Name: P300-basierte Brain-Computer-Schnittstelle Rechtschreiber-Leistungsschätzung mit klassifikatorbasierter Latenzschätzung (Video) | JoVE Journal
Uploaded: 2023-09-08T12:00:00.000+00:00
Duration: 6 min 9 s
Description: Lernen Sie die CBLE-Methode zur Leistungsschätzung von P300-Brain-Computer-Schnittstellen mit minimalem Datensatz. Diese Technik ermöglicht präzise Vorhersagen der Nutzergenauigkeit für Echtzeitanwendungen.

ai_agent_IP

ai_agent

maintenance

instantTrialDurationMinutes

isBiopharma

enableNewMyJoveSectionDesign

educationFeatures

seoMetaApi

ai_copilot_institution_blacklist

ai_chat_institution_blacklist

freeAccessWindow

ssoRoleCapture

scheduledMaintenanceBanner

joveLabsFeatures

disable_autoplay_for_bots

extended_trial_duration

5 minutes

playerTrialDesktop

The data used for representative results were collected from the work supported by the National Institute of Child Health and Human Development (NICHD), the National Institutes of Health (NIH) under Grant R21HD054697, and the National Institute on Disability and Rehabilitation Research (NIDRR) in the Department of Education under Grant H133G090005 and Award Number H133P090008. The rest of the work was funded in part by the National Science Foundation (NSF) under award #1910526. Findings and opinions within this work do not necessarily reflect the positions of NICHD, NIH, NIDRR or NSF.

