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

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

detecting bio-signals from a bio-signal detector, the bio-signals including at least electroencephalograph (EEG) signals from a subject;

using a processing device, transforming the electroencephalograph signals into a plurality of different representations, including separating the electroencephalograph signals into different epochs and generating representations of the electroencephalograph signal epochs in a plurality of different frequency domain representations, a plurality of different temporal domain representations and a plurality of different spatial domain representations;

detecting values of a plurality of different properties of each of the plurality of different frequency domain representations, plurality of different temporal domain representations and plurality of different spatial domain representations; and

applying a mental state detection algorithm to the detected values of the properties in order to classify whether the electroencephalograph signals indicate the presence of a predetermined mental state of the subject.

2. The method according to claim 1 , wherein the different frequency domain representations are obtained by dividing each electroencephalograph signal epoch into distinguishable frequency bands.

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

detecting bio-signals from a bio-signal detector, the bio-signals including at least electroencephalograph (EEG) signals from a subject;

using a processing device, transforming the electroencephalograph signals into a plurality of different representations, including separating the bio-signals into different epochs, generating representations of the electroencephalograph signal epochs into a plurality of different domains, the different domains including different temporal domain representations, wherein the different temporal domain representations are obtained by dividing each electroencephalograph signal epoch into a plurality of time segments;

detecting values of properties of the transformed representations; and

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

4. The method according to claim 3 , wherein the plurality of time segments in each epoch are temporally overlapping.

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

detecting bio-signals from a bio-signal detector, the bio-signals including at least electroencephalograph (EEG) signals from a subject;

using a processing device, transforming the electroencephalograph signals into a plurality of different representations, including separating the electroencephalograph signals into different epochs, generating representations of the electroencephalograph signal epochs into a plurality of different domains, the different domains including different spatial domain representations, wherein the different spatial domain representations are obtained by dividing each electroencephalograph signal epoch into a plurality of spatially distinguishable channels;

detecting values of properties of the transformed representations; and

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

6. The method according to claim 5 , wherein each channel is derived from a different bio-signal detector.

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

8. The method according to claim 7 , wherein one or more than one property comprises signal power of one or more than one electroencephalograph signal representations.

9. The method according to claim 7 , wherein one or more than one property comprises signal power of one or more than one spatially distinguishable channels.

10. The method according to claim 7 , wherein one or more than one property comprises an increase in signal power of one or more than one electroencephalograph signal representations.

11. The method according to claim 7 , wherein one or more than one property comprises increase in signal power of one or more than one spatially distinguishable channels.

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

13. The method according to claim 12 , wherein at least coherence or correlation are detected between different electroencephalograph signal representations.

14. The method according to claim 13 , wherein one or more than one property comprises the correlation or coherence between signal power in different spatially distinguishable channels.

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

detecting bio-signals from a bio-signal detector, the bio-signals including at least electroencephalograph (EEG) signals from a subject;

using a processing device, transforming the electroencephalograph signals into a plurality of different representations,

detecting values of properties of the transformed representation, including detecting values of properties between different representations, wherein the properties include correlation or coherence between increases in signal power in different frequency bands; and

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

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

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

evaluating the detected values of the properties of the electroencephalograph signal representations; and

comparing results of the evaluation to a signature defining a plurality of distinctive characteristics of selected properties of the electroencephalograph signal representations corresponding to the predetermined mental state.