We are pleased to share our latest contribution:
Gulmina Malik, Imran Chowdhury Dipto, Muhammad Umar Masood, Mashboob Cheruvakkadu Mohamed, Stefano Straullu, Sai Kishore Bhyri, Gabriele Maria Galimberti, Antonio Napoli, João Pedro, Walid Wakim & Vittorio Curri
“SOP-Based Anomaly Detection Leveraging Machine Learning for Proactive Optical Restoration,” ONDM 2025.
🔗 Access the paper: https://hdl.handle.net/11583/3001256
Highlights:
- Introduces a monitoring framework that continuously tracks state of polarization (SOP) fluctuations in optical fibers to detect environmental or malicious disturbances. iris.polito.it+1
- Uses supervised machine-learning algorithms to distinguish benign environmental vibrations from critical disruptive events—achieving ~95% detection accuracy in experimental setups.
- Enables proactive optical network restoration, reducing the risk of service outages and infrastructure damage by triggering alerts and remediation early.
- Aligns with the Allegro EU Project’s goals of enhancing network resilience using data-driven and real-time sensing methods.