Brain-computer interface with high-speed eye tracking features

1. An apparatus, comprising:

a display configured to present an interactive environment to a user;

an eye-tracker configured to record eye-movement signals generated by the user;

a neural recording device configured to record neural signals generated by the user;

an interfacing device, operatively coupled to the display, the eye-tracker, and the neural recording device, the interfacing device including:

a memory; and

a processor operatively coupled to the memory and configured to:

receive the eye-movement signals from the eye-tracker, and the neural signals from the neural recording device;

generate and present a stimulus, via the interactive environment, to the user;

determine a pointing control signal based on the eye-movement signals;

determine an action control signal based on the neural signals;

generate a composite set of data by combining a first portion based on the pointing control signal and a second portion based on the action control signal;

provide the composite set of data to a machine learning model to determine a point of focus of the user, based on the composite set of data and

identify an action intended by the user and based on the point of focus of the user.

2. The apparatus of claim 1 , wherein:

the eye-tracker is a video-based eye-tracker.

3. The apparatus of claim 1 , wherein:

the neural signals include electroencephalogram (EEG) signals including at least one of visually evoked potentials, auditory evoked potentials, motor imagery signals, Event Related Potentials (ERP), and brain state dependent signals.

4. The apparatus of claim 1 , wherein the stimulus includes at least one of a visual, an auditory, and a haptic stimulus.

5. The apparatus of claim 1 , wherein the stimulus includes a visual presentation of media via the display, and processor is further configured to define a set of portions of the display, and present the stimulus repeatedly, in one portion from the set of portions of the display, based on the point of focus of the user.

6. The apparatus of claim 1 , wherein the processor is further configured to implement a lag-less filter and a classifier to process the eye-movement signals to determine the pointing control signal.

7. The apparatus of claim 1 , wherein the processor is further configured to implement a dual Kalman filter and a classifier to process the eye-movement signals to determine the pointing control signal.

8. The apparatus of claim 1 , wherein the processor is further configured to:

train a gaze-kinematics model to:

receive a first input associated with parameters of the user, a second input associated with the eye-tracker, and a third input associated with a stimulus from the set of stimuli;

calculate, based on the first input, the second input, and the third input, a set of predicted gaze signals associated with an eye-movement of the user;

identify a set of missing data points in the eye-movement signals;

compute a set of replacement data points to replace the set of missing data points in the eye-movement signals, based on the set of predicted gaze signals calculated using the gaze-kinematics model; and

incorporate the set of replacement data points to replace the set of missing data points and to generate updated eye-movement signals, the first portion being based on the updated eye-movement signals.

9. A non-transitory processor-readable medium storing code representing instructions to be executed by a processor, the instructions comprising code to cause the processor to:

define a set of stimuli that can be presented to a user via an interactive user environment;

present a stimulus from the set of stimuli to the user, via the interactive user environment;

receive, from an eye-tracker a pointing control signal related to an eye-movement of the user and receive, from a neural recording device, an action control signal related to the eye-movement of the user;

generate a composite data set by combining a first portion based on the pointing control signal and a second portion based on the action control signal;

provide the composite data set to a machine learning model to identify a point of focus of the user;

determine, based on the point of focus and the stimulus presented, an action intended by the user; and

implement the action intended by the user via the interactive user environment.

10. The non-transitory processor-readable medium of claim 9 , wherein the code to receive inputs includes code to cause the processor to:

extract, from the action control signal received from the neural recording device, electroencephalogram (EEG) signals generated by the user, the EEG signals including at least one of visually evoked potentials, auditory evoked potentials, motor imagery signals, Event Related Potentials (ERP), and brain state dependent signals, the second portion being based on the EEG signals.

11. The non-transitory processor-readable medium of claim 9 , wherein the code to cause the processor to determine the action intended by the user includes code to cause the processor to:

extract information related to the stimulus from the set of stimuli;

apply a first weight from a set of weights to the point of focus and a second weight from the set of weights to the information related to the presented stimulus, to generate a weighted representation of data; and

generate, based on the weighted representation of data, a prediction of the action intended by the user.

12. The non-transitory processor-readable medium of claim 9 , wherein the code to cause the processor to determine the action intended by the user includes code to cause the processor to:

extract eye-movement signals from the pointing control signal received from the eye-tracker; and

implement a lag-less filter and a classifier to determine the first portion based on the pointing control signal.

