Decoding the visual attention of an individual from electroencephalographic signals

Abstract

A method for determining the focus of the visual attention of an individual from electroencephalographic signals. At least one visual stimulus to be displayed is generated from at least one graphical object, a visual stimulus being an animated graphical object obtained by applying to a graphical object a temporal succession of elementary transformations that is temporally parameterized by a corresponding modulation signal. From a plurality of electroencephalographic signals produced by the individual focusing his visual attention to one of the visual stimuli, a modulation signal is reconstructed. A visual stimulus corresponding to the modulation signal for which the degree of statistical dependence with the reconstructed modulation signal is higher than a first threshold is identified.

What is claimed is: 
     
         1 . A computer-implemented method comprising;
 generating a plurality of visual stimuli using a plurality of graphical objects and a plurality of modulation signals;   presenting the plurality of visual stimuli in a display of a computation device to a user;   recording a first plurality of electroencephalographic signals produced by the user while the user is paying attention to the displayed plurality of visual stimuli;   in response to detecting ambiguity in an identification of two or more visual stimuli of the plurality of visual stimuli using the modulation signal and the plurality of electroencephalographic signals, performing operations comprising:   modifying an order of appearance of the plurality of visual stimuli to more frequently display the two or more visual stimuli;   recording a second plurality of electroencephalographic signals produced by the user; and   in response to identifying one visual stimulus of the two visual stimuli using the second plurality of electroencephalographic signals and the plurality of modulation signals, triggering one or more operations of the computational device.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 reconstructing a modulation signal from the plurality of electroencephalographic signals in order to obtain a reconstructed modulation signal;   computing a degree of statistical dependence between the reconstructed modulation signal and each modulation signal of the plurality of modulation signals;   searching, among the plurality of modulation signals, for a modulation signal for which a degree of statistical dependence with the reconstructed modulation signal is maximal; and   identifying a visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is maximal.   
     
     
         3 . The computer-implemented method of  claim 1 , wherein the plurality of modulation signals are composed so that an overall degree of statistical dependence determined in a domain, for all pairs of the plurality of modulation signals corresponding to two separate visual stimuli, is lower than a second threshold. 
     
     
         4 . The computer-implemented method of  claim 3 , wherein the domain is a time domain. 
     
     
         5 . The computer-implemented method of  claim 3 , wherein the domain is a frequency domain. 
     
     
         6 . The computer-implemented method of  claim 2 , wherein the reconstruction is carried out by applying a reconstruction model to the plurality of electroencephalographic signals. 
     
     
         7 . The computer-implemented method of  claim 6 ,
 wherein the reconstruction model comprises a plurality of parameters of combinations of electroencephalographic signals, and   wherein the method further comprises determining values of parameters of the plurality of parameters of the combinations of electroencephalographic signals in an initial learning phase.   
     
     
         8 . A system comprising:
 at least one processor; and   at least one memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising;   generating a plurality of visual stimuli using a plurality of graphical objects and a plurality of modulation signals;   presenting the plurality of visual stimuli in a display of a computation device to a user;   recording a first plurality of electroencephalographic signals produced by the user while the user is paying attention to the displayed plurality of visual stimuli;   in response to detecting ambiguity in an identification of two or more visual stimuli of the plurality of visual stimuli using the modulation signal and the plurality of electroencephalographic signals, performing operations comprising:   modifying an order of appearance of the plurality of visual stimuli to more frequently display the two or more visual stimuli;   recording a second plurality of electroencephalographic signals produced by the user; and   in response to identifying one visual stimulus of the two visual stimuli using the second plurality of electroencephalographic signals and the plurality of modulation signals, triggering one or more operations of the computational device.   
     
     
         9 . The computing apparatus of  claim 8 , wherein the operations further comprise:
 reconstructing a modulation signal from the plurality of electroencephalographic signals in order to obtain a reconstructed modulation signal;   computing a degree of statistical dependence between the reconstructed modulation signal and each modulation signal of the plurality of modulation signals;   searching, among the plurality of modulation signals, for a modulation signal for which a degree of statistical dependence with the reconstructed modulation signal is maximal; and   identifying a visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is maximal.   
     
     
         10 . The computing apparatus of  claim 8 , wherein the plurality of modulation signals are composed so that an overall degree of statistical dependence determined in a domain, for all pairs of the plurality of modulation signals corresponding to two separate visual stimuli, is lower than a second threshold. 
     
     
         11 . The computing apparatus of  claim 10 , wherein the domain is a time domain. 
     
     
         12 . The computing apparatus of  claim 10 , wherein the domain is a frequency domain. 
     
     
         13 . The computing apparatus of  claim 9 , wherein the reconstruction is carried out by applying a reconstruction model to the plurality of electroencephalographic signals. 
     
     
         14 . The computing apparatus of  claim 13 ,
 wherein the reconstruction model comprises a plurality of parameters of combinations of electroencephalographic signals, and   wherein the method further comprises determining values of parameters of the plurality of parameters of the combinations of electroencephalographic signals in an initial learning phase.   
     
     
         15 . A non-transitory computer-readable storage medium storing computer-executable instructions, that when executed by a computer, cause the computer to perform operations comprising;
 generating a plurality of visual stimuli using a plurality of graphical objects and a plurality of modulation signals;   presenting the plurality of visual stimuli in a display of a computation device to a user;   recording a first plurality of electroencephalographic signals produced by the user while the user is paying attention to the displayed plurality of visual stimuli;   in response to detecting ambiguity in an identification of two or more visual stimuli of the plurality of visual stimuli using the modulation signal and the plurality of electroencephalographic signals, performing operations comprising:   modifying an order of appearance of the plurality of visual stimuli to more frequently display the two or more visual stimuli;   recording a second plurality of electroencephalographic signals produced by the user; and   in response to identifying one visual stimulus of the two visual stimuli using the second plurality of electroencephalographic signals and the plurality of modulation signals, triggering one or more operations of the computational device.   
     
     
         16 . The non-transitory computer-readable storage medium of  claim 15 , wherein the operations further comprise:
 reconstructing a modulation signal from the plurality of electroencephalographic signals in order to obtain a reconstructed modulation signal;   computing a degree of statistical dependence between the reconstructed modulation signal and each modulation signal of the plurality of modulation signals;   searching, among the plurality of modulation signals, for a modulation signal for which a degree of statistical dependence with the reconstructed modulation signal is maximal; and   identifying a visual stimulus corresponding to a modulation signal for which the degree of statistical dependence is maximal.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 15 , wherein the plurality of modulation signals are composed so that an overall degree of statistical dependence determined in a domain, for all pairs of the plurality of modulation signals corresponding to two separate visual stimuli, is lower than a second threshold. 
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the domain is a time domain. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the domain is a frequency domain. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 16 , wherein the reconstruction is carried out by applying a reconstruction model to the plurality of electroencephalographic signals.