Cited by 7EEG and Brain-Computer InterfacesMuscle activation and electromyography studiesFree Will and Agency

Detecting intention to execute the next movement while performing current movement from EEG using global optimal constrained ICA

Eilbeigi, Elnaz, Setarehdan, Seyed Kamaledin·2018·Computers in Biology and Medicine

Abstract

Background Brain-computer interfaces (BCIs) are a promising tool in neurorehabilitation. The intention to perform a motor action can be detected from brain signals and used to control robotic devices. Most previous studies have focused on the starting of movements from a resting state, while in daily life activities, motions occur continuously and the neural activities correlated to the evolving movements are yet to be investigated.Method First we investigate the existence of neural correlates of intention to replace an object on the table during a holding phase. Next, we present a new method to extract the movement-related cortical potentials (MRCP) from a single-trial EEG. A novel method called Global optimal constrained ICA (GocICA) is proposed to overcome the limitations of cICA which is implemented based on Particle Swarm Optimization (PSO) and Charged System Search (CSS) techniques. GocICA is then utilized for decoding the intention to grasp and lift and intention to replace movements where the results were compared.Results It was found that GocICA significantly improves the intention detection performance. Best results in offline detection were obtained with CSS-cICA for both kinds of intentions. Furthermore, pseudo-online decoding showed that GocICA was able to predict both intentions before the onset of related movements with the highest probability.Conclusions Decoding of the next movement intention during current movement is possible, which can be used to create more natural neuroprostheses. The results demonstrate that GocICA is a promising new algorithm for single-trial MRCP detection which can be used for detecting other types of ERPs such as P300.

Integrity signals

Registry

Crossref · 10.1016/j.compbiomed.2018.05.024

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Cites

Flagged first, then by citations

2 of the 43 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Eilbeigi, E., & Setarehdan, S. K.
Affiliations
University of Tehran (IR)
Corresponding author
Setarehdan, Seyed Kamaledin
Venue
Computers in Biology and Medicine
Publisher
Elsevier BV
Published
2018-08
Volume
99
Pages
63-75
ISSN
0010-4825 (ISSN-L)
OpenAlex
W2804555462
Cited by
7
References
43
Citations by year
2026: 1 · 2021: 3 · 2020: 2 · 2019: 1
FWCI
0.89
Type
journal article
Language
en
Open access
closed
Locations
  • Computers in Biology and Medicine (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
  • Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Free Will and Agency
Keywords
motion intention recognition, movement-related cortical potentials, single-trial EEG, independent component analysis, EEG source localization, object replacement, neural prostheses, brain-computer interface, neurorehabilitation, event-related potentials
MeSH terms
Adult, Algorithms, Brain, Electroencephalography, Evoked Potentials, Female, Humans, Male, Movement, Intention, Brain-Computer Interfaces

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review