2016
DOI: 10.1016/j.protcy.2016.08.048
|View full text |Cite
|
Sign up to set email alerts
|

Classification of Electroencephalogram Data from Hand Grasp and Release Movements for BCI Controlled Prosthesis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
19
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 39 publications
(21 citation statements)
references
References 17 publications
0
19
0
Order By: Relevance
“…This result indicates that similar and dissimilar faces in fact shares some non-discriminatively low-level features that may contribute to misclassification of them as belong to similar faces. Carefully selecting those features and ranking them or even removing them might produce better results for this algorithm, such as using Linear Discriminant Analysis (LDA) [24]. However, for the purpose of AVRS development, it requires faster algorithm such as proposed, and thus we chose D = 7 for the development of the system and we omit any feature ranking or feature discrimination methods.…”
Section: B Results On Face Similarity Detectionmentioning
confidence: 99%
“…This result indicates that similar and dissimilar faces in fact shares some non-discriminatively low-level features that may contribute to misclassification of them as belong to similar faces. Carefully selecting those features and ranking them or even removing them might produce better results for this algorithm, such as using Linear Discriminant Analysis (LDA) [24]. However, for the purpose of AVRS development, it requires faster algorithm such as proposed, and thus we chose D = 7 for the development of the system and we omit any feature ranking or feature discrimination methods.…”
Section: B Results On Face Similarity Detectionmentioning
confidence: 99%
“…CAS Filho et al used the graph method to classify human hands signals, achieving a high recognition rate of up to 98% [ 49 ]. Research shows that the recognition of motor information in brain signals using the BCI is an effective method [ 50 , 51 , 52 ]. Although it is very accurate to identify motion characteristics using EEG, the authors cannot confirm that it also has an efficient motion recognition rate when the auxiliary robot is controlled in real time outside the field of vision.…”
Section: Discussionmentioning
confidence: 99%
“…Based on the average accuracies on Tables 1 -3, Mu and Beta waves calculated using the CSP algorithm as the features showed a good result in helping to separate the 2-class imaginary movement. In a previous study, CSP also demonstrated high accuracies (above 73 %) for calculating the features (EMG based marker) in distinguishing grasping and release movement combined with the Linear Discriminant Analysis (LDA) as a classifier [19]. The previous study used real movements as features, while this study tried to use imaginary movements to generate the signal like a post-stroke patient who could not move their hand freely.…”
Section: Classifying Imaginary Hand Movement Through Eeg Signalmentioning
confidence: 95%