基于非线性加权K-相关的核爆地震识别

地下核爆炸和天然地震的识别一直是国际核查的重点研究内容之一，基于地下核爆炸和天然地震事件的相关性，提出了一种非线性加权K-相关分类方法，对地下核爆炸和天然地震进行分类，详细阐述了它的分类原理，讨论了训练样本个数和K值两个参数的选取问题，并将它和最大相关法及K-近邻法进行了比较。实际分类结果表明了该方法的有效性。

Identification of underground nuclear explosions and natural earthquakes based on K-correlation of nonlinear weighting

Automatic discrimination of underground nuclear explosions and natural earthquakes is al ways worth to study because of the problem of classification accuracy. In this paper, a method of non linear weighting .K-correlation is proposed to discriminate the underground nuclear explosions and natu ral earthquakes, the basic idea is that the sum of K correlation coefficients for each class is used as a criterion to discriminate these two kinds of events, and to magnify the difference of this criterion to i dentify these two events with higher probability, a method of nonlinear weighting is used. Besides, the comparison with the maximum correlation classification and k-nearest neighbor classification is expatiat ed. Theoretical analysis and practical identification results indicate this method is feasible.