This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Research on Driver Driving Style and Driving Condition Recognition Model Based on SVM and XGBoost
Technical Paper
2022-01-0227
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
At present, the remote monitoring cloud platform of many automobile companies only displays the collected data information, and it does not fully mine the deep-level information of the data. This paper uses data mining and machine learning methods to build a driver's driving style and driving condition prediction and recognition model based on the historical driving information generated by the vehicle, so as to improve the supervision and safety of the driver and the vehicle by automobile companies and other automobile-related industries. First, 36 standard driving cycles are utilized to construct an initial operating condition block data set. Second, we obtain the feature variables of driving style and driving conditions through feature engineering, and two recognition model data sets use the principal component analysis (PCA) and clustering algorithm for data dimensionality reduction and cluster analysis. Then, two types of supervised learning, support vector machine (SVM) and extreme gradient boosting model (XGBoost), are selected for training, 50% of the data in the data set is randomly selected to predict the two recognition models ten times. Results show that the average prediction accuracy and time of the driving style recognition model are 99.4% and 0.00239 s, and the average prediction accuracy and time of the driving condition recognition model are 99.2% and 0.03198 s, which have good predictive performance. The vehicle data in the company's online cloud platform is further applied for predictive verification, and the results demonstrate that the established model has high feasibility.
Authors
Citation
Shi, S., Wang, T., Ding, Y., Qian, Y. et al., "Research on Driver Driving Style and Driving Condition Recognition Model Based on SVM and XGBoost," SAE Technical Paper 2022-01-0227, 2022, https://doi.org/10.4271/2022-01-0227.Also In
References
- Marafie , Z. , Lin , K. , Wang , D. , Lyu , H. et al. AutoCoach: An Intelligent Driver Behavior Feedback Agent with Personality-Based Driver Models Electronics 10 11 2021 1361 10.3390/electronics10111361
- Zhang , J. 2020 10.27517/d.cnki.gzkju.2020.002001
- Arooj , A. , Farooq , M.S. , Akram , A. , Iqbal , R. et al. Big Data Processing and Analysis in Internet of Vehicles: Architecture, Taxonomy, and Open Research Challenges Arch. Comput. Methods Eng. 2021 10.1007/s11831-021-09590-x
- Chen , X. , 2020 10.27634/d.cnki.gzrgu.2020.000211
- Junyuan , B. , 2020 10.27251/d.cnki.gnjdc.2020.000476
- Li , M. , Sun , Y. , Wang , X. , and Shi , Y. Research on The Model of UBI Car Insurance Rates Rating Based on CNN-Softmax Algorithm J. Phys. Conf. Ser. 1802 3 2021 032071 10.1088/1742-6596/1802/3/032071
- Guodong , Z. , 2020 10.27101/d.cnki.ghfgu.2020.001561
- Chen , Q. , Yin , C. , Zhang , J. , and Qin , W. Research on Energy Management Algorithms for Plug-In Hybrid Electric Vehicles Based on Dynamic Programming and Machine Learning Automotive Technology 10 2020 51 57 10.19620/j.cnki.1000-3703.20191172
- Yu , Z. , Gu , T. , Leng , B. , and Xiong , L. Research on the Method of Building Vehicle Driving Condition Recognition Model Beijing Automotive 01 2020 39 42 10.14175/j.issn.1002-4581.2020.01.011
- Jensen , D.,.Q. and Zeng , Y. Hybrid Electric Vehicle Energy Management Strategy Based on Genetic Optimization K-Means Clustering Algorithm Working Condition Recognition Chinese Journal of Highway and Transport 29 04 2016 130 137+152 10.3969/ j.issn.1001-7372.2016.04.016
- Gejingting , X. , Ruiqiong , J. , Wei , W. , Libao , J. et al. Correlation Analysis and Causal Analysis in the Era of Big Data IOP Conf. Ser. Mater. Sci. Eng. 563 2019 042032 10.1088/1757-899X/563/4/042032
- Hu , J. , Liu , M. , Gong , R. , Jiang , Z. et al. Analysis and Evaluation of Vehicle Handling Comfort Based on Principal Component Analysis China Mechanical Engineering 22 20 2011 2456 2459 10.3969/j.issn .1004-910X.2014.09.001
- Eler , D.M. , Batista Martins Teixeira , J. , Macanha , P.A. , and Garcia , R.E. Simplified Stress and Simplified Silhouette Coefficient to a Faster Quality Evaluation of Multidimensional Projection Techniques and Feature Spaces 2015 19th International Conference on Information Visualisation 2015 133 139 10.1109/iV.2015.33
- Aranganayagi , S. and Thangavel , K. Clustering Categorical Data Using Silhouette Coefficient as a Relocating Measure International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007) 2007 13 17 10.1109/ICCIMA.2007.328
- Liu , L. , Martín-Barragán , B. , and Prieto , F.J. A Projection Multi-Objective SVM Method for Multi-Class Classification Comput. Ind. Eng. 158 2021 107425 10.1016/j.cie.2021.107425
- Li , M. , Zhang , Z. , Song , X. , Cao , H. et al. A Driving Style Classification Model Based on a Multi-Class Semi-Supervised Learning Algorithm Journal of Hunan University (Natural Science Edition) 47 4 2020 10 15 10.16339/j.cnki.hdxbzkb.2020.04.002
- Wang , Y. and Chen , S. A Survey of Classifier Evaluation and Design Based on AUC Pattern Recognition and Artificial Intelligence 24 1 2011 64 71 10.3969/j.issn.1003-6059.2011.01.008
- Chen , T. and Guestrin , C. XGBoost: A Scalable Tree Boosting System Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Association for Computing Machinery, New York, NY, USA 2016 978-1-4503-4232-2 785 794 10.1145/2939672.2939785
- Li , Z. and Liu , Z. XGBoost-Based Feature Selection Algorithm Journal of Communications 40 10 2019 101 108 10.11959/j.issn.1000-436x.2019154
- Lu , Y. , Fu , X. , Guo , E. , and Tang , F. XGBoost Algorithm-Based Monitoring Model for Urban Driving Stress: Combining Driving Behaviour, Driving Environment, and Route Familiarity IEEE Access 9 2021 21921 21938 10.1109/ACCESS.2021.3055551