xDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface

Rivet, Bertrand; Souloumiac, Antoine; Attina, Virginie; Gibert, Guillaume

doi:10.1109/tbme.2009.2012869

Cited by 454 publications

(374 citation statements)

References 27 publications

Supporting

Mentioning

369

Contrasting

Unclassified

Order By: Relevance

“…In the remaining two cases, we compared two preprocessing methods previously used in the literature: xDAWN [15] and Canonical Correlation Analysis, CCA [16]. These methods are described in detail below.…”

Section: Assessing Classifier Generalisationmentioning

confidence: 99%

“…The final step requires to solve the optimisation problem by a combination of QR decomposition and singular value decomposition applied to X and D matrices. For further details we refer to [15]. Note that the Generalised Eigenvalue Decomposition is a common approach to solve the Rayleigh quotient optimisation problem [18].…”

Section: Assessing Classifier Generalisationmentioning

confidence: 99%

See 1 more Smart Citation

Spatial filters yield stable features for error-related potentials across conditions

Iwane

Chavarriaga

Iturrate

et al. 2016

2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

Abstract-Error-related potentials (ErrP) have been increasingly studied in psychophysical experiments as well as for brainmachine interfacing. In the latter case, the generalisation capabilities of ErrP decoders is a crucial element to avoid frequent recalibration processes, thus increasing their usability. Previous studies have suggested that ErrP signals are rather stable across recording sessions. Also, studies using protocols of serial stimuli presentation show that these potentials do not change significantly with the presentation rate. Here we complement these studies by analysing the decoding generalisation capabilities. Using data from monitoring experiments, we evaluate how much the performance degrades when tested in a condition different than the one the decoder was trained with. Moreover, we compare different spatial filtering techniques to see which preprocessing steps yield less-sensitive features for ErrP decoding.

show abstract

Section: Assessing Classifier Generalisationmentioning

confidence: 99%

Section: Assessing Classifier Generalisationmentioning

confidence: 99%

Spatial filters yield stable features for error-related potentials across conditions

Iwane

Chavarriaga

Iturrate

et al. 2016

2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

show abstract

“…In this subsection, we further compare the proposed kernel FDA-SVM P300 detector with other commonly used detectors, including LDA (also called Fisher LDA, FLDA) [26], Bayesian LDA (BLDA) [28,29,37], and the gradient boosting with ordinary least squares regression (OLS) algorithm [27]. In the following, we briefly review these methods and then provide the comparison results.…”

Section: Comparison With Other P300 Detectorsmentioning

confidence: 99%

“…Linear discriminant analysis (LDA) method was applied to classify P300 and non-P300 potentials in [26]. The Bayesian LDA (BLDA)-based P300 detector was further used in the different P300 BCIs [28,29]. In addition to LDA, the support vector machine (SVM) has also gained wild acceptance in P300 BCIs [24,25,30,31].…”

Section: Introductionmentioning

confidence: 99%

A Self-Paced P300 Healthcare Brain-Computer Interface System with SSVEP-Based Switching Control and Kernel FDA + SVM-Based Detector

Liu

Wang

2016

Applied Sciences

View full text Add to dashboard Cite

This paper presents a novel brain-computer interface (BCI)-based healthcare control system, which is based on steady-state visually evoked potential (SSVEP) and P300 of electroencephalography (EEG) signals. The proposed system is composed of two modes, a brain switching mode and a healthcare function selection mode. The switching mode can detect whether a user has the intent to activate the function selection mode by detecting SSVEP in an ongoing EEG. During the function selection mode, the user is able to select any functions that he/she wants to activate through a healthcare control panel, and the function selection is done by detecting P300 in the user's EEG signals. The panel provides 25 functions representing 25 frequently performed activities of daily life. Therefore, users with severe motor disabilities can activate the system and any functions in a self-paced manner, achieving the goal of autonomous healthcare. To achieve high P300 detection accuracy, a novel P300 detector based on kernel Fisher's discriminant analysis (kernel FDA) and support vector machine (SVM) is also proposed. Experimental results, carried out on five subjects, show that the proposed BCI system achieves high SSVEP detection (93%) and high P300 detection (95.5%) accuracies, meaning that the switching mode has a high sensitivity, and the function selection mode has the ability to accurately detect the functions that the users want to trigger. More important, only three electrodes (Oz, Cz, and Pz) are required to measure EEG signals, enabling the system to have good usability in practical use.

show abstract

“…Given the noisy nature of the EEG signal, a xDawn spatial filter was applied in order to enhance the P300 response. The xDAWN algorithm [26] allows the estimation of a set of spatial filters for optimizing the signal to signal-plus-noise (SSNR) ratio. The xDAWN method assumes that there exists a typical response synchronized with the target stimuli superimposed on an evoked response to all the stimuli, and that the evoked responses to target stimuli could be enhanced by spatial filtering.…”

Section: Training Sessionmentioning

confidence: 99%

A low-cost auditory multi-class brain-computer interface based on pitch, spatial and timbre cues

Vamvakousis

Ramírez

2013

Preprint

View full text Add to dashboard Cite

P300-based brain-computer interfaces (BCIs) are especially useful for people with illnesses, which prevent them from communicating in a normal way (e.g. brain or spinal cord injury).However, most of the existing P300-based BCI systems use visual stimulation which may not be suitable for patients with sight deterioration (e.g. patients suffering from amyotrophic lateral sclerosis). Moreover, P300-based BCI systems rely on expensive equipment, which greatly limits their use outside the clinical environment. Therefore, we propose a multi-class BCI system based solely on auditory stimuli, which makes use of low-cost EEG technology.We explored different combinations of timbre, pitch and spatial auditory stimuli (TimPiSp:timbre-pitch-spatial, TimSp: timbre-spatial, and Timb: timbre-only) and three inter-stimulus intervals (150ms, 175ms and 300ms), and evaluated our system by conducting an oddball task on 7 healthy subjects. This is the first study in which these 3 auditory cues are compared. After averaging several repetitions in the 175ms inter-stimulus interval, we obtained average selection accuracies of 97.14%, 91.43%, and 88.57% for modalities TimPiSp, TimSp, and Timb, respectively. Best subject's accuracy was 100% in all modalities and inter-stimulus intervals. Average information transfer rate for the 150ms inter-stimulus interval in the TimPiSp modality was 14.85 bits/min. Best subject's information transfer rate was 39.96 bits/min for 175ms Timbre condition. Based on the TimPiSp modality, an auditory P300 speller was implemented and evaluated by asking users to type a 12-characters-long phrase. Six out of 7 users completed the task. The average spelling speed was 0.56 chars/min and best subject's performance was 0.84 chars/min. The obtained results show that the proposed auditory BCI is successful with healthy subjects and may constitute the basis for future implementations of more practical and affordable auditory P300-based BCI systems. PeerJ PrePrints

show abstract

xDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface

Cited by 454 publications

References 27 publications

Spatial filters yield stable features for error-related potentials across conditions

Spatial filters yield stable features for error-related potentials across conditions

A Self-Paced P300 Healthcare Brain-Computer Interface System with SSVEP-Based Switching Control and Kernel FDA + SVM-Based Detector

A low-cost auditory multi-class brain-computer interface based on pitch, spatial and timbre cues

Contact Info

Product

Resources

About