Supervised and Dynamic Neuro-Fuzzy Systems to Classify Physiological Responses in Robot-Assisted Neurorehabilitation

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

This paper presents the application of an Adaptive Resonance Theory (ART) based on neural networks combined with Fuzzy Logic systems to classify physiological reactions of subjects performing robot-assisted rehabilitation therapies. First, the theoretical background of a neuro-fuzzy classifier called S-dFasArt is presented. Then, the methodology and experimental protocols to perform a robot-assisted neurorehabilitation task are described. Our results show that the combination of the dynamic nature of S-dFasArt classifier with a supervisory module are very robust and suggest that this methodology could be very useful to take into account emotional states in robot-assisted environments and help to enhance and better understand human-robot interactions.

Related collections

Most cited references 12

Record: found
Abstract: found
Article: not found

Dissociated neural representations of intensity and valence in human olfaction.

A. K. Anderson, K Christoff, I Stappen … (2003)

Affective experience has been described in terms of two primary dimensions: intensity and valence. In the human brain, it is intrinsically difficult to dissociate the neural coding of these affective dimensions for visual and auditory stimuli, but such dissociation is more readily achieved in olfaction, where intensity and valence can be manipulated independently. Using event-related functional magnetic resonance imaging (fMRI), we found amygdala activation to be associated with intensity, and not valence, of odors. Activity in regions of orbitofrontal cortex, in contrast, were associated with valence independent of intensity. These findings show that distinct olfactory regions subserve the analysis of the degree and quality of olfactory stimulation, suggesting that the affective representations of intensity and valence draw upon dissociable neural substrates.

0 comments Cited 191 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Dissociation of neural representation of intensity and affective valuation in human gustation.

Darren Gitelman, Brian Gregory, M. Marcel Mesulam … (2003)

We used a 2 x 2 factorial design to dissociate regions responding to taste intensity and taste affective valence. Two intensities each of a pleasant and unpleasant taste were presented to subjects during event-related fMRI scanning. The cerebellum, pons, middle insula, and amygdala responded to intensity irrespective of valence. In contrast, valence-specific responses were observed in anterior insula/operculum extending into the orbitofrontal cortex (OFC). The right caudolateral OFC responded preferentially to pleasant compared to unpleasant taste, irrespective of intensity, and the left dorsal anterior insula/operculuar region responded preferentially to unpleasant compared to pleasant tastes equated for intensity. Responses best characterized as an interaction between intensity and pleasantness were also observed in several limbic regions. These findings demonstrate a functional segregation within the human gustatory system. They also show that amygdala activity may be driven by stimulus intensity irrespective of valence, casting doubt upon the notion that the amygdala responds preferentially to negative stimuli.

0 comments Cited 161 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps.

G.A. Carpenter, S Grossberg, N. Markuzon … (1992)

A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may represent fuzzy or crisp sets of features. The architecture, called fuzzy ARTMAP, achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Four classes of simulation illustrated fuzzy ARTMAP performance in relation to benchmark backpropagation and generic algorithm systems. These simulations include finding points inside versus outside a circle, learning to tell two spirals apart, incremental approximation of a piecewise-continuous function, and a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE systems and with Simpson's FMMC system.

0 comments Cited 146 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Catalin Buiu: Role: Academic Editor

Journal

Journal ID (nlm-ta): PLoS One

Journal ID (iso-abbrev): PLoS ONE

Journal ID (publisher-id): plos

Journal ID (pmc): plosone

Title: PLoS ONE

Publisher: Public Library of Science (San Francisco, CA USA )

ISSN (Electronic): 1932-6203

Publication date Collection: 2015

Publication date (Electronic): 22 May 2015

Volume: 10

Issue: 5

Electronic Location Identifier: e0127777

Affiliations

[1 ]Biomedical Neuroengineering Group, Universidad Miguel Hernández, Elche, Alicante, Spain

[2 ]Systems Engineering and Automation Department, Universidad Politécnica de Cartagena, Cartagena, Murcia, Spain

Politehnica University of Bucharest, ROMANIA

Author notes

Competing Interests: The authors have declared that no competing interests exist.

Conceived and designed the experiments: FJB NGA JMSN EF. Performed the experiments: LDL. Analyzed the data: LDL FJB NGA. Contributed reagents/materials/analysis tools: LDL JMCI MA. Wrote the paper: LDL FJB NGA JMSN EF.

‡These authors also contributed equally to this work.

* E-mail: llledo@ 123456umh.es

Article

Publisher ID: PONE-D-14-56808

DOI: 10.1371/journal.pone.0127777

PMC ID: 4441369

PubMed ID: 26001214

SO-VID: d30207e3-4b3b-4864-8003-b059c272477d

License:

This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited

History

Date received : 8 January 2015

Date accepted : 19 April 2015

Page count

Figures: 7, Tables: 3, Pages: 16

Funding

This work was supported by the European Commission (ICT-22-2014: Multimodal and Natural computer interaction) through the project AIDE: "Adaptive Multimodal Interfaces to Assist Disabled People in Daily Activities" (grant agreement no: 645322).

Custom metadata

Data Availability The authors confirm that all data underlying the findings are fully available without restriction. All relevant data are within the paper and its Supporting Information files.

Supervised and Dynamic Neuro-Fuzzy Systems to Classify Physiological Responses in Robot-Assisted Neurorehabilitation

Read this article at

Abstract

Related collections

PLOS Climate

Most cited references 12

Dissociated neural representations of intensity and valence in human olfaction.

Dissociation of neural representation of intensity and affective valuation in human gustation.

Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps.

Author and article information

Contributors

Journal

Affiliations

Author notes

Article

History

Page count

Funding

Categories

Custom metadata

Comments

Comment on this article

Similar content 122

Cited by 2

Most referenced authors 159