Systems and methods for identifying biological structures associated with neuromuscular source signals

Abstract

A system comprising a plurality of neuromuscular sensors, each of which is configured to record a time-series of neuromuscular signals from a surface of a user's body; and at least one computer hardware processor programmed to perform: applying a source separation technique to the time series of neuromuscular signals recorded by the plurality of neuromuscular sensors to obtain a plurality of neuromuscular source signals and corresponding mixing information; providing features, obtained from the plurality of neuromuscular source signals and/or the corresponding mixing information, as input to a trained statistical classifier and obtaining corresponding output; and identifying, based on the output of the trained statistical classifier, and for each of one or more of the plurality of neuromuscular source signals, an associated set of one or more biological structures.

1 . A computer-implemented method, comprising:
 recording a plurality of time series of neuromuscular-signal data from a user's body via a plurality of surface neuromuscular sensors, wherein:
 the plurality of time series of neuromuscular-signal data comprise a mixing of a plurality of neuromuscular source signals; and 
 each of the plurality of neuromuscular source signals corresponds to a different one of a plurality of biological structures; 
   applying a source separation technique to the plurality of time series of neuromuscular-signal data recorded by the plurality of surface neuromuscular sensors to unmix the plurality of neuromuscular source signals from the plurality of time series of neuromuscular-signal data; and   controlling at least one device based, at least in part, on one or more of the unmixed plurality of neuromuscular source signals.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising identifying, for at least one of the unmixed plurality of neuromuscular source signals, an associated biological structure, wherein controlling the device is based, at least in part, on the at least one of the unmixed plurality of neuromuscular source signals having been generated by the associated biological structure. 
     
     
         3 . The computer-implemented method of  claim 2 , wherein identifying the associated biological structure for the at least one of the unmixed plurality of neuromuscular source signals comprises aligning the unmixed plurality of neuromuscular source signals to a plurality of template neuromuscular source signals derived via electrodes inserted into corresponding biological structures. 
     
     
         4 . The computer-implemented method of  claim 2 , wherein the associated biological structure comprises one of:
 a muscle;   a muscle group; or   a motor unit.   
     
     
         5 . The computer-implemented method of  claim 2 , wherein the associated biological structure comprises a muscle fiber. 
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 classifying a first one of the unmixed plurality of neuromuscular source signals as having been generated by an extensor muscle; and   classifying a second one of the unmixed plurality of neuromuscular source signals as having been generated by a flexor muscle, wherein controlling the device is based, at least in part, on the first one of the unmixed plurality of neuromuscular source signals having been generated by the extensor muscle and the second one of the unmixed plurality of neuromuscular source signals having been generated by the flexor muscle.   
     
     
         7 . The computer-implemented method of  claim 1 , wherein controlling the device comprises:
 updating a virtual representation of the user's body based, at least in part, on one or more of the unmixed plurality of neuromuscular source signals; and   causing the device to present the updated virtual representation to the user.   
     
     
         8 . The computer-implemented method of  claim 1 , wherein controlling the device comprises:
 predicting that the user will perform a control action with respect to a control interface of the device based, at least in part, on one or more of the unmixed plurality of neuromuscular source signals; and   causing the device to respond to the control action before the user completes performance of the control action.   
     
     
         9 . The computer-implemented method of  claim 1 , wherein controlling the device comprises:
 determining, based on one or more of the unmixed plurality of neuromuscular source signals, musculo-skeletal position information describing a spatial relation between two or more connected segments of rigid body segments in a musculo-skeletal representation of the user;   updating the musculo-skeletal representation based on the musculo-skeletal position information; and   controlling, based on the musculo-skeletal representation, a visual representation of a character in a virtual reality environment presented by the device.   
     
     
         10 . The computer-implemented method of  claim 1 , wherein a number of the plurality of time series of neuromuscular-signal data is at least two times greater than a number of the plurality of neuromuscular source signals. 
     
