Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention provides an EMS-based exercise method and system to solve the traditional shortcoming of slow exercise effect.
To achieve the above and other related objects, the present invention provides an EMS-based fitness method, including:
acquiring physiological parameter data of a user;
generating a control signal according to the physiological parameter data;
outputting a pulse signal in response to the control signal;
and outputting an electrical stimulation signal according to the pulse signal.
Optionally, generating a control signal according to the physiological parameter data specifically includes:
determining a motion parameter according to the physiological parameter data;
and generating a control signal according to the motion parameter.
Optionally, determining a motion parameter according to the physiological parameter data specifically includes:
and taking the physiological parameter data as the input of a neural network model, and taking the motion parameter as the output of the neural network model.
Optionally, the neural network model is obtained by:
collecting historical motion data of a user and using the historical motion data as a sample set;
and carrying out neural network training by using the sample set to obtain a neural network model.
To achieve the above and other related objects, the present invention also provides an EMS-based exercise system, including:
the acquisition terminal is used for acquiring physiological parameter data of a user;
the user side is used for generating a control signal according to the physiological parameter data;
the control end is used for responding to the control signal and outputting a pulse signal;
and the stimulation end is used for outputting an electrical stimulation signal according to the pulse signal.
Optionally, the user terminal includes:
the motion parameter determining unit is used for determining motion parameters according to the physiological parameter data;
and the control signal generating unit is used for generating a control signal according to the motion parameter.
Optionally, determining a motion parameter according to the physiological parameter data specifically includes:
and taking the physiological parameter data as the input of a neural network model, and taking the motion parameter as the output of the neural network model.
Optionally, the neural network model is obtained by:
collecting historical motion data of a user and using the historical motion data as a sample set;
and carrying out neural network training by using the sample set to obtain a neural network model.
Optionally, the system further comprises a management platform connected with the plurality of user terminals.
To achieve the above and other related objects, the present invention also provides an EMS-based fitness system, comprising:
a memory for storing a computer program;
a processor for executing the computer program stored in the memory to cause the exercise system to perform the exercise method.
As described above, the EMS-based fitness method and system according to the present invention have the following advantages:
1. the exercise parameters are set through the user side, customized parameters can be output according to the personal physical condition of the user and expected exercise effect, and the best exercise effect is guaranteed.
2. Through the neural network algorithm, an optimal training scheme can be customized for a user, the best effect is achieved, and the training time waste caused by frequent adjustment of the training scheme by the user in the training process is avoided.
3. In the management platform, the details of each operation of each user are recorded, and along with the increase of sample data, more reasonable exercise modes can be recommended better according to individual characteristics.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification.
The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
As shown in fig. 1, the present invention provides an EMS-based fitness method, which includes:
s1, acquiring physiological parameter data of the user;
s2 generating a control signal according to the physiological parameter data;
s3 outputting a pulse signal in response to the control signal;
s4 outputting an electrical stimulation signal according to the pulse signal.
In step S1, physiological parameter data of the user is acquired.
Specifically, the physiological parameter data may include one or more of parameters such as weight, height, body fat content, muscle mass, and the like.
In step S2, a control signal is generated from the physiological parameter data.
Specifically, as shown in fig. 2, the steps at least include:
s21 determining a motion parameter from the physiological parameter data. The exercise parameters referred to herein include, for example, frequency, pulse width, intensity, ramp-up time, exercise/rest time. The motion pattern is formed by these parameters, and a training course is formed by a combination of several motion patterns.
Specifically, the physiological parameter data is used as an input of a neural network model, and the motion parameter is an output of the neural network model.
The neural network model is obtained by the following method: collecting historical motion data of a user and using the historical motion data as a sample set; and carrying out neural network training by using the sample set to obtain a neural network model. According to the principle of neural network system establishment and parameter selection, the design of the prediction model models of different physiological parameters corresponding to different exercise intensity parameters comprises the following aspects: in the aspect of parameter selection of a BP neural network input layer, the method follows the following two points of extraction, namely the selected parameters have great influence on the test life of the model, the extracted data are convenient to count, and the counting cost is not too high. Considering comprehensively, the input layer of the motion parameter prediction system comprises n nodes, and the physiological parameter data may include one or more of parameters such as weight, height, body fat content, muscle mass and the like. The output layer is m nodes, that is, the motion parameter data may include one or more of parameters such as electrical stimulation intensity and training time.
