Machine Learning-Based Methods for Force Mapping With an Optical Fiber Sensing System

Macro-bend sensors multiplexed in a single optical fiber can allow different systems to operate in quasi-distributed tactile sensing. This letter uses a pressure-sensitive platform instrumented with five macro-bend sensors divided into 16 sensing regions. The sensing system was tested with the simul...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE sensors letters 2024-07, Vol.8 (7), p.1-4
Hauptverfasser: Flores, Walter Oswaldo Cutipa, Carvalho, Vinicius, Martins, Victor Hugo, Fabris, Jose Luis, Muller, Marcia, Lopes, Heitor Silverio, Lazzaretti, Andre Eugenio
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 4
container_issue 7
container_start_page 1
container_title IEEE sensors letters
container_volume 8
creator Flores, Walter Oswaldo Cutipa
Carvalho, Vinicius
Martins, Victor Hugo
Fabris, Jose Luis
Muller, Marcia
Lopes, Heitor Silverio
Lazzaretti, Andre Eugenio
description Macro-bend sensors multiplexed in a single optical fiber can allow different systems to operate in quasi-distributed tactile sensing. This letter uses a pressure-sensitive platform instrumented with five macro-bend sensors divided into 16 sensing regions. The sensing system was tested with the simultaneous positioning of different loads (0.5 and 2.4 kg) on two of the 16 sensing areas. The dataset contains 240 samples related to the randomly chosen load configurations. Each sample is the light transmitted in the 400-850 nm spectral range measured with steps of 0.27 nm. Three classification models were used to obtain the best results for the location of the masses: support vector machine (SVM), deep neural network (DNN), and random convolutional Kernel transform, achieving F1-Score above 93% for the SVM model.
doi_str_mv 10.1109/LSENS.2024.3418294
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10572288</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10572288</ieee_id><sourcerecordid>3075427022</sourcerecordid><originalsourceid>FETCH-LOGICAL-c177t-6063bb7c020582280b3c5e08a0a6b723fac06a131c54ff0d25d1f2e2d5c6ea33</originalsourceid><addsrcrecordid>eNpNkE9PwkAQxTdGEwnyBYyHTTwXZ2e73XJUAmoCcijG42a7nUoJtHW3Hvj2FuHAaSZ5782fH2P3AsZCwORpkc0-sjECxmMZixQn8RUbYKxVJGKN1xf9LRuFsAWA3qVBwoB9Lq3bVDXxBVlfV_V39GIDFXxJ3aYpAi8bz-eNd8SXtm17nX9V3Ybbmq_arnJ2x-dVTp5nVIejmh1CR_s7dlPaXaDRuQ7Zej5bT9-ixer1ffq8iJzQuosSSGSeawcIKkVMIZdOEaQWbJJrlKV1kFghhVNxWUKBqhAlEhbKJWSlHLLH09jWNz-_FDqzbX593W80ErSK-x8RexeeXM43IXgqTeurvfUHI8AcAZp_gOYI0JwB9qGHU6gioouA0v2dqfwDF2prPA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3075427022</pqid></control><display><type>article</type><title>Machine Learning-Based Methods for Force Mapping With an Optical Fiber Sensing System</title><source>IEEE Electronic Library (IEL)</source><creator>Flores, Walter Oswaldo Cutipa ; Carvalho, Vinicius ; Martins, Victor Hugo ; Fabris, Jose Luis ; Muller, Marcia ; Lopes, Heitor Silverio ; Lazzaretti, Andre Eugenio</creator><creatorcontrib>Flores, Walter Oswaldo Cutipa ; Carvalho, Vinicius ; Martins, Victor Hugo ; Fabris, Jose Luis ; Muller, Marcia ; Lopes, Heitor Silverio ; Lazzaretti, Andre Eugenio</creatorcontrib><description>Macro-bend sensors multiplexed in a single optical fiber can allow different systems to operate in quasi-distributed tactile sensing. This letter uses a pressure-sensitive platform instrumented with five macro-bend sensors divided into 16 sensing regions. The sensing system was tested with the simultaneous positioning of different loads (0.5 and 2.4 kg) on two of the 16 sensing areas. The dataset contains 240 samples related to the randomly chosen load configurations. Each sample is the light transmitted in the 400-850 nm spectral range measured with steps of 0.27 nm. Three classification models were used to obtain the best results for the location of the masses: support vector machine (SVM), deep neural network (DNN), and random convolutional Kernel transform, achieving F1-Score above 93% for the SVM model.