Multiple source localization using partitioning: algorithms

This paper addresses the problem of estimating the number of sources, the directions of narrowband signals and the signals emitted by a number of sources. The proposed solution is based on the reformulation of the problem in a way so that the measurement equation can be expressed as a non-linear function of a vector consisting of the locations as well as the signals emitted by the sources. Simulations illustrate that the proposed method selects the correct dimension of this augmented location vector (i.e. it correctly selects the number of sources) while at the same time successfully identifying the source locations and signals, even for a sufficiently small number of snapshots, Furthermore, the method is adaptive in the sense that it has the ability to track changes in the model structure in real time, successfully. Finally, an interesting feature of the proposed algorithm is its natural decoupled form, which makes it amenable for parallel implementations.