CN115590537A - Exercise health management method and device, electronic equipment and storage medium - Google Patents
Exercise health management method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115590537A CN115590537A CN202211497674.8A CN202211497674A CN115590537A CN 115590537 A CN115590537 A CN 115590537A CN 202211497674 A CN202211497674 A CN 202211497674A CN 115590537 A CN115590537 A CN 115590537A
- Authority
- CN
- China
- Prior art keywords
- signal
- function
- mapping
- value
- dimension
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention discloses a sports health management method, a device, electronic equipment and a storage medium, wherein the sports energy value of a human body is evaluated by utilizing an electromyographic signal generated by the body surface during a human body movement test, and then a corresponding sports method and a sports recipe are formulated for the human body based on the sports energy value, so that the problem of movement risks caused by blind movement, wrong movement modes and the sports recipe can be avoided, and the safety of the human body during movement is guaranteed while the human body is helped to carry out scientific and effective exercise.
Description
Technical Field
The invention belongs to the technical field of exercise health management, and particularly relates to an exercise health management method and device, electronic equipment and a storage medium.
Background
Scientific research shows that lack of exercise is one of the main reasons for sub-health of the body, and active physical activity and scientific exercise are effective strategies for reducing the incidence of chronic non-infectious diseases, and play an important role in preventing, delaying, reversing and treating chronic diseases.
Physical activity insufficiency and sitting and movement lack are the common life styles at present, and the health problems caused by the two life styles are concerned by people in all circles, so people pay more and more attention to physical exercise and movement; at present, under the environment of advocating sports fitness, most people do sports according to own will and thinking, and the sports lacks guidance and planning, and has the following defects: the blind exercise and the adoption of wrong exercise modes and exercise recipes often result in certain exercise risks, and under the condition that the improper amount of exercise may have certain negative effects on human bodies, how to carry out scientific and effective exercise becomes a very important problem, so that the method for managing the exercise health capable of scientifically helping people to carry out exercise is urgently provided.
Disclosure of Invention
The invention aims to provide an exercise health management method, an exercise health management device, electronic equipment and a storage medium, which are used for solving the problems that the exercise in the prior art is lack of guidance and planning, and the exercise risk is brought by blind exercise.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, an exercise health management method is provided, including:
acquiring electromyographic signals of different designated parts of a target human body in a motion test process;
carrying out multidimensional characteristic mapping on each electromyographic signal to obtain a multidimensional characteristic signal corresponding to each electromyographic signal, wherein the mapping dimension of any multidimensional characteristic signal is more than or equal to 2;
obtaining a signal component characteristic value of each multi-dimensional characteristic signal based on each multi-dimensional characteristic signal, and calculating a motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal;
acquiring an exercise function management table, wherein the exercise function management table comprises a plurality of exercise function calibration values, and an exercise method and an exercise recipe corresponding to each of the plurality of exercise function calibration values;
and determining a motor function calibration value matched with the motor function evaluation value from the motor function management table based on the motor function evaluation value of the target human body, and obtaining a motor health management suggestion of the target human body based on a motor method and a motor recipe corresponding to the motor function calibration value matched with the motor function evaluation value.
Based on the disclosure, the invention firstly collects the myoelectric signals (which can reflect the motor function of the human body) generated by different designated parts of the body in the process of the movement test of the target human body (such as walking or jogging); then, multi-dimensional characteristic signals reflecting human body functions are reconstructed by using one signal through multi-dimensional characteristic mapping of the electromyographic signals of all parts, so that a plurality of multi-dimensional characteristic signals reflecting human body functions can be reconstructed by using the electromyographic signals of different parts; then, performing component characteristic analysis on the multi-dimensional characteristic signals to obtain a signal component characteristic value of each multi-dimensional characteristic signal, thereby representing the motion function of the target human body by using the signal component characteristic value, wherein the larger the signal component characteristic value is, the more complex the signal component is represented, and the component complexity of the electromyographic signal is closely related to the motion function, so the signal component characteristic value is adopted as the evaluation index of the motion function of the target human body, thereby obtaining the motion function evaluation value of the target human body based on the signal component characteristic values of the multi-dimensional characteristic signals; and finally, finding the motion method and the motion recipe matched with the motion function evaluation value in the motion function management table, thereby obtaining the motion health management suggestion of the target human body according to the matched motion method and recipe.
Through the design, the myoelectric signals generated by the body surface during the human body movement test are utilized to evaluate the movement kinetic energy value of the human body, and then the corresponding movement method and the movement recipe are formulated for the human body based on the movement kinetic energy value, so that the problem of movement risk caused by blind movement, wrong movement modes and the movement recipe can be avoided, and the safety of the human body during movement is guaranteed while the human body is helped to carry out scientific and effective exercise.
In one possible design, performing multidimensional feature mapping on each electromyographic signal to obtain a multidimensional feature signal corresponding to each electromyographic signal, includes:
for any electromyographic signal, determining an electromyographic time sequence signal corresponding to the electromyographic signal in the movement process of the target human body;
obtaining the mapping delay time of the electromyographic time series signal based on the electromyographic time series signal;
determining the optimal mapping dimension of the myoelectric time series signals according to the mapping delay time of the myoelectric time series signals;
carrying out multidimensional characteristic mapping on the electromyographic time series signals according to the following formula (1) based on the mapping delay time and the optimal mapping dimension so as to obtain multidimensional characteristic signals of any electromyographic signals after the mapping is finished;
in the above-mentioned formula (1),
a multi-dimensional characteristic signal representing any electromyographic signal,
a myoelectric time series signal representing any myoelectric signal,
a mapping delay time representing the myoelectric time series signal corresponding to any myoelectric signal,
represents the optimal mapping dimension of any electromyographic signal corresponding to an electromyographic time series signal, wherein,
and is and
represents the above
The length of the sequence of (c).
Based on the above disclosure, the present invention discloses a specific process of multi-dimensional feature mapping, that is, a mapping delay time is determined first, then an optimal mapping dimension is determined according to the mapping delay time, and then mapping of signals is performed according to the mapping delay time and the optimal mapping dimension, so as to realize reconstruction of signals and obtain multi-dimensional feature signals under the optimal mapping dimension.
In one possible design, deriving a mapping delay time of the myoelectric time series signal based on the myoelectric time series signal includes:
and constructing an autocorrelation function of the electromyographic time series signal by taking the time delay value as an argument, wherein the autocorrelation function is as follows:
in the above-mentioned formula (2),
the auto-correlation function is represented by a function,
a value representing a time delay of the time delay,
to represent
Obtaining a myoelectric time series signal after the myoelectric time series signal is subjected to the time delay value;
and obtaining a calibration autocorrelation function value, and calculating to obtain a time delay value corresponding to the calibration autocorrelation function value based on the calibration autocorrelation function value and the autocorrelation function, so as to take the time delay value corresponding to the calibration autocorrelation function value as the mapping delay time.
