Neural network optimization for multi-target multi-sensor passive tracking

In this paper, we review a number of neural network approaches to combinatorial optimization. We specifically address the difficult problem of localizing multiple targets using only passive sensors. In other words, the sensors detect only bearing angles. Therefore, target positions mast be found through triangulation. An efficient solution to this problem has been of particular interest in air defense applications and has led to the development of a number of different approaches, including general heuristics, integer programming, Lagrangian relaxation (LR), and genetic algorithms. In this paper, we describe two different neural network bared approaches for solving this passive tracking problem. In particular we demonstrate the use of a Hopfield neural network approach which is used to preface the subsequent development of the multiple elastic modules (MEM) model. The MEM model is presented as a significant extension to current self-organizing neural network. The general applicability of the MEM model to combinatorial optimization problems as well as its application to the passive tracking problem are presented. We describe the unique features of the MEM model, including nonhomogeneous adaptive temperature field for escaping from poor local optima, and locking and expectation features used for dealing with dynamic real-world problems. Applications of the MEM model to other areas, including computer vision, are also briefly described.