Optimizing Spatial filters for Robust EEG Single-Trial Analysis

Blankertz, Benjamin; Tomioka, Ryota; Lemm, Steven; Kawanabe, Motoaki; Müller, Klaus Robert

doi:10.1109/msp.2008.4408441

Cited by 1,770 publications

(1,541 citation statements)

References 34 publications

Supporting

Mentioning

1,432

Contrasting

Unclassified

Order By: Relevance

“…The CSP algorithm is effective in constructing optimal spatial filters that discriminate two classes of EEG measurements in MI-BCI [10,17,18,19]. The spatial filter maximizes the variance of signals of one class and at the same time minimizes the variance of signals of the other class.…”

Section: Common Spatial Patternsmentioning

confidence: 99%

Removing Unrelated Features Based on Linear Dynamical System for Motor-Imagery-Based Brain-Computer Interface

Shi

2011

Neural Information Processing

View full text Add to dashboard Cite

Abstract. Common spatial pattern (CSP) is very successful in constructing spatial filters for detecting event-related synchronization and event-related desynchronization. In statistics, a CSP filter can optimally separate the motor-imagery-related components. However, for a single trail, the EEG features extracted after a CSP filter still include features not related to motor imagery. In this study, we introduce a linear dynamical system (LDS) approach to motor-imagery-based brain-computer interface (MI-BCI) to reduce the influence of these unrelated EEG features. This study is conducted on a BCI competition data set, which comprises EEG signals from several subjects performing various movements. Experimental results show that our proposed algorithm with LDS performs better than a traditional algorithm on average. The results reveal a promising direction in the application of LDS-based approach to MI-BCI.

show abstract

Section: Common Spatial Patternsmentioning

confidence: 99%

Removing Unrelated Features Based on Linear Dynamical System for Motor-Imagery-Based Brain-Computer Interface

Shi

2011

Neural Information Processing

View full text Add to dashboard Cite

show abstract

“…[5], shorter segments result in more responsive but more noisy feedback signal. Longer segments give a smoother control signal, but the delay from intention to control becomes longer.…”

Section: Time Length Of the Trialsmentioning

confidence: 99%

“…[5] to introduce the CSP method, where s(t) were assumed to be two different distributions for two classes respectively.…”

Section: Linear Mixing Modelmentioning

confidence: 99%

“…In Ref. [5], a 2-D toy example was used to make a good understanding on CSP. It was reported that CSP algorithm was used more popular than others such as standard ear-reference, common average reference (CAR), small Laplacian (3 cm to set of surrounding electrodes), large Laplacian (6 cm to set of surrounding electrodes), Principal Commonents Analysis (PCA) and Independent Components Analysis (ICA) [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Model based generalization analysis of common spatial pattern in brain computer interfaces

et al. 2010

View full text Add to dashboard Cite

In the motor imagery based Brain Computer Interface (BCI) research, Common Spatial Pattern (CSP) algorithm is used widely as a spatial filter on multi-channel electroencephalogram (EEG) recordings. Recently the overfitting effect of CSP has been gradually noticed, but what influence the overfitting is still unclear. In this work, the generalization of CSP is investigated by a simple linear mixing model. Several factors in this model are discussed, and the simulation results indicate that channel numbers and the correlation between signals influence the generalization of CSP significantly. A larger number of training trials and a longer time length of the trial would prevent overfitting. The experiments on real data also verify our conclusion.

show abstract

“…A more adaptive approach is to use data-driven spatial processing such as common spatial pattern (CSP) filtering [41], [42]. This method allows the number of channels to be systematically reduced (see [43] for review); however, spatial and temporal processing remain separated [41]- [45].…”

Section: Technical Challenges In Analysis Of Multisensor Brain Datamentioning

confidence: 99%

Mental State Estimation for Brain--Computer Interfaces

Das

Rizzuto

Nenadic

2009

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Mental state estimation is potentially useful for the development of asynchronous brain-computer interfaces. In this study, four mental states have been identified and decoded from the electrocorticograms (ECoGs) of six epileptic patients, engaged in a memory reach task. A novel signal analysis technique has been applied to high-dimensional, statistically sparse ECoGs recorded by a large number of electrodes. The strength of the proposed technique lies in its ability to jointly extract spatial and temporal patterns, responsible for encoding mental state differences. As such, the technique offers a systematic way of analyzing the spatiotemporal aspects of brain information processing and may be applicable to a wide range of spatiotemporal neurophysiological signals.Index Terms-Brain-computer interfaces (BCIs), classification, curse of dimensionality, electrocorticograms (ECoGs), feature extraction, mental states, small sample size problem.

show abstract

Optimizing Spatial filters for Robust EEG Single-Trial Analysis

Cited by 1,770 publications

References 34 publications

Removing Unrelated Features Based on Linear Dynamical System for Motor-Imagery-Based Brain-Computer Interface

Removing Unrelated Features Based on Linear Dynamical System for Motor-Imagery-Based Brain-Computer Interface

Model based generalization analysis of common spatial pattern in brain computer interfaces

Mental State Estimation for Brain--Computer Interfaces

Contact Info

Product

Resources

About