Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study
Force myography (FMG) detects hand gestures based on muscular contractions, featuring as an alternative to surface electromyography. However, typical FMG systems rely on spatially-distributed arrays of force-sensing resistors to resolve ambiguities. The aim of this proof-of-concept study is to devel...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Automation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4052/3/4/31 |
| _version_ | 1797461467602092032 |
|---|---|
| author | Matheus K. Gomes Willian H. A. da Silva Antonio Ribas Neto Julio Fajardo Eric Rohmer Eric Fujiwara |
| author_facet | Matheus K. Gomes Willian H. A. da Silva Antonio Ribas Neto Julio Fajardo Eric Rohmer Eric Fujiwara |
| author_sort | Matheus K. Gomes |
| collection | DOAJ |
| description | Force myography (FMG) detects hand gestures based on muscular contractions, featuring as an alternative to surface electromyography. However, typical FMG systems rely on spatially-distributed arrays of force-sensing resistors to resolve ambiguities. The aim of this proof-of-concept study is to develop a method for identifying hand poses from the static and dynamic components of FMG waveforms based on a compact, single-channel optical fiber sensor. As the user performs a gesture, a micro-bending transducer positioned on the belly of the forearm muscles registers the dynamic optical signals resulting from the exerted forces. A Raspberry Pi 3 minicomputer performs data acquisition and processing. Then, convolutional neural networks correlate the FMG waveforms with the target postures, yielding a classification accuracy of (93.98 ± 1.54)% for eight postures, based on the interrogation of a single fiber transducer. |
| first_indexed | 2024-03-09T17:19:48Z |
| format | Article |
| id | doaj.art-0ff3deb1d67a432da6eb4212f13c29b7 |
| institution | Directory Open Access Journal |
| issn | 2673-4052 |
| language | English |
| last_indexed | 2024-03-09T17:19:48Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Automation |
| spelling | doaj.art-0ff3deb1d67a432da6eb4212f13c29b72023-11-24T13:14:52ZengMDPI AGAutomation2673-40522022-11-013462263210.3390/automation3040031Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept StudyMatheus K. Gomes0Willian H. A. da Silva1Antonio Ribas Neto2Julio Fajardo3Eric Rohmer4Eric Fujiwara5Laboratory of Photonic Materials and Devices, School of Mechanical Engineering, University of Campinas, Campinas 13083-860, BrazilLaboratory of Photonic Materials and Devices, School of Mechanical Engineering, University of Campinas, Campinas 13083-860, BrazilSchool of Electrical and Computing Engineering, University of Campinas, Campinas 13083-852, BrazilSchool of Electrical and Computing Engineering, University of Campinas, Campinas 13083-852, BrazilSchool of Electrical and Computing Engineering, University of Campinas, Campinas 13083-852, BrazilLaboratory of Photonic Materials and Devices, School of Mechanical Engineering, University of Campinas, Campinas 13083-860, BrazilForce myography (FMG) detects hand gestures based on muscular contractions, featuring as an alternative to surface electromyography. However, typical FMG systems rely on spatially-distributed arrays of force-sensing resistors to resolve ambiguities. The aim of this proof-of-concept study is to develop a method for identifying hand poses from the static and dynamic components of FMG waveforms based on a compact, single-channel optical fiber sensor. As the user performs a gesture, a micro-bending transducer positioned on the belly of the forearm muscles registers the dynamic optical signals resulting from the exerted forces. A Raspberry Pi 3 minicomputer performs data acquisition and processing. Then, convolutional neural networks correlate the FMG waveforms with the target postures, yielding a classification accuracy of (93.98 ± 1.54)% for eight postures, based on the interrogation of a single fiber transducer.https://www.mdpi.com/2673-4052/3/4/31force myographygesture recognitionoptical fiber sensorsuser interfaces |
| spellingShingle | Matheus K. Gomes Willian H. A. da Silva Antonio Ribas Neto Julio Fajardo Eric Rohmer Eric Fujiwara Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study Automation force myography gesture recognition optical fiber sensors user interfaces |
| title | Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study |
| title_full | Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study |
| title_fullStr | Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study |
| title_full_unstemmed | Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study |
| title_short | Detection of Hand Poses with a Single-Channel Optical Fiber Force Myography Sensor: A Proof-of-Concept Study |
| title_sort | detection of hand poses with a single channel optical fiber force myography sensor a proof of concept study |
| topic | force myography gesture recognition optical fiber sensors user interfaces |
| url | https://www.mdpi.com/2673-4052/3/4/31 |
| work_keys_str_mv | AT matheuskgomes detectionofhandposeswithasinglechannelopticalfiberforcemyographysensoraproofofconceptstudy AT willianhadasilva detectionofhandposeswithasinglechannelopticalfiberforcemyographysensoraproofofconceptstudy AT antonioribasneto detectionofhandposeswithasinglechannelopticalfiberforcemyographysensoraproofofconceptstudy AT juliofajardo detectionofhandposeswithasinglechannelopticalfiberforcemyographysensoraproofofconceptstudy AT ericrohmer detectionofhandposeswithasinglechannelopticalfiberforcemyographysensoraproofofconceptstudy AT ericfujiwara detectionofhandposeswithasinglechannelopticalfiberforcemyographysensoraproofofconceptstudy |