76 research outputs found
Brain Invaders 2013a
No full text<p>P300 dataset bi2013a from a “Brain Invaders” experiment (2013) carried-out at University of Grenoble Alpes.</p>
<p>Simple Python scripts for working with the dataset are available at <a href="https://github.com/plcrodrigues/BrainInvaders-2013a-Dataset">https://github.com/plcrodrigues/BrainInvaders-2013a-Dataset</a></p>
<p><strong>Dataset Description</strong></p>
<p>This dataset concerns an experiment carried out at GIPSA-lab (University of Grenoble Alpes, CNRS, Grenoble-INP) in 2013.</p>
<p>Principal Investigators: Erwan Vaineau, Dr. Alexandre Barachant<br>
Scientific Supervisor : Dr. Marco Congedo<br>
Technical Supervisor : Anton Andreev</p>
<p>The experiment uses the <strong><em>Brain Invaders</em></strong> P300-based Brain-Computer Interface [7], which uses the Open-ViBE platform for on-line EEG data acquisition and processing [1, 9]. For classification purposes the Brain Invaders implements on-line Riemannian MDM classifiers [2, 3, 4, 6]. This experiment features both a training-test (classical) mode of operation and a calibration-less mode of operation [4, 5, 6]. </p>
<p>The recordings concerned 24 subjects in total. Subjects 1 to 7 participated to eight sessions, run in different days, subject 8 to 24 participated to one session. Each session consisted in <em>two runs</em>, one in a <em>Non-Adaptive</em> (classical) and one in an <em>Adaptive</em> (calibration-less) mode of operation. The order of the runs was randomized for each session. In both runs there was a <em>Training (calibration) phase</em> and an <em>Online phase</em>, always passed in this order. In the non-Adaptive run the data from the Training phase was used for classifying the trials on the Online phase using the training-test version of the MDM algorithm [3, 4]. In the Adaptive run, the data from the training phase was not used at all, instead the classifier was initialized with generic class geometric means and continuously adapted to the incoming data using the Riemannian method explained in [4]. Subjects were completely blind to the mode of operation and the two runs appeared to them identical.</p>
<p>In the Brain Invaders P300 paradigm, a <em>repetition</em> is composed of 12 flashes, of which 2 include the Target symbol (<em>Target</em> flashes) and 10 do not (<em>non-Target</em> flash). Please see [7] for a description of the paradigm. For this experiment, in the Training phases the number of flashes is fixed (80 Target flashes and 400 non-Target flashes). In the Online phases the number of Target and non-Target still are in a ratio 1/5, however their number is variable because the Brain Invaders works with a fixed number of game levels, however the number of repetitions needed to destroy the target (hence to proceed to the next level) depends on the user’s performance [4, 5]. In any case, since the classes are unbalanced, an appropriate score must be used for quantifying the performance of classification methods (e.g., balanced accuracy, AUC methods, etc).</p>
<p>This database has been used in the development of the common spatio-temporal pattern method for estimating ERPs [8].</p>
<p>Data were acquired with a Nexus (TMSi, The Netherlands) EEG amplifier:</p>
<ul>
<li>Sampling frequency: 512 samples per second</li>
<li>Digital Filter: No</li>
<li>Electrodes: 16 wet Silver/Silver Chloride electrodes positioned at FP1, FP2, F5, AFz, F6, T7, Cz, T8, P7, P3, Pz, P4, P8, O1, Oz, O2 according to the 10/20 international system</li>
<li>Reference: left ear-lobe</li>
<li>Ground: N/A</li>
</ul>
<p>The data for Subject X is available as a subjectX.zip file. In it, there is a folder for each Session that the Subject performed. In each Session's folder, there are four .gdf files, one for each Run performed in the Session. The names of the files and the conditions associated to them are available below and also inside the meta.yml file in the .zip file.</p>
<p> - filename: '1.gdf'<br>
experimental_condition: adaptive<br>
type: training<br>
- filename: '2.gdf'<br>
experimental_condition: adaptive<br>
type: online<br>
- filename: '3.gdf'<br>
experimental_condition: nonadaptive<br>
type: training<br>
- filename: '4.gdf'<br>
experimental_condition: nonadaptive<br>
