Method, system and apparatus for real-time classification of muscle signals from self -selected intentional movements

Abstract

A new method, system and apparatus is provided that enables muscle signals that correspond to muscle contractions to be mapped to one or more functions of an electronic device such as a prosthetic device or gaming apparatus. Muscle signals are classified in real-time from self-selected intentional movements. A self-training protocol allows users to select and label their own muscle contractions, and is operable to automatically determine the discernible and repeatable muscle signals generated by the user. A visual display means is used to provide visual feedback to users illustrating the responsiveness of the system to muscle signals generated by the user.

1 . A method for muscle signal classification characterized by:
 (a) a user moving a device according to intentional movements selected by the user;   (b) recording and compiling the user's muscle signals in association with the selected intentional movements; and   (c) mapping the muscle signals to the selected intentional movements.   
     
     
         2 . The method of  claim 1  characterized by the mapping being accomplished by extracting one or more features of the muscle signals. 
     
     
         3 . The method of  claim 2  characterized by the one or more features of the muscle signals being extracted using a feature extractor. 
     
     
         4 . The method of  claim 2  characterized by the method including the further step of calculating one or more cluster centers in association with the features. 
     
     
         5 . The method of  claim 4  characterized by the method including the step of using the cluster centers to calculate membership values in association with the features, whereby the membership values are used to classify the muscle signals. 
     
     
         6 . The method of  claim 5  characterized by the classification of the muscle signals occurring on a real-time basis. 
     
     
         7 . The method of  claim 4  characterized by the method including the further step of providing means to the user to label the cluster centers according to the selected intentional movements. 
     
     
         8 . The method of  claim 2  characterized by the extraction of the features including calculating natural logarithms of root-mean-square values associated with the muscle signals. 
     
     
         9 . The method of  claim 5  characterized by the cluster centers being calculated using a fuzzy c-means clustering algorithm. 
     
     
         10 . The method of  claim 1  characterized by the device being a prosthesis, a gaming device, a writing apparatus or a computer input device. 
     
     
         11 . The method of  claim 1  characterized by calibrating the device in accordance with the mapped muscle signals. 
     
     
         12 . The method of  claim 1  characterized by the muscle signals being recorded at two or more sites on the body of the user. 
     
     
         13 . A method for muscle signal classification to calibrate a device that is responsive to intentional movements of a user, the method characterized by:
 (a) enabling a user to move the device according to intentional movements selected by the user;   (b) recording and compiling the user's muscle signals in association with the selected intentional movements;   (c) calculating natural logarithms of root-mean-square values associated with the muscle signals to yield features of the muscle signals;   (d) clustering the features using a clustering algorithm, thereby defining one or more cluster centers in association with the features;   (e) calculating membership values by comparing the features and the cluster centers; and   (f) classifying the muscle signals according to the membership values.   
     
     
         14 . A system for muscle signal classification characterized in that the system includes:
 (a) a device operable to record a user's muscle signals in association with one or more intentional movements selected by the user, the device including or being linked to a computer; and   (b) a computer program operable on the computer to compile and classify the muscle signals by:
 (i) recording and compiling the user's muscle signals in association with the selected intentional movements; and 
 (ii) mapping the muscle signals to the selected intentional movements. 
   
     
     
         15 . The system of  claim 14  characterized in that the system includes a feature extractor that is operable to generate features in association with the muscle signals. 
     
     
         16 . The system of  claim 15  characterized in that the features are clustered and the muscle signals are classified according to membership values calculated in relation to cluster centers. 
     
     
         17 . The system of  claim 14  characterized in that the system includes a visual display means that provides cues to the user to perform specific intentional movements selected by the user. 
     
     
         18 . The system of  claim 15  characterized in that the muscle signals are recorded at two or more sites on the body of the user. 
     
     
         19 . The system of  claim 16  characterized in that the muscle signals are classified over a window equal to or less than 0.3 seconds. 
     
     
         20 . The system of  claim 14  characterized in that the system if operable to calibrate the device based on the mapped muscle signals. 
     
     
         21 . A muscle signal activated apparatus characterized in that the apparatus includes:
 (a) a movable portion of the apparatus that is operable to record a user's muscle signals in association with intentional movements;   (b) an electronic device linked to the movable portion, the electronic device being operable to define a calibration mode for enabling the user to calibrate the apparatus, said electronic device being operable to:
 (i) provide cues to the user to perform specific intentional movements selected by the user; 
 (ii) record and compile the user's muscle signals in association with the selected intentional movements, and 
 (iii) map the muscle signals to the selected intentional movements, thereby calibrating the muscle signal activation of the apparatus by the user. 
   
     
     
         22 . The apparatus of  claim 21  characterized in that the electronic device is operable to:
 (a) generate features from the muscles signals using a feature extractor means;   (b) cluster the features thereby defining one or more cluster centers in association with the features;   (c) calculate membership values by comparing the features and the cluster centers; and   (d) classify the muscle signals according to the membership values.   
     
     
         23 . The apparatus as claimed in  claim 22  characterized in that the electronic device includes a controller. 
     
     
         24 . The apparatus as claimed in  claim 23  characterized in that the controller includes a control program that cooperates with the controller to define the operations of the electronic device. 
     
     
         25 . The apparatus of  claim 22  characterized in that the electronic device includes an input means for providing cues to the user, said input means being selected from the group consisting of one or more buttons, a keypad, a touch screen, or a voice recognition system, or any combination thereof. 
     
     
         26 . The apparatus of  claim 22  characterized in that the electronic device includes a feedback means that is operable to enable the user to label the cluster centers according to the selected intentional movements. 
     
     
         27 . A computer program product for mapping muscle signals of a user to intentional movements of a device responsive to intentional movements of the user characterized in that the computer program includes instructions operable on a computer to:
 (a) provide cues to the user to perform specific intentional movements selected by the user;   (b) record and compile the muscle signals in association with the selected intentional movements; and   (c) map the muscle signals to the selected intentional movements, thereby calibrating the muscle signal activation of the device by the user.   
     
     
         28 . The computer program product claimed in  claim 27  characterized in that the computer program further includes instructions operable on the computer to:
 (a) generate features from the muscles signals using a feature extractor means;   (b) cluster the features thereby defining one or more cluster centers in association with the features;   (c) calculate membership values by comparing the features and the cluster centers; and   (d) classify the muscle signals according to the membership values.   
     
     
         29 . The computer program product of  claim 28  characterized in that the computer program further includes instructions operable on the computer to enable the user to label the cluster centers. 
     
     
         30 . The computer program product of  claim 29  characterized in that the computer program further includes instructions operable on the computer to cue the user to perform specific intentional movements corresponding to the labels. 
     
     
         31 . The computer program product of  claim 29  characterized in that the computer program is operable to enable calibration of the device.