A Ф-OTDR event identification based on data augmentation with TSG

Wenhao Ni; Liqin Hu; Kuanglu Yu

doi:10.1117/12.2691540

27 September 2023 A Φ-OTDR event identification based on data augmentation with TSG

Wenhao Ni, Liqin Hu, Kuanglu Yu

Proceedings Volume 12813, Asia-Pacific Optical Sensors Conference (APOS 2023); 1281303 (2023) https://doi.org/10.1117/12.2691540
Event: Asia Pacific Optical Sensors Conference 2023, 2023, Tianjin, China

Abstract

Event identification based on Ф-OTDR stands as a prominent research hotspot in the realm of distributed fiber optic sensing. However, the challenge of collecting rare vibration signals in Ф-OTDR applications limits the model's ability to classify accurately. We propose a TSG data augmentation method based on Time Series Transfer and StyleGAN. The augmented data is enhanced for diversity and generalization. With a sample size of 50 per class, our approach enhances the classification accuracy from 66.89% to 81.61%.

Citation Download Citation

Wenhao Ni, Liqin Hu, and Kuanglu Yu "A Φ-OTDR event identification based on data augmentation with TSG", Proc. SPIE 12813, Asia-Pacific Optical Sensors Conference (APOS 2023), 1281303 (27 September 2023); https://doi.org/10.1117/12.2691540

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