基于VMD与MFE的光纤周界安防入侵事件识别北大核心CSCD

为了提高周界入侵事件的识别率,本文提出一种基于超弱光纤光栅(UWFBG)阵列的光纤周界入侵事件识别方法。该方法通过变分模态分解(VMD)将入侵信号进行分解,然后选择最佳分量并提取其多尺度模糊熵(MFE),与信号过零率(ZCR)相结合构造特征向量,将其输入到Sigmoid函数拟合的支持向量机(SVM),实现对晃动、剪切、刮风、下雨和无入侵5种不同的事件的识别。实验表明,该方法可以准确识别5种常见的事件信号,平均识别率达到98%。此外,该方法可以在输出各入侵事件类别的同时输出各类事件发生的概率值。

Intrusion event identification for fiber optic perimeter security based on VMD and MFE

To improve the recognition rate of perimeter intrusion events,a fiber optic perimeter intrusion event recognition method based onultra weak fiber Bragg grating(UWFBG)arrays is proposed in this paper.The intrusion signal by variational modal decomposition(VMD)is decomposed.Then,the best component is selected and its multiscale fuzzy entropy(MFE)is extracted,and combined with the signal zero crossing rate(ZCR)to construct a feature vector,which is fed into a support vector machine(SVM)fitted with a Sigmoid function to achieve recognition of five different events:waggling,cutting,winding,raining,and non intrusive.Experiments show that the method can accurately identify five common event signals with an average recognition rate of 98%.In addition,the method can output the probability valuesfor the occurrence of each type of event along with each intrusion event category.