Determination of near-fault impulsive signals with multivariate naïve Bayes method

Abstract Near-fault ground motions may contain impulse behavior on velocity records. To calculate the probability of occurrence impulsive signals, a large dataset is collected from various national data providers and strong motion databases. The has number parameters which carry information earthquake physics, ruptured faults, parameters, distance between station several parts fault. Relation signals calculated. It found that fault type, moment magnitude, azimuth site interest surface projection are correlated with impulsiveness signals. Separate models created for strike-slip faults non-strike-slip by using multivariate naïve Bayes classifier method. Naïve allows us to have observing comparable accuracy rates, they more consistent different types respect previous studies.