IMPROVED RELOCATABLE OVER-THE-HORIZON RADAR DETECTION AND TRACKING USING THE MAXIMUM-LIKELIHOOD ADAPTIVE NEURAL SYSTEM ALGORITHM

An advanced detection and tracking system is being developed for the U .S. Navy's Relocatable Over-the-Horizon Radar (ROTHR) to provide impro ved tracking performance against small aircraft typically used in drug -smuggling activities. The development is based on the Maximum Likelih ood Adaptive Neural System (MLANS), a model-based neural network that combines advantages of neural network and model-based algorithmic appr oaches. The objective of the MLANS tracker development effort is to ad dress user requirements for increased detection and tracking capabilit y in clutter and improved track position, heading, and speed accuracy. The MLANS tracker is expected to outperform other approaches to detec tion and tracking for the following reasons. It incorporates adaptive internal models of target return signals, target tracks and maneuvers, and clutter signals, which leads to concurrent clutter suppression, d etection, and tracking (track-before-detect). It is not combinatorial and thus does not require any thresholding or peak picking and can tra ck in low signal-to-noise conditions. It incorporates superresolution spectrum estimation techniques exceeding the performance of convention al maximum likelihood and maximum entropy methods. The unique spectrum estimation method is based on the Einsteinian interpretation of the R OTHR received energy spectrum as a probability density of signal frequ ency. The MLANS neural architecture and learning mechanism are founded on spectrum models and maximization of the ''Einsteinian'' likelihood , allowing knowledge of the physical behavior of both targets and clut ter to be injected into the tracker algorithms. The paper describes th e addressed requirements and expected improvements, theoretical founda tions, engineering methodology, and results of the development effort to date.