Zekai Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zekai Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Fan Yang
Beijing University of Posts and Telecommunications
1 shared publication - Hao Zhou
Beijing University of Posts and Telecommunications
1 shared publication - Wen Zuo
WDM System Department, State Key Laboratory of Mobile Network and Mobile Multimedia Technology, ZTE Corporation, Beijing, China
1 shared publication - Yaojun Qiao
Beijing University of Posts and Telecommunications
1 shared publication
Latest Publications
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (11) , 16864-16871
LADNet: A Lightweight Axial-Depthwise Network for Phase Unwrapping and Fading Suppression in ϕ -OTDR
In this paper, we propose a lightweight axial-depthwise network (LADNet) to address interference fading and large-dynamic-range phase wrapping in phase-sensitive optical time-domain reflectometry (ϕ-OTDR). The lightweight design leverages axis-specific patterns and local spatial correlation in ϕ-OTDR waterfall data, and captures these features using axial depthwise convolutions. We design a U-Net architecture that integrates multi-branch axial depthwise convolutions and attention mechanisms to capture the anisotropic spatiotemporal correlations of ϕ-OTDR signals. To construct paired data for training and evaluation, we generate noisy wrapped-phase samples with fading and corresponding unwrapped-phase references using a physics-driven ϕ-OTDR simulator.On simulated test data (strain range 0–500 nε), LADNet achieves a strain MAE of 1.3 nε with only 1.70 M parameters. Experiments on a 5.6-km ϕ-OTDR system further verify robust phase recovery under large-amplitude vibration, yielding an SNR of 32.2 dB and a strong linear relationship between the recovered phase and the PZT driving voltage (R2 = 0.9974). Overall, the proposed method provides an effective solution for phase demodulation in ϕ-OTDR under large amplitude vibration conditions.
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (11) , 16864-16871
LADNet: A Lightweight Axial-Depthwise Network for Phase Unwrapping and Fading Suppression in ϕ -OTDR
In this paper, we propose a lightweight axial-depthwise network (LADNet) to address interference fading and large-dynamic-range phase wrapping in phase-sensitive optical time-domain reflectometry (ϕ-OTDR). The lightweight design leverages axis-specific patterns and local spatial correlation in ϕ-OTDR waterfall data, and captures these features using axial depthwise convolutions. We design a U-Net architecture that integrates multi-branch axial depthwise convolutions and attention mechanisms to capture the anisotropic spatiotemporal correlations of ϕ-OTDR signals. To construct paired data for training and evaluation, we generate noisy wrapped-phase samples with fading and corresponding unwrapped-phase references using a physics-driven ϕ-OTDR simulator.On simulated test data (strain range 0–500 nε), LADNet achieves a strain MAE of 1.3 nε with only 1.70 M parameters. Experiments on a 5.6-km ϕ-OTDR system further verify robust phase recovery under large-amplitude vibration, yielding an SNR of 32.2 dB and a strong linear relationship between the recovered phase and the PZT driving voltage (R2 = 0.9974). Overall, the proposed method provides an effective solution for phase demodulation in ϕ-OTDR under large amplitude vibration conditions.