2014
DOI: 10.3389/fncom.2014.00100
|View full text |Cite
|
Sign up to set email alerts
|

Physiological modules for generating discrete and rhythmic movements: action identification by a dynamic recurrent neural network

Abstract: In this study we employed a dynamic recurrent neural network (DRNN) in a novel fashion to reveal characteristics of control modules underlying the generation of muscle activations when drawing figures with the outstretched arm. We asked healthy human subjects to perform four different figure-eight movements in each of two workspaces (frontal plane and sagittal plane). We then trained a DRNN to predict the movement of the wrist from information in the EMG signals from seven different muscles. We trained differe… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

2015
2015
2023
2023

Publication Types

Select...
6
1
1

Relationship

3
5

Authors

Journals

citations
Cited by 11 publications
(7 citation statements)
references
References 50 publications
0
7
0
Order By: Relevance
“…The best performance of the best performers will be then compared to less good performance. Sensori-motor strategies based on the dynamic relationship between the multiple EMG profiles and the related kinematics or kinetics will be accurately identified and quantified with the help of DRNN technology (Cheron et al, 2012 ; Bengoetxea et al, 2014 ), and the EEG biomarkers of the related performance will be defined and quantified by mean of ERP analysis linked to external or internal movement events and ongoing high density EEG signals allowing further mathematical analysis such as time frequency (ERSP and ITC) (EEGLab procedures, (Delorme and Makeig, 2004 ; Delorme et al, 2015 )) microstates analysis (CARTOOL) (Brunet et al, 2011 ), coherency/directionality (Nolte et al, 2004 ; Cheron et al, 2014 ) and inverse modeling of the ERP, ERS, ERD, and ITC neural generators (swLORETA) (Cebolla et al, 2011 , 2014 ).…”
Section: From Walking Studies To An Integrated Approach Of Brain Actimentioning
confidence: 99%
“…The best performance of the best performers will be then compared to less good performance. Sensori-motor strategies based on the dynamic relationship between the multiple EMG profiles and the related kinematics or kinetics will be accurately identified and quantified with the help of DRNN technology (Cheron et al, 2012 ; Bengoetxea et al, 2014 ), and the EEG biomarkers of the related performance will be defined and quantified by mean of ERP analysis linked to external or internal movement events and ongoing high density EEG signals allowing further mathematical analysis such as time frequency (ERSP and ITC) (EEGLab procedures, (Delorme and Makeig, 2004 ; Delorme et al, 2015 )) microstates analysis (CARTOOL) (Brunet et al, 2011 ), coherency/directionality (Nolte et al, 2004 ; Cheron et al, 2014 ) and inverse modeling of the ERP, ERS, ERD, and ITC neural generators (swLORETA) (Cebolla et al, 2011 , 2014 ).…”
Section: From Walking Studies To An Integrated Approach Of Brain Actimentioning
confidence: 99%
“…In the context of direction-specific recruitment of muscle synergies, Gentner et al ( 2013 ) investigate adaptation to a visuomotor rotation of a virtual target displacement and show that the structure of muscle synergies is preserved, suggesting that changes in muscle patterns are obtained by rotating the directional tuning of the synergy recruitment. Bengoetxea et al ( 2014a , b ) employ a dynamic recurrent neural network (DRNN) and principal component analysis of EMG activity during discrete and rhythmic arm movements. The authors discuss consistent patterns of muscle groupings in the context of their functional organization for controlling orthogonal movement directions.…”
Section: Muscle Synergiesmentioning
confidence: 99%
“…Since the key observations of Aristotle about locomotion and then the first mechanical model of this seeming simple movement proposed by Borelli ( 1680 ) followed by Marey's first real-time kinematic representations as stick pictograms (1901), fine scientifically minded observers engaged onto the path of Movement Science questioned its most basic tenet: the relations between muscles and movements (Marey, 1901 ). This set the base for conventional movement analysis, integrating kinematics, kinetics and electromyography (EMG; Bengoetxea et al, 2014 , 2015 ). Such a multimodal approach to movement has generated a wealth of data whose analysis requires the necessity to include the compliance of the musculoskeletal system (Gottlieb, 1996 ) and the redundancy problem (Neilson, 1993 ; Sporns and Edelman, 1993 ; Hayashibe and Shimoda, 2014 ).…”
Section: From Muscle Patterns To Artificial Dynamic Neural Networkmentioning
confidence: 99%