The &#34;CBLE Performance Estimation&#34; GUI was applied to two datasets: &#34;BrainInvaders&#34; dataset and Michigan dataset. For the &#34;BrainInvaders&#34; dataset, the data collection was approved by the Ethical Committee of the University of Grenoble Alpes20. Michigan data were collected under the University of Michigan Institutional Review Board approval19. Data were analyzed under Kansas State University exempt protocol 7516. If collecting new data, follow the user&#39;s IRB-approved process for collecting informed consent. Here, the proposed protocol is evaluated using offline analysis of previously-recorded, de-identified data and therefore did not require additional informed consent.
The graphical user interface (GUI) included in this article is proficient in managing two distinct dataset formats. The first format is associated with the BCI2000 software, while the second format is referred to as the &#34;BrainInvaders&#34; dataset. In order to utilize the &#34;Brain Invaders&#34; format, data must be pre-processed as described in step 1 of the protocol section. However, when dealing with the &#34;BCI2000&#34; dataset format, step 1 can be omitted.
1. Data preparation
<ol>
	<li>BrainInvaders only: Generate the input data file in &#34;.mat&#34; file format that can be used with the &#34;CBLE performance Estimation&#34; graphical user interface (GUI). For a sample script, refer to Supplementary Coding File 2. 
	NOTE: Each data file consists of a two-dimensional matrix comprised of rows that represent observations recorded at distinct time samples. The matrix columns numbered 2 to 17 are recordings derived from 16 EEG electrodes. The first column of the matrix denotes the timestamp of each observation, while column 18 encompasses information related to experimental events. In column 19, there are mostly zeros, but when a non-Target (or Target) flash starts, the numbers change to one (or two) at that specific time. A detailed description may be found in the reference20.</li>
</ol>
2. Downloading and installing the GUI package
<ol>
	<li>Download and install the &#34;CBLE Performance Estimation&#34; GUI.</li>
</ol>
3. Storing the dataset in a subfolder of the GUI location
<ol>
	<li>Ensure that the dataset folder remains within the same directory as the GUI.</li>
	<li>For instance, create a new folder and place the &#34;CBLE Performance Estimation&#34; GUI inside it. Keep all the datasets in a subfolder within &#34;CBLE GUI&#34; named &#34;Dataset.&#34;</li>
</ol>
4. Opening the installed GUI
<ol>
	<li>Open MATLAB (see Table of Materials), change the current directory to the folder where the GUI is placed, click on APPS tab, and select MY APPS.</li>
	<li>Under the &#34;MY APPS&#34; tab, select CBLE Performance Estimation.</li>
</ol>
5. Choosing the dataset format
<ol>
	<li>Select a dataset format from the dropdown Select dataset format.</li>
</ol>
6. Loading the EEG data file
<ol>
	<li>Click on the Select input folder button to choose the directory where the dataset is located.</li>
	<li>Observe the count of data files present in that selected folder. 
	NOTE: In the &#34;Brain Invaders&#34; format, each participant is represented by a single data file. Therefore, the total number of data files indicates the number of participants in the study. However, this is not the case for the &#34;BCI2000&#34; format, as each participant may have multiple train and test files.</li>
</ol>
7. Setting the parameters
<ol>
	<li>Type the number of participants that the user intends to use for the estimation process in the &#34;No. of participants&#34; text box.</li>
	<li>BrainInvaders only: Specify the sampling rate of the dataset. 
	NOTE: BCI2000 files include the sample rate.</li>
	<li>Choose a decimation value to downsample the dataset to approximately 20 Hz in order to improve classification performance21. For example, if the sampling frequency is 256 Hz, then select a decimation value of 13.</li>
	<li>Specify the time window for the classification in milliseconds. 
	NOTE: The recommended initial window size is specified, allowing the starting point to vary from 0 to 100 ms and the ending point from 700 to 800 ms. However, it is important to avoid making the window size excessively large to prevent overlapping with another P300 event.</li>
	<li>Define the shift window for CBLE in milliseconds. 
