Abstract

Curvature detection is an essential technique for monitoring landslides, which are frequent and destructive disasters. Existing methods for curvature detection using fiber-optic sensors have limitations such as complex fabrication or large data size. We propose a data processing method for high-accuracy curvature detection that employs deep learning. We experimented using different levels of curvature and compared our method with other methods. Our method achieves 99.82% accuracy for classification and root mean square error of ${0.042}\;{{\rm m}^{- 1}}$ for regression with a simpler structure and smaller data size. Our approach demonstrates its potential for landslide detection and integration with communication systems.

© 2024 Optica Publishing Group

Working memory load recognition with deep learning time series classification

Richong Pang, Haojun Sang, Li Yi, Chenyang Gao, Hongkai Xu, Yanzhao Wei, Lei Zhang, and Jinyan Sun
Biomed. Opt. Express 15(5) 2780-2797 (2024)

Event recognition method based on feature synthesizing for a zero-shot intelligent distributed optical fiber sensor

Yi Shi, Hanfang Liu, Wentao Zhang, Zhongdi Cheng, Jiewei Chen, and Qian Sun
Opt. Express 32(5) 8321-8334 (2024)

Adaptive noise-resilient deep learning for image reconstruction in multimode fiber scattering

Mohammad Mohammadzadeh, Shima Tabakhi, and Mohammad R. Sayeh
Appl. Opt. 63(12) 3003-3014 (2024)

Using machine learning to enlarge the measurement range and promote the compactness of the optical fiber torsion sensor based on the Sagnac interferometer

Jiaqi Cao, Xin Wang, Bingsen Huang, Shuqin Lou, Paul K. Chu, and Zhufeng Sheng
Opt. Express 32(5) 6929-6944 (2024)

Spatially-resolved bending recognition based on a learning-empowered fiber specklegram sensor

Han Gao and Haifeng Hu
Opt. Express 31(5) 7671-7683 (2023)