Deep Learning Algorithms for Signal Recognition in Long Perimeter Monitoring Distributed Fiber Optic Sensors
This work addresses signal recognition for long perimeter security systems, but it appears incremental as it builds on existing deep learning methods for a specific domain.
The paper tackled the challenge of recognizing signals in distributed fiber optic monitoring systems under stringent error requirements and difficult jamming environments, resulting in a two-level detection architecture using an ensemble of deep convolutional networks that can recognize 7 classes of signals with high adaptability.
In this paper, we show an approach to build deep learning algorithms for recognizing signals in distributed fiber optic monitoring and security systems for long perimeters. Synthesizing such detection algorithms poses a non-trivial research and development challenge, because these systems face stringent error (type I and II) requirements and operate in difficult signal-jamming environments, with intensive signal-like jamming and a variety of changing possible signal portraits of possible recognized events. To address these issues, we have developed a twolevel event detection architecture, where the primary classifier is based on an ensemble of deep convolutional networks, can recognize 7 classes of signals and receives time-space data frames as input. Using real-life data, we have shown that the applied methods result in efficient and robust multiclass detection algorithms that have a high degree of adaptability.