In one possible design, determining an optimal mapping dimension of the electromyographic time series signal according to the mapping delay time of the electromyographic time series signal includes:
based on the formula (1) and the mapping delay time, constructing and obtaining a mapping dimension calculation function of any electromyographic signal based on the mapping delay time, wherein an independent variable of the mapping dimension calculation function is a mapping dimension value;
determining a target proximity point of the mapping dimension calculation function according to the mapping dimension calculation function, wherein the distance between the target proximity point and the mapping dimension calculation function is equal to a preset distance;
constructing a dimension approximation function of the mapping dimension calculation function by using the target near point and the mapping dimension calculation function, wherein the independent variable of the dimension approximation function is the mapping dimension value;
and sequentially selecting different mapping dimension values to be substituted into the dimension approximation function according to an increasing mode until the value of the dimension approximation function meets a preset condition, and taking the mapping dimension value meeting the preset condition as the optimal mapping dimension, wherein the preset condition is that the value of the dimension approximation function is larger than a preset threshold value and does not change any more.
Based on the disclosure, the invention discloses a calculation process of an optimal mapping dimension, namely, a mapping dimension calculation function of any electromyographic signal is constructed and obtained by using the construction formula of the multi-dimensional characteristic signal, the mapping delay time as a constant and the mapping dimension value as an independent variable; then, constructing a dimension approximation function of the mapping dimension function based on the mapping dimension function and a proximity point at a preset distance from the mapping dimension function; and finally, substituting different mapping dimension values into the dimension approximation function until the approximation function value meets a preset condition, and obtaining the optimal mapping dimension.
In one possible design, constructing a dimension approximation function that obtains the mapping dimension calculation function by using the target proximity point and the mapping dimension calculation function includes:
calculating a function based on the target proximity point and the mapping dimension, and constructing and obtaining a first approximation function according to the following formula (3);
in the above-mentioned formula (3),
a first approximation function is represented by a first approximation function,
a value representing the dimension of the mapping is represented,
is shown in
The mapping dimension under the dimension is a calculation function,
to represent
The target-proximity point of (2) is,
is shown in
A mapping dimension calculation function in the dimension,
to represent
The target proximity point of (a);
according to the first approximation function and the following formula (4), a second approximation function is constructed;
in the above-mentioned formula (4),
representing a second approximation function;
constructing and obtaining the dimension approximation function by using the second approximation function according to the following formula (5);
in the above-mentioned formula (5),
representing the dimension approximation function in a manner that is independent of the dimension approximation function,
is shown in
A second approximation function in the dimension.
In one possible design, deriving the signal component feature value for each multi-dimensional feature signal based on each multi-dimensional feature signal includes:
for any multi-dimensional characteristic signal, acquiring a morphological structural element of the any multi-dimensional characteristic signal;
performing expansion and corrosion treatment on any multi-dimensional characteristic signal by using the morphological structure element to respectively obtain an expanded signal and a corroded signal;
constructing a signal characteristic component distribution function by using the expanded signal and the corroded signal;
calculating a q-order metric function of the signal characteristic component distribution function to obtain a signal component characteristic value of any one multi-dimensional characteristic signal based on the q-order metric function;
correspondingly, the method for calculating the motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal comprises the following steps:
and calculating the standard deviation of the characteristic values of the plurality of signal components to use the standard deviation as the motor function evaluation value of the target human body.
Based on the disclosure, the invention discloses a specific calculation process of the signal component characteristic value of any multi-dimensional characteristic signal, namely, firstly, performing morphological processing on the signal based on mathematical morphology, and then, constructing a characteristic component distribution function of the processed signal; finally, calculating a q-order metric function of the distribution function, and obtaining a signal component characteristic value of any multi-dimensional characteristic signal based on the q-order metric function; meanwhile, as described above, each multi-dimensional feature signal can be used as a signal reflecting the motion function of the human body, and therefore, after the signal component feature value of each multi-dimensional feature signal is calculated, in order to ensure the reasonability of the evaluation of the motion function of the human body, the standard deviation of a plurality of signal component feature values is used as the final motion function evaluation value of the human body, so that the accuracy of the evaluation can be improved.
In one possible design, constructing a signal feature distribution function using the dilated signal and the eroded signal includes:
constructing and obtaining a distribution function of the characteristic components of the signals according to the following formula (6) based on the expanded signals and the corroded signals;
in the above-mentioned formula (6),
a distribution function representing a characteristic component of the signal,
representing any of the multi-dimensional characteristic signals,
which is indicative of the signal after the expansion,
a signal indicative of the signal after the corrosion,
the structural elements of the form are shown,
the size of the expressed morphology is shown,
the unit structure element is expressed by the unit structure element,
and is and
to represent
The length of (d);
wherein the q-order metric function of the signal feature component distribution function is:
in the above-mentioned formula (7),
a q-order metric function is represented,
the representation metric coefficient:
wherein the content of the first and second substances,
（8）
in the above-mentioned formula (8),
representing the coverage area of the morphological scale to any one of the multi-dimensional mapping functions when the expansion and erosion treatment is carried out on the morphological scale,
representing the grid number obtained by carrying out grid division on the basis of the morphological structure element after any multi-dimensional mapping function is subjected to expansion and corrosion treatment;
correspondingly, obtaining the signal component characteristic value of any multi-dimensional characteristic signal based on the q-order metric function comprises:
calculating a signal component characteristic value of any one multi-dimensional characteristic signal according to the following formula (9);
in the formula (9), the reaction mixture is,
a signal component characteristic value representing said any multi-dimensional characteristic signal.
In a second aspect, there is provided an exercise health management apparatus comprising:
the acquisition unit is used for acquiring myoelectric signals of different designated parts of a target human body in a motion test process;
the multidimensional mapping unit is used for carrying out multidimensional characteristic mapping on each electromyographic signal to obtain a multidimensional characteristic signal corresponding to each electromyographic signal, and the mapping dimensionality of any multidimensional characteristic signal is greater than or equal to 2;
the motion function evaluation unit is used for obtaining a signal component characteristic value of each multi-dimensional characteristic signal based on each multi-dimensional characteristic signal and calculating a motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal;
the acquisition unit is further used for acquiring an exercise function management table, wherein the exercise function management table comprises a plurality of exercise function calibration values, and an exercise method and an exercise recipe corresponding to each of the plurality of exercise function calibration values;
and the exercise health management unit is used for determining an exercise function calibration value matched with the exercise function evaluation value from the exercise function management table based on the exercise function evaluation value of the target human body, so as to obtain an exercise health management suggestion of the target human body based on an exercise method and an exercise recipe corresponding to the exercise function calibration value matched with the exercise function evaluation value.
In a third aspect, another exercise health management apparatus is provided, taking an apparatus as an electronic device for example, and includes a memory, a processor, and a transceiver, which are sequentially connected in a communication manner, where the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the exercise health management method as described in the first aspect or any one of the possible designs of the first aspect.
In a fourth aspect, there is provided a storage medium having stored thereon instructions for performing the method of exercise health management as described in the first aspect or any one of the possible designs of the first aspect when the instructions are run on a computer.
