Risk Levels Classification of Near-Crashes in Naturalistic Driving Data

被引:7
|
作者
Naji, Hasan A. H. [1 ]
Xue, Qingji [1 ]
Lyu, Nengchao [2 ]
Duan, Xindong [1 ]
Li, Tianfeng [1 ]
机构
[1] Nanyang Inst Technol, Sch Digital Media, Chang Jiang Rd 80, Nanyang 473004, Peoples R China
[2] Wuhan Univ Technol, Intelligent Transport Syst Res Ctr, Wuhan 430063, Peoples R China
关键词
near-crash events; driving risk levels; classification; statistical methods; machine learning; deep learning; INJURY SEVERITY; LOGISTIC-REGRESSION; PREDICTION; TIME; IDENTIFICATION; EVENTS;
D O I
10.3390/su14106032
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Identifying dangerous events from driving behavior data has become a vital challenge in intelligent transportation systems. In this study, we compared machine and deep learning-based methods for classifying the risk levels of near-crashes. A dataset was built for the study by considering variables related to naturalistic driving, temporal data, participants, and road geometry, among others. Hierarchical clustering was applied to categorize the near-crashes into several risk levels based on high-risk driving variables. The adaptive lasso variable model was adopted to reduce factors and select significant driving risk factors. In addition, several machine and deep learning models were used to compare near-crash classification performance by training the models and examining the model with testing data. The results showed that the deep learning models outperformed the machine learning and statistical models in terms of classification performance. The LSTM model achieved the highest performance in terms of all evaluation metrics compared with the state-of-the-art models (accuracy = 96%, recall = 0.93, precision = 0.88, and F1-measure = 0.91). The LSTM model can improve the classification accuracy and prediction of most near-crash events and reduce false near-crash classification. The finding of this study can benefit transportation safety in predicting and classifying driving risk. It can provide useful suggestions for reducing the incidence of critical events and forward road crashes.
引用
收藏
页数:21
相关论文
共 50 条
  • [21] Built environment, driving errors and violations, and crashes in naturalistic driving environment
    Ahmad, Numan
    Wali, Behram
    Khattak, Asad J.
    Dumbaugh, Eric
    ACCIDENT ANALYSIS AND PREVENTION, 2021, 157
  • [22] Understanding crashes involving roadway objects with SHRP 2 naturalistic driving study data
    Hao, Haiyan
    Li, Yingfeng
    Medina, Alejandra
    Gibbons, Ronald B.
    Wang, Linbing
    JOURNAL OF SAFETY RESEARCH, 2020, 73 : 199 - 209
  • [23] Driving style classification for vehicle-following with unlabeled naturalistic driving data
    Zhang, Xinjie
    Huang, Yiqing
    Guo, Konghui
    Li, Wentao
    2019 IEEE VEHICLE POWER AND PROPULSION CONFERENCE (VPPC), 2019,
  • [24] Validating risk behavior in driving simulation using naturalistic driving data
    Himmels, Chantal
    Parduzi, Arben
    Loecken, Andreas
    Protschky, Valentin
    Venrooij, Joost
    Riener, Andreas
    TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2024, 107 : 710 - 725
  • [25] Prediction of Near-Crashes from Observed Vehicle Kinematics using Machine Learning
    Osman, Osama A.
    Hajij, Mustafa
    Bakhit, Peter R.
    Ishak, Sherif
    TRANSPORTATION RESEARCH RECORD, 2019, 2673 (12) : 463 - 473
  • [26] Driving Risk Assessment using Cluster Analysis based on Naturalistic Driving Data
    Zheng, Yang
    Wang, Jianqiang
    Li, Xiaofei
    Yu, Chenfei
    Kodaka, Kenji
    Li, Keqiang
    2014 IEEE 17TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2014, : 2584 - 2589
  • [27] Individual driver risk assessment using naturalistic driving data
    Guo, Feng
    Fang, Youjia
    ACCIDENT ANALYSIS AND PREVENTION, 2013, 61 : 3 - 9
  • [28] How does glance behavior influence crash and injury risk? A 'what-if' counterfactual simulation using crashes and near-crashes from SHRP2
    Bargman, Jonas
    Lisovskaja, Vera
    Victor, Trent
    Flannagan, Carol
    Dozza, Marco
    TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2015, 35 : 152 - 169
  • [29] Toward modeling and classification of naturalistic driving
    Torkkola, K
    Gardner, M
    Wood, C
    Schreiner, C
    Massey, N
    Leivian, B
    Summers, J
    Venkatesan, S
    2005 IEEE INTELLIGENT VEHICLES SYMPOSIUM PROCEEDINGS, 2005, : 638 - 643
  • [30] Evaluation of intersection crashes using naturalistic driving data through the lens of future I-ADAS
    Galloway, Andrew J.
    Bareiss, Max
    Hasegawa, Takashi
    Sherony, Rini
    Riexinger, Luke E.
    TRAFFIC INJURY PREVENTION, 2023, 24 (07) : 577 - 582