WO2017075953A1 - Accelerometer-based method and device for predicting heart rate during exercise - Google Patents

Abstract

Provided are an accelerometer-based method and device for predicting heart rate during exercise, the method comprising: step S1: by means of an accelerometer, collecting and calculating for a test subject an acceleration vector generated during exercise; step S2: calculating the energy consumption change of the subject during exercise by analyzing the change of the acceleration vector values on a time axis, and establishing a relational model between acceleration vector and energy consumption; step S3: collecting the basic information of the subject and calculating the basal metabolic rate, maximal heart rate, oxygen uptake and energy consumption of the subject at the maximal heart rate; step S4: establishing a relational model between the heart rate and the energy consumption of the subject during exercise so as to realize the prediction of the heart rate of the subject during exercise. The method is easy to operate and its measurement accuracy can satisfy exercise requirements.

Description

Method and device for predicting heart rate of exercise process based on acceleration sensor Technical field

The invention relates to a method for measuring heart rate of an acceleration sensor, in particular to a method for predicting a heart rate of a motion process based on an acceleration sensor, and relates to a device using the method for predicting a heart rate of a motion process based on an acceleration sensor.

Background technique

The monitoring of human exercise energy consumption and heart rate is of great significance in many fields. It is widely used in medicine, exercise training and daily life. In medicine, traditional heart rate measurement methods rely on ECG for image processing, and professional training is also needed in sports training. Instruments and operations cannot meet the requirements of portability, flexibility and ease of operation; in the prior art, there are also many methods for measuring heart rate by an acceleration sensor, but the existing measurement method only serves as a measurement. However, it is not possible to perform heart rate prediction on the subject during exercise, and this function is an important indicator for monitoring human health and conducting risk pre-judgment, especially for special groups such as the elderly. The ability to perform heart rate prediction during exercise is especially important.

Summary of the invention

The technical problem to be solved by the present invention is to provide a method for predicting the heart rate of a subject under motion by an acceleration sensor, and to provide a device using the method for predicting a heart rate of a motion process based on the acceleration sensor.

In this regard, the present invention provides a method for predicting a heart rate during a motion process based on an acceleration sensor, comprising the steps of:

Step S1, collecting and calculating an acceleration vector generated by the object under motion by the acceleration sensor;

Step S2, by analyzing the change of the acceleration vector value on the time axis, calculating the change of the energy consumption of the measured object during the movement, and establishing a relationship model between the acceleration vector and the energy consumption;

Step S3, collecting basic information of the test object, and calculating the basal metabolic rate, the maximum heart rate, the oxygen uptake under the maximum heart rate, and the energy consumption under the maximum heart rate by the calculation;

Step S4, establishing a relationship model between the center rate and the energy consumption of the motion object of the measured object, and utilizing the change of energy consumption Calculate the change in heart rate and predict the heart rate of the subject during exercise.

A further improvement of the present invention is that the step S1 is to collect the voltage signal generated by the object under test by the multi-axis acceleration sensor, thereby obtaining the acceleration vector of the multi-axis acceleration sensor in various directions, and the acceleration vector in each direction. The acceleration combined vector is calculated.

A further improvement of the invention is that said step S1 comprises the following substeps:

Step S101, obtaining an acceleration vector of the measured object in n directions at time t ₂ by using an n-axis acceleration sensor

And calculate the acceleration vector at time t ₂

Step S102, the acquisition time t is _1, the target object by an acceleration vector in the direction of n by n-axis acceleration sensor

And calculate the acceleration vector at time t ₁

A further improvement of the invention is that said step S2 comprises the following substeps:

Step S201, let t ₂ > t ₁ , according to the time from t ₁ to t ₂ , the acceleration combined vector

Transform to

Then establish a relationship model between the acceleration vector and the energy consumption as:

Where k ₁ is a constant coefficient ranging from 0.005 to 0.010; Δx is a change in energy consumption of the object under motion during the time from t ₁ to t ₂ ;

Step S202, collecting the energy consumption x _{0 of} the measured object at time t ₁ , and then obtaining the energy consumption x of the measured object at time t ₂ is:

A further improvement of the invention is that the value of k ₁ is 0.007.

