssupporting

confidence: 93%

Section: Methodsmentioning

confidence: 99%

“…For example, refs. [ 5 , 36 ] believed that 7:00 a.m.–10:00 a.m. is a peak period. However, as shown in the speed curve in Figure 2 , this division of time does not fit this dataset.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver’s Driving Style: A Case Study in China

Liu

2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…One uses the thresholds of vehicle kinematic parameters to identify the start and end of driving behaviors. Ma et al [ 18 ] identified three kinds of driving behaviors, namely, turning, acceleration, and deceleration, by thresholds of vehicle angular velocity and longitudinal acceleration, with three styles, aggressive, normal, and cautious, to explore the differences in driving styles during different driving stages of online car-hailing. Although this method is simple and easy to comprehend, most of the thresholds in existing research are determined empirically, leading to weak identification effects, with the identified driving behaviors requiring manual verifications in most cases.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Xie

Chen

et al. 2021

IJERPH

Self Cite

View full text Add to dashboard Cite

Real-time driving behavior identification has a wide range of applications in monitoring driver states and predicting driving risks. In contrast to the traditional approaches that were mostly based on a single data source with poor identification capabilities, this paper innovatively integrates driver expression into driving behavior identification. First, 12-day online car-hailing driving data were collected in a non-intrusive manner. Then, with vehicle kinematic data and driver expression data as inputs, a stacked Long Short-Term Memory (S-LSTM) network was constructed to identify five kinds of driving behaviors, namely, lane keeping, acceleration, deceleration, turning, and lane changing. The Artificial Neural Network (ANN) and XGBoost algorithms were also employed as a comparison. Additionally, ten sliding time windows of different lengths were introduced to generate driving behavior identification samples. The results show that, using all sources of data yields better results than using the kinematic data only, with the average F1 value improved by 0.041, while the S-LSTM algorithm is better than the ANN and XGBoost algorithms. Furthermore, the optimal time window length is 3.5 s, with an average F1 of 0.877. This study provides an effective method for real-time driving behavior identification, and thereby supports the driving pattern analysis and Advanced Driving Assistance System.

show abstract

Consistency Analysis of Driving Style Classification Based on Subjective Evaluation and Objective Driving Behavior

Zhang

Mao³

et al. 2023

HCI in Mobility, Transport, and Automotive Systems

View full text Add to dashboard Cite

Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry

Cited by 53 publications

References 31 publications

The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver’s Driving Style: A Case Study in China

The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver’s Driving Style: A Case Study in China

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Consistency Analysis of Driving Style Classification Based on Subjective Evaluation and Objective Driving Behavior

Contact Info

Product

Resources

About