Highlights A traffic crash severity prediction framework using deep learning was proposed. A generalized image transformation technique was employed to convert crash data to images. The deep learning network was trained using a customized f1-loss function. An inference setting was proposed for practical application. The result showed an improved performance for fatal and injury crashes.

    Abstract Highway work zones are most vulnerable roadway segments for congestion and traffic collisions. Hence, providing accurate and timely prediction of the severity of traffic collisions at work zones is vital to reduce the response time for emergency units (e.g., medical aid), accordingly improve traffic safety and reduce congestion. In predicting the severity of traffic collisions, previous studies used different statistical and machine learning models with accuracy as the main evaluating factor. However, the performance of these models was generally not good, especially on fatal and injury crashes. Also, looking into the prediction accuracy only is misleading. This paper aims to propose a novel deep learning-based approach with a customized f1-loss function to predict the severity of traffic crashes. Underlying this objective is to compare the results of deep learning models with machine learning model considering two performance indicators, namely precision, and recall. The data used in the analysis include a sample of traffic crashes that occurred at work zones in Louisiana from 2014 to 2018. This dataset includes valuable information (features) related to road, vehicle, and human factors affecting the occurrence and severity of those crashes. The proposed methodology is based on transforming these features/variables into images. Image transformation is conducted using a nonlinear dimensionality reduction technique t-SNE and convex hull algorithm. A CNN based deep learning algorithm with a customized loss function was used to directly optimize the model for precision and recall. The results showed improved performance in predicting the crash severity of fatal and injury crashes using the deep learning approach, which can help to improve traffic safety as well as traffic congestion at work zones and possibly other roadways segments.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A deep learning based traffic crash severity prediction framework


    Beteiligte:


    Erscheinungsdatum :

    2021-03-10




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Real time traffic crash severity prediction tool

    RATROUT NEDAL / MANSOOR UMER / ALAM GULZAR | Europäisches Patentamt | 2022

    Freier Zugriff

    Deep hybrid learning framework for spatiotemporal crash prediction using big traffic data

    Mohammad Tamim Kashifi / Mohammed Al-Turki / Abdul Wakil Sharify | DOAJ | 2023

    Freier Zugriff

    An Improved Deep Learning Model for Traffic Crash Prediction

    Chunjiao Dong / Chunfu Shao / Juan Li et al. | DOAJ | 2018

    Freier Zugriff

    Applications of Deep Learning in Severity Prediction of Traffic Accidents

    Pradhan, Biswajeet / Ibrahim Sameen, Maher | Springer Verlag | 2019


    Applications of Deep Learning in Severity Prediction of Traffic Accidents

    Sameen, Maher Ibrahim / Pradhan, Biswajeet / Shafri, H. Z. M. et al. | TIBKAT | 2019