CN113730892A - Athlete training method and system - Google Patents
Athlete training method and system Download PDFInfo
- Publication number
- CN113730892A CN113730892A CN202111158240.0A CN202111158240A CN113730892A CN 113730892 A CN113730892 A CN 113730892A CN 202111158240 A CN202111158240 A CN 202111158240A CN 113730892 A CN113730892 A CN 113730892A
- Authority
- CN
- China
- Prior art keywords
- training
- motion parameters
- parameters
- athlete
- heart rate
- 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.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B69/00—Training appliances or apparatus for special sports
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2230/00—Measuring physiological parameters of the user
- A63B2230/04—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations
- A63B2230/06—Measuring physiological parameters of the user heartbeat characteristics, e.g. ECG, blood pressure modulations heartbeat rate only
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physical Education & Sports Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to an athlete training method and system. The method comprises the following steps: obtaining the motion parameters of the athlete to be trained before training, and inputting the motion parameters before training into a radial basis function neural network to obtain the training parameters. The invention can obtain proper training parameters aiming at different athletes and improve the training effect.
Description
Technical Field
The invention relates to the technical field of sports training, in particular to a training method and a training system for athletes.
Background
Cardiopulmonary endurance is a hallmark of a person's physical health, and a person with high cardiopulmonary endurance can maintain high-intensity activities for a long period of time without feeling tired. In the training of track and field sports, the cardiopulmonary endurance parameters can reflect the performance of the heart, lungs and muscles in medium and high intensity sports.
Prior art adopts wearable equipment such as bracelet, gather each item parameter such as participant's geographical position in real time, the rhythm of the heart, speed, stride frequency and body temperature, make participant master self real-time training state, reasonable control speed and stride frequency, in time adjust and breathe the rhythm, avoid intensity not enough, can not reach the training effect, also can avoid intensity too big, cause the injury to the health, can also make the coach carry out data analysis and comparison (for example best rhythm of the heart interval, remaining physical strength percentage, before running and run modes such as data contrast), draw the problem that participant exists in training process, improve the training effect.
However, the above modes are set by experience accumulation of the participants and coaches and statistical rules of motion data of most people, differential dynamic management aiming at characteristics of the participants is lacked, training effect cannot be maximized, and the mode of one-to-one tracking management of the coaches is adopted, which is laborious and laborious, cannot be popularized, is limited by personal energy and level of the coaches, and training quality is difficult to improve.
Disclosure of Invention
The invention aims to provide an athlete training method and system, which can obtain proper training parameters for different athletes and improve the training effect.
In order to achieve the purpose, the invention provides the following scheme:
a method of athlete training, comprising:
acquiring motion parameters of an athlete to be trained before training; the motion parameters comprise heart rate, speed, acceleration, resting heart rate and recovery heart rate;
inputting the motion parameters before training into a radial basis function neural network to obtain training parameters, wherein the training parameters are used for guiding the training of athletes; the training parameters include: target heart rate, target velocity, and target acceleration.
Optionally, before inputting the motion parameters into the radial basis function neural network to obtain training parameters, the method further includes:
and carrying out data cleaning on the motion parameters to obtain the cleaned motion parameters.
Optionally, before the data of the motion parameters is cleaned to obtain the cleaned motion parameters, the method further includes:
and sequentially carrying out baseline drift removal processing, filtering processing and feature extraction on the motion parameters to obtain the preprocessed motion parameters.
Optionally, the filtering process includes power frequency filtering and signal filtering.
An athlete training system, comprising:
the acquisition module is used for acquiring the motion parameters of the athlete to be trained before training; the motion parameters comprise heart rate, speed, acceleration, resting heart rate and recovery heart rate;
the training parameter determining module is used for inputting the motion parameters before training into a radial basis function neural network to obtain training parameters, and the training parameters are used for guiding the training of athletes; the training parameters include: target heart rate, target velocity, and target acceleration.
Optionally, the sports training system further includes:
and the data cleaning module is used for carrying out data cleaning on the motion parameters to obtain the cleaned motion parameters.
Optionally, the sports training system further includes:
and the preprocessing module is used for sequentially carrying out baseline drift removal processing, filtering processing and feature extraction on the motion parameters to obtain the preprocessed motion parameters.
