Evaluating movement of a subject

Abstract

According to an aspect, there is provided a computer-implemented method for evaluating movement of a subject. The method includes obtaining a first signal from a first sensor; processing the first signal to determine a value of a quality measure for the first signal; and determining a configuration for a movement evaluation algorithm. The configuration of the movement evaluation algorithm is dependent on the determined value of the quality measure for the first signal such that either or both of a decision threshold of the movement evaluation algorithm is determined based on the determined value of the quality measure; and one or more weightings used in the movement evaluation algorithm for the one or more first features that are to be derived from a signal from the first sensor are determined based on the determined value of the quality measure. A corresponding apparatus and computer program product are also provided.

What is claimed is: 
     
         1 . A computer-implemented method when executed on data processing hardware causes the data processing hardware to perform operations comprising:
 obtaining a first plurality of measurements measured by a first sensor;   determining a value of a quality measure representing an amount of signal artefacts present in the first plurality of measurements;   configuring, based on the value of the quality measure, one or more parameters of a movement evaluation algorithm; and   after configuring the one or more parameters of the movement evaluation algorithm:
 receiving a second plurality of measurements associated with a subject; and 
 processing, using the movement evaluation algorithm, the second plurality of measurements to evaluate movement of the subject. 
   
     
     
         2 . The method of  claim 1 , wherein:
 the signal artefacts comprise one or more of an offset, a noise, a calibration error, or a calibration drift; and   the value of the quality measure comprises one or more of an offset amount, a noise level, a signal-to-noise ratio, a signal variance, an autocorrelation, a median absolute deviation, or an entropy.   
     
     
         3 . The method of  claim 1 , wherein:
 the one or more parameters comprise a decision threshold; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 when the value of the quality measure satisfies a first criteria, configuring the decision threshold to have a first value; and 
 when the value of the quality measure does not satisfy the first criteria, configuring the decision threshold to have a second different value. 
   
     
     
         4 . The method of  claim 1 , wherein:
 the one or more parameters comprise a first weight factor and a second weight factor; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 configuring, based on the value of the quality measure, the first weight factor associated with detecting a first movement feature; and 
 configuring, based on the value of the quality measure, the second weight factor associated with detecting a second movement feature. 
   
     
     
         5 . The method of  claim 4 , wherein the first weight factor and the second weight factor are configured with different values. 
     
     
         6 . The method of  claim 4 , wherein processing, using the movement evaluation algorithm, the second plurality of measurements to evaluate movement of the subject comprises determining a combination of a detection of the first movement feature weighted with the first weight factor and a detection of the second movement feature weighted with the second weight factor. 
     
     
         7 . The method of  claim 1 , wherein:
 the one or more parameters comprise a weight factor; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 when the value of the quality measure satisfies a first criteria, configuring the weight factor to have a first value; and 
 when the value of the quality measure does not satisfy the first criteria, configuring the weight factor to have a second value different than the first value. 
   
     
     
         8 . The method of  claim 1 , wherein:
 the one or more parameters comprise a decision threshold; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 when the value of the quality measure satisfies a first criteria, configuring the decision threshold to represent a first operating point on a first receiver operating characteristics (ROC) curve that represents a first specificity and a first detection probability; and 
 when the value of the quality measure does not satisfy the first criteria, configuring the decision threshold to represent a second operating point on a second ROC curve that represents a second specificity that is different from the first specificity and a second detection probability that is different from the first detection probability. 
   
     
     
         9 . The method of  claim 1 , wherein:
 the first plurality of measurements represent measured accelerations; and   the value of the quality measure comprises an offset between measured accelerations and gravitational acceleration.   
     
     
         10 . The method of  claim 1 , wherein:
 the first plurality of measurements represent measured air pressures; and   the value of the quality measure comprises an air pressure variation.   
     
     
         11 . The method of  claim 1 , wherein:
 the second plurality of measurements associated with the subject are measured by the first sensor implemented on a user device associated with the user; and   receiving the second plurality of measurements comprises receiving the second plurality of measurements from the first sensor in communication with the data processing hardware via a wireless network.   
     
     
         12 . The method of  claim 11 , wherein the data processing hardware resides on a server. 
     
     
         13 . The method of  claim 11 , wherein the data processing hardware resides on the user device. 
     
