Asynchronous BCI Based on Motor Imagery With Automated Calibration and Neurofeedback Training

Kuś, Rafał; Valbuena, Diana; Żygierewicz, Jarosław; Malechka, Tatsiana; Graeser, Axel; Durka, P.J.

doi:10.1109/tnsre.2012.2214789

Cited by 55 publications

(33 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarity between the movement imagination and the real movement was also confirmed by the research, in which healthy patients and patients with motor disabilities were subjected to the neuropsychological observation [16, 33]. This fact causes that the movement imagination plays an important role as a control signal in the brain–computer interfaces [62] which are dedicated to patients who partly or entirely lost the voluntary muscle contraction such as in the ’locked-in’ state [3, 28, 36, 45, 60]. A key factor in the successful design of the BCI systems is the method used to process and extract the meaningful information from the brain signal.…”

Section: Introductionmentioning

confidence: 72%

Analysis of EEG signal by flicker-noise spectroscopy: identification of right-/left-hand movement imagination

Broniec

2016

Med Biol Eng Comput

View full text Add to dashboard Cite

Flicker-noise spectroscopy (FNS) is a general phenomenological approach to analyzing dynamics of complex nonlinear systems by extracting information contained in chaotic signals. The main idea of FNS is to describe an information hidden in correlation links, which are present in the chaotic component of the signal, by a set of parameters. In the paper, FNS is used for the analysis of electroencephalography signal related to the hand movement imagination. The signal has been parametrized in accordance with the FNS method, and significant changes in the FNS parameters have been observed, at the time when the subject imagines the movement. For the right-hand movement imagination, abrupt changes (visible as a peak) of the parameters, calculated for the data recorded from the left hemisphere, appear at the time corresponding to the initial moment of the imagination. In contrary, for the left-hand movement imagination, the meaningful changes in the parameters are observed for the data recorded from the right hemisphere. As the motor cortex is activated mainly contralaterally to the hand, the analysis of the FNS parameters allows to distinguish between the imagination of the right- and left-hand movement. This opens its potential application in the brain–computer interface.

show abstract

Section: Introductionmentioning

confidence: 72%

Analysis of EEG signal by flicker-noise spectroscopy: identification of right-/left-hand movement imagination

Broniec

2016

Med Biol Eng Comput

View full text Add to dashboard Cite

show abstract

“…Subject F has been trained regularly for 12 months on the ERD/ERS-BCI. She also attended the study published in [7] but was the only trained subject available at the time of the sBCI study. In all cases the SSVEP based BCI was used to control the selected device.…”

Section: Subject and Data Acquisition And Resultsmentioning

confidence: 99%

“…Signal processing for the BCI signals is carried out with a Bremen-BCI software package, which was described [4][5][6] including results of European Project BRAIN [7]. In this paper, we are reporting first test results.…”

Section: State Visual Evoked Potential Brain Computer Interfaces (Ssvmentioning

confidence: 99%

“…As first, logistic regression classifier is trained to discriminate between non-control (NC) and IC states. If the data represents a potential IC state, it is passed to the second stage classification procedure, which performs the discrimination between three IC states [7]. In the operational phase, the participants used the asynchronous ERD/ERS-BCI to scroll through the device submenu and select a device of interest.…”

