In tactical scenarios, there is limited knowledge available about an adversary’s encrypted traffic. To improve traffic classification performance in these scenarios, a new modified naïve Bayes kernel classifier (MNBK) is proposed based on optimal weight-based kernel bandwidth selection. By generating several traffic types expected in modern tactical edge networks, we demonstrate that the proposed MNBK classifier not only improves classification performance on the existing classes, but also detects unknown traffic with very high accuracy, precision, and recall compared with the traditional classifiers. In addition, a real time learning model is proposed based on MNBK and applied to real time traffic classification.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Machine Learning-Based Traffic Classification of Wireless Traffic


    Contributors:


    Publication date :

    2019-05-01


    Size :

    695135 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    GPS-Based Traffic Conditions Classification Using Machine Learning Approaches

    Ahmed, Usman / Tu, Ran / Xu, Junshi et al. | Transportation Research Record | 2022


    Federal learning traffic prediction method based on traffic mode classification

    ZHANG XINMIN / SUN SHU / QIAN JINCHUAN et al. | European Patent Office | 2025

    Free access

    Classification of Traffic Accident Severity Using Machine Learning Models

    Hamdan, Noura / Sipos, Tibor | Springer Verlag | 2025