     
         14 . The method of  claim 11 , wherein the data processing hardware resides on another user device associated with the user. 
     
     
         15 . The method of  claim 11 , wherein the user device comprises a smart watch, a smart phone, a personal emergency response system (PERS) device, a computing device, or a tablet device. 
     
     
         16 . A system comprising:
 data processing hardware; and   memory hardware storing instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations comprising:
 obtaining a first plurality of measurements measured by a first sensor; 
 determining a value of a quality measure representing an amount of signal artefacts present in the first plurality of measurements; 
 configuring, based on the value of the quality measure, one or more parameters of a movement evaluation algorithm; and 
 after configuring the one or more parameters of the movement evaluation algorithm:
 receiving a second plurality of measurements associated with a subject; and 
 processing, using the movement evaluation algorithm, the second plurality of measurements to evaluate movement of the subject. 
 
   
     
     
         17 . The system of  claim 16 , wherein:
 the signal artefacts comprise one or more of an offset, a noise, a calibration error, or a calibration drift; and   the value of the quality measure comprises one or more of an offset amount, a noise level, a signal-to-noise ratio, a signal variance, an autocorrelation, a median absolute deviation, or an entropy.   
     
     
         18 . The system of  claim 16 , wherein:
 the one or more parameters comprise a decision threshold; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 when the value of the quality measure satisfies a first criteria, configuring the decision threshold to have a first value; and 
 when the value of the quality measure does not satisfy the first criteria, configuring the decision threshold to have a second different value. 
   
     
     
         19 . The system of  claim 16 , wherein:
 the one or more parameters comprise a first weight factor and a second weight factor; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 configuring, based on the value of the quality measure, the first weight factor associated with detecting a first movement feature; and 
 configuring, based on the value of the quality measure, the second weight factor associated with detecting a second movement feature. 
   
     
     
         20 . The system of  claim 19 , wherein the first weight factor and the second weight factor are configured with different values. 
     
     
         21 . The system of  claim 19 , wherein processing, using the movement evaluation algorithm, the second plurality of measurements to evaluate movement of the subject comprises determining a combination of a detection of the first movement feature weighted with the first weight factor and a detection of the second movement feature weighted with the second weight factor. 
     
     
         22 . The system of  claim 16 , wherein:
 the one or more parameters comprise a weight factor; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 when the value of the quality measure satisfies a first criteria, configuring the weight factor to have a first value; and 
 when the value of the quality measure does not satisfy the first criteria, configuring the weight factor to have a second value different than the first value. 
   
     
     
         23 . The system of  claim 16 , wherein:
 the one or more parameters comprise a decision threshold; and   configuring the one or more parameters of the movement evaluation algorithm comprises:
 when the value of the quality measure satisfies a first criteria, configuring the decision threshold to represent a first operating point on a first receiver operating characteristics (ROC) curve that represents a first specificity and a first detection probability; and 
 when the value of the quality measure does not satisfy the first criteria, configuring the decision threshold to represent a second operating point on a second ROC curve that represents a second specificity that is different from the first specificity and a second detection probability that is different from the first detection probability. 
   
     
     
         24 . The system of  claim 16 , wherein:
 the first plurality of measurements represent measured accelerations; and   the value of the quality measure comprises an offset between measured accelerations and gravitational acceleration.   
     
     
         25 . The system of  claim 16 , wherein:
 the first plurality of measurements represent measured air pressures; and   the value of the quality measure comprises an air pressure variation.   
     
     
         26 . The system of  claim 16 , wherein:
 the second plurality of measurements associated with the subject are measured by the first sensor implemented on a user device associated with the user; and   receiving the second plurality of measurements comprises receiving the second plurality of measurements from the first sensor in communication with the data processing hardware via a wireless network.   
     
     
         27 . The system of  claim 26 , wherein the data processing hardware resides on a server. 
     
     
         28 . The system of  claim 26 , wherein the data processing hardware resides on the user device. 
     
     
         29 . The system of  claim 26 , wherein the data processing hardware resides on another user device associated with the user. 
     
     
         30 . The system of  claim 26 , wherein the user device comprises a smart watch, a smart phone, a personal emergency response system (PERS) device, a computing device, or a tablet device.