In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of managing exercise health as described in the first aspect or any one of the possible designs of the first aspect.
Has the beneficial effects that:
(1) The invention utilizes the electromyographic signals generated by the body surface during the human body movement test to evaluate the movement kinetic energy value of the human body, and then, a corresponding movement method and a movement recipe are made for the human body based on the movement kinetic energy value, thus the problem of movement risk caused by blind movement, wrong movement mode and movement recipe can be avoided, and the safety of the human body during movement is ensured while the human body is helped to carry out scientific and effective exercise.
Drawings
Fig. 1 is a schematic flow chart illustrating steps of a method for exercise health management according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an exercise health management apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the embodiments or the description in the prior art, it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists independently, B exists independently, and A and B exist simultaneously; for the term "/and" as may appear herein, which describes another associative object relationship, it means that there may be two relationships, e.g., a/and B, which may mean: a exists independently, and A and B exist independently; in addition, with respect to the character "/" which may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
Example (b):
as shown in fig. 1, the exercise health management method provided in this embodiment can obtain the exercise function of the human body according to the electromyographic signals of the body surface of the human body during the exercise test, and thus, the corresponding exercise method and exercise recipe can be matched based on the exercise function of the human body, so as to help the human body to perform scientific and effective exercise, thereby avoiding the problem of exercise risk caused by traditional blind exercise and adoption of wrong exercise mode and recipe; in this embodiment, the method may be, but is not limited to, executed on a motion management end, where the motion management end may be, but is not limited to, a Personal Computer (PC), a tablet PC, a smart phone, and/or a Personal Digital Assistant (PDA), and it is understood that the foregoing execution subject does not constitute a limitation to the embodiment of the present application, and accordingly, the execution steps of the method may be, but are not limited to, as shown in steps S1 to S5 below.
S1, acquiring electromyographic signals of different designated parts of a target human body in a motion test process; in specific application, the wearable electromyographic signal measuring device can be used for acquiring electromyographic signals of different designated parts of a target human body, such as a NeuSen WM series wireless electromyographic acquisition device; alternatively, the different designated locations may include, but are not limited to: the left or right leg of the target human body includes rectus femoris, vastus lateralis, vastus medialis and/or semitendinosus muscle, etc., of course, the specific location thereof may be specifically set according to the actual use, and is not limited to the foregoing examples; further, the exercise test may be, but is not limited to, walking or jogging at 6-8 kilometers per hour and exercise test time is greater than or equal to 5 minutes; therefore, by using the device and the operation test method, the body surface electromyographic signals of all designated parts of the target human body in the motion test process can be acquired and obtained.
After the body surface electromyographic signals of different designated parts of the target human body are acquired, the motor function of the target human body can be evaluated by utilizing the acquired electromyographic signals so as to match corresponding exercise health management suggestions on the basis of the evaluated motor function values; in the present embodiment, the reason why the myoelectric signal is used for the motion estimation is: the electromyographic signal is a physiological signal generated by muscle contraction and relaxation change during human body movement, so the signal is equivalent to a reaction signal of the body function during human body movement, and thus, the motor function of the target human body can be accurately evaluated by utilizing the collected electromyographic signal; the process of estimating the motor function of the target human body based on the electromyographic signal is shown in steps S2 and S3 below.
S2, carrying out multi-dimensional feature mapping on each electromyographic signal to obtain a multi-dimensional feature signal corresponding to each electromyographic signal, wherein the mapping dimension of any multi-dimensional feature signal is more than or equal to 2; when the method is applied specifically, multidimensional feature mapping is carried out on any electromyographic signal, namely, the feature of the signal is subjected to dimension raising, so that the signal is mapped from a low-dimensional space to a high-dimensional space, and thus multidimensional features are obtained, and thus, the step is equivalent to reconstructing a multidimensional feature signal capable of reflecting human body functions by using any electromyographic signal; therefore, the step S2 maps each multi-dimensional feature, that is, uses myoelectric signals of different designated parts to reconstruct a multi-dimensional feature signal whose respective part can reflect the function of the human body, and then, can evaluate the motor function of the target human body based on a plurality of multi-dimensional feature signals; specifically, since the multidimensional mapping process of each electromyographic signal is the same, the following will specifically describe any electromyographic signal by taking as an example, and the steps may be, but are not limited to, the following steps S21 to S24.
S21, determining an electromyographic time sequence signal corresponding to any electromyographic signal in the movement process of the target human body; in specific application, any electromyographic signal is sampled to obtain a corresponding electromyographic time series signal, optionally, any electromyographic signal can be sampled at a sampling frequency of 1Khz to obtain a data point with a length of 200, and the 200 data points can form the electromyographic time series signal of any electromyographic signal; of course, the parameters for sampling any electromyographic signals may be specifically set according to actual use, and are not limited to the above examples.
After obtaining the electromyographic time series signal of any electromyographic signal, a mapping parameter for performing the multidimensional feature mapping may be determined, in this embodiment, the parameter for determining the feature mapping mainly includes: mapping delay time and optimal mapping parameters; therefore, the following describes a specific determination process of the aforementioned mapping parameters, as shown in the following steps S22 and S23, respectively.
S22, obtaining the mapping delay time of the myoelectric time series signal based on the myoelectric time series signal; in particular, the present embodiment uses an autocorrelation function to determine the mapping delay time of the myoelectric time-series signal, wherein the process of determining the mapping delay time by using the autocorrelation function is shown in the following steps S22a and S22b.
S22a, constructing an autocorrelation function of the electromyographic time sequence signal by taking a time delay value as an argument; in a specific application, the autocorrelation function may be, but is not limited to, the following formula (2).
In the above-mentioned formula (2),
the auto-correlation function is represented by a function,
a value representing a time delay of the time delay,
represent
And obtaining the myoelectric time series signal after the time delay value.
S22b, a calibration autocorrelation function value is obtained, a time delay value corresponding to the calibration autocorrelation function value is calculated and obtained based on the calibration autocorrelation function value and the autocorrelation function, and the time delay value corresponding to the calibration autocorrelation function value is used as the mapping delay time.
The principle of the foregoing steps S22a and S22b is: based on the fact that each data point in the electromyographic time-series signal is known, the method in the formula (2) is
Then it is a known value, and therefore, in the whole equation (2),
it becomes an independent variable and the like,
it is a dependent variable, so this embodiment sets a calibrated autocorrelation function value for it, and calculates a corresponding time delay value based on the calibrated autocorrelation function value; optionally, the calibrated autocorrelation function value may be, but is not limited to, 1-1/e of an initial value of the autocorrelation function, and the initial value may be, but is not limited to, a value corresponding to a time delay value of 0The function value is the mean square value of the myoelectric time series signal.
Based on the steps S22a and S22b, the mapping delay time can be calculated, and then, based on the mapping delay time, the optimal mapping dimension under the mapping delay time can be calculated, as shown in the following step S23.
