Method and System for Detecting and Classifying Mental States

Abstract

A method of detecting and classifying mental states, comprising the steps of receiving bio-signals from one or more bio-signal detectors; generating multiple different representations of each bio-signal; determining the value of one or more features of the each bio-signal representation; and comparing the feature values to one or more than one mental state signature, each mental state signature defining reference feature values indicative of a predetermined mental state.

1 . A method of detecting and classifying mental states, comprising the steps of: 
 receiving bio-signals from one or more bio-signal detectors;    generating multiple different representations of each bio-signal;    determining the value of one or more features of the each bio-signal representation; and    comparing the feature values to one or more than one mental state signature, each mental state signature defining reference feature values indicative of a predetermined mental state.    
   
   
       2 . The method according to  claim 1 , wherein the step of generating multiple different representations of each bio-signal comprises the step of dividing the bio-signals into different epochs.  
   
   
       3 . The method according to  claim 2 , wherein the step of generating multiple different representations of each bio-signal 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 time segments in each epoch are temporally overlapping.  
   
   
       8 . The method according to  claim 6 , wherein the time segments in each epoch do not temporally overlap.  
   
   
       9 . 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.  
   
   
       10 . The method according to  claim 9 , wherein each channel is derived from a different bio-signal detector.  
   
   
       11 . The method according to  claim 1 , wherein the step of determining the value of one or more features of the each bio-signal representation comprises determining values of features of individual bio-signal representations.  
   
   
       12 . The method according to  claim 11 , wherein one or more than one feature comprises signal power of one or more than one bio-signal representations.  
   
   
       13  The method according to  claim 11 , wherein one or more than one feature comprises signal power of one or more than one spatially distinguishable channels.  
   
   
       14 . The method according to  claim 11 , wherein one or more than one feature comprises a change in signal power of one or more than one bio-signal representations.  
   
   
       15 . The method according to  claim 11 , wherein one or more than one feature comprises a change in signal power of one or more than one spatially distinguishable channels.  
   
   
       16 . The method according to  claim 1 , wherein the step of determining the value of one or more features of the each bio-signal representation comprises determining values of features between different bio-signal representations.  
   
   
       17 . The method according to  claim 16 , wherein at least coherence or correlation are detected between different bio-signal representations.  
   
   
       18 . The method according to  claim 17 , wherein one or more than one feature comprises the correlation or coherence between signal power in different spatially distinguishable channels.  
   
   
       19 . The method according to  claim 17 , wherein one or more than one feature comprises correlation or coherence between changes in signal power in different frequency bands.  
   
   
       20 . The method according to  claim 1 , wherein the step of determining the value of one or more features of the each bio-signal representation comprises applying one or more transforms to the different bio-signal representations.  
   
   
       21 . The method according to  claim 20 , wherein the one or more transforms comprises any one or more of a Fourier Transform, wavelet transform or other linear or non-linear mathematical transform.  
   
   
       22 . The method according to  claim 1 , wherein the step of comparing the feature values to one or more than one mental state signature comprises: 
 using a neural network to classify whether the feature values are indicative of the presence of a predefined mental state.    
   
   
       23 . The method according to  claim 1 , wherein the step of comparing the feature values to one or more than one mental state signature comprises: 
 performing a distance measure to measure the similarity between the feature values and the reference features values to classify whether the feature values are indicative of the presence of a predefined mental state.    
   
   
       24 . The method according to  claim 1 , wherein the mental state is an emotional state.  
   
   
       25 . The method according to  claim 1 , wherein the mental state results from mental focus on a task, image or other willed experience.  
   
   
       26 . A method of creating a signature for use in a method of detecting and classifying mental states according to  claim 1 , comprising the steps of: 
 eliciting a desired mental state from a user;    determining the features of the bio-signal representations that most significantly indicate the presence of the desired mental state by the user; and    generating the signature from a combination of those features.    
   
   
       27 . A method according to  claim 26 , wherein the step of determining the features of the bio-signal representations that most significantly indicate the presence of the desired mental state by the user comprises the step of: 
 performing any one or more of an ANOVA test, a T test, a Discriminant Function analysis, a MANOVA test, a Bonferroni analysis, False Discovery Rate analysis and Dunn Sidack analysis on the bio-signal representation features.    
   
   
       28 . A method according to  claim 26 , wherein the desired mental state is not predefined.  
   
   
       29 . A method according to  claim 26 , and further comprising the step of: 
 using feature values determined when the desired mental state is elicited from one or more users to update the signature for that mental state.    
   
   
       30 . An apparatus for detecting and classifying mental states, comprising: 
 a processor and associated memory device for carrying out a method according to  claim 1 .    
   
   
       31 . A computer program product, tangibly stored on machine readable medium, the product comprising instructions operable to cause a processor to carry out a method according to  claim 1.