Effectiveness of spectral band selection/extraction techniques for spectral data
SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
The dissimilarity representation as a tool for three-way data classification: a 2D measure
SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Classification of three-way data by the dissimilarity representation
Signal Processing
Hi-index | 0.00 |
Spectral content of seismic signals contains essential information for discriminating different classes of volcanic earthquakes. Such an information is largely redundant; therefore, a reduce number of spectral regions may provide almost the same description of the original events. By reducing the number of bands considered, the amount of data to be processed is significantly decreased and the interpretability of the characterization results is enhanced as well. We consider several spectral band selection methods in a two-class classification problem of volcanic earthquakes recorded at Nevado del Ruiz Volcano. Selection approaches have been compared to each other in terms of classification accuracy as well as by looking at the resulting spectral divisions. Detailed discussions about the technical considerations of the selection approaches as well as regarding their possible physical interpretations have been conducted. Results show that the sequential selection approach is the most flexible and powerful for classifying and characterizing volcanic earthquakes.