Contribution to Passive Acoustic Ocean Tomography- Part IV: A Data Fusion Strategy For Blind Source Separation and Classification

Vallez Simon (1) , Martin Arnaud (1) , Ali Mansour (2) , Cedric Gervaise , Khnechaf Ali (1)

1 Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
2 Lab-STICC_ENSTAB_CACS_COM

In this paper we applied Fusion algorithm in a passive Ocean Acoustic Tomography context. We applied several types of independent component analysis algorithms an a large number of realistic data and we propose to classify their respective outputs according to the principal properties of the opportunity sources. Finally, we apply a fusions model.. the Belief functions theory to outperform the Blind Source Separation/classification approach.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Vallez Simon, Martin Arnaud, Ali Mansour, Cedric Gervaise, Khnechaf Ali. Contribution to Passive Acoustic Ocean Tomography- Part IV: A Data Fusion Strategy For Blind Source Separation and Classification. IEEE Conference & Exhibition OCEANS'05 Europe, Jun 2005, Brest, France. ⟨hal-00802811⟩