In-Vehicle Data for Predicting Road Conditions and Driving Style Using Machine Learning

被引:15
作者
Al-refai, Ghaith [1 ]
Elmoaqet, Hisham [1 ]
Ryalat, Mutaz [1 ]
机构
[1] German Jordanian Univ, Dept Mechatron Engn, Amman 11180, Jordan
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 18期
关键词
machine learning; decision trees; random forests; SVM; supervised machine learning; road conditions prediction; driving style prediction; in-vehicle data; CAN;
D O I
10.3390/app12188928
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Many network protocols such as Controller Area Network (CAN) and Ethernet are used in the automotive industry to allow vehicle modules to communicate efficiently. These networks carry rich data from the different vehicle systems, such as the engine, transmission, brake, etc. This in-vehicle data can be used with machine learning algorithms to predict valuable information about the vehicle and roads. In this work, a low-cost machine learning system that uses in-vehicle data is proposed to solve three categorization problems; road surface conditions, road traffic conditions and driving style. Random forests, decision trees and support vector machine algorithms were evaluated to predict road conditions and driving style from labeled CAN data. These algorithms were used to classify road surface condition as smooth, even or full of holes. They were also used to classify road traffic conditions as low, normal or high, and the driving style was classified as normal or aggressive. Detection results were presented and analyzed. The random forests algorithm showed the highest detection accuracy results with an overall accuracy score between 92% and 95%.
引用
收藏
页数:13
相关论文
共 33 条
[1]   Permutation importance: a corrected feature importance measure [J].
Altmann, Andre ;
Tolosi, Laura ;
Sander, Oliver ;
Lengauer, Thomas .
BIOINFORMATICS, 2010, 26 (10) :1340-1347
[2]  
Alvarez-Coello D, 2019, IEEE INT VEH SYM, P165, DOI 10.1109/IVS.2019.8814069
[3]  
[Anonymous], Numpy
[4]  
[Anonymous], About Pandas
[5]   Analytics and machine learning in vehicle routing research [J].
Bai, Ruibin ;
Chen, Xinan ;
Chen, Zhi-Long ;
Cui, Tianxiang ;
Gong, Shuhui ;
He, Wentao ;
Jiang, Xiaoping ;
Jin, Huan ;
Jin, Jiahuan ;
Kendall, Graham ;
Li, Jiawei ;
Lu, Zheng ;
Ren, Jianfeng ;
Weng, Paul ;
Xue, Ning ;
Zhang, Huayan .
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH, 2023, 61 (01) :4-30
[6]   A Survey and Comparison of Low-Cost Sensing Technologies for Road Traffic Monitoring [J].
Bernas, Marcin ;
Placzek, Bartlomiej ;
Korski, Wojciech ;
Loska, Piotr ;
Smyla, Jaroslaw ;
Szymala, Piotr .
SENSORS, 2018, 18 (10)
[7]   A random forest guided tour [J].
Biau, Gerard ;
Scornet, Erwan .
TEST, 2016, 25 (02) :197-227
[8]   Vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication in a heterogeneous wireless network - Performance evaluation [J].
Dey, Kakan Chandra ;
Rayamajhi, Anjan ;
Chowdhury, Mashrur ;
Bhavsar, Parth ;
Martin, James .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2016, 68 :168-184
[9]   Pothole Detection Using Computer Vision and Learning [J].
Dhiman, Amita ;
Klette, Reinhard .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 21 (08) :3536-3550
[10]   An overview of Controller Area Network [J].
Farsi, M ;
Ratcliff, K ;
Barbosa, M .
COMPUTING & CONTROL ENGINEERING JOURNAL, 1999, 10 (03) :113-120