Skip to Main Content
We consider estimating multiple transmitter locations based on received signal strength measurements by a sensor network of randomly located receivers. This problem is motivated by the search for available spectrum in cognitive radio applications. We create a quasi expectation maximization (EM) algorithm for localization under lognormal shadowing. Simulated performance is compared to random guessing and to global optimization using constriction particle swarm (CPSO). Results show that the proposed quasi EM algorithm outperforms both alternatives given a fixed number of guesses, and the performance gap grows as the number of transmitters increases.