     
         11 . A system comprising:
 a plurality of surface neuromuscular sensors, each of which is configured to record a time series of neuromuscular signals from a surface of a user's body; and   signal processing circuitry configured to:
 record a plurality of time series of neuromuscular-signal data from a user's body via the plurality of surface neuromuscular sensors, wherein:
 the plurality of time series of neuromuscular-signal data comprise two or more overlapping neuromuscular source signals; and 
 each of the overlapping neuromuscular source signals corresponds to a different one of a plurality of biological structures; 
 
 apply a source separation technique to the plurality of time series of neuromuscular-signal data recorded by the plurality of surface neuromuscular sensors to decompose the overlapping neuromuscular source signals from the plurality of time series of neuromuscular-signal data; and 
 control at least one device based, at least in part, on one or more of the decomposed neuromuscular source signals. 
   
     
     
         12 . The system of  claim 11 , wherein:
 the signal processing circuitry is further configured to identify, for at least one of the decomposed neuromuscular source signals, an associated biological structure; and   the signal processing circuitry is configured to control the device based, at least in part, on the at least one of the decomposed neuromuscular source signals having been generated by the associated biological structure.   
     
     
         13 . The system of  claim 12 , wherein the signal processing circuitry is configured to identify the associated biological structure for the at least one of the decomposed neuromuscular source signals by aligning the decomposed neuromuscular source signals to a plurality of template neuromuscular source signals derived via electrodes inserted into corresponding biological structures. 
     
     
         14 . The system of  claim 12 , wherein the associated biological structure comprises one of:
 a muscle;   a muscle group; or   a motor unit.   
     
     
         15 . The system of  claim 12 , wherein the associated biological structure comprises a muscle fiber. 
     
     
         16 . The system of  claim 11 , wherein:
 the signal processing circuitry is further configured to:
 classify a first one of the decomposed neuromuscular source signals as having been generated by an extensor muscle; and 
 classify a second one of the decomposed neuromuscular source signals as having been generated by a flexor muscle; and 
   the signal processing circuitry is configured to control the device based, at least in part, on the first one of the decomposed neuromuscular source signals having been generated by the extensor muscle and the second one of the decomposed neuromuscular source signals having been generated by the flexor muscle.   
     
     
         17 . The system of  claim 11 , wherein the signal processing circuitry is configured to control the device by:
 updating a virtual representation of the user's body based, at least in part, on one or more of the decomposed neuromuscular source signals; and   causing the device to present the updated virtual representation to the user.   
     
     
         18 . The system of  claim 11 , wherein the signal processing circuitry is configured to control the device by:
 predicting that the user will perform a control action with respect to a control interface of the device based, at least in part, on one or more of the decomposed neuromuscular source signals; and   causing the device to respond to the control action before the user completes performance of the control action.   
     
     
         19 . The system of  claim 11 , wherein the signal processing circuitry is configured to control the device by:
 determining, based on one or more of the decomposed neuromuscular source signals, musculo-skeletal position information describing a spatial relation between two or more connected segments of rigid body segments in a musculo-skeletal representation of the user;   updating the musculo-skeletal representation based on the musculo-skeletal position information; and   controlling, based on the musculo-skeletal representation, a visual representation of a character in a virtual reality environment presented by the device.   
     
     
         20 . A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to:
 record a plurality of time series of neuromuscular-signal data from a user's body via a plurality of surface neuromuscular sensors, wherein:
 the plurality of time series of neuromuscular-signal data comprise a mixing of a plurality of neuromuscular source signals; and 
 each of the plurality of neuromuscular source signals corresponds to a different one of a plurality of biological structures; 
   apply a source separation technique to the plurality of time series of neuromuscular-signal data recorded by the plurality of surface neuromuscular sensors to unmix the plurality of neuromuscular source signals from the plurality of time series of neuromuscular-signal data; and   control at least one device based, at least in part, on one or more of the unmixed plurality of neuromuscular source signals.