In view of the problems of insufficient confidence in threat assessment of cruise missile, data coupling in multi-attribute decision-making and the accuracy of assessment affected by subjective experience, a threat assessment model, which bases on unsupervised learning and TOPSIS combing with robust principal component analysis improved by smooth L 0 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L_{0}$$\end{document} norm, was proposed. The model uses the robust principal component analysis improved by smooth L 0 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L_{0}$$\end{document} norm to extract features, realizes decoupling of features, and determines the factors of threat assessment. In allusion to the situation of insufficient acquisition of assessment factors under complex electromagnetic environment, we use MeanShift combing with unsupervised fuzzy c-means clustering algorithm to fit similar features and calculate the threat degree. Using robust principal component to define the weights of TOPSIS can evaluate threat degree more objectively. Finally, the combination of evaluation results is weighted to improve the non-convex generalization ability and the evaluation accuracy of model. The simulation results show that the threat assessment model of cruise missile based on synthetic weights has better accuracy and objectivity, and meets the requirements of threat assessment missions in the battlefield.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Threat Assessment Model of Cruise Missile Based on Unsupervised Learning


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Wu, Meiping (Herausgeber:in) / Niu, Yifeng (Herausgeber:in) / Gu, Mancang (Herausgeber:in) / Cheng, Jin (Herausgeber:in) / Li, Chenxuan (Autor:in) / Zhu, Pingyun (Autor:in) / Qian, Kun (Autor:in) / Wang, Yao (Autor:in)

    Kongress:

    International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021



    Erscheinungsdatum :

    18.03.2022


    Format / Umfang :

    10 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Threat Assessment Model of Cruise Missile Based on Unsupervised Learning

    Li, Chenxuan / Zhu, Pingyun / Qian, Kun et al. | British Library Conference Proceedings | 2022


    Threat Assessment Model of Cruise Missile Based on Unsupervised Learning

    Li, Chenxuan / Zhu, Pingyun / Qian, Kun et al. | TIBKAT | 2022