Thus, the general expression of the motion parameter prediction is represented as
N=f(f1,···fn)
In the formula f1···fnTo be physiological parameters, N is a kinetic parameter.
In BP neural network structure selection, determining to adopt a BP model with a three-layer structure to predict motion parameters, and predicting the output of the model
The input layer is the selected and extracted input parameter and is a physiological parameter data value, so the number of the neurons of the input layer is set to be n; the expected output of the BP prediction model is the predicted motion parameter value, so the number of neurons in the output layer is set to be m, and the number of neurons in the hidden layer can be determined by the following empirical formula:
S=log2 n
S=2m+1
in the formula, S represents the number of hidden layer neurons, n represents the number of input layer neurons, and m represents the number of output layer neurons
And then a Levenberg-Marquardt algorithm is selected as a BP neural network model in the motion parameter prediction, the convergence rate of the algorithm is high during sample learning training, and the number of initial thresholds required to be determined in the algorithm is small.
More specifically, the training process of the BP neural network model is as follows:
the physiological parameter data is first preprocessed to remove severely distorted samples and then normalized to [0,1] interval, where the mapminmax (p _ u) normalization function in MATLAB is used.
The relevant parameters are set as follows:
the sample learning rate is set to 0.01, the motion factor is set to 0.9, and the target error is set to 0.0001.
The specific BP model training process is as follows:
initializing a BP neural network. Setting connection weight wijThreshold value thetajAnd gammajIs any value within the interval (-1, 1);
selecting physiological parameter data in any group of samples as input data, using motion parameter data as a tag value of output data, giving motion parameters, and predicting a neural network model;
inputting by using BP neural network model
And a connection weight w
ijAnd a threshold value theta
jJointly obtaining BP neural network model intermediate layer input s
jThen inputting s with the intermediate layer
jCalculating each unit input s of BP neural network middle layer through transfer function
jThen by s
jCalculating the output of each unit in the middle layer of BP neural network by transfer function
bj=f(sj),j=1,2···p
In the formula ajRepresenting the actual output of the hidden layer, f(s)j) Is a sigmoid type function:
step four, utilizing output b of BP neural network intermediate layerjConnection right vjiAnd a threshold value gammajCalculating the response C of each unit of the BP neural network output layer through a transfer functiont,
Step five, target vector of motion parameter prediction model
Computing generalized error of output layer
Then, the generalized error of each unit in the middle layer is calculated
Step six, correcting the connection weight and the threshold value of the input layer and the middle layer
An input layer:
the data representing the physiological parameter in a set of samples is input data to the input layer.
An output layer:
and step seven, randomly selecting one from the rest training samples and providing the selected training sample to the BP neural network, and returning to the step three until the m input samples are trained.
And eighthly, randomly selecting a group of BP neural network input and target samples from the m learning samples again, and returning to the third step until the network global error E is less than a preset minimum value, namely the BP neural network converges.
According to exercise history data of a user, and body data collected by a human body composition analyzer before the exercise, the optimal exercise scheme and exercise mode are recommended in a personalized mode, and the exercise mode comprises muscle building, shaping and the like. In the above formula
The motion parameters are the motion parameters required by the invention.
S22 generates a control signal based on the motion parameter.
In step S3, a pulse signal is output in response to the control signal.
In step S4, an electrical stimulation signal is output according to the pulse signal.
In an embodiment of the present invention, the electrical stimulation signal is emitted by a stimulation electrode, at least one stimulation electrode is attached to a wearable device, and the wearable device is a wearable smart gym suit.
The intelligent fitness garment can be a garment or trousers made of flexible fabric, and a plurality of stimulation electrodes are embedded on one side, close to the skin of a human body, of the flexible fabric. Each stimulation electrode is fixed at different position points of the intelligent fitness garment, so that after a user wears the intelligent fitness garment, each stimulation electrode can be attached to each muscle of the body of the user. In the intelligent fitness clothes, a control module can be embedded for generating pulse signals, and each stimulation electrode is connected with the control module respectively.
