Adaptive calibration for sensor-equipped athletic garments

Abstract

An exercise feedback system calibrates sensors of an athletic garment worn by an athlete while performing exercises. The sensors can record physiological data such as muscle activation. The system instructs the athlete to perform a calibration workout. The system generates a calibration value based on physiological data from the calibration workout and/or user information. The calibration value indicates, for example, the predicted maximum amplitude for the muscle activation of a particular muscle group (for example, glutes, hamstrings, or quadriceps) of the athlete. The system can update the calibration value over time as the system receives additional physiological data from subsequent exercises performed by the athlete. The system may determine a confidence level of the calibration value and may update the calibration value if the confidence level becomes too low. The system provides biofeedback to the athlete generated based on the calibration value.

What is claimed is: 
     
         1 . A method comprising:
 providing information describing a calibration workout to a client device of a user;   receiving a first set of physiological data from a garment worn by the user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing the calibration workout, the garment including a plurality of sensors configured to generate physiological data;   receiving user information from the client device;   determining a calibration value based at least in part on the first set of physiological data and the user information;   receiving a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing a subsequent workout;   modifying the calibration value based on the second set of physiological data; and   providing biofeedback to the client device for communication to the user, the biofeedback generated based on the modified calibration value.   
     
     
         2 . The method of  claim 1 , wherein the calibration value is further determined based on a perceived user effort corresponding to the calibration workout. 
     
     
         3 . The method of  claim 2 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data and the perceived user effort. 
     
     
         4 . The method of  claim 3 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         5 . The method of  claim 1 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data. 
     
     
         6 . The method of  claim 5 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         7 . The method of  claim 5 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         8 . The method of  claim 5 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         9 . The method of  claim 1 , further comprising:
 receiving bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is further determined based on the bioimpedance data.   
     
     
         10 . The method of  claim 9 , further comprising:
 determining a level of data quality for each of the first set of physiological data and the second set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the levels of data quality.   
     
     
         11 . The method of  claim 1 , further comprising:
 receiving heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is further determined based on the heart rate information.   
     
     
         12 . The method of  claim 1 , further comprising:
 determining a confidence level of the calibration value based at least in part on the calibration workout;   determining a difference between an amplitude of a data subset of the second set of physiological data and the calibration value; and   modifying the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         13 . The method of  claim 12 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         14 . The method of  claim 12 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         15 . The method of  claim 1 , wherein the biofeedback indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         16 . The method of  claim 1 , further comprising modifying additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         17 . The method of  claim 1 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         18 . The method of  claim 1 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first or second set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         19 . The method of  claim 1 , wherein the user information is received from a third party application associated with the client device of the user. 
     
     
         20 . A method comprising:
 receiving user information from a client device of a user;   determining a calibration value based on a model configured to generate the calibration value based on the user information;   receiving a first set of physiological data from a garment worn by the user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing a workout, the garment including a plurality of sensors configured to generate physiological data;   modifying the calibration value based on the first set of physiological data;   generating biofeedback based on the modified calibration value, the biofeedback indicating a metric of athletic performance of the user; and   providing the biofeedback to the client device for communication to the user.   
     
     
         21 . The method of  claim 20 , wherein the calibration value is further determined based on a second set of physiological data from a calibration workout and a perceived user effort corresponding to the calibration workout. 
     
     
         22 . The method of  claim 21 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data and the perceived user effort. 
     
     
         23 . The method of  claim 22 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         24 . The method of  claim 20 , wherein the calibration value is further determined based on a second set of physiological data from a calibration workout including at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data. 
     
     
         25 . The method of  claim 24 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         26 . The method of  claim 24 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         27 . The method of  claim 24 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         28 . The method of  claim 20 , further comprising:
 receiving bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is further determined based on the bioimpedance data.   
     
     
         29 . The method of  claim 28 , further comprising:
 determining a level of data quality of the first set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the level of data quality.   
     
     
         30 . The method of  claim 20 , further comprising:
 receiving heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is further determined based on the heart rate information.   
     
     
         31 . The method of  claim 20 , further comprising:
 determining a confidence level of the calibration value based at least in part on the user information;   determining a difference between an amplitude of a data subset of the first set of physiological data and the calibration value; and   modifying the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         32 . The method of  claim 31 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         33 . The method of  claim 31 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         34 . The method of  claim 20 , wherein the biofeedback further indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         35 . The method of  claim 20 , further comprising modifying additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         36 . The method of  claim 20 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         37 . The method of  claim 20 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         38 . The method of  claim 20 , wherein the user information is received from a third party application associated with the client device of the user. 
     