	NOTE: The &#39;shift window&#39; refers to the expanded time range that the CBLE&#8239;method searches to find the P3 response.&#8239; The classifier will be applied to the epoch starting at the first element of the shift window.&#8239; The classifier is then sequentially applied to epochs starting one sample later, until the epoch extends outside the shift window.&#8239; Thus, the shift window must be larger than the original window; empirically, values less than 100 ms from each side perform well.&#8239; In any case, the margin should be held to less than half the ISI.</li>
	<li>BC2000 only: Enter the length of the subject ID indicated in the dataset files within the &#34;ID length&#34; field. 
	NOTE: The GUI expects the first sub_len characters of the filenames to encode the subject ID.</li>
	<li>BCI2000 only: In the &#34;Channel ID&#34; field, indicate either the total number of channels or specify the specific channel numbers to be used for the analysis.</li>
	<li>Click on the Set parameters button to set all the parameters required for the analysis.</li>
</ol>
8. BrainInvaders only: Splitting the dataset into training and test set
<ol>
	<li>Select a number of targets that represents the size of the training set. The remaining portion of the dataset will be considered as the test dataset. 
	NOTE: To ensure proper training of the model, it is essential to have a sufficiently large training sample. The recommended minimum training sample size is 20, though this may vary depending on the overall dataset size. If regression errors occur during training sessions, it is advisable to increase the training sample size.</li>
	<li>Press the &#34;Split the dataset&#34; button to divide the dataset into the training and test sets. 
	&#8203;NOTE: Each participant will have an equal amount of training data. However, the number of test data may not be equal for all participants due to the possibility of multiple attempts during the task. Consequently, the total number of targets or flashes presented may vary from person to person.</li>
</ol>
9. Training a model with the training dataset
NOTE: Step 9.1 is applicable for &#34;Brain Invaders&#34; format, and step 9.2 is applicable for &#34;BCI2000&#34; format.
<ol>
	<li>BrainInvaders only: Click on the Train a model button to apply linear regression on the training dataset using Equation 2 for training a classifier model.</li>
	<li>BCI2000 only: Indicate training and testing filenames along with their data format (.dat) to distinguish the training and testing files from all files. Then, click on the Train a model button to apply linear regression on the training dataset.</li>
</ol>
10. Predicting the accuracy of the test set
<ol>
	<li>Click on Predict accuracy to apply the trained classifier model to the test feature set and predict&#160;accuracy&#160;using Equation 1.</li>
</ol>
11. Getting X-target accuracies
<ol>
	<li>Select a maximum target number, X, to consider in the test set.</li>
	<li>BCI2000 only: Select a test file number if the user has multiple test files.</li>
	<li>Press Find X target accuracy.</li>
</ol>
12. Calculating vCBLE
<ol>
	<li>Click on the Find vCBLE button to get the vCBLE for all targets.</li>
</ol>
13. Calculating the Root mean square error (RMSE) of BCI accuracy and vCBLE
<ol>
	<li>Click on the Calculate RMSE button to calculate the RMSE between both predictions based on vCBLE with BCI accuracy, and X-target accuracy with BCI accuracy.</li>
</ol>
14. Visualizing the analysis results
<ol>
	<li>Click on the Accuracy vs vCBLE button to observe the relation between total accuracy and total vCBLE for all participants.</li>
	<li>Press on the RMSE of BCI &#38; vCBLE button to show the RMSE curve of BCI accuracy and vCBLE.</li>
</ol>
15. Predicting the performance of an individual participant
<ol>
	<li>To predict the accuracy of an individual participant, place the subject ID in Sub ID. 
	NOTE: Here, the dataset of all participants, excluding the test participant, will be used to train a linear regression model. The vCBLE scores of all other participants and their corresponding test accuracies will be utilized as predictors and labels, respectively, for the classifier.</li>
	<li>Select a target number, n. The prediction will be made based on the accuracy of n-testing characters.</li>
	<li>Click on the Predict button to get the predicted accuracy of the test participant.</li>
</ol>