S23, determining the optimal mapping dimension of the electromyographic time series signals according to the mapping delay time of the electromyographic time series signals; in specific application, a mapping dimension calculation function of the myoelectric time series signal can be constructed based on a multi-dimensional characteristic mapping formula, then, a dimension approximation function of the dimension calculation function is constructed by utilizing the mapping dimension calculation function and a proximity point at a preset distance from the mapping dimension calculation function, and finally, the optimal mapping dimension can be obtained based on the dimension approximation function; alternatively, the specific determination process of the optimal mapping dimension may be, but is not limited to, as shown in steps S23a to S23d described below.
S23a, constructing and obtaining a mapping dimension calculation function of any electromyographic signal based on the mapping delay time based on a formula (1) and the mapping delay time, wherein an independent variable of the mapping dimension calculation function is a mapping dimension value; in specific application, the formula (1) is a multidimensional feature mapping formula, as shown below:
in the above-mentioned formula (1),
a multi-dimensional characteristic signal representing any electromyographic signal,
represents the myoelectric time series signal corresponding to any myoelectric signal,
indicating that any of the myoelectric signals corresponds to a muscleThe mapping delay time of the electrical time series signal,
represents an optimal mapping dimension of any electromyographic signal corresponding to an electromyographic time series signal, wherein,
and is and
represents the above
The length of the sequence of (c).
As can be seen from the above formula (1), on the basis that the mapping delay time is a known quantity, the variables in the whole formula (1) have only the optimal mapping dimension sum
Therefore, equivalently, a multidimensional characteristic mapping formula is used for carrying out reverse extrapolation to obtain the optimal mapping dimension corresponding to the myoelectric time series signal; based on this, the above equation (1) can be changed into the mapping dimension calculation function, which can be, but is not limited to, as shown in the following equation (10):
in the above-mentioned formula (10),
a function representing the calculation of the dimensions of the mapping,
representing the mapping dimension value.
As can be seen from the above equation (10), it is equivalent to that the values are different
Determining an optimal value by using the calculation function, so that the optimal value is taken as an optimal mapping dimension; in specific application, a dimension approximation function is constructed based on the mapping dimension calculation function and the corresponding adjacent points thereof, and finally, the mapping dimension values are sequentially increased in an incremental manner until the function value of the dimension approximation function is larger than a preset threshold value and does not change any more, so that the optimal mapping dimension can be obtained; alternatively, the construction process of the aforementioned dimension approximation function may be, but is not limited to, as shown in step S23b and step S23c below.
S23b, determining a target proximity point of the mapping dimension calculation function according to the mapping dimension calculation function, wherein the distance between the target proximity point and the mapping dimension calculation function is equal to a preset distance; in a specific application, the preset distance may be, but is not limited to, in [10,50], in the present embodiment, preferably 25; meanwhile, on the basis of the known mapping dimension calculation function and the distance between the function and a target proximity point, the target proximity point can be obtained by using the calculation principle between lines and points, and further, according to the formula (10), the mapping dimension calculation function includes a plurality of points, so that, in step S23b, the target proximity point of each point in the calculation function is the target proximity point (for example, when i =1, the first point in the function is the target proximity point corresponding to the first point in the function, and when i =2, the second point in the function is the target proximity point corresponding to the second point in the function), and then, based on each point in the function and the target proximity point of each point, the dimension approximation function can be constructed, and the specific steps are as shown in the following step S23c.
S23c, constructing a dimension approximation function of the mapping dimension calculation function by using the target near point and the mapping dimension calculation function, wherein the independent variable of the dimension approximation function is the mapping dimension value; in specific application, the first approximation function may be constructed according to the following formula (3), and then the second approximation function is constructed according to the first approximation function, so that the dimension approximation function is obtained by the second approximation function, and the formula is specifically constructed as shown below.
Wherein the first approximation function is:
in the above-mentioned formula (3),
a first approximation function is represented by a first approximation function,
a value representing the dimension of the mapping is represented,
is shown in
A mapping dimension calculation function in the dimension,
to represent
The target-proximity point of (2) is,
is shown in
A mapping dimension calculation function in the dimension,
to represent
Is near the point.
Based on the above formula (3), when the values of i are different, the calculation is at the second place
Under dimensionIs different from the function value corresponding to its target proximity point, and
comparing the difference value between the function under the dimensionality and the function value corresponding to the target adjacent point of the function under the dimensionality with the difference value to obtain a first approximation function value; if i =1, then it is the calculation of
Under dimension
And with
And calculating the difference of
Under dimension
And
the difference between the two values is calculated, and then the ratio of the two values is calculated, and the same is true when i is the rest value.
After the first approximation function is obtained, a second approximation function can be constructed and obtained by using the first approximation function, as shown in the following formula (4):
in the above-mentioned formula (4),
representing a second approximation function; as can be seen from the above equation (4), this is equivalent to substituting each point in the mapping dimension calculation function into the above equation (4), so as to utilize each point in the function and its corresponding target proximity point to calculate the mapping dimensionConstructing a second approximation function, i.e. calculating, i starting from 1 and going to
。
Similarly, after the second approximation function is obtained, the second approximation function can be used to construct a dimension approximation function, as shown in the following formula (5).
In the above-mentioned formula (5),
representing the dimension approximation function in a manner that is independent of the dimension approximation function,
is shown in
A second approximation function in dimension; based on the formula (5), it can be known that each point in the mapping dimension calculation function is substituted into the formula (4) in different mapping dimensions, so that second approximation function values in different mapping dimensions are calculated based on the function value of each point in the function and the function value of the target adjacent point corresponding to each point, and the ratio of the second approximation function values in different mapping dimensions is used as a dimension approximation value, so that the optimal mapping dimension can be determined according to the formula (5), as shown in the following step S23d.
S23d, sequentially selecting different mapping dimension values to be substituted into the dimension approximation function in an increasing mode, and stopping until the value of the dimension approximation function meets a preset condition, so that the mapping dimension value meeting the preset condition is used as the optimal mapping dimension, wherein the preset condition is that the value of the dimension approximation function is larger than a preset threshold value and does not change any more; when the method is applied specifically, the initial value of the one-dimensional mapping is determined, and then different images are displayed in an increasing modeSubstituting the initial value of the dimension mapping into the formula (5) to obtain dimension approximation function values under different dimensions, and finally ending the iteration when the value of the dimension approximation function calculated by the iteration is larger than a preset threshold and does not change any more, wherein the value of the mapping dimension when the iteration condition (namely the preset condition) is met is the optimal mapping dimension; e.g. the initial value of the map dimension value is 2, e.g.
If not, the mapping dimension value is accumulated to 1, the second function approximation value under the 4 th dimension and the 3 rd dimension is calculated again, the two values are continuously compared to obtain a dimension approximation function value under the 3 rd dimension, the judgment is carried out in the same way, and iteration is carried out again until the calculated dimension approximation function value meets the preset condition; if it is
If the calculated dimension approximation function value satisfies the preset condition, the optimal mapping dimension is 5.