A further improvement of the invention is that said step S3 comprises the following substeps:

Step S301, calculating the basal metabolic rate BMR of the test subject according to the sex, weight, height and age of the test subject;

Step S302, calculating a maximum heart rate y _{max of the} test object;

Step S303, measuring the resting heart rate y _{rest of the} subject under quiet, obtaining the oxygen uptake VO _{2max at the} maximum heart rate per unit volume by the maximum heart rate y _max and the resting heart rate y _rest ;

Step S304, the energy consumption x _{max of the} subject under the maximum heart rate is obtained by the oxygen uptake amount VO _2max at the maximum heart rate.

A further improvement of the present invention is that, in the step S301, the basal metabolic rate BMR _{male of the male subject} is BMR _male = α ₁ + α ₂ * weight + α ₃ *height + α ₄ *age; The basal metabolic rate BMR _female is BMR _female = β ₁ + β ₂ * weight + β ₃ *height + β ₄ *age; where weight is the weight of the subject, height is the height of the subject, and age is the subject The ages, α ₁ , α ₂ , α ₃ , α ₄ , β ₁ , β ₂ , β ₃ and β ₄ are preset constant coefficients, and the α ₁ ranges from 50 to 80, and the α ₂ The value ranges from 10 to 20, the range of α ₃ ranges from 1 to 10, the range of α ₄ ranges from -10 to 0, and the range of β ₁ ranges from 500 to 700. The value of β ₂ ranges from 5 to 15, the range of β ₃ ranges from 0 to 5, and the range of β ₄ ranges from -10 to 0;

In the step S302, the maximum heart rate y _{max of the} object to be tested is calculated by y _max =k ₂ +k ₃ *age, where k ₂ is a constant coefficient ranging from 190 to 220, and k ₃ is a value range a constant coefficient of 0.5 to 1;

In step S303, the oxygen uptake VO _2max at the maximum heart rate per unit volume is obtained by the maximum heart rate y _max and the resting heart rate y _rest : VO _2max =k ₄ *weight*y _max /y _rest , where k ₄ is taken The value ranges from 0.01 to 0.03;

In the step S304, the energy consumption x _max of the measured object at the maximum heart rate is: x _max =k ₅ *VO _2max , where k ₅ is a constant coefficient ranging from 19.5 to 21.5.

A further improvement of the invention is that said step S4 comprises the following substeps:

Step S401, establishing a relationship model between the center rate and the energy consumption of the motion of the measured object is: y=[ln(x _max /(k ₆ *BMR)-1)-ln(x _max /x-1)]/ k ₇ , wherein k ₆ is a constant coefficient ranging from 0.002 to 0.004, and k ₇ is a constant coefficient ranging from 0.015 to 0.070;

Step S402, measuring an acceleration vector of the measured object at a certain moment during the movement by the acceleration sensor, and converting it into an energy consumption x _max under the maximum heart rate, and then substituting the value of the energy consumption x _max at the maximum heart rate into the The heart rate prediction value y corresponding to the time is obtained by describing the formula of step S401.

A further improvement of the present invention is that, in the step S301, the value of α ₁ is 65, the value of α ₂ is 13.73, the value of α ₃ is 5, and the value of α ₄ is -6.9, and the value of β ₁ is taken. The value is 660, the value of β ₂ is 9.6, the value of β ₃ is 1.72, and the value of β ₄ is -4.7. In the step S302, the value of k ₂ is 210, and the value of k ₃ is 0.7; In the step S303, the value of k ₄ is 0.015; in the step S304, the value of k ₅ is 20.5; in the step S401, the value of k ₆ is 0.0029, and the value of k ₇ is 0.035.

The present invention also provides an apparatus for predicting a heart rate of a motion process based on an acceleration sensor, which employs a method of predicting a heart rate of a motion process based on an acceleration sensor as described above.

Compared with the prior art, the invention has the beneficial effects that the heart rate of the object under test can be predicted by the acceleration sensor, which is simple and easy to operate, and the measurement accuracy can meet the training requirement; more specifically, the invention proposes to adopt the acceleration The sensor realizes the method of predicting the heart rate of the measured object during the movement process, solves the problem that the traditional heart rate measurement method requires professional operation, equipment and can not be portable, and expands the application of heart rate prediction in various fields such as exercise training and health monitoring. Popularization, the invention can only predict the heart rate of the object under test by using the acceleration sensor, is simple and easy to operate, and the measurement accuracy satisfies the requirements of ordinary physical training, especially for the elderly or special people with heart rate health problems, the meaning is more major.

