Cargando…

Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks

Liquid crystal (LC)-based materials are promising platforms to develop rapid, miniaturised and low-cost gas sensor devices. In hybrid gel films containing LC droplets, characteristic optical texture variations are observed due to orientational transitions of LC molecules in the presence of distinct...

Descripción completa

Detalles Bibliográficos
Autores principales: Frazão, José, Palma, Susana I. C. J., Costa, Henrique M. A., Alves, Cláudia, Roque, Ana C. A., Silveira, Margarida
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8073403/
https://www.ncbi.nlm.nih.gov/pubmed/33919620
http://dx.doi.org/10.3390/s21082854
_version_ 1783684122107969536
author Frazão, José
Palma, Susana I. C. J.
Costa, Henrique M. A.
Alves, Cláudia
Roque, Ana C. A.
Silveira, Margarida
author_facet Frazão, José
Palma, Susana I. C. J.
Costa, Henrique M. A.
Alves, Cláudia
Roque, Ana C. A.
Silveira, Margarida
author_sort Frazão, José
collection PubMed
description Liquid crystal (LC)-based materials are promising platforms to develop rapid, miniaturised and low-cost gas sensor devices. In hybrid gel films containing LC droplets, characteristic optical texture variations are observed due to orientational transitions of LC molecules in the presence of distinct volatile organic compounds (VOC). Here, we investigate the use of deep convolutional neural networks (CNN) as pattern recognition systems to analyse optical textures dynamics in LC droplets exposed to a set of different VOCs. LC droplets responses to VOCs were video recorded under polarised optical microscopy (POM). CNNs were then used to extract features from the responses and, in separate tasks, to recognise and quantify the vapours exposed to the films. The impact of droplet diameter on the results was also analysed. With our classification models, we show that a single individual droplet can recognise 11 VOCs with small structural and functional differences (F1-score above 93%). The optical texture variation pattern of a droplet also reflects VOC concentration changes, as suggested by applying a regression model to acetone at 0.9–4.0% (v/v) (mean absolute errors below 0.25% (v/v)). The CNN-based methodology is thus a promising approach for VOC sensing using responses from individual LC-droplets.
format Online
Article
Text
id pubmed-8073403
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-80734032021-04-27 Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks Frazão, José Palma, Susana I. C. J. Costa, Henrique M. A. Alves, Cláudia Roque, Ana C. A. Silveira, Margarida Sensors (Basel) Article Liquid crystal (LC)-based materials are promising platforms to develop rapid, miniaturised and low-cost gas sensor devices. In hybrid gel films containing LC droplets, characteristic optical texture variations are observed due to orientational transitions of LC molecules in the presence of distinct volatile organic compounds (VOC). Here, we investigate the use of deep convolutional neural networks (CNN) as pattern recognition systems to analyse optical textures dynamics in LC droplets exposed to a set of different VOCs. LC droplets responses to VOCs were video recorded under polarised optical microscopy (POM). CNNs were then used to extract features from the responses and, in separate tasks, to recognise and quantify the vapours exposed to the films. The impact of droplet diameter on the results was also analysed. With our classification models, we show that a single individual droplet can recognise 11 VOCs with small structural and functional differences (F1-score above 93%). The optical texture variation pattern of a droplet also reflects VOC concentration changes, as suggested by applying a regression model to acetone at 0.9–4.0% (v/v) (mean absolute errors below 0.25% (v/v)). The CNN-based methodology is thus a promising approach for VOC sensing using responses from individual LC-droplets. MDPI 2021-04-18 /pmc/articles/PMC8073403/ /pubmed/33919620 http://dx.doi.org/10.3390/s21082854 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Frazão, José
Palma, Susana I. C. J.
Costa, Henrique M. A.
Alves, Cláudia
Roque, Ana C. A.
Silveira, Margarida
Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks
title Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks
title_full Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks
title_fullStr Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks
title_full_unstemmed Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks
title_short Optical Gas Sensing with Liquid Crystal Droplets and Convolutional Neural Networks
title_sort optical gas sensing with liquid crystal droplets and convolutional neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8073403/
https://www.ncbi.nlm.nih.gov/pubmed/33919620
http://dx.doi.org/10.3390/s21082854
work_keys_str_mv AT frazaojose opticalgassensingwithliquidcrystaldropletsandconvolutionalneuralnetworks
AT palmasusanaicj opticalgassensingwithliquidcrystaldropletsandconvolutionalneuralnetworks
AT costahenriquema opticalgassensingwithliquidcrystaldropletsandconvolutionalneuralnetworks
AT alvesclaudia opticalgassensingwithliquidcrystaldropletsandconvolutionalneuralnetworks
AT roqueanaca opticalgassensingwithliquidcrystaldropletsandconvolutionalneuralnetworks
AT silveiramargarida opticalgassensingwithliquidcrystaldropletsandconvolutionalneuralnetworks