Weakly-supervised learning from ambient data

Tue, 16 May 2023 00:00:00 +0000

Distributed acoustic sensing is a technology that captures real-world acoustic and vibration events at the speed of light. Just as a lighthouse serves as a reference point for navigating ships across the vast ocean, manholes can be employed as landmarks to determine the locations of other detected acoustic events around the cable.

During the summer of 2021, I had the privilege of supervising an internship project focused on localizing manholes within existing networks through learning from ambient data. Our team developed an innovative solution based on deep multiple instance learning, pushing the boundaries of utilizing ambient environment data for fiber sensing tasks with less human annotation. In addition, manhole also serves as the key accessing point and this approach holds great promise in enhancing operational efficiency of telecom carriers and reducing field work.

To Know More

Eigenvalue-based method for earthquake sensing and localization

Mon, 27 Mar 2023 00:00:00 +0000

Seventy percent of our planet is covered by water, and it is crucial to monitor disturbances beneath the ocean’s surface for the protection of trans-oceanic communication cables and the tracking of various activities including earthquakes, tsunamis, volcanic events, and maritime traffic.

In the summer of 2022, I supervised an internship project aimed at utilizing fiber sensing technology over submarine cables to precisely locate disturbances. By analyzing changes in light transmission within the cable, our team developed a cutting-edge solution that utilizes the matrix similarity property to effectively separate the contributions from each span. This breakthrough enables us to achieve highly accurate earthquake localization via polarization sensing and enhances our ability to monitor and mitigate potential risks in underwater environments.

To Know More

Use Linear Algebra to Localize Earthquakes through Submarine Fiber Sensing, NEC Labs blog
Polarization Sensing Using Polarization Rotation Matrix Eigenvalue Method, (Oral presentation) OFC 2023,
Improvement of resilience of submarine networks based on fiber sensing, SubOptic 2023

Fiber Sensing | Shaobo Han

Weakly-supervised learning from ambient data

To Know More

Eigenvalue-based method for earthquake sensing and localization

To Know More