type: online </p>
<p><strong><em>References</em></strong></p>
<p>[1] Arrouët C, Congedo M, Marvie J-E, Lamarche F, Lècuyer A, Arnaldi B (2005) Open-ViBE: a 3D Platform for Real-Time Neuroscience. Journal of Neurotherapy, 9(1), 3-25. people.rennes.inria.fr/Anatole.Lecuyer/Open-ViBE.pdf)</p>
<p>[2] Barachant A, Bonnet S, Congedo M, Jutten C (2013) Classification of covariance matrices using a Riemannian-based kernel for BCI applications. Neurocomputing 112, 172-178. (hal.archives-ouvertes.fr/hal-00820475/document)</p>
<p>[3] Barachant A, Bonnet S, Congedo M, Jutten C (2012) Multi-Class Brain Computer Interface Classification by Riemannian Geometry. IEEE Transactions on Biomedical Engineering 59(4), 920-928. (hal.archives-ouvertes.fr/hal-00681328/document)</p>
<p>[4] Barachant A, Congedo M (2014) A Plug & Play P300 BCI using Information Geometry, arXiv:1409.0107. (https://arxiv.org/pdf/1409.0107.pdf)</p>
<p>[5] Congedo M, Barachant A, Andreev A (2013) A New Generation of Brain-Computer Interface Based on Riemannian Geometry. arXiv:1310.8115 (arxiv.org/ftp/arxiv/papers/1310/1310.8115.pdf)</p>
<p>[6] Congedo M, Barachant A, Bhatia R (2017) Riemannian Geometry for EEG-based Brain-Computer Interfaces; a Primer and a Review. Brain-Computer Interfaces, 4(3), 155-174. (hal.archives-ouvertes.fr/hal-01570120/document)</p>
<p>[7] Congedo M, Goyat M, Tarrin N, Ionescu G, Rivet B,Varnet L, Rivet B, Phlypo R, Jrad N, Acquadro M, Jutten C (2011) “Brain Invaders”: a prototype of an open-source P300-based video game working with the OpenViBE platform. Proc. IBCI Conf., Graz, Austria, 280-283. (hal.archives-ouvertes.fr/hal-00641412/document)</p>
<p>[8] Congedo M, Korczowski L, Delorme A, Lopes da Silva F. (2016) Qpatio-temporal common pattern: A companion method for ERP analysis in the time domain. Journal of Neuroscience Methods, 267, 74-88. (hal.archives-ouvertes.fr/hal-01343026/document)</p>
<p>[9] Renard Y, Lotte F, Gibert G, Congedo M, Maby E, Delannoy V, Bertrand O, Lécuyer A (2010) OpenViBE: An Open-Source Software Platform to Design, Test and Use Brain-Computer Interfaces in Real and Virtual Environments. PRESENCE : Teleoperators and Virtual Environments 19(1), 35-53. (hal.archives-ouvertes.fr/hal-00477153/document)</p>
Brain Invaders 2013a
No full text<p>P300 dataset bi2013a from a “Brain Invaders” experiment (2013) carried-out at University of Grenoble Alpes.</p>
<p>Simple Python scripts for working with the dataset are available at <a href="https://github.com/plcrodrigues/BrainInvaders-2013a-Dataset">https://github.com/plcrodrigues/BrainInvaders-2013a-Dataset</a></p>
<p><strong>Dataset Description</strong></p>
<p>This dataset concerns an experiment carried out at GIPSA-lab (University of Grenoble Alpes, CNRS, Grenoble-INP) in 2013.</p>
<p>Principal Investigators: Erwan Vaineau, Dr. Alexandre Barachant<br>
Scientific Supervisor : Dr. Marco Congedo<br>
Technical Supervisor : Anton Andreev</p>
<p>The experiment uses the <strong><em>Brain Invaders</em></strong> P300-based Brain-Computer Interface [7], which uses the Open-ViBE platform for on-line EEG data acquisition and processing [1, 9]. For classification purposes the Brain Invaders implements on-line Riemannian MDM classifiers [2, 3, 4, 6]. This experiment features both a training-test (classical) mode of operation and a calibration-less mode of operation [4, 5, 6]. </p>
<p>The recordings concerned 24 subjects in total. Subjects 1 to 7 participated to eight sessions, run in different days, subject 8 to 24 participated to one session. Each session consisted in <em>two runs</em>, one in a <em>Non-Adaptive</em> (classical) and one in an <em>Adaptive</em> (calibration-less) mode of operation. The order of the runs was randomized for each session. In both runs there was a <em>Training (calibration) phase</em> and an <em>Online phase</em>, always passed in this order. In the non-Adaptive run the data from the Training phase was used for classifying the trials on the Online phase using the training-test version of the MDM algorithm [3, 4]. In the Adaptive run, the data from the training phase was not used at all, instead the classifier was initialized with generic class geometric means and continuously adapted to the incoming data using the Riemannian method explained in [4]. Subjects were completely blind to the mode of operation and the two runs appeared to them identical.</p>
