Detail publikačního výsledku

Trains Detection Using State of Polarization Changes Measurement and Convolutional Neural Networks

DEJDAR, P.; MYŠKA, V.; MÜNSTER, P.; BURGET, R.

Originální název

Trains Detection Using State of Polarization Changes Measurement and Convolutional Neural Networks

Anglický název

Trains Detection Using State of Polarization Changes Measurement and Convolutional Neural Networks

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

Fiber optic infrastructure security is of growing interest. The current distributed sensor systems are robust and expensive solutions, and their practical applications are uncommon. Research into simple and cost-effective solutions based on changes in the state of polarization is crucial. This paper expands the use of a vibration sensor based on the sensing of rapid changes in the state of polarization (SOP) of light in a standard single-mode optical fiber by using a convolutional neural network to detect trains running along the optical fiber infrastructure. It is a simple system that determines ongoing events near the optical fiber route by simply determining the signal boundaries that define the idle state. By using a neural network, it is possible to eliminate the distortion caused by the temperature changes and, for example, to improve detection in the the zones where the vibrations are not strong enough for a simple threshold resolution.

Anglický abstrakt

Fiber optic infrastructure security is of growing interest. The current distributed sensor systems are robust and expensive solutions, and their practical applications are uncommon. Research into simple and cost-effective solutions based on changes in the state of polarization is crucial. This paper expands the use of a vibration sensor based on the sensing of rapid changes in the state of polarization (SOP) of light in a standard single-mode optical fiber by using a convolutional neural network to detect trains running along the optical fiber infrastructure. It is a simple system that determines ongoing events near the optical fiber route by simply determining the signal boundaries that define the idle state. By using a neural network, it is possible to eliminate the distortion caused by the temperature changes and, for example, to improve detection in the the zones where the vibrations are not strong enough for a simple threshold resolution.

Klíčová slova

artificial intelligence; machine learning; optical fiber sensor; state of polarization changes; vibration

Klíčová slova v angličtině

artificial intelligence; machine learning; optical fiber sensor; state of polarization changes; vibration

Autoři

DEJDAR, P.; MYŠKA, V.; MÜNSTER, P.; BURGET, R.

Rok RIV

2021

Vydáno

25.05.2021

Nakladatel

IEEE

ISBN

978-1-7281-5099-4

Kniha

2021 IEEE International Symposium on Inertial Sensors and Systems (INERTIAL) Proceedings

Strany od

1

Strany do

4

Strany počet

4

URL

https://ieeexplore.ieee.org/document/9430469

Plný text v Digitální knihovně

http://hdl.handle.net/11012/203013

BibTex

@inproceedings{BUT171700,
  author="Petr {Dejdar} and Vojtěch {Myška} and Petr {Münster} and Radim {Burget}",
  title="Trains Detection Using State of Polarization Changes Measurement and Convolutional Neural Networks",
  booktitle="2021 IEEE International Symposium on Inertial Sensors and Systems (INERTIAL) Proceedings",
  year="2021",
  pages="1--4",
  publisher="IEEE",
  doi="10.1109/INERTIAL51137.2021.9430469",
  isbn="978-1-7281-5099-4",
  url="https://ieeexplore.ieee.org/document/9430469"
}

Dokumenty

IEEE_Inertial_2021_v4_manuskript
9430469_accepted