A Nonparametric Multiclass Pattern Classifier Used for the Prediction of Earthquake Occurrence Locations

In this paper,a nonparametric multiclass pattern classifier is used to study the discriminatory classification of places where earthquakes arc liable to occur.Each pattern class is described by hyperrectangles in the measurement space.These hyperrectangles are generated by the basic event generation (BEG) algorithm provided by Manabu Ichino.The classification of a new pattern is performed by examining if it is incl-uded in those basic events.Applications of the classifier indicate that it applies to earthquake study effectively.