13. The non-transitory processor-readable medium of claim 9 , wherein the code to receive inputs includes code to cause the processor to:

train a gaze-kinematics model to:

receive a first input associated with parameters of the user, a second input associated with the eye-tracker, and a third input associated with a stimulus from the set of stimuli;

calculate, based on the first input, the second input, and the third input, a set of predicted gaze signals associated with an eye-movement of the user;

extract eye-movement signals from the pointing control signal received from the eye-tracker;

identify a set of missing data points in the eye-movement signals;

estimate a set of replacement data points to replace the set of missing data points in the eye-movement signals, based on the set of predicted gaze signals calculated using the gaze-kinematics model; and

incorporate the set of replacement data points to replace the set of missing data points to generate updated eye-movement signals, the first portion being based on the updated eye-movement signals.

14. The non-transitory processor-readable medium of claim 9 , wherein the code to receive inputs includes code to cause the processor to:

train a gaze-kinematics model to:

receive a first input associated with parameters of the user, a second input associated with the eye-tracker, and a third input associated with a stimulus from the set of stimuli;

calculate, based on the first input, the second input, and the third input, a set of predicted gaze signals associated with an eye-movement of the user;

extract eye-movement signals from the pointing control signal received from the eye-tracker;

identify artifactual data points in the eye-movement signals;

estimate a set of replacement data points to replace the artifactual data points in the eye-movement signals, based on the set of predicted gaze signals calculated using the gaze-kinematics model; and

incorporate the set of replacement data points to replace the artifactual data points to generate updated eye-movement signals, the first portion being based on the updated eye-movement signals.

15. A method, comprising:

presenting, to a user, a stimulus via an interactive user interface;

receiving, from an eye-tracker, a pointing control signal associated with a eye-movement of the user;

receiving, from a neural recording device, an action control signal associated with the eye-movement of the user;

receiving information related to the stimulus;

generating a composite set of data by combining a first portion based on the pointing control signal and a second portion based on the action control signal;

providing the composite set of data to a machine learning model to identify a point of focus of the user, the point of focus being associated with the stimulus and the eye-movement;

determining, based on the point of focus, an action intended by the user; and

implementing the action via the interactive user interface.

16. The method of claim 15 , wherein the presented stimulus includes a dynamic, visual-stimulus, the method further comprising:

detecting a movement of the dynamic, visual-stimulus;

tracking the movement of the dynamic, visual-stimulus; and

tagging the dynamic, visual-stimulus.

17. The method of claim 15 , further comprising:

extracting eye-movement signals from the pointing control signal received from the eye-tracker; and

applying a lag-less filter to the eye-movement signals to determine the first portion.

18. The method of claim 15 , further comprising:

training a gaze-kinematics model to:

receive a first input associated with parameters of the user, a second input associated with the eye-tracker, and a third input associated with a stimulus from the set of stimuli;

calculate, based on the first input, the second input, and the third input, a set of predicted gaze signals associated with an eye-movement of the user;

extracting eye-movement signals from the pointing control signal received from the eye-tracker;

identifying a set of missing data points in the eye-movement signals;

estimating a set of replacement data points to replace the set of missing data points in the eye-movement signals, based on the set of predicted gaze signals calculated using the gaze-kinematics model; and

incorporating the set of replacement data points to replace the set of missing data points and to generate updated eye-movement signals.

19. The method of claim 15 , wherein the generating the composite set of data includes:

applying a first weight from a set of weights to the pointing control signal to generate the first portion, applying a second weight from the set of weights to the action control signal to generate the second portion, the composite set of data including a weighted representation of the pointing control signal and the action control signal.

20. The method of claim 15 , further comprising:

training a gaze-kinematics model to:

receive a first input associated with parameters of the user, a second input associated with the eye-tracker, and a third input associated with a stimulus from the set of stimuli; and

calculate, based on the first input, the second input, and the third input, a set of predicted gaze signals associated with an eye-movement of the user;

extracting eye-movement signals from the pointing control signal received from the eye-tracker in response to;

computing filtered eye-movement signals, based on the eye-movement signals received from the eye-tracker and the predicted gaze signals calculated by the gaze-kinematics model, the first portion being based on the filtered eye-movement signals.