Combined Optimization of Spatial and Temporal Filters for Improving Brain-Computer Interfacing

Dornhege, Guido; Blankertz, Benjamin; Krauledat, Matthias; Losch, Florian; Curio, Gabriel; Müller, Klaus Robert

doi:10.1109/tbme.2006.883649

Cited by 354 publications

(233 citation statements)

References 23 publications

Supporting

Mentioning

226

Contrasting

Unclassified

Order By: Relevance

“…3, 5) while obtaining a high degree of classification accuracy (80.6%). Although the original CSP method has been extended and improved in a number of directions (Lemm et al 2005;Tomioka et al 2006;Dornhege et al 2006;Blankertz et al 2008), the present study utilizes the original implementation since we were not interested in specific practical applications, where the highest classifications rates are desirable. Although it is possible that using one of the many extensions of the method could improve our classification accuracy, the values already attained are high considering that no artifacts were removed in the data and no trials were discarded based on artifacts.…”

Section: Discussionmentioning

confidence: 99%

Distinct dynamical patterns that distinguish willed and forced actions

et al. 2010

View full text Add to dashboard Cite

The neural pathways for generating willed actions have been increasingly investigated since the famous pioneering work by Benjamin Libet on the nature of free will. To better understand what differentiates the brain states underlying willed and forced behaviours, we performed a study of chosen and forced actions over a binary choice scenario. Magnetoencephalography recordings were obtained from six subjects during a simple task in which the subject presses a button with the left or right finger in response to a cue that either (1) specifies the finger with which the button should be pressed or (2) instructs the subject to press a button with a finger of their own choosing. Three independent analyses were performed to investigate the dynamical patterns of neural activity supporting willed and forced behaviours during the preparatory period preceding a button press. Each analysis offered similar findings in the temporal and spatial domains and in particular, a high accuracy in the classification of single trials was obtained around 200 ms after cue presentation with an overall average of 82%. During this period, the majority of the discriminatory power comes from differential neural processes observed bilaterally in the parietal lobes, as well as some differences in occipital and temporal lobes, suggesting a contribution of these regions to willed and forced behaviours.

show abstract

Section: Discussionmentioning

confidence: 99%

Distinct dynamical patterns that distinguish willed and forced actions

et al. 2010

View full text Add to dashboard Cite

show abstract

“…The data gathered during the training session was sliced in 10-second windows. These samples were whitened [2], and the variance was computed as an indication of the power in the window. A support vector machines (SVM) classifier trained on the training session data provided different weights for each of the EEG channels.…”

Section: Eeg Analysis and Mappingmentioning

confidence: 99%

A Study in User-Centered Design and Evaluation of Mental Tasks for BCI

Bos

Poel

Nijholt

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Current brain-computer interfacing (BCI) research focuses on detection performance, speed, and bit rates. However, this is only a small part of what is important to the user. From human-computer interaction (HCI) research, we can apply the paradigms of user-centered design and evaluation, to improve the usability and user experience. Involving the users in the design process may also help in moving beyond the limited mental tasks that are currently common in BCI systems. To illustrate the usefulness of these methods to BCI, we involved potential users in the design process of a BCI system, resulting in three new mental tasks. The experience of using these mental tasks was then evaluated within a prototype BCI system using a commercial online role-playing game. Results indicate that user preference for certain mental tasks is primarily based on the recognition of brain activity by the system, and secondly on the ease of executing the task.

show abstract

“…Chin et al [6] presented discriminative channel addition (DCA) approach and discriminative channel reduction (DCR) approach to select subject-specific discriminative channels by iteratively adding or removing channels based on the cross-validation classification accuracies. Moreover, several novel approaches, called, common spatio-spectral pattern (CSSP) [4], common sparse spectral spatial pattern (CSSSP) [7], filter bank common spatial pattern (FBCSP) [8] and common spatial-spectral boosting pattern (CSSBP) [9,10] were proposed. These methods simultaneously optimize a spatial filter and a spectral filter to enhance discriminability rates of multichannel EEG.…”

Section: Introductionmentioning

confidence: 99%

Motor Imagery EEG Classification using Wavelet Common Spatial Boosting Pattern

2017

The 5th International Conference on Advanced Computer Science Applications and Technologies (ACSAT 2017)

View full text Add to dashboard Cite

Abstract. Feature Extraction is one of the most important steps in brain-computer interface (BCI) systems. In particular, the common spatial patterns (CSP) is one of the most successful solutions which has been widely used in MI-BCIs. However, studies have reported that the performance of CSP heavily depends on its channels configuration. To the best of our current knowledge, it is not available to obtain the active channels related to brain activities of stroke patients in advance. Hence, we usually set a relatively broad channels or try to select a subject-specific channels when applying CSP to stroke patients. In this paper, we present a novel approach which employs wavelet transform and boosting algorithm to improve accuracy and robustness of the conventional CSP. In our proposed approach, the channel configurations are initially divided into multiple preconditions. Then, the informative features of the predefined channels are obtained using the Wavelet Common Spatial Pattern (W-CSP) algorithm that provided high-temporal-spectral resolution. Eventually, we train weak classifiers on the obtained features and combine these weak classifiers to a weighted combinational model using boosting strategy. Extensive experiments have been performed on datasets from the famous BCI competition III and IV. The results demonstrate its superior performance.

show abstract

Combined Optimization of Spatial and Temporal Filters for Improving Brain-Computer Interfacing

Cited by 354 publications

References 23 publications

Distinct dynamical patterns that distinguish willed and forced actions

Distinct dynamical patterns that distinguish willed and forced actions

A Study in User-Centered Design and Evaluation of Mental Tasks for BCI

Motor Imagery EEG Classification using Wavelet Common Spatial Boosting Pattern

Contact Info

Product

Resources

About