Seismic Discrimination between Earthquakes and Explosions Using Support Vector Machine

The discrimination between earthquakes and explosions is a serious issue in seismic signal analysis. This paper proposes a seismic discrimination method using support vector machine (SVM), wherein the amplitudes of the P-wave and the S-wave of the seismic signals are selected as feature vectors. Fur...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2020-03, Vol.20 (7), p.1879
Main Authors: Kim, Sangkyeum, Lee, Kyunghyun, You, Kwanho
Format: Article
Language:English
Subjects:
Accuracy
Classification
Compensation
Discrimination
Earthquakes
Error analysis
Error compensation
Explosions
heterodyne laser interferometer
Hough transform
Hough transformation
Lasers
Linear vibration
Machine learning
measurement accuracy
Neural networks
Nonlinearity
S waves
Seismic analysis
seismic discrimination
Seismic response
Seismic waves
Seismographs
Signal analysis
Signal processing
support vector machine
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The discrimination between earthquakes and explosions is a serious issue in seismic signal analysis. This paper proposes a seismic discrimination method using support vector machine (SVM), wherein the amplitudes of the P-wave and the S-wave of the seismic signals are selected as feature vectors. Furthermore, to improve the seismic discrimination performance using a heterodyne laser interferometer for seismic wave detection, the Hough transform is applied as a compensation method for the periodic nonlinearity error caused by the frequency-mixing in the laser interferometric seismometer. In the testing procedure, different kernel functions of SVM are used to discriminate between earthquakes and explosions. The outstanding performance of a laser interferometer and Hough transform method for precision seismic measurement and nonlinearity error compensation is confirmed through some experiments using a linear vibration stage. In addition, the effectiveness of the proposed discrimination method using a heterodyne laser interferometer is verified through a receiver operating characteristic curve and other performance indices obtained from practical experiments.
ISSN:1424-8220
1424-8220
DOI:10.3390/s20071879