Regresar

Evaluation of characterization techniques for classification of seismic-volcanic signals of the nevado del ruiz

Abstract:

Currently, researches have been carried out on automatic classification of seismic-volcanic events-mainly based on machine learning techniques-aimed at identifying the nature of the recorded event. In this sense, several approaches have been introduced. Nonetheless, due to these signals’ variability, there is no still a conclusive method of characterization, and it is in fact an open and challenging research problem. In this work, a methodology for comparing features extraction techniques is developed aimed at the discrimination of seismic events of volcanic origin. Representation of the signals in the domain of time, frequency, time-frequency and Cepstral is used. The set of attributes is optimized by selecting characteristics by assigning weights. A supervised classification is executed using known records. Finally, classification performance measures were obtained to determine the subset of characteristics that best represent and discriminate the signals.