Development and Implementation of Metrics for Identifying Military Impulse Noise

摘要

This project sought to more accurately classify military noise. A high-fidelity library of measured noise waveforms was created. Four signal metrics (kurtosis, crest factor, spectral slope, and weighted square error) were identified as features that can be used for noise classification using an artificial neural network (ANN). Two prototype systems were fabricated and deployed. The University of Pittsburgh (UPitt) algorithm was combined with the Bearing Amplitude and Measurement Array System (BAMAS) (Applied Physical Sciences, Inc.) in a PC/104 based hardware platform. Two prototypes were deployed at Marines Corps Base Camp Lejeune. While the overall accuracy of the UPitt classifier alone was somewhat lower (89%) than desired, nonblast noise was rejected at over a 99% rate (which meets the objective to reduce false positives). When the UPitt and BAMAS algorithms were combined, blast noise was identified at over 98% accuracy, while aircraft, wind, and vehicle noise were rejected at over 98-99% accuracy. The device is at Technology Readiness Level 7, ready for demonstration and validation, before being commercialized.