In this paper, we present a deep hybrid model to detect abnormal flights. Deep hybrid models for anomaly detection use deep neural networks mainly autoencoder as feature extractors, the features learned within the hidden representations of autoencoder are then input to cluster algorithm to detect abnormal flights. The model can detect flight anomalies and associated risks without requiring predefined criteria or domain knowledge. In this paper, 2018 annual flight data of Daocheng Yading airport was taken as the experimental data which contains 981 flights. Our model performed well and 91 abnormal flights were detected.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Flight Anomaly Detection Based on Deep Hybrid Model


    Contributors:
    Wang, Qixin (author) / Qin, Kun (author) / Lu, Binbin (author)


    Publication date :

    2020-10-14


    Size :

    413030 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multiclass Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model

    Memarzadeh, Milad / Matthews, Bryan / Templin, Thomas | AIAA | 2022

    Free access

    Multi-Class Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model

    Memarzadeh, Milad / Matthews, Bryan / Templin, Thomas | AIAA | 2021


    MULTI-CLASS ANOMALY DETECTION IN FLIGHT DATA USING SEMI-SUPERVISED EXPLAINABLE DEEP LEARNING MODEL

    Memarzadeh, Milad / Matthews, Bryan / Templin, Thomas | TIBKAT | 2021


    Active Learning in Flight Anomaly Detection

    Mural, Prashant C. / GN, Rathna / Bhola, Virat | AIAA | 2024