Modular learning strategy for signal detection in a nonstationary environment

We describe a novel modular learning strategy for the detection of a target signal of interest in a nonstationary environment, which is motivated by the information preservation rule. The strategy makes no assumptions on the environment. It incorporates three functional blocks: (1) time-frequency analysis, (2) feature extraction, and (3) pattern classification, the delineations of which are guided by the information preservation rule. The time-frequency analysis, which is implemented using the Wigner-Ville distribution (WVD), transforms the incoming received signal into a time-frequency image that accounts for the time-varying nature of the received signal's spectral content. This image provides a common input to a pair of channels, one of which is adaptively matched to the interference acting alone, and the other is adaptively matched to the target signal plus interference. Each channel of the receiver consists of a principal components analyzer (for feature extraction) followed by a multilayer perceptron (for feature classification), which are implemented using self-organized and supervised forms of learning in feedforward neural networks, respectively. Experimental results based on real-life radar data are presented to demonstrate the superior performance of the new detection strategy over a conventional detector using constant false-alarm rate (CFAR) processing. The data used in the experiment pertain to an ocean environment, representing radar returns from small ice targets buried in sea clutter; they were collected with an instrument quality coherent radar and properly ground truthed.