DRAWINGS

1 is a schematic diagram showing the structure of a workflow according to an embodiment of the present invention.

detailed description

The preferred embodiments of the present invention are further described in detail below with reference to the accompanying drawings:

Example 1:

As shown in FIG. 1, this example provides a method for predicting a heart rate during a motion process based on an acceleration sensor, including the following steps:

Step S1, collecting and calculating an acceleration vector generated by the object under motion by the acceleration sensor;

Step S2, by analyzing the change of the acceleration vector value on the time axis, calculating the change of the energy consumption of the measured object during the movement, and establishing a relationship model between the acceleration vector and the energy consumption;

Step S3, collecting basic information of the test object, and calculating the basal metabolic rate, the maximum heart rate, the oxygen uptake under the maximum heart rate, and the energy consumption under the maximum heart rate by the calculation;

In step S4, a relationship model between the center rate and the energy consumption of the motion object of the test object is established, and the change of the heart rate is calculated by using the change of the energy consumption to realize the prediction of the heart rate of the test object during the exercise process.

In this example, the heart rate value of the object during exercise is calculated by the acceleration sensor according to the human body oxygen consumption rate and the basal metabolic rate, and the acceleration sensor used can sense and collect the acceleration vector generated by the object during the movement, and the acceleration sensor mainly includes the piezoelectric element. Accelerometers, piezoresistive accelerometers, and accelerometers based on other acquisition principles and methods, such as uniaxial accelerometers, multi-axis accelerometers, angular acceleration sensors, and geomagnetic composite sensors, and then calculate the acceleration vector The result of the acquisition and calculation is used as the acceleration basic data in the motion process. The acceleration basic data acquisition and calculation can be realized by real-time data acquisition, average data, indirect discrete acquisition data, continuous acquisition data or more.

This example utilizes measurable, known basic information of the subject, the basic information of the subject includes resting heart rate, gender, age, height and weight, and the resting heart rate is in a quiet state of the subject. Heart rate, and then calculate the maximum heart rate of different individuals, the oxygen consumption at the maximum heart rate, and the basal metabolic rate, and then use the oxygen consumption at the maximum heart rate to determine the energy consumption at the maximum heart rate, which is the energy consumption. . During the motion, the acceleration vector of the measured object changes, the value of the acceleration after a certain time is recorded, and the change of the energy consumption caused by the change of the acceleration during this period is calculated, and the energy consumption at the starting time is added. It is the new energy consumption after this period of time; the energy consumption under the maximum heart rate and the newly calculated new energy consumption and the basal metabolic rate are substituted into the calculation model between the established center rate and energy of the motion process, and then can be predicted. Heart rate during exercise.

Specifically, the step S1 in the present example is to collect the voltage signals generated by the multi-axis acceleration sensor during the motion by the multi-axis acceleration sensor, and then obtain the acceleration vector of the multi-axis acceleration sensor in each direction, and calculate the acceleration vector in each direction. Acceleration vector. The various directions refer to the direction of the multi-axis acceleration sensor. For example, the three-axis acceleration sensor includes acceleration vectors of three directions of front, back, horizontal and vertical.

Step S1 in this example uses an acceleration sensor to collect a voltage signal or other form of signal generated during the motion of the object under test, and converts the degree of motion into a value of the acceleration vector, which is calculated from the acceleration vectors in n directions. Acceleration vector; said step S1 comprises the following sub-steps:

Step S101, obtaining an acceleration vector of the measured object in n directions at time t ₂ by using an n-axis acceleration sensor

And calculate the acceleration vector at time t ₂

Step S102, the acquisition time t is _1, the target object by the acceleration vector in the direction of n by n-axis acceleration sensor

And calculate the acceleration vector at time t ₁

In step S2 of the example, the change of the acceleration combined vector obtained in step S1 is used to calculate the change of the energy consumption of the measured object during the movement, and the relationship model between the acceleration combined vector and the energy consumption is established, and the change of the acceleration combined vector is obtained. Thereafter, the value of the corresponding new energy consumption; the step S2 comprises the following sub-steps:

Step S201, let t ₂ > t ₁ , according to the time from t ₁ to t ₂ , the acceleration combined vector

Transform to

Then establish a relationship model between the acceleration vector and the energy consumption as:

Where k ₁ is a constant coefficient ranging from 0.005 to 0.010, and the optimal value of k ₁ is 0.007; Δx is the energy consumption change of the measured object during the movement from time t _{1 to} time t ₂ the amount;

Step S202, collecting the energy consumption x _{0 of} the measured object at time t ₁ , and then obtaining the energy consumption x of the measured object at time t ₂ is:

Step S3 in the present example determines the basal metabolic rate, the maximum heart rate, the oxygen uptake at the maximum heart rate, and the energy consumption at the maximum heart rate based on the underlying information such as age, height, weight, and gender of the subject. The step S3 includes the following sub-steps:

Step S301, calculating the basal metabolic rate BMR of the test subject according to the sex, weight, height and age of the test subject;

Step S302, calculating a maximum heart rate y _{max of the} test object;

Step S303, measuring the resting heart rate y _{rest of the} subject under quiet, obtaining the oxygen uptake VO _{2max at the} maximum heart rate per unit volume by the maximum heart rate y _max and the resting heart rate y _rest ;

Step S304, the energy consumption x _{max of the} subject under the maximum heart rate is obtained by the oxygen uptake amount VO _2max at the maximum heart rate.

In step S301 of the present example, the basal metabolic rate of the _{male subject} is BMR _male = α ₁ + α ₂ * weight + α ₃ *height + α ₄ *age; the basal metabolic rate of the _female subject BMR _female BMR _female =β ₁ +β ₂ *weight+β ₃ *height+β ₄ *age; where weight is the weight of the subject, height is the height of the subject, age is the age of the subject, α ₁ , α ₂ , α ₃ , α ₄ , β ₁ , β ₂ , β _{3 ,} and β ₄ are preset constant coefficients, and the value of α ₁ ranges from 50 to 80, and the range of α ₂ is 10 to 20, the value of the α _{3 is} in the range of 1 to 10, the value of the α _{4 is} in the range of -10 to 0, and the value of the β _{1 is} in the range of 500 to 700, and the β ₂ is taken. The value ranges from 5 to 15, the value of β ₃ ranges from 0 to 5, and the value of β ₄ ranges from -10 to 0;

In the step S302, the maximum heart rate y _{max of the} object to be tested is calculated by y _max =k ₂ +k ₃ *age, where k ₂ is a constant coefficient ranging from 190 to 220, and k ₃ is a value range a constant coefficient of 0.5 to 1;

In step S303, the oxygen uptake VO _2max at the maximum heart rate per unit volume is obtained by the maximum heart rate y _max and the resting heart rate y _rest : VO _2max =k ₄ *weight*y _max /y _rest , where k ₄ is taken The value ranges from 0.01 to 0.03;

In the step S304, the energy consumption x _max of the measured object at the maximum heart rate is: x _max =k ₅ *VO _2max , where k ₅ is a constant coefficient ranging from 19.5 to 21.5.

Step S4 in this example establishes a relationship model between heart rate and energy consumption, and uses the change of energy consumption to predict and calculate the change of heart rate, thereby realizing the function of predicting the heart rate of the measured object during the exercise; the step S4 includes the following sub step:

Step S401, establishing a relationship model between the center rate and the energy consumption of the motion of the measured object is: y=[ln(x _max /(k ₆ *BMR)-1)-ln(x _max /x-1)]/ k ₇ , wherein k ₆ is a constant coefficient ranging from 0.002 to 0.004, and k ₇ is a constant coefficient ranging from 0.015 to 0.070;

Step S402, measuring an acceleration vector of the measured object at a certain moment during the movement by the acceleration sensor, and converting it into an energy consumption x _max under the maximum heart rate, and then substituting the value of the energy consumption x _max at the maximum heart rate into the The heart rate prediction value y corresponding to the time is obtained by describing the formula of step S401. The certain moment is the time at which the heart rate of the object to be measured is to be known. This is set according to the user's needs, and the acceleration vector in each direction is obtained through the moment, and the acceleration combined vector can be obtained, and the value of the energy consumption is combined. , you can calculate the moment