After the optimal mapping dimension is obtained, multidimensional feature mapping may be performed on the myoelectric time series signal of any myoelectric signal according to the formula (1) by combining the mapping delay time, so as to obtain a multidimensional feature signal of any myoelectric signal, as shown in the following step S24.
And S24, carrying out multi-dimensional feature mapping on the electromyographic time series signals according to the following formula (1) based on the mapping delay time and the optimal mapping dimension, so as to obtain the multi-dimensional feature signals of any electromyographic signals after the mapping is finished.
In the above-mentioned formula (1),
a multi-dimensional characteristic signal representing any electromyographic signal,
a myoelectric time series signal representing any myoelectric signal,
a mapping delay time representing the myoelectric time series signal corresponding to any myoelectric signal,
represents the optimal mapping dimension of any electromyographic signal corresponding to an electromyographic time series signal, wherein,
and is and
represents the above
The length of the sequence of (c).
Therefore, based on the steps S21 to S24, the multi-dimensional characteristic signal of each electromyographic signal can be obtained; of course, in this embodiment, the principle of multi-dimensional feature mapping of the remaining electromyographic signals is the same as that of any one of the above electromyographic signals, and is not described herein again.
After obtaining the multi-dimensional characteristic signal of each electromyographic signal, a signal component analysis may be performed to obtain a signal component characteristic value of each multi-dimensional characteristic signal, so as to perform a motor function evaluation of the target human body based on the plurality of signal component characteristic values, wherein the signal component analysis process is as shown in the following step S3.
S3, obtaining a signal component characteristic value of each multi-dimensional characteristic signal based on each multi-dimensional characteristic signal, and calculating a motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal; during specific application, firstly, morphological processing is carried out on each multi-dimensional characteristic signal based on mathematical morphology, and then a characteristic component distribution function of each processed signal is constructed; finally, calculating q-order metric functions of all the distribution functions, and obtaining signal component characteristic values of all the multi-dimensional characteristic signals based on all the q-order metric functions; specifically, since the component analysis process of each multi-dimensional feature signal is the same, the following description will be made by taking any multi-dimensional feature signal as an example, and the steps may be, but are not limited to, the steps S31 to S34 described below.
S31, for any multi-dimensional characteristic signal, acquiring a morphological structure element of the any multi-dimensional characteristic signal; in specific application, the morphological structural element is obtained by a morphological scale and a unit structural element, namely the morphological scale is defined as
The unit structure element is
Then the morphological structural element is
(ii) a Alternatively, the unit structural element may be, but is not limited to, a flat structural element having a length of 3.
After the morphological structure elements are obtained, morphological processing can be performed using the morphological structure elements, specifically, in the present embodiment, expansion and erosion processing is performed on any multi-dimensional feature signal, as shown in step S32 below.
S32, performing expansion and corrosion treatment on any multi-dimensional characteristic signal by using the morphological structural element to respectively obtain an expanded signal and a corroded signal; after the morphological processing, the feature component distribution function of any of the multi-dimensional feature signals can be constructed using the morphological signal, as shown in step S33 below.
S33, constructing a signal characteristic component distribution function by using the expanded signal and the corroded signal; in a specific application, the signal feature component distribution function may be constructed according to, but not limited to, the following formula (6):
in the above-mentioned formula (6),
a distribution function representing a characteristic component of the signal,
representing any of the multi-dimensional characteristic signals,
which is indicative of the signal after the expansion is completed,
a signal indicative of the signal after the corrosion,
the structural elements of the form are shown,
the size of the expressed morphology is shown,
the unit structure element is expressed by the unit structure element,
and is made of
To represent
Length of (d).
As can be seen from the above-mentioned formula (6),
the difference between the expanded signal and the corroded signal of any multi-dimensional characteristic signal is represented, the function of the difference is equivalent to the number of boxes required on a single grid (the grid is equivalent to a grid obtained by dividing the grid based on morphological structure elements after the any multi-dimensional characteristic signal is subjected to the morphological processing (namely, the expanded signal and the corroded signal are subtracted), the number of boxes is used for measuring a fractal set of the signals and is used as a basis for measuring the fractal dimension of the signals, and thus, the distribution function describes the distribution of the difference between two morphological processing results, so that the nonuniformity of the signals on different morphological dimensions can be described through the singularity represented by a high-order matrix of the distribution function; based on this, the present embodiment calculates the q-order metric function of the distribution function, so as to realize the calculation of the signal component characteristic value based on the q-order metric function, as shown in step S34 below.
S34, calculating a q-order metric function of the signal characteristic component distribution function to obtain a signal component characteristic value of any multi-dimensional characteristic signal based on the q-order metric function; in a specific application, the q-order metric function may be, but is not limited to, as shown in the following formula (7):
in the above-mentioned formula (7),
a q-order metric function is represented,
a metric coefficient is represented, and the metric coefficient is:
in the above-mentioned formula (8),
representing the coverage area of the morphological scale to any one of the multi-dimensional mapping functions when the expansion and erosion treatment is carried out on the morphological scale,
representing the grid number obtained by carrying out grid division on the basis of the morphological structural element after any multi-dimensional mapping function is subjected to expansion and corrosion treatment, wherein the grid number is substantially the signal obtained by subtracting the corroded signal from the expanded signal, and the grid number divided under the morphological structural element, and the grid number is different under different scales by combining the formula of the morphological structural element; meanwhile, as can be seen from the above formula, introducing the length of any multi-dimensional feature signal into the morphological structural element is equivalent to performing morphological processing on each point of the signal.
When it is used in detail, examples
Therefore, after the q-order metric function is obtained, the signal component characteristic value of any multi-dimensional characteristic signal can be calculated and obtained by using the following formula (9).
In the formula (9), the reaction mixture is,
a signal component characteristic value representing said any multi-dimensional characteristic signal.
When the method is implemented, the method is equivalent to the sum of q-order metric functions
Performing least squares linear fit to obtain a signal component complexity estimate for any multi-dimensional signature, wherein q can be taken to be 0, thereby simplifying the multi-feature analysis to be based on mathematical formsSingle-dimensional feature analysis of morphology; thus, by adopting the same method, the signal component characteristic value of each multi-dimensional characteristic signal can be calculated, and then the motor function evaluation value of the target human body can be calculated based on a plurality of signal component characteristic values.
In this embodiment, the principle of using the signal component characteristic value to evaluate the motor function is as follows: the larger the signal component characteristic value is, the more complex the representation signal component is, and the component complexity of the electromyographic signal is closely related to the motor function, so that the signal component characteristic value is adopted as the evaluation index of the motor function of the target human body in the embodiment, and the motor function evaluation value of the target human body is obtained based on the signal component characteristic values of the multi-dimensional characteristic signals; alternatively, but not limited to, a standard deviation of a plurality of signal component feature values may be calculated, and the standard deviation may be used as the motor function evaluation value of the target human body.
After the motor function of the target human body is evaluated according to the electromyographic signals of different designated parts of the target human body, corresponding exercise health management can be performed according to the obtained motor function evaluation value, wherein the management process can be but is not limited to the following steps S4 and S5.
