Novel energy-based localization technique for multiple sources

Source localization using acoustic sensor networks has been drawing a lot of research interest recently. In a sensor network, there are a large number of inexpensive sensors which are densely deployed in a region of interest (ROI). This dense deployment enables accurate intensity (energy) based target localization. The maximum-likelihood is the predominant objective which leads to a variety of source localization approaches. However, the investigation on the energy-based localization for multiple sources has been very rare. The corresponding robust and efficient algorithms are still being pursuit by researchers nowadays. In this paper, we would like to combat the energy-based multiple-source localization problem. We propose two new algorithms, namely alternating projection (AP) algorithm and expectation maximization (EM) algorithm, which can combat the energy-based localization problem for multiple sources.