We propose a global optimization approach to locating multiple transmitters within a geographic area. A set of sensor nodes are assumed to be present in the region and to measure total power received at their respective locations. These measurements are communicated to a processing node, which uses particle swarm optimization to find the transmitter locations that minimize the difference between the true received power and the estimated power based on the chosen propagation model. Clustering is used to generate initial estimates of the transmitter locations, thereby increasing the likelihood that the particle-based optimizer reaches the global minimum. Simulation results show that global optimization is an effective method for multiple transmitter localization and that generating "smart" initial conditions via clustering can yield an average performance improvement of over 25% compared to random initial conditions.

We study the problem of determining optimal pinging strategies in multistatic sonar systems with multiple sources. We are specifically investigating algorithms that determine optimal pinging strategies both for generalized search scenarios, and for holding confirmed target tracks with constraints related to maintaining search performance in the rest of the area. An important part of this work is the development of metrics to be used in the optimization procedures. For maintaining search coverage, we used a "probability of target presence" metric formulation. This formulation utilizes sonar performance prediction and a Bayesian update equation to incorporate negative information (i.e., searching an area but finding no targets). We also discuss strategies that can be used to increase the performance of a multistatic field, such as the use of bandwidth diversity.

In this paper we present a novel optimization algorithm that estimates gradients over regions to search for optima of a non-convex function on both a local and global scale. The proposed architecture is based on three concepts: using the memory of previously evaluated points, multiresolutional search, and the estimation of gradients at these different resolutions to direct the search. This multiresolution estimated gradient architecture (MEGA) shows promise to perform competitively when compared to standard global searches. Comparisons on the Rosenbrock, Griewank, and sinusoidal test functions show that MEGA can converge faster than particle swarm optimization, particularly as dimensionality of a problem increases. I. INTRODUCTIONWe propose an architecture for global optimization of black-box objective functions. The focus is on optimizing functions which are relatively costly or time-consuming to evaluate. We discuss how our proposed algorithm relates to existing successful algorithms, focusing on the use of memory, gradient estimation, and multiresolutional search. The proposed algorithm combines these three properties and the goal of minimizing the number of parameters that must be tuned for each application.The proposed architecture is described in pseudocode in Section III. The architecture description leaves many details open. A specific implementation of the details follows the pseudocode. The given implementation performed well over a number of test functions without the need for parameters to be tuned. Test results are summarized in Section IV. This implementation is compared to two particle swarm optimizers, and the performance is competitive in both convergence rate and number of function evaluations per run. The algorithms were compared on a number of objective functions with variable input dimensionality, and the MEGA performance is more consistent than the particle swarm optimizers as the dimensionality of the problem increases. This feature makes MEGA a promising choice for solving complex problems. A more complete discussion of the performance may be found in Section V.

No abstract