S4, acquiring a motion function management table, wherein the motion function management table comprises a plurality of motion function calibration values, and a motion method and a motion recipe corresponding to each motion function calibration value in the plurality of motion function calibration values; when the exercise management terminal is used specifically, the exercise function management table is preset into the exercise management terminal and can be read when the exercise management terminal is used.
S5, based on the motor function evaluation value of the target human body, determining a motor function calibration value matched with the motor function evaluation value from the motor function management table, and obtaining a motor health management suggestion of the target human body based on a motor method and a motor recipe corresponding to the motor function calibration value matched with the motor function evaluation value; in specific application, the exercise method and the exercise recipe corresponding to the exercise function calibration value matched with the exercise function evaluation value can be used as exercise health management suggestions for visual display, and can also be sent to terminals corresponding to a target human body, such as a mobile phone, a computer and the like.
In addition, in this embodiment, for example, the exercise function management table may be further subdivided, for example, under the same exercise function calibration value, based on different genders, heights, and physical health conditions, the exercise function management table may be further subdivided into different exercise methods and exercise recipes; if the sex is male, the height is 180cm and the body is a target body without any diseases, the exercise method A and the exercise recipe A are correspondingly arranged; if the sex is female, the height is 180cm and the body is a target body without any disease, the exercise method B and the exercise recipe B are correspondingly arranged; if the sex is male, the height is 170cm and the body is a target body without any diseases, the movement method C and the movement recipe C are correspondingly arranged; for example, the sex is male, the height is 170cm, and the body has target human body with chronic respiratory disease, and the corresponding motion method D and the motion recipe D are provided; of course, the rest target human bodies with different heights and physical conditions are also provided with corresponding exercise methods and exercise recipes, which are not described in detail herein.
Therefore, through the exercise health management method described in detail in the steps S1 to S5, the exercise energy value of the human body is evaluated by using the electromyographic signals generated on the body surface during the human body exercise test, and then the corresponding exercise method and exercise recipe are formulated for the human body based on the exercise energy value, so that the problem of exercise risks caused by blind exercise, wrong exercise modes and the exercise recipe can be avoided, and the safety of the human body during the exercise can be guaranteed while the human body is helped to do scientific and effective exercises.
As shown in fig. 2, a second aspect of the present embodiment provides a hardware device for implementing the exercise health management method in the first aspect of the embodiment, including:
the acquisition unit is used for acquiring electromyographic signals of different designated parts of the target human body in the motion test process.
And the multidimensional mapping unit is used for carrying out multidimensional characteristic mapping on each electromyographic signal to obtain a multidimensional characteristic signal corresponding to each electromyographic signal, and the mapping dimension of any multidimensional characteristic signal is greater than or equal to 2.
And the motion function evaluation unit is used for obtaining a signal component characteristic value of each multi-dimensional characteristic signal based on each multi-dimensional characteristic signal and calculating the motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal.
The acquisition unit is further used for acquiring a motion function management table, wherein the motion function management table comprises a plurality of motion function calibration values, and a motion method and a motion recipe corresponding to each of the plurality of motion function calibration values.
And the exercise health management unit is used for determining an exercise function calibration value matched with the exercise function evaluation value from the exercise function management table based on the exercise function evaluation value of the target human body, so as to obtain an exercise health management suggestion of the target human body based on an exercise method and an exercise recipe corresponding to the exercise function calibration value matched with the exercise function evaluation value.
For the working process, the working details, and the technical effects of the apparatus provided in this embodiment, reference may be made to the first aspect of the embodiment, which is not described herein again.
As shown in fig. 3, a third aspect of the present embodiment provides another exercise health management apparatus, taking an apparatus as an electronic device as an example, including: a memory, a processor and a transceiver, which are in communication with each other in sequence, wherein the memory is used for storing a computer program, the transceiver is used for transceiving a message, and the processor is used for reading the computer program and executing the exercise health management method according to the first embodiment.
For example, the Memory may include, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Flash Memory (Flash Memory), a First In First Out (FIFO), a First In Last Out (FILO), and/or a First In Last Out (FILO); in particular, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field Programmable Gate Array), and a PLA (Programmable Logic Array), and may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state and is also referred to as a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state.
In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit) which is responsible for rendering and drawing contents required to be displayed on the display screen, for example, the processor may not be limited to a processor using a model STM32F105 series microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, an X86 or the like architecture processor or an integrated embedded neural Network Processor (NPU); the transceiver may be, but is not limited to, a wireless fidelity (WIFI) wireless transceiver, a bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee wireless transceiver (ieee 802.15.4 standard-based low power local area network protocol), a 3G transceiver, a 4G transceiver, and/or a 5G transceiver, etc. In addition, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, the working details, and the technical effects of the electronic device provided in this embodiment, reference may be made to the first aspect of the embodiment, which is not described herein again.
A fourth aspect of the present embodiment provides a storage medium storing instructions including the exercise health management method according to the first aspect of the present embodiment, that is, the storage medium stores instructions that, when executed on a computer, perform the exercise health management method according to the first aspect.
The storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, a flash disk and/or a Memory Stick (Memory Stick), etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, the working details, and the technical effects of the storage medium provided in this embodiment, reference may be made to the first aspect of the embodiment, which is not described herein again.
A fifth aspect of the present embodiments provides a computer program product comprising instructions which, when run on a computer, wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus, cause the computer to perform the method of exercise health management according to the first aspect of the embodiments.
Finally, it should be noted that: the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An exercise health management method, comprising:
acquiring electromyographic signals of different designated parts of a target human body in a motion test process;
performing multidimensional characteristic mapping on each electromyographic signal to obtain a multidimensional characteristic signal corresponding to each electromyographic signal, wherein the mapping dimensionality of any multidimensional characteristic signal is greater than or equal to 2;
obtaining a signal component characteristic value of each multi-dimensional characteristic signal based on each multi-dimensional characteristic signal, and calculating a motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal;
acquiring a motor function management table, wherein the motor function management table comprises a plurality of motor function calibration values, and a motor method and a motor recipe corresponding to each motor function calibration value in the plurality of motor function calibration values;
and determining an exercise function calibration value matched with the exercise function evaluation value from the exercise function management table based on the exercise function evaluation value of the target human body, so as to obtain an exercise health management suggestion of the target human body based on an exercise method and an exercise recipe corresponding to the exercise function calibration value matched with the exercise function evaluation value.
