Method and apparatus for automatically determining somatic state

• US 5,601,090 A
• Filed: 07/12/1994
• Issued: 02/11/1997
• Est. Priority Date: 07/12/1994
• Status: Expired due to Term

• Current Assignee: Brain Functions Laboratory, Inc.
• Original Assignee: Brain Functions Laboratory, Inc.
• Inventors: Musha, Toshimitsu
• Primary Examiner(s): Sykes, Angela D.
• Assistant Examiner(s): HUANG, STEPHEN D
• Application Number:
  US08/274,196
• Time in Patent Office: 945 Days
• Field of Search: 128/731, 128/732, 128/733
• US Class Current: 600/544
• 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 5/375 using biofeedback
• CPC Class Codes: A61B 5/378 Visual stimuli
• CPC Class Codes: A61B 5/38 Acoustic or auditory stimuli
• CPC Class Codes: A61B 5/7257 using Fourier transforms
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 128/925 Neural network

Abstract

An apparatus and a method for automatically determining the present somatic state of a human subject. The characteristic values of the subject (e.g., scalp potential, muscle potential, heart-rate, eye-movement and frequency of eye blinks, or any combination thereof) are detected and output signals corresponding to the detected characteristic values are produced, amplified and digitized. The Fourier transformation is performed on the output signals. A set of state variables for each selected frequency sub-band of a selected frequency band for each of the output signals is determined. Sets of reference weights and sets of reference biases for a neural network from sets of state reference variables corresponding to known somatic states are formed. Each of the sets of state variables, the sets of reference weights and the sets of reference biases are applied to the neural network to determine present somatic state of the subject. The present somatic state of the subject is displayed.

Claims

1. Apparatus for automatically determining a present somatic state of a human subject, comprising:

a plurality of sensors which produce output signals for detecting characteristic values of said subject when affixed to a body of said subject;

amplifiers for amplifying said output signals;

a processor for;

digitizing said output signals,

performing Fourier transformations on said digitized output signals,

determining a set of state variables for each of a plurality of selected frequency sub-bands of a selected frequency band for each of said output signals,

containing sets of reference weights and sets of reference biases for a neural network, wherein each of said sets of reference weights and each of said sets of reference biases is formed from a set of state reference variables corresponding to a known somatic state, and

applies each of said sets of state variables, and sets of reference weights and said sets of reference biases to said neural network to determine present somatic state of said subject; and

a display for displaying the present somatic state of said subject;

wherein;

the present somatic state is an emotional state selected from the group consisting of joy, anger, happiness, sadness, elation, surprise, disgust and fear.

2. The apparatus of claim 1 wherein said plurality of sensors detects scalp potential at a plurality of points on scalp of said subject.

3. The apparatus of claim 1 wherein said plurality of sensors detect muscle potential at a plurality of points on body of said subject.

4. The apparatus of claim 1 wherein said plurality of sensors detect heart-rate of said subject.

5. The apparatus of claim 1 wherein said plurality of sensors detect eye movements of said subject.

6. The apparatus of claim 1 wherein said plurality of sensors detect frequency of eye blinks of said subject.

7. The apparatus of claim 1 wherein said set of state variables is created from cross-correlating pairs of spectral power values of the sensor output signals.

8. The apparatus of claim 1 wherein said processor means determines said set of state variables from spectral power of each digitized output signal.

9. The apparatus of any one of claims 1 through 8 wherein said selected frequency band is α

band.

10. The apparatus of one of claims 1 through 8 wherein said selected frequency band is α

band.

11. The apparatus of any one of claims 1 through 8 wherein said selected frequency band is γ

band.

12. A method for automatically determining a present somatic state of a human subject, comprising the steps of:

detecting characteristic values of said subject and producing output signals corresponding to said characteristic values;

amplifying said output signals;

digitizing said output signals;

performing Fourier transformations on said digitized output signals;

determining a set of state variables for each of a plurality of selected frequency sub-band of a selected frequency band for each of said output signals;

forming sets of reference weights and sets of reference biases for a neural network from sets of state reference variables corresponding to known somatic states;

applying each of said sets of state variables, said sets of reference weights and said sets of reference biases to said neural network to determine present somatic state of said subject; and

displaying the present somatic state of said subject;

wherein;

the present somatic state is an emotional state selected from the group consisting of joy, anger, happiness, sadness, elation, surprise, disgust and fear.

13. The method of claim 12 wherein said step of detecting characteristic values comprises detecting scalp potential at a plurality of points on scalp of said subject.

14. The method of claim 12 wherein said step of detecting characteristic values comprises detecting muscle potential at a plurality of points on body of said subject.

15. The method of claim 12 wherein said step of detecting characteristic values comprises detecting heart-rate of said subject.

16. The method of claim 12 wherein said step of detecting characteristic values comprises detecting eye movements of said subject.

17. The method of claim 12 wherein said step of detecting characteristic values comprises detecting frequency of eye blinks of said subject.

18. The method of claim 12 wherein said step of determining said set of state variables comprises cross-correlating pairs of spectral power values of the sensor output signals.

19. The method of claim 12 wherein said step of determining said set of state variables comprises determining spectral power of each digitized output signal.

20. The method of any one of claims 12 through 19 wherein said selected frequency band is α

band.

21. The method of any one of claims 12 through 19 wherein said selected frequency band is β

band.

22. The method of any one of claims 12 through 19 wherein said selected frequency band is γ

band.