The muscle groups mainly exercised for different fitness purposes are different. Thus, the stimulation electrodes that need to be activated are also different for different fitness programs. When the muscle group of the arm needs to be exercised, the stimulation electrode positioned at the arm is activated, and when the muscle group of the leg needs to be exercised, the stimulation electrode positioned at the leg is activated.
In the foregoing, the intelligent fitness garment has a plurality of stimulation electrodes, each stimulation electrode corresponds to a different muscle group, so that different electrodes need to be controlled independently, the independence of multi-output is ensured, and the problem of mutual interference cannot occur.
As shown in fig. 3, the present invention further provides an EMS-based exercise system, which at least includes an acquisition end 1, a user end 2, a control end 3 and a stimulation end 4.
The acquisition terminal is used for acquiring physiological parameter data of the user.
In one embodiment, the physiological parameter data may include one or more of weight, height, body fat content, muscle mass, and the like.
And the user side is used for generating a control signal according to the physiological parameter data.
In one embodiment, the user terminal is a terminal installed with APP software, including but not limited to a smart phone, a tablet, a PC, and the like.
The control end is used for responding to the control signal and outputting a pulse signal;
and the stimulation end is used for outputting an electrical stimulation signal according to the pulse signal.
In an embodiment, as shown in fig. 4, the user side includes:
a motion parameter determination unit 21 for determining a motion parameter according to the physiological parameter data;
a control signal generating unit 22, configured to generate a control signal according to the motion parameter.
In an embodiment, the determining the motion parameter according to the physiological parameter data specifically includes:
and taking the physiological parameter data as the input of a neural network model, and taking the motion parameter as the output of the neural network model.
In one embodiment, the neural network model is obtained by:
collecting historical motion data of a user and using the historical motion data as a sample set;
and carrying out neural network training by using the sample set to obtain a neural network model.
More specifically, the algorithm of the neural network first inputs a set of x1,x2,...,xmComing to the input layer, a set of data s is then generated by the connection weights with the hidden layer1,s2,...,snAs the input of the hidden layer, the theta () activation function of the hidden layer node is changed into theta(s)j) Wherein s isjThe output produced by the jth node of the hidden layer is represented, and then the loss function is defined by the minimized root mean square deviation:
and then, obtaining the gradient of L (e) to the connection weight w by a random gradient descent method. By using
Representing the connection weight of the ith node of the input layer to the jth node of the hidden layer,
representing the connection weight of the i-th node of the hidden layer to the j-th node of the output layer,
represents the input of the jth node of the hidden layer,
representing the input of the j-th point of the output layer.
The upper
right hand corner 1 represents the first level connection weight and 2 represents the second level connection weight. Then there are
Finally, the error is transmitted back by the weight obtained in the previous step, and an output layer is obtained:
according to exercise history data of a user, the optimal exercise scheme and the optimal exercise mode are recommended in a personalized mode by combining body data collected by a human body composition analyzer before the exercise. In the above formula
The motion parameters are the motion parameters required by the invention.
In an embodiment, the system further comprises a management platform connected to the plurality of the user terminals, so that all the data collected by the user terminals or the commands sent by the user terminals can be stored on the management platform. In the management platform, the details of each operation of each user are recorded, and along with the increase of sample data, more reasonable exercise modes can be recommended better according to individual characteristics. Different exercise modes correspond to different electrical stimulation parameters.
Fig. 5 is a work flow of the control end.
When the human body fat collecting device is used, the user side is connected with the control side, user information and body building requirements are input on the user side, the body fat data are collected through the collecting side (a human body composition analyzer is adopted in the embodiment), the user side sends motion parameters to the control side, and the control side outputs corresponding pulses according to a neural network algorithm.
In one aspect, the output pulse signal may be varied based on the user's condition during exercise.
And on the other hand, the control end detects the connection state of the stimulation electrode in real time, and if the electrode is disconnected, the electrode is adjusted and the like, and then the connection electrode outputs a corresponding electrical stimulation signal.
The present invention also provides an EMS-based fitness system, comprising:
a memory for storing a computer program;
a processor for executing the computer program stored in the memory to cause the exercise system to perform the exercise method.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit or an external storage device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a flash Card (FlashCard), and the like. Further, the memory may also include both an internal storage unit and an external storage device. The memory is used for storing the computer program and other programs and data. The memory may also be used to temporarily store data that has been or will be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may comprise any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, etc.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.