According to the research of the inventor, in step S301 of this example, the optimal value of α ₁ is 65, the optimal value of α ₂ is 13.73, the best value of α ₃ is 5, and the best value of α _{4 is obtained} . The value is -6.9, the optimal value of β ₁ is 660, the optimal value of β ₂ is 9.6, the optimal value of β ₃ is 1.72, and the optimal value of β ₄ is -4.7; the step S302 The optimal value of k ₂ is 210, and the optimal value of k ₃ is 0.7; in step S303, the optimal value of k ₄ is 0.015; in step S304, the best value of k ₅ is taken. The value is 20.5; in the step S401, the optimal value of k ₆ is 0.0029, and the optimal value of k ₇ is 0.035.

It is worth mentioning that the method for predicting the heart rate of the motion process based on the acceleration sensor in this example has one-to-one correspondence data for each object to be tested, and the data is data having its own uniqueness for each object to be tested. Therefore, the final calculated heart rate predicted value y is also in one-to-one correspondence with each subject, and the heart rate predicted value y is related to the basic data of the subject, that is, the resting heart rate, gender, and the subject. Age, height, weight and historical data are relevant and therefore very informative.

This example proposes a method of using the acceleration sensor to predict the heart rate of the subject under motion, and solves the problem that the traditional heart rate measurement method requires professional operation, equipment and can not be portable, and expands the heart rate prediction in sports training and health monitoring. The application and popularization of multiple fields, the invention can only predict the heart rate of the measured object during exercise by using the acceleration sensor, is simple and easy to operate, and the measurement accuracy satisfies the general training requirements, especially for the elderly or special with heart rate health problems. The crowd is even more significant.

Example 2:

Based on the first embodiment, this example performs an actual simulation test to test a method for predicting the heart rate of a motion process based on a three-axis acceleration sensor, including the following steps:

Step A, the three-axis acceleration sensor senses the acceleration signals generated by the object in the front, back, horizontal and vertical directions, and measures the acceleration vectors in the three directions of X, Y and Z, and calculates the acceleration vector corresponding to the time. .

Step B, establishing a relationship model between the amount of change in the acceleration and the vector on the time axis and the energy consumption

The amount of change in energy consumption is obtained, and a value of the new energy consumption is obtained, and the coefficient k ₁ ranges from 0.005, 0.007, and 0.010.

Step C, calculating the basal metabolic rate BMR of the tested subject according to the sex, weight, height and age of the subject, wherein the basal metabolic rate method of the _male BMR _male =α ₁ +α ₂ *weight+α ₃ *height +α ₄ *age, coefficient α ₁ , α ₂ , α ₃ , α ₄ , basal metabolic rate method for women BMR _female =β ₁ +β ₂ *weight+β ₃ *height+β ₄ *age, coefficient β ₁ , β ₂ , β ₃ , β ₄ ; α _{1 has} the best value of 65, α _{2 has} the best value of 13.73, α _{3 has} the best value of 5, and α _{4 has} the best value - 6.9; The optimal value of β ₁ is 660, the best value of α ₂ is 9.6, the best value of β ₃ is 1.72, and the best value of β ₄ is -4.7.

In step D, the maximum heart rate y _{max is} obtained by the formula y _max =k ₂ +k ₃ *age, and k ₂ and k ₃ are constants. The range of k ₂ is [190, 220], the range of k ₃ is [0.5, 1], the best value of k ₂ is 210, and the optimum value of k ₃ is 0.7. And using the measured resting heart rate y _rest , calculate the maximum heart rate oxygen consumption VO _2max = k ₄ * weight * y _max / y _rest . The coefficient selected in the calculation method of the oxygen consumption at the maximum heart rate is k ₄ . The range of k ₄ is [0.01, 0.03], and the optimum value of k ₄ is 0.015.

Step E, VO _2max x _max energy is calculated at the maximum heart rate, energy consumption is calculated at the maximum heart rate x _max x _max by the method of maximum heart rate, oxygen consumption = k ₅ * VO _2max, coefficient k _5. The range of k ₅ is [19.5, 21.5], and the optimum value of k ₅ is 20.5.