<ol><li>Rezeika, A., Benda, M., Stawicki, P., Gembler, F., Saboor, A., Volosyak, I. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Brain-Computer+Interface+spellers%3A+A+review%5BTitle%5D)+AND+%22Brain+Science%22%5BJournal%5D)">Brain-Computer Interface spellers: A review.</a> Brain Science. 8 (4), 57(2018).</li>
<li>Gannouni, S., Aledaily, A., Belwafi, K., Aboalsamh, H. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Emotion+detection+using+electroencephalography+signals+and+a+zero-time+windowing-based+epoch+estimation+and+relevant+electrode+identification%5BTitle%5D)+AND+%22Scientific+Reports%22%5BJournal%5D)">Emotion detection using electroencephalography signals and a zero-time windowing-based epoch estimation and relevant electrode identification.</a> Scientific Reports. 11 (1), 7071(2021).</li>
<li>Daly, J. J., Wolpaw, J. R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Brain-computer+interfaces+in+neurological+rehabilitation%5BTitle%5D)+AND+%22Lancet+Neurology%22%5BJournal%5D)">Brain-computer interfaces in neurological rehabilitation.</a> Lancet Neurology. 7 (11), 1032-1043 (2008).</li>
<li>Birbaumer, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Breaking+the+silence%3A+brain-computer+interfaces+%28BCI%29+for+communication+and+motor+control%5BTitle%5D)+AND+%22Psychophysiology%22%5BJournal%5D)">Breaking the silence: brain-computer interfaces (BCI) for communication and motor control.</a> Psychophysiology. 43 (6), 517-532 (2006).</li>
<li>Riccio, A., Simione, L., Schettini, F., Pizzimenti, A., Inghilleri, M., Belardinelli, M. O. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Attention+and+P300-based+BCI+performance+in+people+with+amyotrophic+lateral+sclerosis%5BTitle%5D)+AND+%22Frontiers+in+Human+Neuroscience%22%5BJournal%5D)">Attention and P300-based BCI performance in people with amyotrophic lateral sclerosis.</a> Frontiers in Human Neuroscience. 7, 732(2013).</li>
<li>Finke, A., Lenhardt, A., Ritter, H. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((The+MindGame%3A+a+P300-based+brain-computer+interface+game%5BTitle%5D)+AND+%22Neural+Network%22%5BJournal%5D)">The MindGame: a P300-based brain-computer interface game.</a> Neural Network. 22 (9), 1329-1333 (2009).</li>
<li>Farwell, L. A., Donchin, E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Talking+off+the+top+of+your+head%3A+toward+a+mental+prosthesis+utilizing+event-related+brain+potentials.+Electroencephalogr%5BTitle%5D)+AND+%22Clinical+Neurophysiology%22%5BJournal%5D)">Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr.</a> Clinical Neurophysiology. 70 (6), 510-523 (1988).</li>
<li>Li, Q., Lu, Z., Gao, N., Yang, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Optimizing+the+performance+of+the+visual+P300-speller+through+active+mental+tasks+based+on+color+distinction+and+modulation+of+task+difficulty%5BTitle%5D)+AND+%22Frontiers+in+Human+Neuroscience%22%5BJournal%5D)">Optimizing the performance of the visual P300-speller through active mental tasks based on color distinction and modulation of task difficulty.</a> Frontiers in Human Neuroscience. 13, 130(2019).</li>
<li>McFarland, D. J., Sarnacki, W. A., Townsend, G., Vaughan, T., Wolpaw, J. R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((The+P300-based+brain-computer+interface+%28BCI%29%3A+effects+of+stimulus+rate%5BTitle%5D)+AND+%22Clinical+Neurophysiology%22%5BJournal%5D)">The P300-based brain-computer interface (BCI): effects of stimulus rate.</a> Clinical Neurophysiology. 122 (4), 731-737 (2011).</li>
<li>Krusienski, D. J., Sellers, E. W., Cabestaing, F., Bayoudh, S., McFarland, D. J., Vaughan, T. M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+comparison+of+classification+techniques+for+the+P300+Speller%5BTitle%5D)+AND+%22Journal+of+Neural+Engineering%22%5BJournal%5D)">A comparison of classification techniques for the P300 Speller.</a> Journal of Neural Engineering. 3 (4), 299-305 (2006).</li>
<li>Sellers, E. W., Donchin, E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+P300-based+brain-computer+interface%3A+initial+tests+by+ALS+patients%5BTitle%5D)+AND+%22Clinical+Neurophysiology%22%5BJournal%5D)">A P300-based brain-computer interface: initial tests by ALS patients.</a> Clinical Neurophysiology. 117 (3), 538-548 (2006).</li>