</description><identifier>ISSN: 2475-1472</identifier><identifier>EISSN: 2475-1472</identifier><identifier>DOI: 10.1109/LSENS.2024.3418294</identifier><identifier>CODEN: ISLECD</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Artificial neural networks ; force mapping ; Kernel functions ; Load modeling ; Machine learning ; macro-bend ; optical fiber ; Optical fiber sensors ; Optical fibers ; Sensor applications ; Sensor arrays ; Sensors ; Support vector machines ; Transforms</subject><ispartof>IEEE sensors letters, 2024-07, Vol.8 (7), p.1-4</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c177t-6063bb7c020582280b3c5e08a0a6b723fac06a131c54ff0d25d1f2e2d5c6ea33</cites><orcidid>0000-0001-5630-1193 ; 0000-0003-1861-3369 ; 0000-0003-3984-1432 ; 0000-0002-4463-3526</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10572288$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,777,781,793,27905,27906,54739</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10572288$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Flores, Walter Oswaldo Cutipa</creatorcontrib><creatorcontrib>Carvalho, Vinicius</creatorcontrib><creatorcontrib>Martins, Victor Hugo</creatorcontrib><creatorcontrib>Fabris, Jose Luis</creatorcontrib><creatorcontrib>Muller, Marcia</creatorcontrib><creatorcontrib>Lopes, Heitor Silverio</creatorcontrib><creatorcontrib>Lazzaretti, Andre Eugenio</creatorcontrib><title>Machine Learning-Based Methods for Force Mapping With an Optical Fiber Sensing System</title><title>IEEE sensors letters</title><addtitle>LSENS</addtitle><description>Macro-bend sensors multiplexed in a single optical fiber can allow different systems to operate in quasi-distributed tactile sensing. This letter uses a pressure-sensitive platform instrumented with five macro-bend sensors divided into 16 sensing regions. The sensing system was tested with the simultaneous positioning of different loads (0.5 and 2.4 kg) on two of the 16 sensing areas. The dataset contains 240 samples related to the randomly chosen load configurations. Each sample is the light transmitted in the 400-850 nm spectral range measured with steps of 0.27 nm. Three classification models were used to obtain the best results for the location of the masses: support vector machine (SVM), deep neural network (DNN), and random convolutional Kernel transform, achieving F1-Score above 93% for the SVM model.</description><subject>Artificial neural networks</subject><subject>force mapping</subject><subject>Kernel functions</subject><subject>Load modeling</subject><subject>Machine learning</subject><subject>macro-bend</subject><subject>optical fiber</subject><subject>Optical fiber sensors</subject><subject>Optical fibers</subject><subject>Sensor applications</subject><subject>Sensor arrays</subject><subject>Sensors</subject><subject>Support vector machines</subject><subject>Transforms</subject><issn>2475-1472</issn><issn>2475-1472</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkE9PwkAQxTdGEwnyBYyHTTwXZ2e73XJUAmoCcijG42a7nUoJtHW3Hvj2FuHAaSZ5782fH2P3AsZCwORpkc0-sjECxmMZixQn8RUbYKxVJGKN1xf9LRuFsAWA3qVBwoB9Lq3bVDXxBVlfV_V39GIDFXxJ3aYpAi8bz-eNd8SXtm17nX9V3Ybbmq_arnJ2x-dVTp5nVIejmh1CR_s7dlPaXaDRuQ7Zej5bT9-ixer1ffq8iJzQuosSSGSeawcIKkVMIZdOEaQWbJJrlKV1kFghhVNxWUKBqhAlEhbKJWSlHLLH09jWNz-_FDqzbX593W80ErSK-x8RexeeXM43IXgqTeurvfUHI8AcAZp_gOYI0JwB9qGHU6gioouA0v2dqfwDF2prPA</recordid><startdate>20240701</startdate><enddate>20240701</enddate><creator>Flores, Walter Oswaldo Cutipa</creator><creator>Carvalho, Vinicius</creator><creator>Martins, Victor Hugo</creator><creator>Fabris, Jose Luis</creator><creator>Muller, Marcia</creator><creator>Lopes, Heitor Silverio</creator><creator>Lazzaretti, Andre Eugenio</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-5630-1193</orcidid><orcidid>https://orcid.org/0000-0003-1861-3369</orcidid><orcidid>https://orcid.org/0000-0003-3984-1432</orcidid><orcidid>https://orcid.org/0000-0002-4463-3526</orcidid></search><sort><creationdate>20240701</creationdate><title>Machine Learning-Based Methods for Force Mapping With an Optical Fiber Sensing System</title><author>Flores, Walter Oswaldo Cutipa ; Carvalho, Vinicius ; Martins, Victor Hugo ; Fabris, Jose Luis ; Muller, Marcia ; Lopes, Heitor Silverio ; Lazzaretti, Andre Eugenio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c177t-6063bb7c020582280b3c5e08a0a6b723fac06a131c54ff0d25d1f2e2d5c6ea33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>force mapping</topic><topic>Kernel functions</topic><topic>Load modeling</topic><topic>Machine learning</topic><topic>macro-bend</topic><topic>optical fiber</topic><topic>Optical fiber sensors</topic><topic>Optical fibers</topic><topic>Sensor applications</topic><topic>Sensor arrays</topic><topic>Sensors</topic><topic>Support vector machines</topic><topic>Transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Flores, Walter Oswaldo Cutipa</creatorcontrib><creatorcontrib>Carvalho, Vinicius</creatorcontrib><creatorcontrib>Martins, Victor Hugo</creatorcontrib><creatorcontrib>Fabris, Jose Luis</creatorcontrib><creatorcontrib>Muller, Marcia</creatorcontrib><creatorcontrib>Lopes, Heitor Silverio</creatorcontrib><creatorcontrib>Lazzaretti, Andre Eugenio</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE sensors letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Flores, Walter Oswaldo Cutipa</au><au>Carvalho, Vinicius</au><au>Martins, Victor Hugo</au><au>Fabris, Jose Luis</au><au>Muller, Marcia</au><au>Lopes, Heitor Silverio</au><au>Lazzaretti, Andre Eugenio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning-Based Methods for Force Mapping With an Optical Fiber Sensing System</atitle><jtitle>IEEE sensors letters</jtitle><stitle>LSENS</stitle><date>2024-07-01</date><risdate>2024</risdate><volume>8</volume><issue>7</issue><spage>1</spage><epage>4</epage><pages>1-4</pages><issn>2475-1472</issn><eissn>2475-1472</eissn><coden>ISLECD</coden><abstract>Macro-bend sensors multiplexed in a single optical fiber can allow different systems to operate in quasi-distributed tactile sensing. This letter uses a pressure-sensitive platform instrumented with five macro-bend sensors divided into 16 sensing regions. The sensing system was tested with the simultaneous positioning of different loads (0.5 and 2.4 kg) on two of the 16 sensing areas. The dataset contains 240 samples related to the randomly chosen load configurations. Each sample is the light transmitted in the 400-850 nm spectral range measured with steps of 0.27 nm. Three classification models were used to obtain the best results for the location of the masses: support vector machine (SVM), deep neural network (DNN), and random convolutional Kernel transform, achieving F1-Score above 93% for the SVM model.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LSENS.2024.3418294</doi><tpages>4</tpages><orcidid>https://orcid.org/0000-0001-5630-1193</orcidid><orcidid>https://orcid.org/0000-0003-1861-3369</orcidid><orcidid>https://orcid.org/0000-0003-3984-1432</orcidid><orcidid>https://orcid.org/0000-0002-4463-3526</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2475-1472
ispartof IEEE sensors letters, 2024-07, Vol.8 (7), p.1-4
issn 2475-1472
2475-1472
language eng
recordid cdi_ieee_primary_10572288
source IEEE Electronic Library (IEL)
subjects Artificial neural networks
force mapping
Kernel functions
Load modeling
Machine learning
macro-bend
optical fiber
Optical fiber sensors
Optical fibers
Sensor applications
Sensor arrays
Sensors
Support vector machines
Transforms
title Machine Learning-Based Methods for Force Mapping With an Optical Fiber Sensing System
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T00%3A14%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning-Based%20Methods%20for%20Force%20Mapping%20With%20an%20Optical%20Fiber%20Sensing%20System&rft.jtitle=IEEE%20sensors%20letters&rft.au=Flores,%20Walter%20Oswaldo%20Cutipa&rft.date=2024-07-01&rft.volume=8&rft.issue=7&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.issn=2475-1472&rft.eissn=2475-1472&rft.coden=ISLECD&rft_id=info:doi/10.1109/LSENS.2024.3418294&rft_dat=%3Cproquest_RIE%3E3075427022%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3075427022&rft_id=info:pmid/&rft_ieee_id=10572288&rfr_iscdi=true