PASSIVE ACOUSTIC SIGNAL CLASSIFICATION USING UNCONVENTIONAL TECHNIQUES

Advances in passive acoustic systems exacerbate the problem of signal classification in a high contact-density environment. Increased contact loading forces the operator to classify contacts more rapidly, reducing his effectiveness. New methods that assist feature extraction, provide automated detection and classification, and offer potential for new and unique classification clues are required to maintain the Navy's technological edge against an increasingly quiet threat. Phase I will explore classification methods utilizing unconventional signal processing techniques. These techniques, in conjunction with visually-based image processing techniques, will form an integrated detection and feature extraction process that promises improved detection and extraction of low-SNR features (such as transients) contained within beam-formed , time-frequency data. We seek to understand the key signature features revealed by this analysis approach, with a focus towards automating the process. Phase I will evaluate the feature extraction and classification capabilities of the unconventional techniques, which include wavelet transforms, higher-order spectral analysis, time-frequency distributions, and image processing, on simulated acoustic data. We will also research the applicability of advanced GUI methods to user displays and controls. Phase II will implement a Combined Acoustic Signature Analysis Station for validation of the most promising techniques against real measured data.