2. The method of claim 1, wherein performing multidimensional feature mapping on each electromyographic signal to obtain a multidimensional feature signal corresponding to each electromyographic signal comprises:
for any electromyographic signal, determining an electromyographic time sequence signal corresponding to the electromyographic signal in the movement process of the target human body;
obtaining the mapping delay time of the myoelectric time series signal based on the myoelectric time series signal;
determining the optimal mapping dimension of the electromyographic time sequence signal according to the mapping delay time of the electromyographic time sequence signal;
carrying out multidimensional characteristic mapping on the electromyographic time series signals according to the following formula (1) based on the mapping delay time and the optimal mapping dimension so as to obtain multidimensional characteristic signals of any electromyographic signals after the mapping is finished;
in the above-mentioned formula (1),
a multi-dimensional characteristic signal representing any electromyographic signal,
represents the myoelectric time series signal corresponding to any myoelectric signal,
a mapping delay time representing the myoelectric time series signal corresponding to any myoelectric signal,
represents an optimal mapping dimension of any electromyographic signal corresponding to an electromyographic time series signal, wherein,
and is and
represents the above
The length of the sequence of (c).
3. The method according to claim 2, wherein deriving the mapping delay time of the electromyographic time series signal based on the electromyographic time series signal comprises:
and constructing an autocorrelation function of the myoelectric time series signal by taking the time delay value as an argument, wherein the autocorrelation function is as follows:
in the above-mentioned formula (2),
the auto-correlation function is represented by a function,
a value representing a time delay of the time delay,
to represent
Obtaining a myoelectric time series signal after the myoelectric time series signal is subjected to the time delay value;
and obtaining a calibration autocorrelation function value, and calculating to obtain a time delay value corresponding to the calibration autocorrelation function value based on the calibration autocorrelation function value and the autocorrelation function, so as to take the time delay value corresponding to the calibration autocorrelation function value as the mapping delay time.
4. The method according to claim 2, wherein determining an optimal mapping dimension of the electromyographic time series signals according to the mapping delay time of the electromyographic time series signals comprises:
based on the formula (1) and the mapping delay time, constructing a mapping dimension calculation function of any electromyographic signal based on the mapping delay time, wherein an independent variable of the mapping dimension calculation function is a mapping dimension value;
determining a target proximity point of the mapping dimension calculation function according to the mapping dimension calculation function, wherein the distance between the target proximity point and the mapping dimension calculation function is equal to a preset distance;
constructing a dimension approximation function of the mapping dimension calculation function by using the target near point and the mapping dimension calculation function, wherein the independent variable of the dimension approximation function is the mapping dimension value;
and sequentially selecting different mapping dimension values to be substituted into the dimension approximation function according to an increasing mode until the value of the dimension approximation function meets a preset condition, and taking the mapping dimension value meeting the preset condition as the optimal mapping dimension, wherein the preset condition is that the value of the dimension approximation function is larger than a preset threshold value and does not change any more.
5. The method of claim 4, wherein constructing a dimension approximation function that yields the mapping dimension calculation function using the target proximity point and the mapping dimension calculation function comprises:
calculating a function based on the target proximity point and the mapping dimension, and constructing and obtaining a first approximation function according to the following formula (3);
in the above-mentioned formula (3),
a first approximation function is represented by a first approximation function,
a value representing the dimension of the mapping is represented,
is shown in
The mapping dimension under the dimension is a calculation function,
to represent
Is close to the point of the object of (1),
is shown in
A mapping dimension calculation function in the dimension,
to represent
The target approach point of (1);
according to the first approximation function and the following formula (4), a second approximation function is constructed;
in the above-mentioned formula (4),
representing a second approximation function;
constructing and obtaining the dimension approximation function by using the second approximation function according to the following formula (5);
in the above-mentioned formula (5),
a function representing the approximation of the dimension is represented,
is shown in
A second approximation function in the dimension.
6. The method of claim 1, wherein deriving a signal component feature value for each multi-dimensional feature signal based on each multi-dimensional feature signal comprises:
for any multi-dimensional characteristic signal, acquiring a morphological structural element of the any multi-dimensional characteristic signal;
performing expansion and corrosion treatment on any multi-dimensional characteristic signal by using the morphological structural element to respectively obtain an expanded signal and a corroded signal;
constructing a signal characteristic component distribution function by using the expanded signal and the corroded signal;
calculating a q-order metric function of the signal characteristic component distribution function to obtain a signal component characteristic value of any multi-dimensional characteristic signal based on the q-order metric function;
correspondingly, the method for calculating the motion function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal comprises the following steps:
and calculating the standard deviation of the characteristic values of the plurality of signal components to use the standard deviation as the motor function evaluation value of the target human body.
7. The method of claim 6, wherein using the dilated signal and the eroded signal to construct a signal feature distribution function comprises:
constructing and obtaining a characteristic component distribution function of the signal based on the expanded signal and the corroded signal according to the following formula (6);
in the above-mentioned formula (6),
a distribution function representing a characteristic component of the signal,
representing any of the multi-dimensional characteristic signals,
which is indicative of the signal after the expansion is completed,
a signal indicative of the signal after the corrosion,
the structural elements of the form are represented,
the size of the expressed morphology is shown,
the unit structure element is expressed by a unit structure element,
and is made of
Represent
The length of (d);
wherein the q-order metric function of the signal feature component distribution function is:
in the above-mentioned formula (7),
a q-order metric function is represented,
the representation metric coefficient:
wherein, the first and the second end of the pipe are connected with each other,
（8）
in the above-mentioned formula (8),
representing the coverage area of the morphological scale to any one of the multi-dimensional mapping functions when the expansion and erosion treatment is carried out on the morphological scale,
representing the grid number obtained by carrying out grid division on the basis of the morphological structure element after any multi-dimensional mapping function is subjected to expansion and corrosion treatment;
correspondingly, obtaining the signal component characteristic value of any one multi-dimensional characteristic signal based on the q-order metric function comprises:
calculating a signal component characteristic value of any multi-dimensional characteristic signal according to the following formula (9);
in the formula (9), the reaction mixture is,
a signal component characteristic value representing said any multi-dimensional characteristic signal.
8. An exercise health management device, comprising:
the acquisition unit is used for acquiring myoelectric signals of different designated parts of a target human body in a motion test process;
the multidimensional mapping unit is used for carrying out multidimensional characteristic mapping on each electromyographic signal to obtain a multidimensional characteristic signal corresponding to each electromyographic signal, and the mapping dimension of any multidimensional characteristic signal is greater than or equal to 2;
the motor function evaluation unit is used for obtaining a signal component characteristic value of each multi-dimensional characteristic signal based on each multi-dimensional characteristic signal and calculating a motor function evaluation value of the target human body by using the signal component characteristic value of each multi-dimensional characteristic signal;
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is further used for acquiring a motion function management table, and the motion function management table comprises a plurality of motion function calibration values and a motion method and a motion recipe corresponding to each of the plurality of motion function calibration values;
and the exercise health management unit is used for determining an exercise function calibration value matched with the exercise function evaluation value from the exercise function management table based on the exercise function evaluation value of the target human body, so as to obtain an exercise health management suggestion of the target human body based on an exercise method and an exercise recipe corresponding to the exercise function calibration value matched with the exercise function evaluation value.
9. An electronic device, comprising: a memory, a processor and a transceiver, which are connected in sequence in communication, wherein the memory is used for storing a computer program, the transceiver is used for transmitting and receiving messages, and the processor is used for reading the computer program and executing the exercise health management method according to any one of claims 1 to 7.