Step F, establish a relationship model between the heart rate and the energy consumption of the measured object during the exercise: y-[ln(x _max /(k ₆ *BMR)-1)-ln(x _max /x-1) ] / k ₇ , the energy consumption x _max and the basal metabolic rate BMR in the relationship model involving the maximum heart rate can be calculated by the previous steps, and the coefficient k ₆ ranges from [0.002, 0.004], the coefficient k The value range of ₇ is [0.015, 0.070], the optimum value of k ₆ is 0.0029, and the optimum value of k ₇ is 0.035.

Step G, converting the acceleration combined vector measured by the acceleration sensor into the energy consumption x _max under the maximum heart rate, and substituting the relationship model between the heart rate and the energy consumption of the object under the motion, that is, the relationship into the step F The module can get the predicted value y of the heart rate.

Example 3:

The present invention also provides an apparatus for predicting a heart rate of a motion process based on an acceleration sensor, wherein the apparatus for predicting a heart rate of a motion process based on the acceleration sensor employs a method of predicting a heart rate of a motion process based on an acceleration sensor as described in Embodiment 1 or Embodiment 2.

Preferably, the device for predicting the heart rate of the exercise process based on the acceleration sensor in the present example is a watch, and when the elderly or a special person with a heart rate health problem carries the device for predicting the heart rate of the exercise process based on the acceleration sensor according to the present invention, Time statistics and analysis can achieve heart rate prediction during exercise, which is very significant.

The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and cannot be determined. The specific implementation of the invention is limited only to these descriptions. It will be apparent to those skilled in the art that the present invention may be made without departing from the spirit and scope of the invention.

Claims (16)

1. A method for predicting a heart rate during a motion process based on an acceleration sensor, comprising the steps of:

   Step S1, collecting and calculating an acceleration vector generated by the object under motion by the acceleration sensor;

   Step S2, by analyzing the change of the acceleration vector value on the time axis, calculating the change of the energy consumption of the measured object during the movement, and establishing a relationship model between the acceleration vector and the energy consumption;

   Step S3, collecting basic information of the test object, and calculating the basal metabolic rate, the maximum heart rate, the oxygen uptake under the maximum heart rate, and the energy consumption under the maximum heart rate by the calculation;

   In step S4, a relationship model between the center rate and the energy consumption of the motion object of the test object is established, and the change of the heart rate is calculated by using the change of the energy consumption to realize the prediction of the heart rate of the test object during the exercise process.
2. The method for predicting a heart rate of a motion process based on an acceleration sensor according to claim 1, wherein the step S1 is to collect a voltage signal generated by the object under test by a multi-axis acceleration sensor to obtain a multi-axis acceleration sensor. The acceleration vector in each direction is calculated by the acceleration vector in each direction to obtain the acceleration combined vector.
3. The method according to claim 1, wherein the step S1 comprises the following substeps:

   Step S101, obtaining an acceleration vector of the measured object in n directions at time t ₂ by using an n-axis acceleration sensor

   

   And calculate the acceleration vector at time t ₂

   

   

   Step S102, the acquisition time t is _1, the target object by an acceleration vector in the direction of n by n-axis acceleration sensor

   

   And calculate the acceleration vector at time t ₁

   

   
4. A method for predicting a heart rate of a motion process based on an acceleration sensor according to claim 3, wherein The step S2 includes the following sub-steps:

   Step S201, let t ₂ > t ₁ , according to the time from t ₁ to t ₂ , the acceleration combined vector

   

   Transform to

   

   Then establish a relationship model between the acceleration vector and the energy consumption as:

   

   Where k ₁ is a constant coefficient ranging from 0.005 to 0.010; Δx is a change in energy consumption of the object under motion during the time from t ₁ to t ₂ ;

   Step S202, collecting the energy consumption x _{0 of} the measured object at time t ₁ , and then obtaining the energy consumption x of the measured object at time t ₂ is:

   
5. The method according to claim 4, wherein the value of k ₁ is 0.007.
6. The method for predicting a heart rate of a motion process based on an acceleration sensor according to any one of claims 1 to 5, wherein the step S3 comprises the following substeps:

   Step S301, calculating the basal metabolic rate BMR of the test subject according to the sex, weight, height and age of the test subject;

   Step S302, calculating a maximum heart rate y _{max of the} test object;

