Title :
Classification using feature extraction based on time-frequency analysis and BCM theory
Author_Institution :
Naval Undersea Warfare Center, Newport, RI
Abstract :
Marine mammal sounds classification is demonstrated using a novel application of wavelet time/frequency decomposition, and feature extraction using the BCM neuron. The system achieves outstanding classification performance even when tested with mammal sounds recorded at very different locations (from training)
Keywords :
acoustic signal processing; aquaculture; biocommunications; biology computing; feature extraction; neural nets; pattern classification; time-frequency analysis; underwater sound; wavelet transforms; BCM neuron; Bienenstock Cooper Munro theory; classification performance; feature extraction; marine mammal sounds classification; time-frequency analysis; wavelet time/frequency decomposition; Background noise; Computational efficiency; Equations; Feature extraction; Neurons; Performance evaluation; Time frequency analysis; Vectors; Wavelet transforms; Whales;
Conference_Titel :
Time-Frequency and Time-Scale Analysis, 1996., Proceedings of the IEEE-SP International Symposium on
Conference_Location :
Paris
Print_ISBN :
0-7803-3512-0
DOI :
10.1109/TFSA.1996.547456
