The rapid development of artificial intelligence has achieved significant success in traffic accident detection. However, the complexity of deep neural network algorithms and the large number of parameters make these models opaque and difficult to understand, resulting in uncontrollable potential risks and limiting large-scale applications in critical areas such as traffic safety. By using SHapley Additive exPlanations and Local Interpretable Model-agnostic Explanations methods to explain the decision-making process of traffic accident prediction models and presenting the results visually, we found that both methods yielded similar outcomes across different traffic scenarios. The model identified vehicle collisions as the primary feature of traffic accident scenes and regular spacing between vehicles as the main characteristic of normal traffic flow scenes. We also discovered that the model considers multiple features in its predictions and uses secondary features as supplementary information. This approach can significantly help researchers effectively understand the decisions made by the model, identify decision biases, and make targeted corrections to enhance model performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Enhancing Model Transparency: A Comparative Analysis of SHAP and LIME in Explaining Traffic Accident Prediction Models


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Jia, Limin (Herausgeber:in) / Yao, Dechen (Herausgeber:in) / Ma, Feng (Herausgeber:in) / Zhang, Liguo (Herausgeber:in) / Chen, Yuejian (Herausgeber:in) / Xue, Qingwan (Herausgeber:in) / Zhang, Xianzhe (Autor:in) / Xue, Qingwan (Autor:in) / Guo, Weiwei (Autor:in) / Tan, Jiyuan (Autor:in)

    Kongress:

    International Conference on Artificial Intelligence and Autonomous Transportation ; 2024 ; Beijing, China December 06, 2024 - December 08, 2024



    Erscheinungsdatum :

    28.03.2025


    Format / Umfang :

    9 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Predicting and explaining severity of road accident using artificial intelligence techniques, SHAP and feature analysis

    Panda, Chakradhara / Mishra, Alok Kumar / Dash, Aruna Kumar et al. | Taylor & Francis Verlag | 2023


    Training method of traffic accident prediction model and traffic accident prediction method and device

    WANG NIANMING / CHEN YANG / ZHOU MINGKE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Traffic Accident Prediction based on CNN Model

    Thaduri, Amani / Polepally, Vijayakumar / Vodithala, Swathy | IEEE | 2021


    Tunnel traffic flow and accident prediction model

    ZHENG QI / LI ZHIYANG / WANG PENGHUI | Europäisches Patentamt | 2025

    Freier Zugriff

    Explaining Local Path Plans Using LIME

    Halilovic, Amar / Lindner, Felix | Springer Verlag | 2022