   Step S303, measuring the resting heart rate y _{pest of the} subject under quiet, obtaining the oxygen uptake VO _{2max at the} maximum heart rate per unit volume by the maximum heart rate y _max and the resting heart rate y _pest ;

   Step S304, the energy consumption x _{max of the} subject under the maximum heart rate is obtained by the oxygen uptake amount VO _2max at the maximum heart rate.
7. A method for predicting a heart rate of a motion process based on an acceleration sensor according to claim 6, wherein in step S301, a basal metabolic rate BMR _{male of a male subject} is BMR _male = α ₁ + α ₂ * weight + α ₃ *height+α ₄ *age; basal metabolic rate of _female subjects BMR _female is BMR _female =β ₁ +β ₂ *weight+β ₃ *height+β ₄ *age; where weight is the weight of the subject , height is the height of the subject, age is the age of the subject, α ₁ , α ₂ , α ₃ , α ₄ , β ₁ , β ₂ , β ₃ and β ₄ are preset constant coefficients, the α The value of ₁ ranges from 50 to 80, the range of α ₂ ranges from 10 to 20, the value of α ₃ ranges from 1 to 10, and the range of α ₄ ranges from -10 to 0. The value of β ₁ ranges from 500 to 700, the value of β ₂ ranges from 5 to 15, the range of β ₃ ranges from 0 to 5, and the range of β ₄ ranges from 10 to 10. ～0;

   The step S2 includes the following sub-steps:

   Step S201, let t ₂ > t ₁ , according to the time from t ₁ to t ₂ , the acceleration combined vector

   

   Transform to

   

   Then establish a relationship model between the acceleration vector and the energy consumption as:

   

   Where k ₁ is a constant coefficient ranging from 0.005 to 0.010; Δx is a change in energy consumption of the object under motion during the time from t ₁ to t ₂ ;

   Step S202, collecting the energy consumption x _{0 of} the measured object at time t ₁ , and then obtaining the energy consumption x of the measured object at time t ₂ is:

   
8. The method according to claim 4, wherein the value of k ₁ is 0.007.
9. The method for predicting a heart rate of a motion process based on an acceleration sensor according to any one of claims 1 to 5, wherein the step S3 comprises the following substeps:

   Step S301, calculating the basal metabolic rate BMR of the test subject according to the sex, weight, height and age of the test subject;

   Step S302, calculating a maximum heart rate y _{max of the} test object;

   Step S303, measuring the resting heart rate y _{pest of the} subject under quiet, obtaining the oxygen uptake VO _{2max at the} maximum heart rate per unit volume by the maximum heart rate y _max and the resting heart rate y _pest ;

   Step S304, the energy consumption x _{max of the} subject under the maximum heart rate is obtained by the oxygen uptake amount VO _2max at the maximum heart rate.
10. A method according to claim acceleration sensor motion prediction based on the heart rate, wherein said 6, the step S301, the male subject, basal metabolic rate BMR _male test subject is _{BMR male = α 1 + α 2} * weight + α ₃ *height+α ₄ *age; basal metabolic rate of _female subjects BMR _female is BMR _female =β ₁ +β ₂ *weight+β ₃ *height+β ₄ *age; where weight is the weight of the subject , height is the height of the subject, age is the age of the subject, α ₁ , α ₂ , α ₃ , α ₄ , β ₁ , β ₂ , β ₃ and β ₄ are preset constant coefficients, the α The value of ₁ ranges from 50 to 80, the range of α ₂ ranges from 10 to 20, the value of α ₃ ranges from 1 to 10, and the range of α ₄ ranges from -10 to 0. The value of β ₁ ranges from 500 to 700, the value of β ₂ ranges from 5 to 15, the range of β ₃ ranges from 0 to 5, and the range of β ₄ ranges from 10 to 10. ～0;

    In the step S302, the maximum heart rate y _{max of the} object to be tested is calculated by y _max =k ₂ +k ₃ *age, where k ₂ is a constant coefficient ranging from 190 to 220, and k ₃ is a value range a constant coefficient of 0.5 to 1;

    In step S303, the oxygen uptake VO _2max at the maximum heart rate per unit volume is obtained by the maximum heart rate y _max and the resting heart rate y _pest : VO _2max =k ₄ *weight*y _max /y _pest , where k ₄ is taken The value ranges from 0.01 to 0.03;

