Research on Driving Style Classification and Recognition Methods Based on Driving Events

被引：0

作者：

Qin, Datong ^{[1
]}

Chen, Moji ^{[1
]}

Cao, Yuhang ^{[1
]}

Gao, Di ^{[1
]}

机构：

[1] State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing

来源：

Zhongguo Jixie Gongcheng/China Mechanical Engineering | 2024年 / 35卷 / 09期

关键词：

driving event; driving style; random forest; spectral clustering;

D O I：

10.3969/j.issn.1004-132X.2024.09.002

中图分类号：

学科分类号：

摘要：

Aiming at the problems that, based on data Statistical characteristics, thc Classification and recognition method of driving style was easy to ignore the diversity of driving style during driving, a Classification and recognition method of driving style was proposed based on driving events, spectral clustering and random forest. Experiments were designed to collect driving data, and the data were preprocessed to extract turning events and braking events. After standardization and dimension-ality reduetion, the spectral clustering algorithm was used to clustcr thc driving style of turning events and braking events respectively. The entropy weight method was used to obtain thc driving style weights of each driver, and the aecuraey of five machinc learning algorithms was compared for driving style recognition. Rcsults show that thc aecuraey of driving style recognition is as 92.73% based on random forest, which significantly improves the aecuraey of driving style recognition. © 2024 Chinese Mechanical Engineering Society. All rights reserved.

引用

页码：1534 / 1541

页数：7

共 16 条

[1]

LI Jingwei, ZHAO Zhiguo, SHEN Peihong, Et al., Research on Methods of K-means Clustering and Recognition for Driving Style[J], Automobile Technology, 12, pp. 8-12, (2018)

[2]

ROY H K, MCGORDON A, JENNINGS P A., A Generalized Powertrain Design Optimization Meth-odology to Reduce Fuel Economy Variability in Hybrid Electric Vehicles, IEEE Transactions on Vehicular Technology, 63, 3, pp. 1055-1070, (2014)

[3]

JIANG Zhenyu, Automatic Driving Motion Planning Method Based on Driving Style Reasoning and Rein-forcement Learning[D], (2022)

[4]

WANG Wenshuo, XI Junqiang, ZHAO Ding, Driving Style Analysis Using Primitive Driving Pat-terns with Bayesian Nonparametric Approaches[J], IEEE Transactions on Intelligent Transportation Systems, 20, 8, pp. 2986-2998, (2019)

[5]

ZHU Bing, YAN Shude, ZHAO Jian, Et al., Per-sonalized Lane-change Assistance System with Driv-er Behavior Identification[J], IEEE Transactions on Vehicular Technology, 67, 11, pp. 10293-10306, (2018)

[6]

HAN Wei, WANG Wenshuo, LI Xiaohan, Et al., Statistical-based Approach for Driving Style Recognition Using Bayesian Probability with Kernel Density Estimation[J], IET Intelligent Transport Systems, 13, 1, pp. 22-30, (2019)

[7]

ZHAN Sen, Energy Management Strategy of Hybrid Electric Vehicle Based on the Recognition of Driving Cycle and Driving Style [D], (2016)

[8]

ZHU Bing, JIANG Yuande, ZHAO Jian, Et al., Typical-driving-style-oriented Personalized Adaptive Cruise Control Design Based on Human Driving Da-ta[J], Transportation Research Part C= Emerging Technologies, 100, pp. 274-288, (2019)

[9]

SUZDALEVA E, NAGY I., An Online Estimation of Driving Style Using Data-dependent Pointer Model [J], Transportation Research Part C= Emerging Technologies, 86, pp. 23-36, (2018)

[10]

QIN Datong, WANG Kang, FENG Jihao, Et al., Research on Shift Schedule of DCT Vehicle on Flat-straight Road Based on Driving Data Mining, Automotive Engineering, 44, 11, pp. 1763-1771, (2022)

← 1 2 →