基于DBSCAN的地震电离层扰动异常数据检测方法

Detection Method for Seismic Ionospheric Disturbance Anomaly Data Based on DBSCAN

电离层扰动变化可以作为地震的短临前兆,为提升电离层扰动数据分析准确性,剔除异常数据,提出了基于DBSCAN的地震电离层扰动异常数据检测方法。首先利用DBSCAN方法的中心思想,分析电离层扰动数据,结合无线传感器网络数据的特点,将欧式距离设定为指标,对比不同电离层扰动数据并进行划分聚类,然后计算地震电离层扰动数据相似度。再利用DBSCAN方法提取相关的环境特征集,通过特征集实现地震电离层扰动异常数据检测。最后实验分析与传统方法相比,运行时间、误报率、漏报率以及检测率的对比结果。结果表明:所提方法的所需时间短,误报率和漏报率明显降低,检测率大大提高。

To improve the accuracy of the analysis of ionospheric disturbance data and eliminate anomalous data,this study proposes a detection method for seismic ionospheric disturbance anomaly data based on DBSCAN.According to the characteristics of wireless sensor network data,the Euclidean distance is set as the index,and different ionospheric disturbance data are compared and clustered.The similarities of the seismic ionospheric disturbance data are then calculated.The DBSCAN method is used to extract relevant environmental feature sets,through which the seismic ionospheric disturbance anomaly data can be detected.The run time,false positive rate,false negative rate,and detection rate of the proposed method are compared with those of a traditional method.Experimental results show that the proposed method requires minimal time,significantly reduces false positive and false negative rates,and improves detection rates.