Open AccessProceedings Article10.1145/1102351.1102410

A brain computer interface with online feedback based on magnetoencephalography

- 07 Aug 2005

- pp 465-472

TL;DR: This paper is the first working online MEG-based BCI and is therefore a "proof of concept" for a brain computer interface (BCI) based on magnetoencephalography.

Abstract: The aim of this paper is to show that machine learning techniques can be used to derive a classifying function for human brain signal data measured by magnetoencephalography (MEG), for the use in a brain computer interface (BCI). This is especially helpful for evaluating quickly whether a BCI approach based on electroencephalography, on which training may be slower due to lower signal-to-noise ratio, is likely to succeed. We apply RCE and regularized SVMs to the experimental data of ten healthy subjects performing a motor imagery task. Four subjects were able to use a trained classifier to write a short name. Further analysis gives evidence that the proposed imagination task is suboptimal for the possible extension to a multiclass interface. To the best of our knowledge this paper is the first working online MEG-based BCI and is therefore a "proof of concept".

1. What are the contributions in "A brain computer interface with online feedback based on magnetoencephalography" ?

The aim of this paper is to show that machine learning techniques can be used to derive a classifying function for human brain signal data measured by magnetoencephalography ( MEG ), for the use in a brain computer interface ( BCI ).. The authors apply recursive channel elimination and regularized SVMs to the experimental data of ten healthy subjects performing a motor imagery task.. To the best of their knowledge this paper is the first working online BCI based on MEG recordings and is therefore a “ proof of concept ”.. Copyright 2005 by the author ( s ) /owner ( s ).. Further analysis gives evidence that the proposed imagination task is suboptimal for the possible extension to a multiclass interface.

Figure 6. For four MEG channels of subject H that are situated symmetrically over motor cortex areas spectrograms of the time interval two to three seconds and 0 Hz to 100 Hz were generated. For every point of the time/frequency space, a ROC-score is plotted in the four boxes of the top graphic. Red regions code for decreased mu-activity of cortex regions that are involved in the planning of left little finger movements. Blue regions would be associated with brain regions involved in the planning of tongue movements (please see text for an explanation). Since clearly clustered blue regions cannot be found, we conclude that the MEG measurements did not capture possible decreases of mu-activity associated with imagined tongue movements. In the lower part of the plot blue and red regions are clearly visible. These ROC-scores were generated from data of subject H during a separate experiment using left hand versus right hand imagination.

Figure 1. Overview of the trial structure during the data collection phase. The time interval used for classifier training started 0.5 seconds after the cue had ended. Relaxation intervals of randomized duration separated the trials. During the intervals marked with a “+”, the fixation cross was visible.

Figure 7. Screenshot of the projection screen while a subject writes the word “JOHN” (shown at the upper left box). The lower left box contains the letters “JOH” spelled so far. About every seven seconds, the subject imagines a movement to maneuver within the binary spelling tree. In the present situation the next letter “N” to write is among the letters of the right box. The subject can chose this box by imagining tongue movements (indicated by the thumbnail pictures added underneath the speller as reminders). In this case a subset of letters “EINAR” would appear next. An imagined finger movement would communicate that the intended letter is not among the displayed ones and the empty left box would be chosen. In this case the speller changes to the sibling branch and a different set of letters will appear next. After a few iterations only one letter remains. If it is chosen by the subject, the letter will be appended to the word spelled so far.

Figure 2. The left plot shows the 20-fold cross validation error of seven different AR model orders for the ten subjects. The estimates were based on data from all 150 channels. The right plot contains the averaged errors of the AR model orders along with standard errors.

Figure 4. The graph shows the cross validation error estimates plotted against the number N of the best ranked channels. The error estimate of ,e.g., N = 8 was calculated based on the data from channels ranked 1th to 8th (and not only from the single channel at rank 8). Bars denote the standard errors. In this example, a combination of the 18 best ranked channels yielded the lowest average error. We are interested in the minimal number of channels such that if one further channel is dropped the resulting error rate will be significantly higher than the minimal error. We estimate this subset of channels by finding the smallest number of ranked channels such that the resulting error rate still lies within the two standard errors (α) or one standard error interval (β) of the minimal error. In case of (β) the 11 best ranked channels would be selected.

Figure 3. This plot describes the process of calculating an estimate of the expected risk when only using the best N ranked channels for classification. First the data is split into 20 train/test folds. The channels are ranked on each training set using Recursive Channel Elimination, a classifier is trained using the best N features only and tested on the corresponding test set. The 20 test errors are averaged. Please note that the set of channels used by the different classifiers might vary (figure from (Lal et al., 2004)).

Citations

•Journal Article•10.3390/S120201211

Brain Computer Interfaces, a Review

Luis F. Nicolas-Alonso, +1 more

- 31 Jan 2012

- Sensors

TL;DR: The state-of-the-art of BCIs are reviewed, looking at the different steps that form a standard BCI: signal acquisition, preprocessing or signal enhancement, feature extraction, classification and the control interface.