Section: Erd/ers-bcimentioning

confidence: 99%

See 1 more Smart Citation

sBCI-Headset—Wearable and Modular Device for Hybrid Brain-Computer Interface

et al. 2015

Self Cite

View full text Add to dashboard Cite

Severely disabled people, like completely paralyzed persons either with tetraplegia or similar disabilities who cannot use their arms and hands, are often considered as a user group of Brain Computer Interfaces (BCI). In order to achieve high acceptance of the BCI by this user group and their supporters, the BCI system has to be integrated into their support infrastructure. Critical disadvantages of a BCI are the time consuming preparation of the user for the electroencephalography (EEG) measurements and the low information transfer rate of EEG based BCI. These disadvantages become apparent if a BCI is used to control complex devices. In this paper, a hybrid BCI is described that enables research for a Human Machine Interface (HMI) that is optimally adapted to requirements of the user and the tasks to be carried out. The solution is based on the integration of a Steady-state visual evoked potential (SSVEP)-BCI, an Event-related (de)-synchronization (ERD/ERS)-BCI, an eye tracker, an environmental observation camera, and a new EEG head cap for wearing comfort and easy preparation. The design of the new fast multimodal BCI (called sBCI) system is described and first test results, obtained in experiments with six healthy subjects, are presented. The sBCI concept may also become useful for healthy people in cases where a "hands-free" handling of devices is necessary. OPEN ACCESSMicromachines 2015, 6 292

show abstract

“…the timing of epochs was pre-determined and the subjects were instructed to follow the visual cues indicating MI and rest. In recent studies, also asynchronous approaches for MI-BCI feedback have been proposed [66,67], in which the subject is allowed to perform MI at a self-determined pace. In this case, the data analysis should be done in sliding time windows over the course of the measurement, which requires more computation than processing one epoch at a time.…”

Section: Discussionmentioning

confidence: 99%

Comparing Features for Classification of MEG Responses to Motor Imagery

Halme

Parkkonen

2016

PLoS ONE

View full text Add to dashboard Cite

BackgroundMotor imagery (MI) with real-time neurofeedback could be a viable approach, e.g., in rehabilitation of cerebral stroke. Magnetoencephalography (MEG) noninvasively measures electric brain activity at high temporal resolution and is well-suited for recording oscillatory brain signals. MI is known to modulate 10- and 20-Hz oscillations in the somatomotor system. In order to provide accurate feedback to the subject, the most relevant MI-related features should be extracted from MEG data. In this study, we evaluated several MEG signal features for discriminating between left- and right-hand MI and between MI and rest.MethodsMEG was measured from nine healthy participants imagining either left- or right-hand finger tapping according to visual cues. Data preprocessing, feature extraction and classification were performed offline. The evaluated MI-related features were power spectral density (PSD), Morlet wavelets, short-time Fourier transform (STFT), common spatial patterns (CSP), filter-bank common spatial patterns (FBCSP), spatio—spectral decomposition (SSD), and combined SSD+CSP, CSP+PSD, CSP+Morlet, and CSP+STFT. We also compared four classifiers applied to single trials using 5-fold cross-validation for evaluating the classification accuracy and its possible dependence on the classification algorithm. In addition, we estimated the inter-session left-vs-right accuracy for each subject.ResultsThe SSD+CSP combination yielded the best accuracy in both left-vs-right (mean 73.7%) and MI-vs-rest (mean 81.3%) classification. CSP+Morlet yielded the best mean accuracy in inter-session left-vs-right classification (mean 69.1%). There were large inter-subject differences in classification accuracy, and the level of the 20-Hz suppression correlated significantly with the subjective MI-vs-rest accuracy. Selection of the classification algorithm had only a minor effect on the results.ConclusionsWe obtained good accuracy in sensor-level decoding of MI from single-trial MEG data. Feature extraction methods utilizing both the spatial and spectral profile of MI-related signals provided the best classification results, suggesting good performance of these methods in an online MEG neurofeedback system.

show abstract

Asynchronous BCI Based on Motor Imagery With Automated Calibration and Neurofeedback Training

Cited by 55 publications

References 40 publications

Analysis of EEG signal by flicker-noise spectroscopy: identification of right-/left-hand movement imagination

Analysis of EEG signal by flicker-noise spectroscopy: identification of right-/left-hand movement imagination

sBCI-Headset—Wearable and Modular Device for Hybrid Brain-Computer Interface

Comparing Features for Classification of MEG Responses to Motor Imagery

Contact Info

Product

Resources

About