基于改进EWT和LogitBoost集成分类器的地震事件分类识别算法

Classification and recognition algorithm for earthquake events based on the improved EWT and LogitBoost ensemble classifier

快速、准确地识别天然地震和人工爆破事件是地震台网监测的重要工作之一,也是提高地震观测记录质量、开展地震研究工作的重要基础。针对反向传播神经网络、支持向量机等主流分类识别方法在地震事件分类识别应用上的不足,提出一种基于改进EWT和LogitBoost集成分类器的地震事件分类识别算法。首先,基于S谱能量曲线对传统经验小波变换进行改进,将信号自适应分解为按频率和能量分布的本征模函数;其次,提取P波与S波最大振幅比,前4个本征模函数的香农熵、对数能量熵,以及去噪后重构信号主频等特征;最后,采用基于集成学习LogitBoost的决策树集成分类器进行分类。实验结果表明,所提算法具有较高的鲁棒性,能有效解决样本不足的问题,识别准确率达93.1%以上,比集成学习AdaBoost、反向传播神经网络和支持向量机等方法提高了1%以上,且分类识别效果好。

The rapid and accurate identification of natural earthquakes and artificial blasting events is one of the most important tasks of seismic monitoring networks and is also an important basis for improving the quality of seismic observation records and conducting seismic research.In view of the shortcomings of the mainstream classification and recognition methods,such as the back propagation(BP)neural network and support vector machine(SVM),a classification and recognition algorithm for earthquake events based on the improved empirical wavelet transform(EWT)and LogitBoost ensemble classifier was proposed.First,the traditional EWT was improved based on the S-transform spectrum energy curve,and the signal was adaptively decomposed into several intrinsic mode functions.Then,the maximum amplitude ratio of the P-wave to S-wave,the Shannon entropy and logarithmic energy entropy of the first four intrinsic mode functions,and the main frequency of the reconstructed signal after de-noising were extracted.Finally,a decision tree ensemble classifier based on LogitBoost was designed to classify earthquake events.Experimental results show that the proposed algorithm has good robustness and can effectively solve the problem of insufficient samples,and the classification accuracy rate is over 93.1%.Compared with the ensemble learning AdaBoost,BP neural network,and SVM,the classification accuracy of the proposed algorithm is improved by more than 1%and has an excellent classification ability.