Machine learning-based analysis of multiple simultaneous disturbances applied on a transmission-reflection analysis based distributed sensor using a nanoparticle-doped fiber

• DOI: 10.1364/prj.471301
• Publication Date: 2022-12-09T22:00:14Z
• Authors: Letícia Avellar; Anselmo Frizera; Helder Rocha; Mariana Silveira; Camilo Díaz; Wilfried Blanc; Carlos Marques; Arnaldo Leal-Junior
• Keywords: 02 engineering and technology; 0210 nano-technology

Photonic technology combined with artificial intelligence plays a key role in the development of latest smart system trends, integrating cutting-edge machine learning models. This paper proposes transmission-reflection analysis based using dielectric nanoparticle-doped fiber to address one major problems distributed sensing approach: reducing cost while maintaining high spatial resolution close gap between sensors and general public. Machine learning-based models are designed classify perturbed positions when same force is used regression different forces applied on each position. The results show an accuracy 99.43% position classification multiple disturbances rms error <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="m1"> <mml:mrow> <mml:mn>1.53</mml:mn> <mml:mtext> </mml:mtext> <mml:mi mathvariant="normal">N</mml:mi> </mml:mrow> </mml:math> regression, which represents 5% range. In addition, environment current proposed, presented 100% identifying persons environment. enables remote home care patients reliability, intelligent decision-making, predictive capability.