<li>Donchin, E., Spencer, K. M., Wijesinghe, R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((The+mental+prosthesis%3A+assessing+the+speed+of+a+P300-based+brain-computer+interface%5BTitle%5D)+AND+%22IEEE+Transactions+on+Rehabilitation+Engineering%22%5BJournal%5D)">The mental prosthesis: assessing the speed of a P300-based brain-computer interface.</a> IEEE Transactions on Rehabilitation Engineering. 8 (2), 174-179 (2000).</li>
<li>Höhne, J., Schreuder, M., Blankertz, B., Tangermann, M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+novel+9-class+auditory+ERP+paradigm+driving+a+predictive+text+entry+system%5BTitle%5D)+AND+%22Frontiers+in+Neuroscience%22%5BJournal%5D)">A novel 9-class auditory ERP paradigm driving a predictive text entry system.</a> Frontiers in Neuroscience. 5, 99(2011).</li>
<li>Acqualagna, L., Treder, M. S., Blankertz, B. Chroma Speller: Isotropic visual stimuli for truly gaze-independent spelling. 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER), , (2013).</li>
<li>Townsend, G., LaPallo, B. K., Boulay, C. B., Krusienski, D. J., Frye, G. E., Hauser, C. K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+novel+P300-based+brain-computer+interface+stimulus+presentation+paradigm%3A+moving+beyond+rows+and+columns%5BTitle%5D)+AND+%22Clinical+Neurophysiology%22%5BJournal%5D)">A novel P300-based brain-computer interface stimulus presentation paradigm: moving beyond rows and columns.</a> Clinical Neurophysiology. 121 (7), 1109-1120 (2010).</li>
<li>Guger, C., Daban, S., Sellers, E., Holzner, C., Krausz, G., Carabalona, R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((How+many+people+are+able+to+control+a+P300-based+brain-computer+interface+%28BCI%29%5BTitle%5D)+AND+%22Neuroscience+Letters%22%5BJournal%5D)">How many people are able to control a P300-based brain-computer interface (BCI).</a> Neuroscience Letters. 462 (1), 94-98 (2009).</li>
<li>Mowla, M. R., Gonzalez-Morales, J. D., Rico-Martinez, J., Ulichnie, D. A., Thompson, D. E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+comparison+of+classification+techniques+to+predict+Brain-computer+interfaces+accuracy+using+classifier-based+latency+estimation%5BTitle%5D)+AND+%22Brain+Science%22%5BJournal%5D)">A comparison of classification techniques to predict Brain-computer interfaces accuracy using classifier-based latency estimation.</a> Brain Science. 10 (10), 734(2020).</li>
<li>Thompson, D. E., Warschausky, S., Huggins, J. E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Classifier-based+latency+estimation%3A+a+novel+way+to+estimate+and+predict+BCI+accuracy%5BTitle%5D)+AND+%22Journal+of+Neural+Engineering%22%5BJournal%5D)">Classifier-based latency estimation: a novel way to estimate and predict BCI accuracy.</a> Journal of Neural Engineering. 10 (1), 016006(2012).</li>
<li>Thompson, D. E., Gruis, K. L., Huggins, J. E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+plug-and-play+brain-computer+interface+to+operate+commercial+assistive+technology%5BTitle%5D)+AND+%22Disability+and+Rehabilitation%3A+Assistive+Technology%22%5BJournal%5D)">A plug-and-play brain-computer interface to operate commercial assistive technology.</a> Disability and Rehabilitation: Assistive Technology. 9 (2), 144-150 (2014).</li>
<li>Korczowski, L., Ostaschenko, E., Andreev, A., Cattan, G., Coelho Rodrigues, P. L., Gautheret, V., Congedo, M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((Brain+Invaders+calibration-less+P300-based+BCI+using+dry+EEG+electrodes+Dataset+%28bi2014a%29+%5BData+set%5D%5BTitle%5D)+AND+%22Zenodo%22%5BJournal%5D)">Brain Invaders calibration-less P300-based BCI using dry EEG electrodes Dataset (bi2014a) [Data set].</a> Zenodo. , (2019).</li>
<li>Krusienski, D. J., Sellers, E. W., Cabestaing, F., Bayoudh, S., McFarland, D. J., Vaughan, T. M., Wolpaw, J. R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/pubmed?term=((A+comparison+of+classification+techniques+for+the+P300+Speller%5BTitle%5D)+AND+%22Journal+of+Neural+Engineering%22%5BJournal%5D)">A comparison of classification techniques for the P300 Speller.</a> Journal of Neural Engineering. 3 (4), 299-305 (2006).</li>
</ol>

