[Back]

C. Reyes, T. Hilaire, C. Mecklenbräuker:
"Distributed Projection Approximation Subspace Tracking Based on Consensus Propagation";
Talk: 9th COST2100 Management Committee Meeting, Vienna, Austria; 09-28-2009 - 09-30-2009.

We develop and investigate a distributed algorithm for signal subspace tracking without the need for a fusion center. We assume that all sensor nodes may broadcast messages to sensors in their neighborhood defined by a finite (small) communication radius. To this aim, we start from Projection Approximation Subspace Tracking (PAST), a well-investigated algorithm suitable for implementation in a centralized way. We arrive at a distributed
approximation of the PAST algorithm by letting each sensor broadcast to its neighbors the local observation variable x_n(t), a filtered observation vector y_n(t), the local weight w_n and the estimated signal subspace W_n(t). Vice versa, the received messages at sensor node n from its neighborhood are fused by employing consensus propagation. Finally, we investigate the proposed distributed algorithm in simulation runs. Simultaneously, some work in progress regarding the distribution of W_n(t) will be presented.

PAST, wireless sensor network, subspace, RLS

http://www.cost2100.org/uploads/File/IX%20MCM/Abstract/TD(09)973.pdf