Deinterleaving and Clustering unknown RADAR pulses

Manon Mottier (1) , Gilles Chardon (1) , Frédéric Pascal (1)

1 L2S - Laboratoire des signaux et systèmes

In this paper, a two-step methodology is developed to deinterlace RADAR signals. We mainly worked from a data simulator to obtain a large diversity of signals representing typical RADARs. First, a clustering algorithm is used to separate the pulses in the F-PW (Frequency-Pulse Width) plane, then a phase of cluster agglomeration is performed using the cluster output of the previous step as a features for an hierarchical agglomerative clustering combined with optimal transport distances. Results on labeled simulated data are given.

Mots clés: Electronic warfare; clustering; optimal transport

Domaines: Machine Learning [stat.ML]; Statistiques [stat]; Intelligence artificielle [cs.AI]; Traitement du signal et de l'image [eess.SP]

Manon Mottier, Gilles Chardon, Frédéric Pascal. Deinterleaving and Clustering unknown RADAR pulses. IEEE Radar Conference 2021, May 2021, ATLANTA (virtual), United States. ⟨10.1109/radarconf2147009.2021.9455272⟩. ⟨hal-03245067⟩