An event recognition method for fiber distributed acoustic sensing systems based on the combination of MFCC and CNN

Fei Jiang; Honglang Li; Zhenhai Zhang; Xuping Zhang

doi:10.1117/12.2286220

10 January 2018 An event recognition method for fiber distributed acoustic sensing systems based on the combination of MFCC and CNN

Fei Jiang, Honglang Li, Zhenhai Zhang, Xuping Zhang

Author Affiliations +

Proceedings Volume 10618, 2017 International Conference on Optical Instruments and Technology: Advanced Optical Sensors and Applications; 1061804 (2018) https://doi.org/10.1117/12.2286220
Event: International Conference on Optical Instruments and Technology 2017, 2017, Beijing, China

Abstract

Fiber distributed acoustic sensing (FDAS) systems have been widely used in many fields such as oil and gas pipeline monitoring, urban safety monitoring, and perimeter security. An event recognition method for fiber distributed acoustic sensing (FDAS) systems is proposed in this paper. The Mel-frequency cepstrum coefficients (MFCC) of the acoustic signals collected by the FDAS system are computed as the features of the events, which are inputted into a convolutional neural network (CNN) to determine the type of the events. Experimental results based on 2300 training samples and 946 test samples show that the precision, recall, and f1-score of the classification model reach as high as 98.02%, 97.99%, and 97.98% respectively, which means that the combination of MFCC and CNN may be a promising event recognition method for FDAS systems.

Citation Download Citation

Fei Jiang, Honglang Li, Zhenhai Zhang, and Xuping Zhang "An event recognition method for fiber distributed acoustic sensing systems based on the combination of MFCC and CNN", Proc. SPIE 10618, 2017 International Conference on Optical Instruments and Technology: Advanced Optical Sensors and Applications, 1061804 (10 January 2018); https://doi.org/10.1117/12.2286220

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