SEISMIC EVENTS DISCRIMINATION BY NEURO-FUZZY-BASED DATA MERGING

This article involves an original method to classify low magnitude sei smic events recorded in France by a network of seismometers. This meth od is based on the merging of high-level data with possibly incomplete low-level data extracted from seismic signals. The merging is perform ed by a multi-layer neural network. A fuzzy coding is applied to the n eural network's inputs to process efficiently incomplete data. The res ults reveal that the fuzzy coding coupled with the data merging increa ses the correct classification rate to more than 90% even when the dat abase contains missing values.