All authors declare they do not have any conflicts of interest.

This article outlined a method for estimating BCI accuracy using a small P300 dataset. Here, the current protocol was developed based on the &#34;bi2014a&#34; dataset, although the efficacy of the protocol was confirmed on two different datasets. To successfully implement this technique, it is crucial to establish certain variables, such as the epoch window for the original data, the window for time shifting, the down-sampling ratio, and the size of both the training and testing datasets. These variables are determined b...

Brain-computer interfaces (BCIs) are a noninvasive technology that allows individuals to communicate through machines directly without regard for physical limitations imposed by the body. BCI can be utilized as an assistive device operated directly by the brain. BCI uses the brain activity of a user to determine if the user intends to choose a certain key (letter, number, or symbol) displayed on the screen1. In a typical computer system, a user physically presses the intended key on a keyboard. However, in a BCI system with a visual display, the user needs to focus on the desired key. Then, BCI will select the intended key by analyzing the measured brain signals1. The activity of the brain can be measured using various techniques. Though there are competing BCIs technologies, electroencephalogram (EEG) is considered a leading technique due to its noninvasive nature, high temporal resolution, reliability, and relatively low cost2.
Applications of BCI include communication, device control, and also entertainment3,4,5,6. One of the most active BCI application areas is the P300 speller, which was introduced by Farwell and Donchin7. The P300 is an event-related potential (ERP) produced in response to the recognition of a rare but relevant stimulus8. When a person recognizes their target stimulus, they automatically produce a P300. The P300 is an effective signal for a BCI because it conveys the participant's recognition of the target event without requiring an outward response9.
The P300 BCI has attracted researchers from computer science, electrical engineering, psychology, human factors, and various other disciplines. Advances have been made in signal processing, classification algorithms, user interfaces, stimulation schemes, and many other areas10,11,12,13,14,15. However, regardless of the research area, the common thread in all of this research is the necessity of measuring the BCI system performance. This task typically requires the generation of a test data set. This necessity is not limited to research; eventual clinical application as an assistive technology will likely require individual validation sets for each end user to ensure the system can generate reliable communication.
Despite the considerable research applied toward the P300 BCI, the systems are still quite slow. While the majority of people are able to use a P300 BCI16, most P300 Spellers produce text on the order of 1-5 characters per minute. Unfortunately, this slow speed means that generating test data sets requires substantial time and effort for participants, experimenters, and eventual end users. Measuring BCI system accuracy is a binomial parameter estimation problem, and many characters of data are necessary for a good estimate.
To estimate the presence or absence of the P300 ERP, most classifiers use a binary classification model, which involves assigning a binary label (e.g., "presence" or "absence") to each trial or epoch of EEG data. The general equation used by most classifiers can be expressed as:
<img alt="Machine learning regression formula: ŷ(x) = wᵀ·f(x) + b, linear prediction model equation." src="/files/ftp_upload/64959/64959eq01.jpg" style="margin: auto;" data-altupdatedat="1788304762000" data-alt="Equation 1">
where <img alt="static equilibrium; ΣFx=0; free body diagram; forces balance; physics; mechanics principle" src="/files/ftp_upload/64959/64959eq02.jpg" style="margin: auto;" data-altupdatedat="1788304762000" data-alt="Equation 2"> is called the classifier's score, which represents the probability of the P300 response being present, x is the feature vector extracted from the EEG signal, and b is a bias term17. The function f is a decision function that maps the input data to the output label, and is learned from a set of labeled training data using a supervised learning algorithm17. During training, the classifier is trained on a labeled dataset of EEG signals, where each signal is labeled as either having a P300 response or not. The weight vector and bias term are optimized to minimize the error between the predicted output of the classifier and the true label of the EEG signal. Once the classifier is trained, it can be used to predict the presence of the P300 response in new EEG signals.
Different classifiers can use different decision functions, such as linear discriminant analysis (LDA), stepwise linear discriminant analysis (SWLDA), least squares (LS), logistic regression, support vector machines (SVM), or neural networks (NNs). The least squares classifier is a linear classifier that minimizes the sum of squared errors between the predicted class labels and the true class labels. This classifier predicts the class label of a new test sample using the following equation:
<img alt="Linear classifier equation: ŷ(x) = sign(ẅ*x), mathematical formula, machine learning concept." src="/files/ftp_upload/64959/64959eq03.jpg" style="margin: auto;" data-altupdatedat="1788304762000" data-alt="Equation 3">    (1)
where the sign function returns +1 if the product is positive and -1 if it is negative, and the weight vector <img alt="Chromatography column system; protein purification; diagram; data analysis; separation process." src="/files/ftp_upload/64959/64959eq04.jpg" style="margin: auto;" data-altupdatedat="1788304762000" data-alt="Equation 4"> is obtained from the feature set of the training data, (x) and class labels (y) using the below equation:
<img alt="Linear regression formula; \(W = (X^TX)^{-1}X^Ty\); math equation for parameter estimation." src="/files/ftp_upload/64959/64959eq05.jpg" style="margin: auto;" data-altupdatedat="1788304762000" data-alt="Equation 5">    (2)
In earlier research, we argued that Classifier-Based Latency Estimation (CBLE) can be used to estimate BCI accuracy17,18,19. CBLE is a strategy for evaluating latency variation by exploiting the classifier's temporal sensitivity18. While the conventional approach to P300 classification involves using a single time window that is synchronized with each stimulus presentation, the CBLE method involves creating multiple time-shifted copies of the post-stimulus epochs. Then it detects the time shift that results in the maximum score in order to estimate the latency of the P300 response17,18. Here, this work presents a protocol that estimates BCI performance from a small dataset using CBLE. As a representative analysis, the number of characters is varied to make predictions of the overall performance of an individual. For both example datasets, the root mean square error (RMSE) for vCBLE and actual BCI accuracy were computed. The results indicate that the RMSE from vCBLE predictions, using its fitted data, was consistently lower than the accuracy derived from 1 to 7 tested characters.
We developed a Graphical User Interface (GUI) called "CBLE Performance Estimation" for the implementation of the proposed methodology. The example code is also provided (Supplementary Coding File 1) that operates on the MATLAB platform. The example code performs all of the steps applied in the GUI, but the steps are provided to assist the reader with adapting to a new dataset. This code employs a publicly available dataset "Brain Invaders calibration-less P300-based BCI using dry EEG electrodes Dataset (bi2014a)" to evaluate the proposed method20. Participants played up to three game sessions of Brain Invaders, each session having 9 levels of the game. The data collection continued until all levels were completed or the participant lost all control over the BCI system. The Brain Invaders interface included 36 symbols that flashed in 12 groups of six aliens. According to the Brain Invaders P300 paradigm, a repetition was created by 12 flashes, one for each group. Out of these 12 flashes, two flashes contained the Target symbol (known as Target flashes), while the remaining 10 flashes did not contain the Target symbol (known as non-Target flashes). More information on this paradigm can be found in the original reference20.
The CBLE approach was also implemented on a Michigan dataset, which contained data from 40 participants18,19. Here, the data of eight participants had to be discarded because their tasks were incomplete. The whole study required three visits from each participant. On the first day, each participant typed a 19-character training sentence, followed by three 23-character testing sentences on Days 1, 2, and 3. In this example, the keyboard included 36 characters which were grouped into six rows and six columns. Each row or column was flashed for 31.25 milliseconds with an interval of 125 milliseconds between flashes. Between characters, a 3.5 s pause was provided.
Figure 1 shows the block diagram of the proposed method. The detailed procedure is described in the protocol section.

