A fuzzy approach towards inductive transfer and human–machine interface control design

Rui Azevedo Antunes, Fernando Vieira Coito, Luís Brito Palma, Hermínio Duarteramos

Research output: Contribution to journalArticle

Abstract

Traditional machines do not adapt to their operators, instead they implicitly demand human adaptation. Human adaptive mechatronics (HAM) is the research topic that covers the design of devices and controllers for assisting the human. HAM devices are capable to measure and estimate the operator’s skill/dexterity, while a real-time assist-controller enhances machine adaptation, improving the overall human–machine performance. Nowadays, the demand for such devices has particular potential in many activities, which involve manual operations, such as in assistive technology. The main contribution of this work is the proposal of a fuzzy clustering methodology to the development of a real-time inductive transfer embedded controller, used for improving the operator’s proficiency, under a human-in-the-loop environment relying on visual feedback information. Other contribution is the proposal of a condition for inductive transfer between human operators, based on correlation analysis. The operator behaviour is modelled and enhanced from a human–machine interface fuzzy classifier and assisting scheme, which uses real-time data and additional information collected from an expert user. Experimental tests were performed by different participants under a driving simulator, for evaluation of the proposed methodology. The fuzzy clustering approach confirmed to significantly improve the transfer learning and the driving skills of the human operators.

Original languageEnglish
Pages (from-to)43-56
Number of pages14
JournalEvolving Systems
Volume9
Issue number1
DOIs
Publication statusPublished - 1 Mar 2018

Fingerprint

Human-machine Interface
Interface Design
Control Design
Fuzzy clustering
Mechatronics
Controllers
Operator
Fuzzy Clustering
Real-time
Controller
Classifiers
Simulators
Feedback
Transfer Learning
Driving Simulator
Assistive Technology
Fuzzy Classifier
Methodology
Correlation Analysis
Human

Keywords

  • Correlation analysis
  • Embedded control
  • Fuzzy clustering
  • Human machine interaction
  • Inductive transfer
  • Performance evaluation

Cite this

@article{e7c7bd29ec364343b69bb4846df8dce8,
title = "A fuzzy approach towards inductive transfer and human–machine interface control design",
abstract = "Traditional machines do not adapt to their operators, instead they implicitly demand human adaptation. Human adaptive mechatronics (HAM) is the research topic that covers the design of devices and controllers for assisting the human. HAM devices are capable to measure and estimate the operator’s skill/dexterity, while a real-time assist-controller enhances machine adaptation, improving the overall human–machine performance. Nowadays, the demand for such devices has particular potential in many activities, which involve manual operations, such as in assistive technology. The main contribution of this work is the proposal of a fuzzy clustering methodology to the development of a real-time inductive transfer embedded controller, used for improving the operator’s proficiency, under a human-in-the-loop environment relying on visual feedback information. Other contribution is the proposal of a condition for inductive transfer between human operators, based on correlation analysis. The operator behaviour is modelled and enhanced from a human–machine interface fuzzy classifier and assisting scheme, which uses real-time data and additional information collected from an expert user. Experimental tests were performed by different participants under a driving simulator, for evaluation of the proposed methodology. The fuzzy clustering approach confirmed to significantly improve the transfer learning and the driving skills of the human operators.",
keywords = "Correlation analysis, Embedded control, Fuzzy clustering, Human machine interaction, Inductive transfer, Performance evaluation",
author = "{Azevedo Antunes}, Rui and {Vieira Coito}, Fernando and {Brito Palma}, Lu{\'i}s and Herm{\'i}nio Duarteramos",
note = "info:eu-repo/grantAgreement/FCT/5876/147324/PT# sem pdf.",
year = "2018",
month = "3",
day = "1",
doi = "10.1007/s12530-016-9172-6",
language = "English",
volume = "9",
pages = "43--56",
journal = "Evolving Systems",
issn = "1868-6478",
publisher = "Springer Verlag",
number = "1",

}

A fuzzy approach towards inductive transfer and human–machine interface control design. / Azevedo Antunes, Rui; Vieira Coito, Fernando; Brito Palma, Luís; Duarteramos, Hermínio.

In: Evolving Systems, Vol. 9, No. 1, 01.03.2018, p. 43-56.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A fuzzy approach towards inductive transfer and human–machine interface control design

AU - Azevedo Antunes, Rui

AU - Vieira Coito, Fernando

AU - Brito Palma, Luís

AU - Duarteramos, Hermínio

N1 - info:eu-repo/grantAgreement/FCT/5876/147324/PT# sem pdf.

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Traditional machines do not adapt to their operators, instead they implicitly demand human adaptation. Human adaptive mechatronics (HAM) is the research topic that covers the design of devices and controllers for assisting the human. HAM devices are capable to measure and estimate the operator’s skill/dexterity, while a real-time assist-controller enhances machine adaptation, improving the overall human–machine performance. Nowadays, the demand for such devices has particular potential in many activities, which involve manual operations, such as in assistive technology. The main contribution of this work is the proposal of a fuzzy clustering methodology to the development of a real-time inductive transfer embedded controller, used for improving the operator’s proficiency, under a human-in-the-loop environment relying on visual feedback information. Other contribution is the proposal of a condition for inductive transfer between human operators, based on correlation analysis. The operator behaviour is modelled and enhanced from a human–machine interface fuzzy classifier and assisting scheme, which uses real-time data and additional information collected from an expert user. Experimental tests were performed by different participants under a driving simulator, for evaluation of the proposed methodology. The fuzzy clustering approach confirmed to significantly improve the transfer learning and the driving skills of the human operators.

AB - Traditional machines do not adapt to their operators, instead they implicitly demand human adaptation. Human adaptive mechatronics (HAM) is the research topic that covers the design of devices and controllers for assisting the human. HAM devices are capable to measure and estimate the operator’s skill/dexterity, while a real-time assist-controller enhances machine adaptation, improving the overall human–machine performance. Nowadays, the demand for such devices has particular potential in many activities, which involve manual operations, such as in assistive technology. The main contribution of this work is the proposal of a fuzzy clustering methodology to the development of a real-time inductive transfer embedded controller, used for improving the operator’s proficiency, under a human-in-the-loop environment relying on visual feedback information. Other contribution is the proposal of a condition for inductive transfer between human operators, based on correlation analysis. The operator behaviour is modelled and enhanced from a human–machine interface fuzzy classifier and assisting scheme, which uses real-time data and additional information collected from an expert user. Experimental tests were performed by different participants under a driving simulator, for evaluation of the proposed methodology. The fuzzy clustering approach confirmed to significantly improve the transfer learning and the driving skills of the human operators.

KW - Correlation analysis

KW - Embedded control

KW - Fuzzy clustering

KW - Human machine interaction

KW - Inductive transfer

KW - Performance evaluation

UR - http://www.scopus.com/inward/record.url?scp=85042864567&partnerID=8YFLogxK

U2 - 10.1007/s12530-016-9172-6

DO - 10.1007/s12530-016-9172-6

M3 - Article

VL - 9

SP - 43

EP - 56

JO - Evolving Systems

JF - Evolving Systems

SN - 1868-6478

IS - 1

ER -