A MCSVM Based High-Efficiency Events Discrimination Method for ADMZI Distributed Infrared Fiber Vibration Sensor

摘要

This paper presents a multi-class support vector machine (MCSVM) based high-efficiency events discrimination method for asymmetric dual Mach-Zehnder interferometers (ADMZI) distributed infrared fiber vibration sensor. This method combined empirical mode decomposition (EMD), kurtosis characteristics with MCSVM, which can improve the recognition rate effectively. Filed experimental results demonstrate that the proposed method can discriminate four common invasive events (climbing the fence, knocking the cable, cutting the fence, and waggling the fence) with an average recognition rate above 90.9%, which can satisfy actual application requirements.