A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition

Emilio Andreozzi, Daniele Esposito, Gaetano Dario Gargiulo, Antonio Fratini, Giovanni d'Addio, Ganesh R Naik, Paolo Bifulco*

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Human machine interfaces (HMIs) are employed in a broad range of applications, spanning from assistive devices for disability to remote manipulation and gaming controllers. In this study, a new piezoresistive sensors array armband is proposed for hand gesture recognition. The armband encloses only three sensors targeting specific forearm muscles, with the aim to discriminate eight hand movements. Each sensor is made by a force-sensitive resistor (FSR) with a dedicated mechanical coupler and is designed to sense muscle swelling during contraction. The armband is designed to be easily wearable and adjustable for any user and was tested on 10 volunteers. Hand gestures are classified by means of different machine learning algorithms, and classification performances are assessed applying both, the 10-fold and leave-one-out cross-validations. A linear support vector machine provided 96% mean accuracy across all participants. Ultimately, this classifier was implemented on an Arduino platform and allowed successful control for videogames in real-time. The low power consumption together with the high level of accuracy suggests the potential of this device for exergames commonly employed for neuromotor rehabilitation. The reduced number of sensors makes this HMI also suitable for hand-prosthesis control.

Original languageEnglish
Article number114
JournalFrontiers in Neurorobotics
Volume13
DOIs
Publication statusPublished - 17 Jan 2020

Fingerprint

Gestures
Hand
Self-Help Devices
Muscles
Forearm
Prostheses and Implants
Volunteers
Rehabilitation
Equipment and Supplies

Bibliographical note

© 2020 Esposito, Andreozzi, Gargiulo, Fratini, D’Addio, Naik and Bifulco. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Keywords

  • Exergaming
  • Hand gesture recognition
  • Human–machine interface
  • Muscle sensors array
  • Piezoresistive sensor
  • Support vector machine

Cite this

Andreozzi, E., Esposito, D., Gargiulo, G. D., Fratini, A., d'Addio, G., Naik, G. R., & Bifulco, P. (2020). A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition. Frontiers in Neurorobotics, 13, [114]. https://doi.org/10.3389/fnbot.2019.00114
Andreozzi, Emilio ; Esposito, Daniele ; Gargiulo, Gaetano Dario ; Fratini, Antonio ; d'Addio, Giovanni ; Naik, Ganesh R ; Bifulco, Paolo. / A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition. In: Frontiers in Neurorobotics. 2020 ; Vol. 13.
@article{0a3d9de5ce6b4a5cb5c1ceefa15100e9,
title = "A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition",
abstract = "Human machine interfaces (HMIs) are employed in a broad range of applications, spanning from assistive devices for disability to remote manipulation and gaming controllers. In this study, a new piezoresistive sensors array armband is proposed for hand gesture recognition. The armband encloses only three sensors targeting specific forearm muscles, with the aim to discriminate eight hand movements. Each sensor is made by a force-sensitive resistor (FSR) with a dedicated mechanical coupler and is designed to sense muscle swelling during contraction. The armband is designed to be easily wearable and adjustable for any user and was tested on 10 volunteers. Hand gestures are classified by means of different machine learning algorithms, and classification performances are assessed applying both, the 10-fold and leave-one-out cross-validations. A linear support vector machine provided 96{\%} mean accuracy across all participants. Ultimately, this classifier was implemented on an Arduino platform and allowed successful control for videogames in real-time. The low power consumption together with the high level of accuracy suggests the potential of this device for exergames commonly employed for neuromotor rehabilitation. The reduced number of sensors makes this HMI also suitable for hand-prosthesis control.",
keywords = "Exergaming, Hand gesture recognition, Human–machine interface, Muscle sensors array, Piezoresistive sensor, Support vector machine",
author = "Emilio Andreozzi and Daniele Esposito and Gargiulo, {Gaetano Dario} and Antonio Fratini and Giovanni d'Addio and Naik, {Ganesh R} and Paolo Bifulco",
note = "{\circledC} 2020 Esposito, Andreozzi, Gargiulo, Fratini, D’Addio, Naik and Bifulco. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.",
year = "2020",
month = "1",
day = "17",
doi = "10.3389/fnbot.2019.00114",
language = "English",
volume = "13",