<table><tbody><tr><td>MATLAB 2021</td><td>Matlab</td><td>N/A</td><td>Any recent MATLAB version can be used.</td></tr></tbody></table>

p300-based brain-computer interface speller performance estimation with classifier-based latency estimation

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Performance estimation is a necessary step in the development and validation of Brain-Computer Interface (BCI) systems. Unfortunately, even modern BCI systems are slow, making collecting sufficient data for validation a time-consuming task for end users and experimenters alike. Yet without sufficient data, the random variation in performance can lead to false inferences about how well a BCI is working for a particular user. For example, P300 spellers commonly operate around 1-5 characters per minute. To estimate accuracy with a 5% resolution requires 20 characters (4-20 min). Despite this time investment, the confidence bounds for accuracy from 20 characters can be as much as &plusmn;23% depending on observed accuracy. A previously published method, Classifier-Based Latency Estimation (CBLE), was shown to be highly correlated with BCI accuracy. This work presents a protocol for using CBLE to predict a user's P300 speller accuracy from relatively few characters (~3-8) of typing data. The resulting confidence bounds are tighter than those produced by traditional methods. The method can thus be used to estimate BCI performance more quickly and/or more accurately.

The proposed protocol has been tested on two different datasets: "BrainInvaders" and the Michigan dataset. These datasets are already introduced briefly in the Introduction section. The parameters used for this two datasets are mentioned in Table 1. Figures 2-4 depict the findings obtained using the "BrainInvaders" dataset, whereas Figures 5-7 demonstrate the results achieved fr...

This article presents a method for estimating same-day P300 speller Brain-Computer Interface (BCI) accuracy using a small testing dataset.

Performance estimation is a necessary step in the development and validation of Brain-Computer Interface (BCI) systems. Unfortunately, even modern BCI ...

