A MCSVM-based high-efficiency events-discrimination method for ADMZI-distributed infrared fiber vibration sensor

Jianchang An; Miao Tian; Chunyu Ma; Zhenchen Li

doi:10.1117/12.2500624

23 October 2018 A MCSVM-based high-efficiency events-discrimination method for ADMZI-distributed infrared fiber vibration sensor

Jianchang An, Miao Tian, Chunyu Ma, Zhenchen Li

Author Affiliations +

Proceedings Volume 10821, Advanced Sensor Systems and Applications VIII; 108211D (2018) https://doi.org/10.1117/12.2500624
Event: SPIE/COS Photonics Asia, 2018, Beijing, China

Abstract

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.

Citation Download Citation

Jianchang An, Miao Tian, Chunyu Ma, and Zhenchen Li "A MCSVM-based high-efficiency events-discrimination method for ADMZI-distributed infrared fiber vibration sensor", Proc. SPIE 10821, Advanced Sensor Systems and Applications VIII, 108211D (23 October 2018); https://doi.org/10.1117/12.2500624

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available