Orders > Conference proceedings > 12th international workshop on systems, signals and image processing
(from Chapter 1: Invited Addresses and Tutorials on Signals, Coding,
 Systems and Intelligent Techniques)
| Full Citation and Abstract
|
Title: |
Classification of Infrasound Events: A Neural Network approach |
| |
Author(s): |
Fredric M. Ham |
| |
Address: |
Harris Professor of Electrical Engineering
Florida Institute of Technology
|
| |
Reference: |
SSIP-SP1, 2005 pp. 7 - 7 |
| |
Abstract/
Summary |
Infrasound is a low-frequency acoustic phenomenon that occurs in nature, and can also result from man-made events, typically in the frequency range 0.01 Hz to 10 Hz. An integral part of the Comprehensive Nuclear-Test-Ban Treaty (CTBT) International Monitoring System is an infrasound-monitoring network. This network has the capability to detect and verify infrasonic signals-of-interest (SOI), e.g., nuclear explosions, from other unwanted infrasound noise sources, i.e., volcano eruptions, bolides, mountain associated waves, and microbaroms, to name a few. Results are presented for a bank of Radial Basis Function (RBF) neural networks, to discriminate between different infrasonic events. Each module in the bank of RBF networks is responsible for classifying one of several events, and thus, is trained to identify only this particular event. However, each module is also trained to not classify all other events. Output thresholds of each module are set according to specific Receiver Operating Characteristic (ROC) curves. Preprocessing of the infrasound signals is carried out by extracting cepstral coefficients and computing the associated derivatives that form the feature vectors used to train and test the RBF networks. |
|
| |
We welcome your comments about this Article  |
