Autoencoder-based anomaly detection in Rayleigh optical fiber sensors

• Grant number: 24/07224-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): August 01, 2024
• Effective date (End): January 31, 2025
• Field of knowledge: Engineering - Electrical Engineering - Telecommunications
• Principal Investigator: Ivan Aritz Aldaya Garde
• Grantee: João Pedro Innocente Gosmin
• Host Institution: Faculdade de Engenharia. Universidade Estadual Paulista (UNESP). Campus Experimental São João da Boa Vista. São João da Boa Vista , SP, Brazil

Abstract

Distributed acoustic sensors (DASs) based on optical fibers have been claimed as one of the key enabling technologies for real-time spatiotemporal monitoring of car traffic, a crucial aspect of smart city implementation. With the technological issues of the physical layout elegantly solved using coherent processing, the signal processing of a large amount of generated data became a challenge. Autoencoders are machine learning tools that have shown their capability to identify anomalies in complex systems. In this project, we propose to use an autoencoder to detect anomalies in data collected in a field-installed DAS system.