Method and system for detecting and classifyng the mental state of a subject

• US 20070060831A1
• Filed: 09/12/2005
• Published: 03/15/2007
• Est. Priority Date: 09/12/2005
• Status: Active Grant

• Current Assignee: Emotiv Systems Pty., Ltd.
• Original Assignee: Emotiv Systems Pty., Ltd.
• Inventors: Thie, Johnson, Delic, Emir, Do, Nam, Pham, Hai, King, William, Le, Tan
• Granted Patent: US 7,865,235 B2
• Time in Patent Office: Days
• 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 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/372 Analysis of electroencephalograms
• 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: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method of detecting and classifying mental states, comprising the steps of: detecting bio-signals from one or more than one bio-signal detector; transforming the bio-signals into one or more than one different representations; detecting values of one or more than one property of the transformed bio-signal representations; and applying one or more than one mental state detection algorithm to the detected properties in order to classify whether the bio-signals indicate the presence of a predetermined response by a subject.

Claims

1. A method of detecting and classifying mental states, comprising the steps of:

detecting bio-signals from one or more than one bio-signal detector;

transforming the bio-signals into one or more different representations;

detecting values of one or more properties of the transformed bio-signal representations; and

applying one or more than one mental state detection algorithm to the detected properties in order to classify whether the bio-signals indicate the presence of a predetermined response by a subject.

2. The method according to claim 1, wherein the step of transforming the bio-signals into a plurality of different representations comprises the step of separating the bio-signals into different epochs.

3. The method according to claim 2, wherein the step of transforming the bio-signals into a plurality of different representations further comprises the step of generating representations of the bio-signal epochs into one or more different domains.

4. The method according to claim 3, wherein each bio-signal epoch is divided into one or more than one of different frequency, temporal and spatial domain representations.

5. The method according to claim 4, wherein the different frequency domain representations are obtained by dividing each bio-signal epoch into distinguishable frequency bands.

6. The method according to claim 4, wherein the different temporal domain representations are obtained by dividing each bio-signal epoch into a plurality of time segments.

7. The method according to claim 6, wherein the plurality of time segments in each epoch are temporally overlapping.

8. The method according to claim 4, wherein the different spatial domain representations are obtained by dividing each bio-signal epoch into a plurality of spatially distinguishable channels.

9. The method according to claim 8, wherein each channel is derived from a different bio-signal detector.

10. The method according to claim 1, wherein the step of detecting values of one or more than one property of the transformed bio-signal representations comprises detecting values of properties of individual bio-signal representations.

11. The method according to claim 10, wherein one or more than one property comprises signal power of one or more than one bio-signal representations.

12. The method according to claim 10, wherein one or more than one property comprises signal power of one or more than one spatially distinguishable channels.

13. The method according to claim 10, wherein one or more than one property comprises an increase in signal power of one or more than one bio-signal representations.

14. The method according to claim 10, wherein one or more than one property comprises increase in signal power of one or more than one spatially distinguishable channels.

15. The method according to claim 1, wherein the step of detecting values of one or more than one property of the transformed bio-signal representations comprises detecting values of properties between different bio-signal representations.

16. The method according to claim 15, wherein at least coherence or correlation are detected between different bio-signal representations.

17. The method according to claim 16, wherein one or more than one property comprises the correlation or coherence between signal power in different spatially distinguishable channels.

18. The method according to claim 16, wherein one or more than one property comprises correlation or coherence between increases in signal power in different frequency bands.

19. The method according to claim 1, wherein the mental state is an emotional state of the subject.

20. The method according to claim 1, wherein the step of applying one or more than one mental state detection algorithm comprises:

evaluating the values of detected properties of the bio-signal representations; and

comparing results of the evaluation to a signature defining one of more distinctive characteristics of selected properties of the bio-signal representations corresponding to the predetermined response.

21. A method of calibrating a signature for use in a method of detecting and classifying mental states according to claim 20, comprising the steps of:

eliciting the predetermined response from the subject;

determining those properties of the bio-signal representations that most significantly indicate the presence of the predetermined response by the subject; and

generating the signature from a combination of those properties.

22. The method according to claim 21, wherein the step of applying one or more than one mental state detection algorithm further comprises performing dimensional reduction on the number of detected values to derive a minimized number of state variables for evaluation.

23. The method according to claim 22, wherein the dimensional reduction is carried out by performing an analysis of variance (ANOVA) test on the detected values.

24. An apparatus for detecting and classifying mental states, comprising:

a) a sensor interface for receiving bio-signals from one or more than one bio-signal detector; and

b) a processing system for applying one or more than one mental state detection algorithm to representations of the bio-signals in order to classify whether the bio-signals indicate the presence of a predetermined response by a subject.