Learning optimization using biofeedback

• US 8,271,077 B1
• Filed: 08/26/2009
• Issued: 09/18/2012
• Est. Priority Date: 08/27/2008
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Rotenberg, Eduard
• Primary Examiner(s): Kahelin, Michael
• Assistant Examiner(s): Messersmith, Eric
• Application Number:
  US12/548,056
• Time in Patent Office: 1,119 Days
• Field of Search: 600/544, 600/545
• US Class Current: 600/545
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/162 Testing reaction times
• CPC Class Codes: A61B 5/168 Evaluating attention deficit, hyperactivity
• CPC Class Codes: A61B 5/375 using biofeedback

Abstract

A system includes a sensor to detect a neuro-physiological state of a student, and a controller to provide a communication if the student is outside a desired neuro-physiological state consistent with a desired learning zone and to provide a lesson intensity control signal as a function of the provided communication and sensed neuro-physiological state.

Claims

1. A system comprising:

a sensor to detect a neuro-physiological state of a student during a lesson;

a controller coupled to receive an output from the sensor to provide a communication if the student is outside a desired neuro-physiological state consistent with a desired learning zone and to provide a lesson intensity control signal as a function of the provided communication and sensed neuro-physiological state; and

a converter to convert the sensed neuro-physiological state of the student to cognitive parameters,

wherein the cognitive parameters are representative of cognitive workload, level of engagement, and alertness and wherein the lesson intensity is regulated using proportional integral control as a function of workload calculated from a sensed neuro-physiological state,

wherein the controller calculates workload as a function of amplitudes at multiple electroencephalograph frequencies, and

wherein the electroencephalograph frequencies include;

α

corresponding to a range 8-12 Hz, β

corresponding to a range of 12-30 Hz, γ

corresponding to a range of 30-100 Hz, θ

corresponding to a range of 4-7 Hz and δ

corresponding to a range 0-4 Hz, and wherein the controller is configured to calculate workload, W(t), according to the following formula;

W(t−

n)=k₁α

(t−

n)+k₂β

(t−

n)+k₃γ

(t−

n)+k₄θ

(t−

n)+k₄δ

(t−

n)+k₅α

(t−

n)/θ

(t−

n)+k₆γ

(t−

n)/α

(t), n=0, 1, 2, . . . , m

2. The system of claim 1 wherein the controller is configured to calculate the lesson intensity value in accordance with:

3. The system of claim 1 wherein the sensor comprises an electroencephalograph.

4. The system of claim 1 wherein the sensor comprises multiple sensors selected from the group consisting of an electroencephalograph, electrocardiograph, galvanic skin response sensor, heart rate variability sensor and pupilometry sensor.

5. The system of claim 1 wherein the controller correlates the cognitive parameters to known patterns of such cognitive parameters to determine whether the student is within the desired learning zone.

6. The system of claim 5 wherein the known patterns are patterns specific to historical performance of the student.

7. The system of claim 1 wherein the communication comprises information on self regulation techniques to improve the neuro-physiological state.

8. The system of claim 7 wherein the controller modifies the lesson intensity as a function of change in neuro-physiological state over time in response to the communication.

9. The system of claim 8 wherein the lesson intensity control signal causes modification of at least one of volume or brightness of the learning environment.

10. The system of claim 8 wherein the lesson intensity control signal causes modification of the difficulty of the learning material presented to the student.

11. A system comprising:

a sensor to provide biosignals representative of a neuro-physiological state of a student;

a converter coupled to the sensor to convert the biosignals to learning zone digital values;

a learning environment for the student responsive to lesson intensity values; and

a controller coupled to the converter to receive learning zone digital values and to provide a communication to the student if the learning zone digital values are indicative of the student being outside a desired neuro-physiological state and to provide lesson intensity values as a function of the provided communication and sensed neuro-physiological state,

wherein the learning zone digital values are representative of cognitive workload, level of engagement, and alertness and wherein the lesson intensity is regulated using proportional integral control as a function of workload calculated from a sensed neuro-physiological state,

wherein the controller calculates workload as a function of amplitudes at multiple electroencephalograph frequencies, and

wherein the electroencephalograph frequencies include;

α

corresponding to a range 8-12 Hz, β

corresponding to a range of 12-30 Hz, γ

corresponding to a range of 30-100 Hz, θ

corresponding to a range of 4-7 Hz and δ

corresponding to a range 0-4 Hz, and wherein the controller is configured to calculate workload, W(t), according to the following formula;

W(t−

n)=k₁α

(t−

n)+k₂β

(t−

n)+k₃γ

(t−

n)+k₄θ

(t−

n)+k₄δ

(t−

n)+k₅α

(t−

n)/θ

(t−

n)+k₆γ

(t−

n)/α

(t), n=0, 1, 2, . . . , m

12. The system of claim 11 wherein the controller provides lesson intensity values as a function of current and historical lesson intensity values.

13. The system of claim 11 wherein the learning environment is a computer controlled learning environment.

14. The system of claim 11 wherein the learning environment is a computer simulation.

15. The system of claim 11 wherein the learning environment is a classroom.

16. The system of claim 11 wherein the sensor comprises multiple sensors selected from the group consisting of an electroencephalograph, electrocardiograph, galvanic skin response sensor, heart rate variability sensor and pupilometry sensor.

17. The system of claim 11 wherein the communication comprises information on self regulation techniques to improve the neuro-physiological state.

18. The system of claim 11 wherein the controller modifies the lesson intensity as a function of change in neuro-physiological state over time in response to the communication.

19. A computer implemented method comprising:

receiving biosignals representative of a neuro-physiological state of a student;

determining a current neuro-physiological state from the received biosignals;

converting the determined neuro-physiological state to cognitive parameters;

providing feedback to the student as a function of the neuro-physiological state;

detecting if the neuro-physiological state of the student has changed following provision of the feedback;

modifying a lesson intensity value as a function of the neuro-physiological state of the student following provision of the feedback; and

providing the modified lesson intensity value to a learning environment,

wherein the cognitive parameters are representative of cognitive workload, level of engagement, and alertness and wherein the lesson intensity is regulated using proportional integral control as a function of workload calculated from a sensed neuro-physiological state,

wherein the controller calculates workload as a function of amplitudes at multiple electroencephalograph frequencies, and

wherein the electroencephalograph frequencies include;

α

corresponding to a range 8-12 Hz, β

corresponding to a range of 12-30 Hz, γ

corresponding to a range of 30-100 Hz, θ

corresponding to a range of 4-7 Hz and δ

corresponding to a range 0-4 Hz, and wherein the controller is configured to calculate workload, W(t), according to the following formula;

W(t−

n)=k₁α

(t−

n)k₂β

(t−

n)+k₃γ

(t−

n)+k₄θ

(t−

n)+k₄δ

(t−

n)+k₅α

(t−

n)/θ

(t−

n)+k₆γ

(t−

n)/α

(t), n=0, 1, 2, . . . , m