10. A storage medium having stored thereon instructions for performing the exercise health management method according to any one of claims 1 to 7 when the instructions are run on a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497674.8A CN115590537B (en) | 2022-11-28 | 2022-11-28 | Exercise health management method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211497674.8A CN115590537B (en) | 2022-11-28 | 2022-11-28 | Exercise health management method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115590537A true CN115590537A (en) | 2023-01-13 |
| CN115590537B CN115590537B (en) | 2023-03-14 |
Family
ID=84852844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211497674.8A Active CN115590537B (en) | 2022-11-28 | 2022-11-28 | Exercise health management method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115590537B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016149832A1 (en) * | 2015-03-26 | 2016-09-29 | GestureLogic Inc. | Systems, methods and devices for exercise and activity metric computation |
| US20170182362A1 (en) * | 2015-12-28 | 2017-06-29 | The Mitre Corporation | Systems and methods for rehabilitative motion sensing |
| US20190344121A1 (en) * | 2018-05-14 | 2019-11-14 | MAD Apparel, Inc. | Exercise training adaptation using physiological data |
| CN110639169A (en) * | 2019-09-25 | 2020-01-03 | 燕山大学 | CPM lower limb rehabilitation training method and system based on game and electromyographic signals |
| CN110974212A (en) * | 2019-11-07 | 2020-04-10 | 曲阜师范大学 | Electrocardio and myoelectric characteristic fused rehabilitation training motion state monitoring method and system |
| CN112800205A (en) * | 2021-02-26 | 2021-05-14 | 中国人民解放军国防科技大学 | Method and device for obtaining question-answer related paragraphs based on semantic change manifold analysis |
| CN113499084A (en) * | 2021-07-09 | 2021-10-15 | 燕山大学 | Method for establishing stroke motor function evaluation model, evaluation method and system |
| US20220037002A1 (en) * | 2020-07-31 | 2022-02-03 | Boe Technology Group Co., Ltd. | Health managing method and storage medium |
| CN114847933A (en) * | 2022-04-19 | 2022-08-05 | 湘潭大学 | Myoelectric signal gesture recognition method and system based on full convolution residual error network |
| CN115211872A (en) * | 2022-07-29 | 2022-10-21 | 广州中医药大学(广州中医药研究院) | Muscle movement state detection method and device, electronic equipment and storage medium |
-
2022
- 2022-11-28 CN CN202211497674.8A patent/CN115590537B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016149832A1 (en) * | 2015-03-26 | 2016-09-29 | GestureLogic Inc. | Systems, methods and devices for exercise and activity metric computation |
| US20170182362A1 (en) * | 2015-12-28 | 2017-06-29 | The Mitre Corporation | Systems and methods for rehabilitative motion sensing |
| US20190344121A1 (en) * | 2018-05-14 | 2019-11-14 | MAD Apparel, Inc. | Exercise training adaptation using physiological data |
| CN110639169A (en) * | 2019-09-25 | 2020-01-03 | 燕山大学 | CPM lower limb rehabilitation training method and system based on game and electromyographic signals |
| CN110974212A (en) * | 2019-11-07 | 2020-04-10 | 曲阜师范大学 | Electrocardio and myoelectric characteristic fused rehabilitation training motion state monitoring method and system |
| US20220037002A1 (en) * | 2020-07-31 | 2022-02-03 | Boe Technology Group Co., Ltd. | Health managing method and storage medium |
| CN112800205A (en) * | 2021-02-26 | 2021-05-14 | 中国人民解放军国防科技大学 | Method and device for obtaining question-answer related paragraphs based on semantic change manifold analysis |
| CN113499084A (en) * | 2021-07-09 | 2021-10-15 | 燕山大学 | Method for establishing stroke motor function evaluation model, evaluation method and system |
| CN114847933A (en) * | 2022-04-19 | 2022-08-05 | 湘潭大学 | Myoelectric signal gesture recognition method and system based on full convolution residual error network |
| CN115211872A (en) * | 2022-07-29 | 2022-10-21 | 广州中医药大学(广州中医药研究院) | Muscle movement state detection method and device, electronic equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| SACHS N A,等: "Continuous movement decoding using a target-dependent model with EMG inputs", 《2011 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE》 * |
| TOSIN M C,等: "sEMG-Based Upper Limb Movement Classifier: Current Scenario and Upcoming Challenges", 《JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH》 * |
| 熊安斌，等: "基于混沌理论的面瘫患者表面肌电信号分析", 《科学通报》 * |
| 高瞻乐，等: "基于知识图谱分析跑步过程中的生物力学的变化与特征", 《中国组织工程研究》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115590537B (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107115111B (en) | Blood flow state analysis system and method | |
| US10679757B2 (en) | Method and apparatus for establishing a blood pressure model and method and apparatus for determining a blood pressure | |
| US8622921B2 (en) | Sleep evaluation device and sleep evaluation method therefor | |
| CN103323615B (en) | A kind of mobile terminal and method being calculated walking speed by acceleration transducer | |
| CN108305246A (en) | The apparatus and system of flow characteristic is predicted based on medical image | |
| CN105167742B (en) | A kind of fetal weight adaptive estimation method and system | |
| CN109872820A (en) | A kind of no cuff blood pressure measuring method, device, equipment and storage medium | |
| Ying et al. | Distributed intelligent sensor network for the rehabilitation of Parkinson's patients | |
| CN104887215A (en) | Signal processing method in heart rate measurement | |
| CN105286842B (en) | A kind of method and device based on acceleration transducer predicted motion process heart rate | |
| CN115590537B (en) | Exercise health management method and device, electronic equipment and storage medium | |
| CN203436329U (en) | Wearable intelligent exercise monitoring system | |
| CN109662712A (en) | A kind of dynamic multi-frequency impedance tomograph imaging method based on impedance spectrum constraint | |
| CN108652604B (en) | Air bag-free blood pressure detection method and system based on electrocardiosignals | |
| CN112472052A (en) | Weight prediction method, device and equipment based on personal motor function index (PAI) | |
| CN106469243B (en) | Human face skin moisture and elasticity index calculation method based on digital image processing technology | |
| CN105662394B (en) | A kind of method and apparatus prompting the user with information | |
| CN110477897B (en) | Physical ability testing method and system | |
| CN102663735B (en) | Quantitative assessment method for image heterogeneity characteristics | |
| CN115624333B (en) | Human body electrical impedance signal acquisition system and working method thereof | |
| CN116687357B (en) | Sleep monitoring method, device, equipment and storage medium based on millimeter wave radar | |
| Petrellis et al. | Evaluation of Sensors' Precision in a Low Cost e-Health Monitoring System. | |
| Felton et al. | Data Compression via Low Complexity Delta Transition Lossless Encoding for Remote Physiological and Environmental Monitoring | |
| CN109077739A (en) | User data detection method and VR/AR equipment for VR/AR equipment | |
| Liu et al. | Learning a policy for coordinated sampling in body sensor networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |