App details
- App market
- >
- c-VEP Speller
c-VEP Speller
A code-modulated visual evoked potential (c-VEP) speller
This app provides a BCI speller based on code-modulated visual evoked potential (c-VEP). The use of c-VEP as control signals is a recent but promising alternative to achieve reliable, high-speed BCIs for communication and control. This paradigm generally allows obtaining accuracies greater than 90% with a very short calibration of only 30 secs. More information on paradigm and signal processing can be found in: Martínez-Cagigal, Víctor, et al. "Brain–computer interfaces based on code-modulated visual evoked potentials (c-VEP): a literature review." Journal of Neural Engineering (2021).
Details
A c-VEP Speller
What is the basis of this paradigm?
Relevant functionalities of the “c-VEP Speller” app
Run Settings:
- The app has two functioning modes: “Train” and “Online”. Use “Train” to record the data for calibrating the system. Use “Online” when you already has a decoding model to select speller commands freely.
- The number of trials and the number of cycles can be configured for the “Train” mode. See the recommendations section below to know more.
- This app does not implement an early stopping approach, so it is required to specify the number of cycles per trial for the “Online” mode.
- The app allows you to specify the presentation rate of the m-sequence. Use 60 Hz if you are using a standard monitor, read the recommendations section to know more.
Timings:
- The app allows you to set the pre- and post-run durations.
Colors:
- The colors functionality allows you to use different colors for the GUI.
Background:
- This feature allows you to personalize your background with a choice between a solid color or a realistic scene. Simply upload an image from your gallery to set it as your background.
Encoding and matrix:
- This app supports the use of m-sequences or burst codes.
- Configure the number of commands in online mode as desired. To ensure that all commands are correctly encoded with the selected parameters, press “Update encoding” to verify the encoding assigned to each command.
Stimuli:
- Select the stimulus design for each event present in the stimulation codes. Three default designs are provided: plain, checkerboard, and grating.
- Customize the stimulus design associated with each sequence event by clicking on the event button and selecting any color or image file.
Model training:
- Use the button “Train model” to train the decoding model. Circular-shifting and bit-wise reconstruction (BWR) approaches are supported.
- Use a filter bank to improve the decoding accuracy for 120 Hz monitor rates!
Recommendations
C-VEPs are exogenous signals generated naturally by our brains in response to stimuli. For that reason, c-VEP-based BCIs do not require users to be trained, but just a small calibration. In calibration stage, user is asked to pay attention to a flickering command encoded with the original m-sequence. We recommend to user, at least, 100 entire cycles (i.e., a full stimulation of the m-sequence) to train the model. That is, two runs of 5 trials each, in which trials are composed of 10 cycles. It is important to avoid blinking when trials are being displayed. Users can freely blink in the inter-trial time window.
If your monitor is capable to refresh at 120 Hz, we recommend using a “Target FPS (Hz)” that matches the monitor refresh rate. Imagine that you are using a 63-bit m-sequence. For a 60 Hz presentation rate, each cycle will last 1.05 s (i.e., 63/60). You can reduce that duration by half using 120 Hz, lasting 0.525 s (i.e., 63/120).
If you are using a 120 Hz presentation rate, we recommend you use more than a single filter. For instance, a filter bank composed of 3 IIR filters: (1, 60), (12, 60) and (30, 60) usually gives good results.
Learn more
If you want to know more about the paradigm, the signal processing pipeline or the state-of-the-art methods that are used in c-VEP-based BCIs, we recommend to read the following paper: Martínez-Cagigal, Víctor, et al. "Brain–computer interfaces based on code-modulated visual evoked potentials (c-VEP): a literature review." Journal of Neural Engineering (2021).
Latest Version
Flexible c-VEP Speller: supports multiple sequences, stimulus designs, and decoding algorithms.
Previous Versions
Adaptation to v2025 (RHEA)
Previous Versions
Introduced parameters for adjusting color opacity and setting an image as the background.
Previous Versions
Minor fix to work with configurations built in other computers
Previous Versions
Improved exception handling. Now users can also chose if artifact rejection must be applied in calibration.
Previous Versions
Improved the method to assign lags to commands.
Previous Versions
Minor fix
Previous Versions
Adaptation to v2024 (KRONOS): - Changed from PyQt5 to PySide6 - Now the app can save all recored signals (not just the EEG) - The app detects several monitors and warns user if monitor refresh rate is not the same
Previous Versions
Improved EEG stream detection for streams with invalid lsl_type.
Previous Versions
Updated encoded visualization
Previous Versions
Fixed a bug where a call to a (now) obsolete PyQt5 function was done
Previous Versions
Fixed a bug where a call to a (now) obsolete PyQt5 function was done
Previous Versions
Updated TCPClient in Unity
Previous Versions
Fixed a bug where an additional trial was displayed in training.
Previous Versions
Initial "cvep_speller" app for MEDUSA Platform v2022.0. This app implements a c-VEP-based BCI speller that uses the circular-shifting paradigm. Currently, only binary m-sequences are supported. Signal processing was implemented following the common "reference method" for circular shifting (i.e., CCA + correlation analysis).
Definitely give this one a try if you're looking for practical BCI communication! It's not hard to get 100% accuracy with less than 1 minute of calibration =)
Edit functionalities
Please, use the editor below to modify the functionalities of your app
Edit tutorial
Please, use the editor below to modify the tutorial of your app
Add a review
Rate this app