<p>In the Brain Invaders P300 paradigm, a <em>repetition</em> is composed of 12 flashes, of which 2 include the Target symbol (<em>Target</em> flashes) and 10 do not (<em>non-Target</em> flash). Please see [7] for a description of the paradigm. For this experiment, in the Training phases the number of flashes is fixed (80 Target flashes and 400 non-Target flashes). In the Online phases the number of Target and non-Target still are in a ratio 1/5, however their number is variable because the Brain Invaders works with a fixed number of game levels, however the number of repetitions needed to destroy the target (hence to proceed to the next level) depends on the user’s performance [4, 5]. In any case, since the classes are unbalanced, an appropriate score must be used for quantifying the performance of classification methods (e.g., balanced accuracy, AUC methods, etc).</p>
<p>This database has been used in the development of the common spatio-temporal pattern method for estimating ERPs [8].</p>
<p>Data were acquired with a Nexus (TMSi, The Netherlands) EEG amplifier:</p>
<ul>
<li>Sampling frequency: 512 samples per second</li>
<li>Digital Filter: No</li>
<li>Electrodes: 16 wet Silver/Silver Chloride electrodes positioned at FP1, FP2, F5, AFz, F6, T7, Cz, T8, P7, P3, Pz, P4, P8, O1, Oz, O2 according to the 10/20 international system</li>
<li>Reference: left ear-lobe</li>
<li>Ground: N/A</li>
</ul>
<p>The data for Subject X is available as a subjectX.zip file. In it, there is a folder for each Session that the Subject performed. In each Session's folder, there are four .gdf files, one for each Run performed in the Session. The names of the files and the conditions associated to them are available below and also inside the meta.yml file in the .zip file.</p>
<p> - filename: '1.gdf'<br>
experimental_condition: adaptive<br>
type: training<br>
- filename: '2.gdf'<br>
experimental_condition: adaptive<br>
type: online<br>
- filename: '3.gdf'<br>
experimental_condition: nonadaptive<br>
type: training<br>
- filename: '4.gdf'<br>
experimental_condition: nonadaptive<br>
type: online </p>
<p><strong><em>References</em></strong></p>
<p>[1] Arrouët C, Congedo M, Marvie J-E, Lamarche F, Lècuyer A, Arnaldi B (2005) Open-ViBE: a 3D Platform for Real-Time Neuroscience. Journal of Neurotherapy, 9(1), 3-25. people.rennes.inria.fr/Anatole.Lecuyer/Open-ViBE.pdf)</p>
<p>[2] Barachant A, Bonnet S, Congedo M, Jutten C (2013) Classification of covariance matrices using a Riemannian-based kernel for BCI applications. Neurocomputing 112, 172-178. (hal.archives-ouvertes.fr/hal-00820475/document)</p>
<p>[3] Barachant A, Bonnet S, Congedo M, Jutten C (2012) Multi-Class Brain Computer Interface Classification by Riemannian Geometry. IEEE Transactions on Biomedical Engineering 59(4), 920-928. (hal.archives-ouvertes.fr/hal-00681328/document)</p>
<p>[4] Barachant A, Congedo M (2014) A Plug & Play P300 BCI using Information Geometry, arXiv:1409.0107. (https://arxiv.org/pdf/1409.0107.pdf)</p>
<p>[5] Congedo M, Barachant A, Andreev A (2013) A New Generation of Brain-Computer Interface Based on Riemannian Geometry. arXiv:1310.8115 (arxiv.org/ftp/arxiv/papers/1310/1310.8115.pdf)</p>
<p>[6] Congedo M, Barachant A, Bhatia R (2017) Riemannian Geometry for EEG-based Brain-Computer Interfaces; a Primer and a Review. Brain-Computer Interfaces, 4(3), 155-174. (hal.archives-ouvertes.fr/hal-01570120/document)</p>
<p>[7] Congedo M, Goyat M, Tarrin N, Ionescu G, Rivet B,Varnet L, Rivet B, Phlypo R, Jrad N, Acquadro M, Jutten C (2011) “Brain Invaders”: a prototype of an open-source P300-based video game working with the OpenViBE platform. Proc. IBCI Conf., Graz, Austria, 280-283. (hal.archives-ouvertes.fr/hal-00641412/document)</p>
<p>[8] Congedo M, Korczowski L, Delorme A, Lopes da Silva F. (2016) Qpatio-temporal common pattern: A companion method for ERP analysis in the time domain. Journal of Neuroscience Methods, 267, 74-88. (hal.archives-ouvertes.fr/hal-01343026/document)</p>