    In the step S304, the energy consumption x _max of the measured object at the maximum heart rate is: x _max =k ₅ *VO _2max , where k ₅ is a constant coefficient ranging from 19.5 to 21.5.
11. The method according to claim 7, wherein the step S4 comprises the following substeps:

    Step S401, establishing a relationship model between the center rate and the energy consumption of the motion of the measured object is: y=[ln(x _max /(k ₆ *BMR)-1)-ln(x _max /x-1)]/ k ₇ , wherein k ₆ is a constant coefficient ranging from 0.002 to 0.004, and k ₇ is a constant coefficient ranging from 0.015 to 0.070;

    Step S402, measuring an acceleration vector of the measured object at a certain moment during the movement by the acceleration sensor, and converting it into an energy consumption x _max under the maximum heart rate, and then substituting the value of the energy consumption x _max at the maximum heart rate into the The heart rate prediction value y corresponding to the time is obtained by describing the formula of step S401.
12. The method for predicting a heart rate of a motion process based on an acceleration sensor according to claim 8, wherein in the step S301, the value of α ₁ is 65, the value of α ₂ is 13.73, and the value of α ₃ is 5. , the value of α ₄ is -6.9, the value of β ₁ is 660, the value of β ₂ is 9.6, the value of β ₃ is 1.72, and the value of β ₄ is -4.7. In step S302, k ₂ The value of the value is 210, the value of k ₃ is 0.7; in the step S303, the value of k ₄ is 0.015; in the step S304, the value of k ₅ is 20.5; in the step S401, k ₆ The value is 0.0029, and the value of k ₇ is 0.035.
13. An apparatus for predicting a heart rate of a motion process based on an acceleration sensor, characterized in that the method for predicting a heart rate of a motion process based on an acceleration sensor according to any one of claims 1 to 9 is employed.

    In the step S302, the maximum heart rate y _{max of the} object to be tested is calculated by y _max =k ₂ +k ₃ *age, where k ₂ is a constant coefficient ranging from 190 to 220, and k ₃ is a value range a constant coefficient of 0.5 to 1;

    In step S303, the oxygen uptake VO _2max at the maximum heart rate per unit volume is obtained by the maximum heart rate y _max and the resting heart rate y _pest : VO _2max =k ₄ *weight*y _max /y _pest , where k ₄ is taken The value ranges from 0.01 to 0.03;

    In the step S304, the energy consumption x _max of the measured object at the maximum heart rate is: x _max =k ₅ *VO _2max , where k ₅ is a constant coefficient ranging from 19.5 to 21.5.
14. The method according to claim 7, wherein the step S4 comprises the following substeps:

    Step S401, establishing a relationship model between the center rate and the energy consumption of the motion of the measured object is: y=[ln(x _max /(k ₆ *BMR)-1)-ln(x _max /x-1)]/ k ₇ , wherein k ₆ is a constant coefficient ranging from 0.002 to 0.004, and k ₇ is a constant coefficient ranging from 0.015 to 0.070;

    Step S402, measuring an acceleration vector of the measured object at a certain moment during the movement by the acceleration sensor, and converting it into an energy consumption x _max under the maximum heart rate, and then substituting the value of the energy consumption x _max at the maximum heart rate into the The heart rate prediction value y corresponding to the time is obtained by describing the formula of step S401.
15. The method for predicting a heart rate of a motion process based on an acceleration sensor according to claim 8, wherein in the step S301, the value of α ₁ is 65, the value of α ₂ is 13.73, and the value of α ₃ is 5. , the value of α ₄ is -6.9, the value of β ₁ is 660, the value of β ₂ is 9.6, the value of β ₃ is 1.72, and the value of β ₄ is -4.7. In step S302, k ₂ The value of the value is 210, the value of k ₃ is 0.7; in the step S303, the value of k ₄ is 0.015; in the step S304, the value of k ₅ is 20.5; in the step S401, k ₆ The value is 0.0029, and the value of k ₇ is 0.035.
16. An apparatus for predicting a heart rate of a motion process based on an acceleration sensor, characterized in that the method for predicting a heart rate of a motion process based on an acceleration sensor according to any one of claims 1 to 9 is employed.

Images