Descriptive information of many accidents and accident symptoms is contained in voluntary reports on civil aviation safety. In order to solve the shortcomings of manual analysis of aviation unsafe information text at this stage, a multi-channel text convolutional neural network-bidirectional gated recurrent unit (TextCNN-BiGRU) analysis model based on attention mechanism is proposed. Firstly, the initial text is vectorized by word2vec, the window values are selected through experiments to form three channels. Then, the strong learning ability of CNN is used to extract local features, the bidirectional gated recurrent unit is used to extract contextual global information, and the attention layer and pooling layer are used to obtain And optimize the important features. Finally, using the softmax function is to minimize the error loss. The simulation experimental verification results show that the classification performance of the proposed model has a classification accuracy of 94%, and the loss function value is stable at about 0.22%.It has good generalization ability and can effectively solve the problem of incomplete information mining for a single model and effectively improve the classification effect.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Aviation Unsafe Information Text Analysis Based on Improved CNN-BiGRU-att Model


    Contributors:


    Publication date :

    2021-10-20


    Size :

    1377593 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    UAV in Aviation: Cost of Unsafe Events

    Tomić, Lidija / Čokorilo, Olja / Torok, Adam et al. | Springer Verlag | 2025


    Risk Analysis and Countermeasures of Civil Aviation Passenger Unsafe Behavior

    Lan, Jun / Wang, Qiquan / Fan, Haiqing | Springer Verlag | 2024


    Study on Typical Unsafe Event in Aviation Based on the OHFAM Model

    Gao, Ping / Liu, Huiying / Luo, Min et al. | IEEE | 2020


    A Ship Trajectory Prediction Model Based on ECA-BiGRU

    Yang, Shenghui / Chen, Siyuan / Liu, Chenshen et al. | IEEE | 2023


    Research on Named Entity Recognition Based on Bert-BiGRU-CRF model in Spacecraft Field

    Tong, Boan / Pan, Jian / Zheng, Leixin et al. | IEEE | 2021