Measuring performance is crucial for any research or clinical application involving brain computer interfaces. CBLE helps evaluate the effectiveness of a system for any particular user. CBLE can be used to predict the user's P300 Speller accuracy from just three to eight characters of data.To begin, install the CBLE performance estimation graphical user interface. Open MATLAB and change the current directory to the graphical user interface folder. Click on the Apps tab, select My apps, and choose CBLE Performance Estimation.In the dropdown menu, click Select dataset format and choose the desired option. Next, click the Select input folder button to choose the directory for the EEG dataset. In the number of participants text box, enter the number of participants for the estimation.If using Brain Invader data, specify the sampling rate of the dataset. Choose a decimation value to downs sample the data set to approximately 20 hertz. Specify the time window for the classification in milliseconds.Then define the shift window for CBLE in milliseconds. Once done, click the Set parameters button to set analysis parameters. To split the data set, select the number of targets for the trainin

p300-based-brain-computer-interface-speller-performance-estimation

Research

JoVE Journal

Neuroscience

Transcranial direct current stimulation (tDCS) over the cerebellum exerts a remote effect on the prefrontal cortex, which can modulate cognition and performance. This was demonstrated using two information-processing tasks of varying complexity, whereby only cathodal tDCS improved performance when the task was difficult, but not easy.

Modulating Cognition Using Transcranial Direct Current Stimulation of the Cerebellum

With this experiment, one might be able to detect consciousness in people with disorders of consciousness. Furthermore, the approach can create a simple communication channel that enables people to give simple YES/NO answers to questions.

Assessment and Communication for People with Disorders of Consciousness

This paper discusses how to build a brain-computer interface by relying on consumer-grade equipment and steady-state visually evoked potentials. For this, a single-channel electroencephalograph exploiting dry electrodes was integrated with augmented reality glasses for stimuli presentation and output data visualization. The final system was non-invasive, wearable, and portable.

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Motor imagery in a virtual reality environment has wide applications in brain-computer interface systems. This manuscript outlines the use of personalized digital avatars that resemble the participants performing movements imagined by the participant in a virtual reality environment to enhance immersion and a sense of body ownership.

Motor Imagery Performance Through Embodied Digital Twins in a Virtual Reality-Enabled Brain-Computer Interface Environment

The study introduces a training-testing paradigm to investigate old/new effects of event-related potentials in confident and doubtful prosodic scenarios. Data reveals an enhanced late positive component between 400-850 ms at Pz and other electrodes. This pipeline can explore factors beyond speech prosody and their influence on cue-binding target identification.

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

This study introduces a brain-computer interface (BCI) system for stroke patients, which combines electroencephalography and electrooculography signals to control an upper limb robotic hand, enhancing daily activities. The evaluation used the Berlin Bimanual Test for Stroke (BeBiTS).

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

This study presents a standardized and reproducible protocol for implementing the Spatial-Temporal-Frequency EEG analysis tool (STFEEG) for motor imagery EEG decoding, incorporating configurable spatial-temporal-frequency segmentation, Common Spatial Patterns (CSP)-based feature extraction, multiple classification algorithms, and visualization capabilities.

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces

A procedure is described for manipulating the activity of cerebral cortical pyramidal neurons optogenetically while the electroencephalogram, electromyogram, and cerebral lactate concentration are monitored. Experimental recordings are performed on cable-tethered mice while they undergo spontaneous sleep/wake cycles. Optogenetic equipment is assembled in our laboratory; recording equipment is commercially available.

Simultaneous Electroencephalography, Real-time Measurement of Lactate Concentration and Optogenetic Manipulation of Neuronal Activity in the Rodent Cerebral Cortex

A novel low-cost human-machine interface for interactive post-stroke balance rehabilitation system is presented in this article. The system integrates off-the-shelf low-cost sensors towards volitionally driven electrotherapy paradigm. The proof-of-concept software interface is demonstrated on healthy volunteers.

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

This article provides a detailed description on the fabrication process of a high contact-density flat interface nerve electrode (FINE). This electrode is optimized for recording and stimulating neural activity selectively within peripheral nerves.

Fabrication of High Contact-Density, Flat-Interface Nerve Electrodes for Recording and Stimulation Applications

Lernen Sie die CBLE-Methode zur Leistungsschätzung von P300-Brain-Computer-Schnittstellen mit minimalem Datensatz. Diese Technik ermöglicht präzise Vorhersagen der Nutzergenauigkeit für Echtzeitanwendungen.

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Weitere Videos entdecken