     
         39 . The method of  claim 20 , further comprising:
 providing information describing a calibration workout to the client device; and   receiving a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing the calibration workout, wherein the calibration value is further determined based on the second set of physiological data.   
     
     
         40 . A method comprising:
 providing information describing a calibration workout to a client device of a user;   receiving a first set of physiological data from a garment worn by the user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing the calibration workout, the garment including a plurality of sensors configured to generate physiological data;   determining a calibration value based at least in part on the first set of physiological data;   receiving a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing a subsequent workout;   modifying the calibration value based on the second set of physiological data; and   providing biofeedback to the client device for communication to the user, the biofeedback generated based on the modified calibration value.   
     
     
         41 . The method of  claim 40 , wherein the calibration value is further determined based on a perceived user effort corresponding to the calibration workout. 
     
     
         42 . The method of  claim 41 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data and the perceived user effort. 
     
     
         43 . The method of  claim 42 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         44 . The method of  claim 40 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data. 
     
     
         45 . The method of  claim 44 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         46 . The method of  claim 44 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         47 . The method of  claim 44 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         48 . The method of  claim 40 , further comprising:
 receiving bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is further determined based on the bioimpedance data.   
     
     
         49 . The method of  claim 48 , further comprising:
 determining a level of data quality for each of the first set of physiological data and the second set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the levels of data quality.   
     
     
         50 . The method of  claim 40 , further comprising:
 receiving heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is further determined based on the heart rate information.   
     
     
         51 . The method of  claim 40 , further comprising:
 determining a confidence level of the calibration value based at least in part on the calibration workout;   determining a difference between an amplitude of a data subset of the second set of physiological data and the calibration value; and   modifying the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         52 . The method of  claim 51 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         53 . The method of  claim 51 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         54 . The method of  claim 40 , wherein the biofeedback indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         55 . The method of  claim 40 , further comprising modifying additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         56 . The method of  claim 40 , further comprising receiving user information from the client device, wherein the calibration value is further determined based on the user information. 
     
     
         57 . The method of  claim 56 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         58 . The method of  claim 56 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first or second set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         59 . The method of  claim 56 , wherein the user information is received from a third party application associated with the client device of the user. 
     
     
         60 . A method comprising:
 retrieving a calibration value;   receiving a first set of physiological data from a garment worn by a user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing a workout, the garment including a plurality of sensors configured to generate physiological data;   modifying the calibration value based on the first set of physiological data;   generating biofeedback based on the modified calibration value, the biofeedback indicating a metric of athletic performance of the user; and   providing the biofeedback to a client device for communication to the user.   
     
     
         61 . The method of  claim 60 , wherein the calibration value is determined based on a second set of physiological data from a calibration workout and a perceived user effort corresponding to the calibration workout. 
     
     
         62 . The method of  claim 61 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data and the perceived user effort. 
     
     
         63 . The method of  claim 62 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         64 . The method of  claim 60 , wherein the calibration value is determined based on a second set of physiological data from a calibration workout including at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data. 
     
     
         65 . The method of  claim 64 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         66 . The method of  claim 64 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         67 . The method of  claim 64 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         68 . The method of  claim 60 , further comprising:
 receiving bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is determined based on the bioimpedance data.   
     
     
         69 . The method of  claim 68 , further comprising:
 determining a level of data quality of the first set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the level of data quality.   
     
     
         70 . The method of  claim 60 , further comprising:
 receiving heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is determined based on the heart rate information.   
     
     
         71 . The method of  claim 60 , further comprising:
 determining a confidence level of the calibration value;   determining a difference between an amplitude of a data subset of the first set of physiological data and the calibration value; and   modifying the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         72 . The method of  claim 71 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         73 . The method of  claim 71 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         74 . The method of  claim 60 , wherein the biofeedback indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         75 . The method of  claim 60 , further comprising modifying additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         76 . The method of  claim 60 , further comprising receiving user information from the client device, wherein the calibration value is further determined based on the user information. 
     
     
         77 . The method of  claim 76 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         78 . The method of  claim 76 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         79 . The method of  claim 76 , further comprising:
 providing information describing a calibration workout to the client device; and   receiving a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing the calibration workout, wherein the calibration value is further determined based on the second set of physiological data.   
     
     
         80 . A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:
 provide information describing a calibration workout to a client device of a user;   receive a first set of physiological data from a garment worn by the user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing the calibration workout, the garment including a plurality of sensors configured to generate physiological data;   receive user information from the client device;   determine a calibration value based at least in part on the first set of physiological data and the user information;   receive a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing a subsequent workout;   modify the calibration value based on the second set of physiological data; and   provide biofeedback to the client device for communication to the user, the biofeedback generated based on the modified calibration value.   
     
