← All projects

Southern University of Science and Technology · Nov 2024–Jun 2025

Acoustic Sensing

Class-incremental event recognition in optical fiber sensing

A distributed acoustic sensor can detect events along an optical fiber, but the set of events encountered in use changes over time. This project connects optical signal processing with a class-incremental learning pipeline for adding event classes while retaining earlier knowledge.

Technologies: Optical fiber sensing, φ-OTDR, MATLAB, Python, ResNet, class-incremental learning

Distributed optical fiber sensing setup used for acoustic measurements.
Distributed optical fiber sensing setup used for acoustic measurements.

Optical sensing and signal preparation

The sensing system uses fiber backscatter as the observation signal. Heterodyne detection supports phase demodulation, and phase variations provide acoustic features. I processed those measurements into image representations for a ResNet-based event classifier.

Optical measurement structure for phase-sensitive distributed acoustic sensing.
Optical measurement structure for phase-sensitive distributed acoustic sensing.

Sequential learning

I developed a hybrid incremental-learning framework that combines exemplar replay, logit distillation, bias correction and attention alignment. Replay keeps representative earlier samples available, while distillation and alignment constrain how the representation changes as new classes enter training.

Sequential training workflow and retained-sample replay.
Sequential training workflow and retained-sample replay.

Model inspection

The retained results include model architecture, feature-space inspection and a confusion matrix across old and new classes. These views make the effect of sequential updates visible beyond one aggregate accuracy number.

Recorded event-class confusion matrix.
Recorded event-class confusion matrix.

Related pipeline-monitoring work

Earlier work on pipeline safety monitoring combined a φ-OTDR sensing system, MATLAB signal demodulation and Python-based deep-learning event recognition. That project received a Bronze Award in the 14th Challenge Cup National Competition.

© 2026 Yifan Ye
Built with Astrofy by Manuel Ernesto