<p>[9] Renard Y, Lotte F, Gibert G, Congedo M, Maby E, Delannoy V, Bertrand O, Lécuyer A (2010) OpenViBE: An Open-Source Software Platform to Design, Test and Use Brain-Computer Interfaces in Real and Virtual Environments. PRESENCE : Teleoperators and Virtual Environments 19(1), 35-53. (hal.archives-ouvertes.fr/hal-00477153/document)</p>
EEG Motor Imagery Dataset from the PhD Thesis "Commande robuste d'un effecteur par une interface cerveau machine EEG asynchrone"
No full text<p>This Dataset contains EEG recordings from 8 subjects, performing 2 task of motor imagination (right hand, feet or rest). Data have been recorded at 512Hz with 16 wet electrodes (Fpz, F7, F3, Fz, F4, F8, T7, C3, Cz, C4, T8, P7, P3, Pz, P4, P8) with a g.tec g.USBamp EEG amplifier.</p>
<p>File are provided in MNE raw file format. A stimulation channel encoding the timing of the motor imagination. The start of a trial is encoded as 1, then the actual start of the motor imagination is encoded with 2 for imagination of a right hand movement, 3 for imagination of both feet movement and 4 with a rest trial.</p>
<p>The duration of each trial is 3 second. There is 20 trial of each class.</p>
Robust control of an actuator by EEG based asynchronous BCI
No full textCette thèse a pour but le développement d’une Interface cerveau-machine (ICM) à partir de la mesure EEG,permettant à l’utilisateur de communiquer avec un dispositif externe directement par l’intermédiaire de son activité cérébrale. Ces travaux ont été menés avec comme ligne directrice le développement d'un système d'ICM utilisable dans un contexte de vie courante, le but étant de réaliser une ICM simple d'utilisation, robuste et ergonomique, permettant le contrôle d'un effecteur avec un temps de calibration minimal.Un brain-switch ou interrupteur cérébral a été réalisé et permet à l'utilisateur d'envoyer une commande binaire. La réalisation d'une telle ICM implique le développement d'algorithmes robustes et leurs mises en œuvre expérimentales. Les travaux réalisés comportent deux volets, l'un concerne le développement de nouveaux algorithmes, l'autre concerne la réalisation de campagne de tests.This thesis presents the development of a Brain computer Interface (BCI) based on EEG signal, allowing its user to communicates with an external device solely by the mean of brain activity. This work as been conduct with the goal of designing a robust, ergonomic and easy to use BCI system for real life applications.In this context, a brain-switch has been developed, allowing it's user to send a binary command to a homeautomation system. This goal can only be achieved by developing new methodologies and algorithms, while testing them on real life experiments. Therefore, this works is two part, the first one is focus on the design of new algorithms, the secondon the design of experimental paradigm
Commande robuste d'un effecteur par une interface cerveau machine EEG asynchrone
No full textThis thesis presents the development of a Brain computer Interface (BCI) based on EEG signal, allowing its user to communicates with an external device solely by the mean of brain activity. This work as been conduct with the goal of designing a robust, ergonomic and easy to use BCI system for real life applications.In this context, a brain-switch has been developed, allowing it's user to send a binary command to a homeautomation system. This goal can only be achieved by developing new methodologies and algorithms, while testing them on real life experiments. Therefore, this works is two part, the first one is focus on the design of new algorithms, the secondon the design of experimental paradigm.Cette thèse a pour but le développement d’une Interface cerveau-machine (ICM) à partir de la mesure EEG,permettant à l’utilisateur de communiquer avec un dispositif externe directement par l’intermédiaire de son activité cérébrale. Ces travaux ont été menés avec comme ligne directrice le développement d'un système d'ICM utilisable dans un contexte de vie courante, le but étant de réaliser une ICM simple d'utilisation, robuste et ergonomique, permettant le contrôle d'un effecteur avec un temps de calibration minimal.Un brain-switch ou interrupteur cérébral a été réalisé et permet à l'utilisateur d'envoyer une commande binaire. La réalisation d'une telle ICM implique le développement d'algorithmes robustes et leurs mises en œuvre expérimentales. Les travaux réalisés comportent deux volets, l'un concerne le développement de nouveaux algorithmes, l'autre concerne la réalisation de campagne de tests
Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset
No full text<p><strong>Summary:</strong></p>
<p>This dataset contains electroencephalographic (EEG) recordings of 24 subjects doing a visual P300 Brain-Computer Interface experiment on PC. The visual P300 is an event-related potential elicited by visual stimulation, peaking 240-600 ms after stimulus onset. The experiment was designed in order to compare the use of a P300-based brain-computer interface on a PC with and without adaptive calibration using Riemannian geometry. The brain-computer interface is based on electroencephalography (EEG). EEG data were recorded thanks to 16 electrodes. A full description of the experiment is available at <a href="https://hal.archives-ouvertes.fr/hal-02103098">https://hal.archives-ouvertes.fr/hal-02103098</a>. Data were recorded during an experiment taking place in the GIPSA-lab, Grenoble, France, in 2013 (Congedo, 2013). Python code for manipulating the data is available at <a href="https://github.com/plcrodrigues/py.BI.EEG.2013-GIPSA">https://github.com/plcrodrigues/py.BI.EEG.2013-GIPSA</a>. The ID of this dataset is<em> BI.EEG.2013-GIPSA</em>.</p>
<p> </p>
<p><strong>Full description of the experiment and dataset:</strong> <a href="https://hal.archives-ouvertes.fr/hal-02103098">https://hal.archives-ouvertes.fr/hal-02103098</a></p>
<p> </p>
<p><strong><em>Principal Investigator</em>:</strong> B.Sc. Erwan Vaineau, Ph.D. Alexandre Barachant</p>
<p> </p>
<p><strong><em>Technical Supervisors</em>: </strong>Eng. Anton Andreev, Eng. Pedro. L. C. Rodrigues, Eng. Grégoire Cattan</p>
<p> </p>
<p><strong><em>Scientific Supervisor:</em></strong> Ph.D. Marco Congedo</p>
<p> </p>
<p><strong>ID of the dataset: </strong><em>BI.EEG.2013-GIPSA</em></p>
A Special Form of SPD Covariance Matrix for Interpretation and Visualization of Data Manipulated with Riemannian Geometry
No full textInternational audienc
Channel Selection Procedure using Riemannian distance for BCI applications
No full textInternational audienceThis article describes a new algorithm to select a subset of electrodes in BCI experiments. It is illustrated on a two-class motor imagery paradigm. The proposed approach is based on the Riemannian distance between spatial covariance matrices which allows to indirectly assess the discriminability between classes. Sensor selection is automatically done using a backward elimination principle. The method is tested on the dataset IVa from BCI competition III. The identified subsets are both consistent with neurophysiological principles and effective, achieving optimal performances with a reduced number of channels
Riemannian Geometry Boosts Representational Similarity Analyses of Dense Neural Time Series
No full textAbstractRepresentational similarity analysis (RSA) is a popular technique to estimate the structure of mental representations from neuroimaging data. However, RSA can be difficult to estimate for neural time series, where mental representations may be distributed in a highly dimensional space. Here, we show that RSA can be efficiently estimated from dense neural time series using Riemannian geometry. Using a public magneto-encephalography dataset, we decoded 24 classes from the brain evoked responses to 720 visual stimuli. RSA estimated from the confusion matrices of a standard regularized logistic regression achieved an average decoding accuracy of 23% (chance=4%). Our approach based on spatial filtering and Riemannian geometry nearly doubled this score with an average 42% decoding accuracy. Finally, our results revealed how RSA becomes ill-conceived when it derives from confusion matrices of highly accurate multivariate pattern classifications. Instead, we propose to directly estimate RSA from Riemannian metrics without fitting a multivariate pattern classifier. Overall, our approach, based on Riemannian geometry provides a principled and efficient basis to study the structure of mental representations from highly dimensional neural time series.</jats:p
- …
