CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data

被引：9

作者：

Cai, Yingfeng ^{[1
]}

Zhao, Ruidong ^{[1
]}

Wang, Hai ^{[2
,3
]}

Chen, Long ^{[1
]}

Lian, Yubo ^{[4
]}

Zhong, Yilin ^{[4
]}

机构：

[1] Jiangsu Univ, Automot Engn Res Inst, Zhenjiang, Peoples R China

[2] Jiangsu Univ, Automot Engn Res Inst, Zhenjiang, Peoples R China

[3] Zhenjiang City Jiangsu Univ Engn Technol Res Inst, Sch Automot & Traff Engn, Zhenjiang 212013, Peoples R China

[4] BYD Auto Ind Co Ltd, Automot Engn Res Inst, Shenzhen 518118, Peoples R China

来源：

IEEE ACCESS | 2023年 / 11卷

基金：

中国国家自然科学基金;

关键词：

Convolutional neural network (CNN); driving style classification; LSTM; neural network; time series data;

D O I：

10.1109/ACCESS.2023.3245146

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper aims to establish a driving style recognition method that is highly accurate, fast and generalizable, considering the lack of data types in driving style classification task and the low recognition accuracy of widely used unsupervised clustering algorithms and single convolutional neural network methods. First, we propose a method to collect the information on driver's operation time sequence in view of the imperfect driving data, and then extract the driver's style features through convolutional neural network. Then, for the collected temporal data, the Long Short Term Memory networks (LSTM) module is added to encode and transform the driving features, to achieve the driving style classification. The results show that the accuracy of driving style recognition reaches over 93%, while the speed is improved significantly.

引用

页码：16203 / 16212

页数：10

共 32 条

[1] Driver identification using only the CAN-Bus vehicle data through an RCN deep learning approach [J].

Abdennour, N. ;

Ouni, T. ;

Amor, N. Ben .

ROBOTICS AND AUTONOMOUS SYSTEMS, 2021, 136

[2]

[Anonymous], 2020, Journal of Hunan University (Natural Sciences), V47, P10

[3] YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving [J].

Cai, Yingfeng ;

Luan, Tianyu ;

Gao, Hongbo ;

Wang, Hai ;

Chen, Long ;

Li, Yicheng ;

Sotelo, Miguel Angel ;

Li, Zhixiong .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70

[4] Driving Style Recognition under Connected Circumstance Using a Supervised Hierarchical Bayesian Model [J].

Chen, Depeng ;

Chen, Zhijun ;

Zhang, Yishi ;

Qu, Xu ;

Zhang, Mingyang ;

Wu, Chaozhong .

JOURNAL OF ADVANCED TRANSPORTATION, 2021, 2021

[5] Driver Profiling Using Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) Methods [J].

Cura, Aslihan ;

Kucuk, Haluk ;

Ergen, Erdem ;

Oksuzoglu, Ismail Burak .

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 22 (10) :6572-6582

[6] Trust in what? Exploring the interdependency between an automated vehicle's driving style and traffic situations [J].

Ekman, Fredrick ;

Johansson, Mikael ;

Karlsson, MariAnne ;

Stromberg, Helena ;

Bligard, Lars-Ola .

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2021, 76 :59-71

[7] Real Time Driver Drowsiness Detection Based on Driver's Face Image Behavior Using a System of Human Computer Interaction Implemented in a Smartphone [J].

Galarza, Eddie E. ;

Egas, Fabricio D. ;

Silva, Franklin M. ;

Velasco, Paola M. ;

Galarza, Eddie D. .

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY & SYSTEMS (ICITS 2018), 2018, 721 :563-572

[8] Advanced driver assistance systems (ADAS): Demographics, preferred sources of information, and accuracy of ADAS knowledge [J].

Greenwood, Pamela M. ;

Lenneman, John K. ;

Baldwin, Carryl L. .

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2022, 86 :131-150

[9] Collaborative driving style classification method enabled by majority voting ensemble learning for enhancing classification performance [J].

Guo, Yi ;

Wang, Xiaolan ;

Huang, Yongmao ;

Xu, Liang .

PLOS ONE, 2021, 16 (07)

[10]

Ishibashi M, 2007, PROCEEDINGS OF SICE ANNUAL CONFERENCE, VOLS 1-8, P1128

← 1 2 3 4 →