Share Email Print
cover

Proceedings Paper

Reliable classification of high explosive and chemical/biological artillery using acoustic sensors
Author(s): Sachi V. Desai; Myron E. Hohil; Henry E. Bass; Jim Chambers
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Feature extraction methods based on the discrete wavelet transform and multiresolution analysis are used to develop a robust classification algorithm that reliably discriminates between conventional and simulated chemical/biological artillery rounds via acoustic signals produced during detonation utilizing a generic acoustic sensor. Based on the transient properties of the signature blast distinct characteristics arise within the different acoustic signatures because high explosive warheads emphasize concussive and shrapnel effects, while chemical/biological warheads are designed to disperse their contents over large areas, therefore employing a slower burning, less intense explosive to mix and spread their contents. The ensuing blast waves are readily characterized by variations in the corresponding peak pressure and rise time of the blast, differences in the ratio of positive pressure amplitude to the negative amplitude, and variations in the overall duration of the resulting waveform. Unique attributes can also be identified that depend upon the properties of the gun tube, projectile speed at the muzzle, and the explosive burn rates of the warhead. The algorithm enables robust classification of various airburst signatures using acoustics. It is capable of being integrated within an existing chemical/biological sensor, a stand-alone generic sensor, or a part of a disparate sensor suite. When emplaced in high-threat areas, this added capability would further provide field personal with advanced battlefield knowledge without the aide of so-called "sniffer" sensors that rely upon air particle information based on direct contact with possible contaminated air. In this work, the discrete wavelet transform is used to extract the predominant components of these characteristics from air burst signatures at ranges exceeding 2km while maintaining temporal sequence of the data to keep relevance to the transient differences of the airburst signatures. Highly reliable discrimination is achieved with a feedforward neural network classifier trained on a feature space derived from the distribution of wavelet coefficients and higher frequency details found within different levels of the multiresolution decomposition the neural network then is capable of classifying new airburst signatures as Chemical/Biological or High Explosive.

Paper Details

Date Published: 12 May 2005
PDF: 11 pages
Proc. SPIE 5795, Chemical and Biological Sensing VI, (12 May 2005); doi: 10.1117/12.603688
Show Author Affiliations
Sachi V. Desai, U.S. Army Research, Development and Engineering Command (United States)
Myron E. Hohil, U.S. Army Research, Development and Engineering Command (United States)
Henry E. Bass, The Univ. of Mississippi (United States)
Jim Chambers, The Univ. of Mississippi (United States)


Published in SPIE Proceedings Vol. 5795:
Chemical and Biological Sensing VI
Patrick J. Gardner, Editor(s)

© SPIE. Terms of Use
Back to Top