     
         81 . The method of  claim 80 , wherein the calibration value is further determined based on a perceived user effort corresponding to the calibration workout. 
     
     
         82 . The method of  claim 81 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data and the perceived user effort. 
     
     
         83 . The non-transitory computer readable storage medium of  claim 82 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         84 . The non-transitory computer readable storage medium of  claim 80 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data. 
     
     
         85 . The non-transitory computer readable storage medium of  claim 84 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         86 . The non-transitory computer readable storage medium of  claim 84 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         87 . The non-transitory computer readable storage medium of  claim 84 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         88 . The non-transitory computer readable storage medium of  claim 80 , having further instructions that when executed by the processor cause the processor to:
 receive bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is further determined based on the bioimpedance data.   
     
     
         89 . The non-transitory computer readable storage medium of  claim 88 , having further instructions that when executed by the processor cause the processor to:
 determine a level of data quality for each of the first set of physiological data and the second set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the levels of data quality.   
     
     
         90 . The non-transitory computer readable storage medium of  claim 80 , having further instructions that when executed by the processor cause the processor to:
 receive heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is further determined based on the heart rate information.   
     
     
         91 . The non-transitory computer readable storage medium of  claim 80 , having further instructions that when executed by the processor cause the processor to:
 determine a confidence level of the calibration value based at least in part on the calibration workout;   determine a difference between an amplitude of a data subset of the second set of physiological data and the calibration value; and   modify the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         92 . The non-transitory computer readable storage medium of  claim 91 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         93 . The non-transitory computer readable storage medium of  claim 91 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         94 . The non-transitory computer readable storage medium of  claim 80 , wherein the biofeedback indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         95 . The non-transitory computer readable storage medium of  claim 80 , having further instructions that when executed by the processor cause the processor to modify additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         96 . The non-transitory computer readable storage medium of  claim 80 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         97 . The non-transitory computer readable storage medium of  claim 80 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first or second set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         98 . The non-transitory computer readable storage medium of  claim 80 , wherein the user information is received from a third party application associated with the client device of the user. 
     
     
         99 . A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:
 receive user information from a client device of a user;   determine a calibration value based on a model configured to generate the calibration value based on the user information;   receive a first set of physiological data from a garment worn by the user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing a workout, the garment including a plurality of sensors configured to generate physiological data;   modify the calibration value based on the first set of physiological data;   generate biofeedback based on the modified calibration value, the biofeedback indicating a metric of athletic performance of the user; and   provide the biofeedback to the client device for communication to the user.   
     
     
         100 . The non-transitory computer readable storage medium of  claim 99 , wherein the calibration value is further determined based on a second set of physiological data from a calibration workout and a perceived user effort corresponding to the calibration workout. 
     
     
         101 . The non-transitory computer readable storage medium of  claim 100 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data and the perceived user effort. 
     
     
         102 . The non-transitory computer readable storage medium of  claim 101 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         103 . The non-transitory computer readable storage medium of  claim 99 , wherein the calibration value is further determined based on a second set of physiological data from a calibration workout including at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data. 
     
     
         104 . The non-transitory computer readable storage medium of  claim 103 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         105 . The non-transitory computer readable storage medium of  claim 103 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         106 . The non-transitory computer readable storage medium of  claim 103 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         107 . The non-transitory computer readable storage medium of  claim 99 , having further instructions that when executed by the processor cause the processor to:
 receive bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is further determined based on the bioimpedance data.   
     
     
         108 . The non-transitory computer readable storage medium of  claim 107 , having further instructions that when executed by the processor cause the processor to:
 determine a level of data quality of the first set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the level of data quality.   
     
     
         109 . The non-transitory computer readable storage medium of  claim 99 , having further instructions that when executed by the processor cause the processor to:
 receive heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is further determined based on the heart rate information.   
     
     
         110 . The non-transitory computer readable storage medium of  claim 99 , having further instructions that when executed by the processor cause the processor to:
 determine a confidence level of the calibration value based at least in part on the user information;   determine a difference between an amplitude of a data subset of the first set of physiological data and the calibration value; and   modify the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         111 . The non-transitory computer readable storage medium of  claim 110 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         112 . The non-transitory computer readable storage medium of  claim 110 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         113 . The non-transitory computer readable storage medium of  claim 99 , wherein the biofeedback further indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         114 . The non-transitory computer readable storage medium of  claim 99 , having further instructions that when executed by the processor cause the processor to modify additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         115 . The non-transitory computer readable storage medium of  claim 99 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         116 . The non-transitory computer readable storage medium of  claim 99 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         117 . The non-transitory computer readable storage medium of  claim 99 , wherein the user information is received from a third party application associated with the client device of the user. 
     
