Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating

Paola Saccomandi, Calogero Maria Oddo, Loredana Zollo, Domenico Formica, Rocco Antonio Romeo, Carlo Massaroni, Michele Arturo Caponero, Nicola Vitiello, Eugenio Guglielmelli, Sergio Silvestri, Emiliano Schena

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This work shows the development and characterization of a fiber optic tactile sensor based on Fiber Bragg Grating (FBG) technology. The sensor is a 3 × 3 array of FBGs encapsulated in a PDMS compliant polymer. The strain experienced by each FBG is transduced into a Bragg wavelength shift and the inverse characteristics of the sensor were computed by means of a feedforward neural network. A 21 mN RMSE error was achieved in estimating the force over the 8 N experimented load range while including all probing sites in the neural network training procedure, whereas the median force RMSE was 199 mN across the 200 instances of a Monte Carlo randomized selection of experimental sessions to evaluate the calibration under generalized probing conditions. The static metrological properties and the possibility to fabricate sensors with relatively high spatial resolution make the proposed design attractive for the sensorization of robotic hands. Furthermore, the proved MRI-compatibility of the sensor opens other application scenarios, such as the possibility to employ the array for force measurement during functional MRI-measured brain activation.

Original languageEnglish
Article number367194
JournalJournal of Sensors
Volume2015
DOIs
Publication statusPublished - 2015

Fingerprint

Feedforward neural networks
Sensor arrays
Fiber Bragg gratings
Magnetic resonance imaging
Bragg gratings
coding
fibers
sensors
Sensors
end effectors
compatibility
Force measurement
brain
fiber optics
End effectors
education
estimating
spatial resolution
Fiber optics
activation

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

Saccomandi, P., Oddo, C. M., Zollo, L., Formica, D., Romeo, R. A., Massaroni, C., ... Schena, E. (2015). Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating. Journal of Sensors, 2015, [367194]. https://doi.org/10.1155/2015/367194

Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating. / Saccomandi, Paola; Oddo, Calogero Maria; Zollo, Loredana; Formica, Domenico; Romeo, Rocco Antonio; Massaroni, Carlo; Caponero, Michele Arturo; Vitiello, Nicola; Guglielmelli, Eugenio; Silvestri, Sergio; Schena, Emiliano.

In: Journal of Sensors, Vol. 2015, 367194, 2015.

Research output: Contribution to journalArticle

Saccomandi, P, Oddo, CM, Zollo, L, Formica, D, Romeo, RA, Massaroni, C, Caponero, MA, Vitiello, N, Guglielmelli, E, Silvestri, S & Schena, E 2015, 'Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating', Journal of Sensors, vol. 2015, 367194. https://doi.org/10.1155/2015/367194
Saccomandi, Paola ; Oddo, Calogero Maria ; Zollo, Loredana ; Formica, Domenico ; Romeo, Rocco Antonio ; Massaroni, Carlo ; Caponero, Michele Arturo ; Vitiello, Nicola ; Guglielmelli, Eugenio ; Silvestri, Sergio ; Schena, Emiliano. / Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating. In: Journal of Sensors. 2015 ; Vol. 2015.
@article{e8cfb6184c614fde9ecf97b11f9f130d,
title = "Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating",
abstract = "This work shows the development and characterization of a fiber optic tactile sensor based on Fiber Bragg Grating (FBG) technology. The sensor is a 3 × 3 array of FBGs encapsulated in a PDMS compliant polymer. The strain experienced by each FBG is transduced into a Bragg wavelength shift and the inverse characteristics of the sensor were computed by means of a feedforward neural network. A 21 mN RMSE error was achieved in estimating the force over the 8 N experimented load range while including all probing sites in the neural network training procedure, whereas the median force RMSE was 199 mN across the 200 instances of a Monte Carlo randomized selection of experimental sessions to evaluate the calibration under generalized probing conditions. The static metrological properties and the possibility to fabricate sensors with relatively high spatial resolution make the proposed design attractive for the sensorization of robotic hands. Furthermore, the proved MRI-compatibility of the sensor opens other application scenarios, such as the possibility to employ the array for force measurement during functional MRI-measured brain activation.",
author = "Paola Saccomandi and Oddo, {Calogero Maria} and Loredana Zollo and Domenico Formica and Romeo, {Rocco Antonio} and Carlo Massaroni and Caponero, {Michele Arturo} and Nicola Vitiello and Eugenio Guglielmelli and Sergio Silvestri and Emiliano Schena",
year = "2015",
doi = "10.1155/2015/367194",
language = "English",
volume = "2015",
journal = "Journal of Sensors",
issn = "1687-725X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Feedforward neural network for force coding of an MRI-compatible tactile sensor array based on fiber bragg grating

AU - Saccomandi, Paola

AU - Oddo, Calogero Maria

AU - Zollo, Loredana

AU - Formica, Domenico

AU - Romeo, Rocco Antonio

AU - Massaroni, Carlo

AU - Caponero, Michele Arturo

AU - Vitiello, Nicola

AU - Guglielmelli, Eugenio

AU - Silvestri, Sergio

AU - Schena, Emiliano

PY - 2015

Y1 - 2015

N2 - This work shows the development and characterization of a fiber optic tactile sensor based on Fiber Bragg Grating (FBG) technology. The sensor is a 3 × 3 array of FBGs encapsulated in a PDMS compliant polymer. The strain experienced by each FBG is transduced into a Bragg wavelength shift and the inverse characteristics of the sensor were computed by means of a feedforward neural network. A 21 mN RMSE error was achieved in estimating the force over the 8 N experimented load range while including all probing sites in the neural network training procedure, whereas the median force RMSE was 199 mN across the 200 instances of a Monte Carlo randomized selection of experimental sessions to evaluate the calibration under generalized probing conditions. The static metrological properties and the possibility to fabricate sensors with relatively high spatial resolution make the proposed design attractive for the sensorization of robotic hands. Furthermore, the proved MRI-compatibility of the sensor opens other application scenarios, such as the possibility to employ the array for force measurement during functional MRI-measured brain activation.

AB - This work shows the development and characterization of a fiber optic tactile sensor based on Fiber Bragg Grating (FBG) technology. The sensor is a 3 × 3 array of FBGs encapsulated in a PDMS compliant polymer. The strain experienced by each FBG is transduced into a Bragg wavelength shift and the inverse characteristics of the sensor were computed by means of a feedforward neural network. A 21 mN RMSE error was achieved in estimating the force over the 8 N experimented load range while including all probing sites in the neural network training procedure, whereas the median force RMSE was 199 mN across the 200 instances of a Monte Carlo randomized selection of experimental sessions to evaluate the calibration under generalized probing conditions. The static metrological properties and the possibility to fabricate sensors with relatively high spatial resolution make the proposed design attractive for the sensorization of robotic hands. Furthermore, the proved MRI-compatibility of the sensor opens other application scenarios, such as the possibility to employ the array for force measurement during functional MRI-measured brain activation.

UR - http://www.scopus.com/inward/record.url?scp=84941710841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941710841&partnerID=8YFLogxK

U2 - 10.1155/2015/367194

DO - 10.1155/2015/367194

M3 - Article

AN - SCOPUS:84941710841

VL - 2015

JO - Journal of Sensors

JF - Journal of Sensors

SN - 1687-725X

M1 - 367194

ER -