Seperability of four-class motor imagery data using independent components analysis

Naeem, Muhammad; Brunner, Clemens; Leeb, Robert; Gramlich, Bernhard; Pfurtscheller, Gert

doi:10.1088/1741-2560/3/3/003

Cited by 249 publications

(143 citation statements)

References 29 publications

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…A few studies showed that the CSP method provided a better classification performance than other spatial filters; for example, 'SLD' by (Muller-Gerking et al 1999), or 'ICA' by (Naeem et al 2006), whereas we found that the CSP method was not better than the other methods in this study. One possible reason may be that we used high-density electrodes over the whole head, and the covariance matrix was 122×122, which might result in model over-fitting.…”

Section: Optimal Spatial Filter Methodscontrasting

confidence: 87%

“…Although many signal processing and pattern recognition techniques have been explored for improving the signalto-noise ratio for greater classification accuracy (Tie and Sahin 2005;Kim et al 2006;Rezaei et al 2006;Townsend et al 2006), it is still difficult to determine more effective solutions for accurate classification because there are no systematic approaches. For example, previous studies investigated either the performance of different spatial filters (Muller-Gerking et al 1999;Naeem et al 2006), or the performance of different classification methods (Garrett et al 2003;Hinterberger et al 2003) independently. Therefore, additional investigation is required to explore more effective combinations of spatial filter, temporal filter and classification methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG

Bai

Lin

Vorbach

et al. 2007

Clinical Neurophysiology

117

View full text Add to dashboard Cite

Objectives-To explore effective combinations of computational methods for the prediction of movement intention preceding the production of self-paced right and left hand movements from single trial scalp electroencephalogram (EEG).Methods-Twelve naïve subjects performed self-paced movements consisting of three key strokes with either hand. EEG was recorded from 128 channels. The exploration was performed offline on single trial EEG data. We proposed that a successful computational procedure for classification would consist of spatial filtering, temporal filtering, feature selection, and pattern This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. classification. A systematic investigation was performed with combinations of spatial filtering using principal component analysis (PCA), independent component analysis (ICA), common spatial patterns analysis (CSP), and surface Laplacian derivation (SLD); temporal filtering using power spectral density estimation (PSD) and discrete wavelet transform (DWT); pattern classification using linear Mahalanobis distance classifier (LMD), quadratic Mahalanobis distance classifier (QMD), Bayesian classifier (BSC), multi-layer perceptron neural network (MLP), probabilistic neural network (PNN), and support vector machine (SVM). A robust multivariate feature selection strategy using a genetic algorithm was employed. NIH Public AccessResults-The combinations of spatial filtering using ICA and SLD, temporal filtering using PSD and DWT, and classification methods using LMD, QMD, BSC and SVM provided higher performance than those of other combinations. Utilizing one of the better combinations of ICA, PSD and SVM, the discrimination accuracy was as high as 75%. Further feature analysis showed that beta band EEG activity of the channels over right sensorimotor cortex was most appropriate for discrimination of right and left hand movement intention.Conclusions-Effective combinations of computational methods provide possible classification of human movement intention from single trial EEG. Such a method could be the basis for a potential brain-computer interface based on human natural movement, which might reduce the requirement of long-term training.Significance-Effective combinations of computational methods can classify human movement intention from single trial EEG with reasonable accuracy.

show abstract

Section: Optimal Spatial Filter Methodscontrasting

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG

Bai

Lin

Vorbach

et al. 2007

Clinical Neurophysiology

117

View full text Add to dashboard Cite

show abstract

“…3) Data set IIa, BCI competition IV: Data set IIa [24], from BCI competition IV 1 comprises EEG signals from 9 subjects who performed left hand, right hand, foot and tongue MI. EEG signals were recorded using 22 electrodes.…”

Section: A Eeg Data Sets Used For Evaluationmentioning

confidence: 99%

Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms

Lotte

Guan

2011

IEEE Trans. Biomed. Eng.

883

596

View full text Add to dashboard Cite

Abstract-One of the most popular feature extraction algorithms for Brain-Computer Interfaces (BCI) is Common Spatial Patterns (CSP). Despite its known efficiency and widespread use, CSP is also known to be very sensitive to noise and prone to overfitting. To address this issue, it has been recently proposed to regularize CSP. In this paper, we present a simple and unifying theoretical framework to design such a Regularized CSP (RCSP). We then present a review of existing RCSP algorithms, and describe how to cast them in this framework. We also propose 4 new RCSP algorithms. Finally, we compare the performances of 11 different RCSP (including the 4 new ones and the original CSP), on EEG data from 17 subjects, from BCI competition data sets. Results showed that the best RCSP methods can outperform CSP by nearly 10% in median classification accuracy and lead to more neurophysiologically relevant spatial filters. They also enable us to perform efficient subject-to-subject transfer. Overall, the best RCSP algorithms were CSP with Tikhonov Regularization and Weighted Tikhonov Regularization, both proposed in this paper.

show abstract

“…Most previous EEG, MEG, and fMRI studies investigating the neuronal correlates of movements examined the differences in neuronal activity associated with the use of different parts of the body (Obermaier et al, 2001;Blankertz et al, 2003;Pfurtscheller et al, 2003;Naeem et al, 2006) or neuronal activity associated with one extremity but different parts of it (Deng et al, 2005). DA and DI for each subject Sx.…”

Section: Noninvasively Measured Brain Activity Related To Movementsmentioning

confidence: 99%

Hand Movement Direction Decoded from MEG and EEG

Waldert¹,

Preißl²,

Demandt³

et al. 2008

J. Neurosci.

375

285

View full text Add to dashboard Cite

Brain activity can be used as a control signal for brain-machine interfaces (BMIs). A powerful and widely acknowledged BMI approach, so far only applied in invasive recording techniques, uses neuronal signals related to limb movements for equivalent, multidimensional control of an external effector. Here, we investigated whether this approach is also applicable for noninvasive recording techniques. To this end, we recorded whole-head MEG during center-out movements with the hand and found significant power modulation of MEG activity between rest and movement in three frequency bands: an increase for Յ7 Hz (low-frequency band) and 62-87 Hz (high-␥ band) and a decrease for 10 -30 Hz (␤ band) during movement. Movement directions could be inferred on a single-trial basis from the low-pass filtered MEG activity as well as from power modulations in the low-frequency band, but not from the ␤ and high-␥ bands. Using sensors above the motor area, we obtained a surprisingly high decoding accuracy of 67% on average across subjects. Decoding accuracy started to rise significantly above chance level before movement onset. Based on simultaneous MEG and EEG recordings, we show that the inference of movement direction works equally well for both recording techniques. In summary, our results show that neuronal activity associated with different movements of the same effector can be distinguished by means of noninvasive recordings and might, thus, be used to drive a noninvasive BMI.

show abstract

Seperability of four-class motor imagery data using independent components analysis

Cited by 249 publications

References 29 publications

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG

Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms

Hand Movement Direction Decoded from MEG and EEG

Contact Info

Product

Resources

About