     
         118 . The non-transitory computer readable storage medium of  claim 99 , having further instructions that when executed by the processor cause the processor to:
 provide information describing a calibration workout to the client device; and   receive a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing the calibration workout, wherein the calibration value is further determined based on the second set of physiological data.   
     
     
         119 . A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:
 provide information describing a calibration workout to a client device of a user;   receive a first set of physiological data from a garment worn by the user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing the calibration workout, the garment including a plurality of sensors configured to generate physiological data;   determine a calibration value based at least in part on the first set of physiological data;   receive a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing a subsequent workout;   modify the calibration value based on the second set of physiological data; and   provide biofeedback to the client device for communication to the user, the biofeedback generated based on the modified calibration value.   
     
     
         120 . The non-transitory computer readable storage medium of  claim 119 , wherein the calibration value is further determined based on a perceived user effort corresponding to the calibration workout. 
     
     
         121 . The non-transitory computer readable storage medium of  claim 120 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data and the perceived user effort. 
     
     
         122 . The non-transitory computer readable storage medium of  claim 121 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         123 . The non-transitory computer readable storage medium of  claim 119 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the first set of physiological data. 
     
     
         124 . The non-transitory computer readable storage medium of  claim 123 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         125 . The non-transitory computer readable storage medium of  claim 123 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         126 . The non-transitory computer readable storage medium of  claim 123 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         127 . The non-transitory computer readable storage medium of  claim 119 , having further instructions that when executed by the processor cause the processor to:
 receive bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is further determined based on the bioimpedance data.   
     
     
         128 . The non-transitory computer readable storage medium of  claim 127 , having further instructions that when executed by the processor cause the processor to:
 determine a level of data quality for each of the first set of physiological data and the second set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the levels of data quality.   
     
     
         129 . The non-transitory computer readable storage medium of  claim 119 , having further instructions that when executed by the processor cause the processor to:
 receive heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is further determined based on the heart rate information.   
     
     
         130 . The non-transitory computer readable storage medium of  claim 119 , having further instructions that when executed by the processor cause the processor to:
 determine a confidence level of the calibration value based at least in part on the calibration workout;   determine a difference between an amplitude of a data subset of the second set of physiological data and the calibration value; and   modify the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         131 . The non-transitory computer readable storage medium of  claim 130 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         132 . The non-transitory computer readable storage medium of  claim 130 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         133 . The non-transitory computer readable storage medium of  claim 119 , wherein the biofeedback indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         134 . The non-transitory computer readable storage medium of  claim 119 , having further instructions that when executed by the processor cause the processor to modify additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         135 . The non-transitory computer readable storage medium of  claim 119 , having further instructions that when executed by the processor cause the processor to receive user information from the client device, wherein the calibration value is further determined based on the user information. 
     
     
         136 . The non-transitory computer readable storage medium of  claim 135 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         137 . The non-transitory computer readable storage medium of  claim 135 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first or second set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         138 . The non-transitory computer readable storage medium of  claim 135 , wherein the user information is received from a third party application associated with the client device of the user. 
     
     
         139 . A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor:
 retrieve a calibration value;   receive a first set of physiological data from a garment worn by a user, the first set of physiological data describing muscle activation of a plurality of muscles of the user while performing a workout, the garment including a plurality of sensors configured to generate physiological data;   modify the calibration value based on the first set of physiological data;   generate biofeedback based on the modified calibration value, the biofeedback indicating a metric of athletic performance of the user; and   provide the biofeedback to a client device for communication to the user.   
     
     
         140 . The non-transitory computer readable storage medium of  claim 139 , wherein the calibration value is determined based on a second set of physiological data from a calibration workout and a perceived user effort corresponding to the calibration workout. 
     
     
         141 . The non-transitory computer readable storage medium of  claim 140 , wherein the calibration workout includes at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the perceived user effort indicating a first effort level for a first set of the at least two sets, and a second effort level for a second set of the at least two sets, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data and the perceived user effort. 
     
     
         142 . The non-transitory computer readable storage medium of  claim 141 , wherein the calibration value model is trained using data collected from a population of athletes including physiological data associated with different perceived effort levels and target calibration values. 
     
