Accession Number : ADA300872

Title :   Low-Frequency Active Target Characterization Using Hidden Markov Models and Classifiers.

Corporate Author : LOCKHEED SANDERS INC NASHUA NH

Personal Author(s) : Kil, David H. ; Shin, Frances B. ; Fricke, J. R.

PDF Url : ADA300872

Report Date : 1995

Pagination or Media Count : 33

Abstract : We investigate various projection spaces and extract key parameters or features from each space to characterize low-frequency active (LFA) target returns in a low-dimensional space. The projection spaces encompass (1) time embedded phase map, (2) segmented matched filter output, (3) various time frequency distribution functions, such as Reduced Interference Distribution, to capture time-varying echo signatures, and (4) principal component inversion for signal cleaning and characterization. We utilize both dynamic and static features and parameterize them with a hybrid classification methodology consisting of hidden Markov models, classifiers, and data fusion. This clue identification and evaluation process is complemented by concurrent work on target physics to enhance our understanding of the target echo formation process. As a function of target aspect, we can observe (1) back scatter dominated by axial n=O modes propagating back and forth along the length of the shell, (2) direct scatter from shell discontinuities, (3) helical or creeping waves from phase matching between the acoustic waves and membrane waves (both shear and compressional), and (4) the "array response" of the shell, with coherent super- position of elemental scattering sites along the shell leading to a peak response near broadside. As a function of target structures (the empty shell and the ribbed/complex shells), we see considerable complexity brought about by multiple reflections of the membrane waves between the rings. We show the merit of fusing parameters estimated from these projection spaces in characterizing LFA target returns using the MIT/NRL scaled model data. Our hybrid classifiers outperform the matched filter-based recognizer by an average of 5 to 25%.

Descriptors :   *TARGET CLASSIFICATION, *LOW FREQUENCY, *MARKOV PROCESSES, *TARGET ECHOES, MATHEMATICAL MODELS, OUTPUT, PROPAGATION, METHODOLOGY, PEAK VALUES, DYNAMICS, ACOUSTIC WAVES, PROBABILITY, ARRAYS, SHELLS(STRUCTURAL FORMS), TARGETS, REDUCTION, TIME, VARIATIONS, TOPOLOGY, PHYSICS, ECHOES, RESPONSE, LENGTH, SIGNALS, INTERFERENCE, CREEP, CLASSIFICATION, SIGNATURES, HYBRID SYSTEMS, INVERSION, DATA FUSION, RINGS, DISCONTINUITIES, STATICS, MATCHED FILTERS, MATCHING, MULTIPURPOSE, WAVES, SEGMENTED, HELIXES.

Subject Categories : Acoustic Detection and Detectors

Distribution Statement : APPROVED FOR PUBLIC RELEASE