}

Andreozzi, E, Esposito, D, Gargiulo, GD, Fratini, A, d'Addio, G, Naik, GR & Bifulco, P 2020, 'A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition', Frontiers in Neurorobotics, vol. 13, 114. https://doi.org/10.3389/fnbot.2019.00114

A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition. / Andreozzi, Emilio; Esposito, Daniele; Gargiulo, Gaetano Dario; Fratini, Antonio; d'Addio, Giovanni; Naik, Ganesh R; Bifulco, Paolo.

In: Frontiers in Neurorobotics, Vol. 13, 114, 17.01.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition

AU - Andreozzi, Emilio

AU - Esposito, Daniele

AU - Gargiulo, Gaetano Dario

AU - Fratini, Antonio

AU - d'Addio, Giovanni

AU - Naik, Ganesh R

AU - Bifulco, Paolo

N1 - © 2020 Esposito, Andreozzi, Gargiulo, Fratini, D’Addio, Naik and Bifulco. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PY - 2020/1/17

Y1 - 2020/1/17

N2 - Human machine interfaces (HMIs) are employed in a broad range of applications, spanning from assistive devices for disability to remote manipulation and gaming controllers. In this study, a new piezoresistive sensors array armband is proposed for hand gesture recognition. The armband encloses only three sensors targeting specific forearm muscles, with the aim to discriminate eight hand movements. Each sensor is made by a force-sensitive resistor (FSR) with a dedicated mechanical coupler and is designed to sense muscle swelling during contraction. The armband is designed to be easily wearable and adjustable for any user and was tested on 10 volunteers. Hand gestures are classified by means of different machine learning algorithms, and classification performances are assessed applying both, the 10-fold and leave-one-out cross-validations. A linear support vector machine provided 96% mean accuracy across all participants. Ultimately, this classifier was implemented on an Arduino platform and allowed successful control for videogames in real-time. The low power consumption together with the high level of accuracy suggests the potential of this device for exergames commonly employed for neuromotor rehabilitation. The reduced number of sensors makes this HMI also suitable for hand-prosthesis control.

AB - Human machine interfaces (HMIs) are employed in a broad range of applications, spanning from assistive devices for disability to remote manipulation and gaming controllers. In this study, a new piezoresistive sensors array armband is proposed for hand gesture recognition. The armband encloses only three sensors targeting specific forearm muscles, with the aim to discriminate eight hand movements. Each sensor is made by a force-sensitive resistor (FSR) with a dedicated mechanical coupler and is designed to sense muscle swelling during contraction. The armband is designed to be easily wearable and adjustable for any user and was tested on 10 volunteers. Hand gestures are classified by means of different machine learning algorithms, and classification performances are assessed applying both, the 10-fold and leave-one-out cross-validations. A linear support vector machine provided 96% mean accuracy across all participants. Ultimately, this classifier was implemented on an Arduino platform and allowed successful control for videogames in real-time. The low power consumption together with the high level of accuracy suggests the potential of this device for exergames commonly employed for neuromotor rehabilitation. The reduced number of sensors makes this HMI also suitable for hand-prosthesis control.

KW - Exergaming

KW - Hand gesture recognition

KW - Human–machine interface

KW - Muscle sensors array

KW - Piezoresistive sensor

KW - Support vector machine

UR - https://www.frontiersin.org/articles/10.3389/fnbot.2019.00114/full

UR - http://www.scopus.com/inward/record.url?scp=85078969695&partnerID=8YFLogxK

U2 - 10.3389/fnbot.2019.00114

DO - 10.3389/fnbot.2019.00114

M3 - Article

C2 - 32009926

VL - 13

M1 - 114

ER -

Andreozzi E, Esposito D, Gargiulo GD, Fratini A, d'Addio G, Naik GR et al. A Piezoresistive Array Armband With Reduced Number of Sensors for Hand Gesture Recognition. Frontiers in Neurorobotics. 2020 Jan 17;13. 114. https://doi.org/10.3389/fnbot.2019.00114