     
         143 . The non-transitory computer readable storage medium of  claim 139 , wherein the calibration value is determined based on a second set of physiological data from a calibration workout including at least two sets of an exercise associated with at least one muscle of the plurality of muscles, the at least two sets including a first set of a first number of repetitions and a second set of a second number of repetitions, each of the first number of repetitions and the second number of repetitions associated with repetition maximums, and wherein the calibration value is determined based on a calibration value model configured to generate the calibration value based on the second set of physiological data. 
     
     
         144 . The non-transitory computer readable storage medium of  claim 143 , where the calibration value model is trained using data collected from a population of athletes including physiological data associated with different associated repetition maxima and target calibration values. 
     
     
         145 . The non-transitory computer readable storage medium of  claim 143 , wherein:
 the exercise comprises one of: a kickback, a leg curl, and a squat; and   the at least one muscle of the plurality of muscles comprising at least one of: a gluteus maximus muscle, a hamstring muscle, and a quadriceps muscle.   
     
     
         146 . The non-transitory computer readable storage medium of  claim 143 , wherein:
 the exercise comprises one of: a chest fly, a bent over row, an arm curl, an arm extension, and an arm raise;   the at least one muscle of the plurality of muscles comprising at least one of: a pectoral muscle, a biceps muscle, a triceps muscle, and a deltoids muscle.   
     
     
         147 . The non-transitory computer readable storage medium of  claim 139 , having further instructions that when executed by the processor cause the processor to:
 receive bioimpedance data from the plurality of sensors of the garment, wherein the calibration value is determined based on the bioimpedance data.   
     
     
         148 . The non-transitory computer readable storage medium of  claim 147 , having further instructions that when executed by the processor cause the processor to:
 determine a level of data quality of the first set of physiological data based on the bioimpedance data, wherein the calibration value is further determined based on the level of data quality.   
     
     
         149 . The non-transitory computer readable storage medium of  claim 139 , having further instructions that when executed by the processor cause the processor to:
 receive heart rate information of the user generated by at least one sensor of the plurality of sensors, wherein the calibration value is determined based on the heart rate information.   
     
     
         150 . The non-transitory computer readable storage medium of  claim 139 , having further instructions that when executed by the processor cause the processor to:
 determine a confidence level of the calibration value;   determine a difference between an amplitude of a data subset of the first set of physiological data and the calibration value; and   modify the confidence level based on the difference of the amplitude of the data subset and the calibration value.   
     
     
         151 . The non-transitory computer readable storage medium of  claim 150 , wherein:
 the confidence level is modified based on a non-linear function that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         152 . The non-transitory computer readable storage medium of  claim 150 , wherein:
 the confidence level is modified based on a machine learning model that generates a confidence level value based on the difference of the amplitude of the data subset and the calibration value, the machine learning model trained using feature vectors based on physiological data associated with a population of users that perform exercises; and   modifying the confidence level includes reducing the confidence level by the confidence level value.   
     
     
         153 . The non-transitory computer readable storage medium of  claim 139 , wherein the biofeedback indicates at least one of: (i) a level of exertion of at least one muscle of the plurality of muscles of the user while performing the subsequent workout, (ii) a level of balance of the user while performing the subsequent workout, (iii) a level of workload of the plurality of muscles while performing the subsequent workout, (iv) a first contribution of a given muscle of the plurality of muscles compared to a second contribution of the plurality of muscles while performing the subsequent workout, (v) a strength progression or regression based on changes to the calibration value over time, and (vi) a comparison of the user and a group of other users. 
     
     
         154 . The non-transitory computer readable storage medium of  claim 139 , having further instructions that when executed by the processor cause the processor to modify additional biofeedback information based on the modified calibration value, the additional biofeedback information based on the calibration value before it was modified. 
     
     
         155 . The non-transitory computer readable storage medium of  claim 139 , having further instructions that when executed by the processor cause the processor to receive user information from the client device, wherein the calibration value is further determined based on the user information. 
     
     
         156 . The non-transitory computer readable storage medium of  claim 155 , wherein the user information describes demographic data of the user, and wherein the calibration value is further determined based on the demographic data. 
     
     
         157 . The non-transitory computer readable storage medium of  claim 155 , wherein the user information describes at least one of: a performance metric of the user, exercises corresponding to the first set of physiological data, and another set of physiological data corresponding to a group of other users. 
     
     
         158 . The non-transitory computer readable storage medium of  claim 155 , having further instructions that when executed by the processor cause the processor to:
 provide information describing a calibration workout to the client device; and   receive a second set of physiological data from the garment worn by the user, the second set of physiological data describing muscle activation of the plurality of muscles of the user while performing the calibration workout, wherein the calibration value is further determined based on the second set of physiological data.