...read moreread less

1.8K

•Journal Article•10.1111/J.1469-8986.2006.00456.X

Breaking the silence: Brain–computer interfaces (BCI) for communication and motor control

Niels Birbaumer

- 01 Nov 2006

- Psychophysiology

TL;DR: It was demonstrated that noninvasive EEG-based BCIs allow brain-derived communication in paralyzed and locked- in patients but not in completely locked-in patients, and the newly developed fMRI-BCI and NIRS-BCIs offer promise for the learned regulation of emotional disorders and also disorders of young children.

...read moreread less

777

Journal Article•10.1152/PHYSREV.00027.2016

Brain-Machine Interfaces: From Basic Science to Neuroprostheses and Neurorehabilitation

Mikhail A. Lebedev, +1 more

- 01 Apr 2017

- Physiological Reviews

TL;DR: Brain-machine interfaces research has been at the forefront of many neurophysiological discoveries, including the demonstration that, through continuous use, artificial tools can be assimilated by the primate brain's body schema.

...read moreread less

551

•Journal Article•10.1016/J.NEUROIMAGE.2007.03.019

An MEG-based brain-computer interface (BCI)

Jürgen Mellinger, +9 more

- 01 Jul 2007

- NeuroImage

TL;DR: The results suggest that an MEG-based BCI that uses voluntary amplitude modulation of sensorimotor mu and beta rhythms is feasible and efficient in terms of user training and a simple spatial filtering method that takes the geometric properties of signal propagation in MEG into account is presented.

...read moreread less

491

Journal Article•10.1016/J.MRI.2007.02.007

Real-time functional magnetic resonance imaging : methods and applications

Nikolaus Weiskopf, +10 more

- 01 Jul 2007

- Magnetic Resonance Imaging

TL;DR: An overview of the different major areas of applications that became possible with rtfMRI: online analysis of single-subject data provides immediate quality assurance and functional localizers guiding the main fMRI experiment or surgical interventions, and brain-computer interfaces with high spatial and temporal resolution and whole-brain coverage.

...read moreread less

273

...

Expand

References

•Journal Article•10.1023/A:1022627411411

Support-Vector Networks

Corinna Cortes, +1 more

- 15 Sep 1995

- Machine Learning

TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.

...read moreread less

42K

Journal Article•10.1016/0967-0661(96)82838-3

Adaptive Filter Theory

Steve Rogers

- 01 Nov 1996

- Control Engineering Practice

TL;DR: A guide to using artificial intelligence in the filmmaking process, as well as practical suggestions for improving the quality and efficiency of existing and new approaches.

...read moreread less

12.6K

•Journal Article•10.1023/A:1012487302797

Gene Selection for Cancer Classification using Support Vector Machines

Isabelle Guyon, +3 more

- 11 Mar 2002

- Machine Learning

TL;DR: In this article, a Support Vector Machine (SVM) method based on recursive feature elimination (RFE) was proposed to select a small subset of genes from broad patterns of gene expression data, recorded on DNA micro-arrays.

...read moreread less

9.5K

•Journal Article•10.1109/86.895946

Optimal spatial filtering of single trial EEG during imagined hand movement

Herbert Ramoser, +2 more

- 01 Dec 2000

TL;DR: It is demonstrated that spatial filters for multichannel EEG effectively extract discriminatory information from two populations of single-trial EEG, recorded during left- and right-hand movement imagery.

...read moreread less

2.5K

Journal Article•10.1038/18581

A spelling device for the paralysed

Niels Birbaumer, +8 more

- 25 Mar 1999

- Nature

TL;DR: A new means of communication for the completely paralysed that uses slow cortical potentials of the electro-encephalogram to drive an electronic spelling device is developed.

...read moreread less

1.6K

...

Expand

A brain computer interface with online feedback based on magnetoencephalography

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions in "A brain computer interface with online feedback based on magnetoencephalography" ?

Figures

Citations

Brain Computer Interfaces, a Review

Breaking the silence: Brain–computer interfaces (BCI) for communication and motor control

Brain-Machine Interfaces: From Basic Science to Neuroprostheses and Neurorehabilitation

An MEG-based brain-computer interface (BCI)

Real-time functional magnetic resonance imaging : methods and applications

References

Support-Vector Networks

Adaptive Filter Theory

Gene Selection for Cancer Classification using Support Vector Machines

Optimal spatial filtering of single trial EEG during imagined hand movement

A spelling device for the paralysed

Related Papers (5)

Brain-computer interfaces for communication and control.

Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials

Optimal spatial filtering of single trial EEG during imagined hand movement

Brain-computer interface technology: a review of the first international meeting

A review of classification algorithms for EEG-based brain–computer interfaces