Optionally, the filtering process in the preprocessing module includes: power frequency filtering and signal filtering.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the athlete training method of the invention comprises the following steps: acquiring motion parameters of an athlete to be trained before training; the motion parameters before training are input into the radial basis function neural network to obtain training parameters, the training parameters are used for guiding the training of athletes, and the radial basis function neural network can be used for obtaining proper training parameters for different athletes, so that the training effect is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for training an athlete in accordance with an embodiment of the present invention;
FIG. 2 is a block diagram of a radial basis function neural network provided by an embodiment of the present invention;
fig. 3 is a block diagram of an athlete training system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the present invention provides an athlete training method, the method comprising:
step 101: acquiring motion parameters of an athlete to be trained before training; the motion parameters comprise heart rate, speed, acceleration, resting heart rate and recovery heart rate, and the heart rate, resting heart rate and recovery heart rate are collectively referred to as heartbeat data.
Step 102: inputting the motion parameters before training into a radial basis function neural network to obtain training parameters, wherein the training parameters are used for guiding the training of athletes; the training parameters include: target heart rate, target velocity, and target acceleration. In some training protocols, heart rate is linear with training intensity. During the training, the average heart rate of the athlete is high, indicating that the athlete has performed intensive training. Once the athlete is over-trained, the heart rate will increase at any running speed. This means that the training intensity is not suitable for the athlete, and according to this principle, by checking the daily heart rate data, the heart rate that the athlete can maintain at different distances can be easily found out, thereby preventing the athlete from starting too fast in long-distance sports and other mistakes. The agility index can help a coach to control the training intensity according to the heart rate, another important function is the sum of agility indexes, the sum can be used for evaluating the reaction of athletes in short-time training, and the acceleration can indicate the speed of the reaction.
As shown in fig. 2, the radial basis function neural network mainly includes an input layer, a hidden layer, and an output layer.
An input layer: for inputting the exercise parameters (X1 to Xn) before the acquisition training.
Hidden layer: the method is characterized by comprising M hidden nodes, wherein an activation function phi of each hidden node is a Gaussian function, and the motion parameters before training are subjected to feature space mapping transformation. In the hidden node determination, firstly, a dynamic K-means clustering method is adopted, feature vectors obtained from different reference group samples are drawn in a feature space, and then clustering analysis is carried out based on the dynamic K-means clustering method to obtain the number of centers.
An output layer: the function of the output layer neuron is a linear function, and the information output by the hidden layer neuron is subjected to linear weighting and then output to obtain training parameters (Y1 to Yt, Y1 to Y3 are heart rate, speed and acceleration respectively).
The training process of the radial basis function neural network comprises the following steps:
firstly, the acquisition and labeling of training data of different contrast group testees need to be completed: the method comprises the steps of collecting motion parameters of an athlete before training on 400 m, 800 m, 3000 m and other sports, and marking the training parameters in corresponding data according to the requirements of a training stage and at intervals of 10 seconds, 30 seconds or 1 minute. And (4) arranging all the measured and marked data to form a training data set.
After the initial parameters of the model are determined, the motion parameters before training in the training data set are used as input, and the corresponding labeled parameters in the training data set are used as output to carry out modeling training on the radial basis function neural network to obtain the trained radial basis function neural network.
In practical application, before inputting the motion parameters into the radial basis function neural network to obtain training parameters, the training parameters are used for guiding the athlete to train, the method further includes:
and carrying out data cleaning on the motion parameters to obtain the cleaned motion parameters.
In practical application, the step of performing data cleaning on the motion parameters to obtain cleaned motion parameters specifically includes: and (4) carrying out feature cleaning on invalid or missing data, and sorting the multi-dimensional data to form a data format meeting the requirement of neural network input.
Firstly, performing feature cleaning on invalid or missing data, specifically: filling missing data, carrying out data verification according to the acquired time stamp, if data are lost, complementing by adopting a median difference method (linear interpolation or secondary interpolation method), and if a section of data are missing too much, discarding the section of data.
Secondly, the multidimensional data are sorted to form a data format meeting the requirement of neural network input, and the method specifically comprises the following steps: the method comprises the steps of regularly aligning motion parameters according to 10-second average, 30-second average or 1-minute average respectively to obtain aligned data, then performing 0-1 normalization on the aligned data to form a feature vector (the feature vector refers to X1, X2.. Xn, and refers to heart rate, speed and acceleration of 10 seconds, 30 seconds and 1 minute levels at the current moment, X1.. X3 refers to the heart rate, speed and acceleration of 10 seconds, X4.. X6 refers to the heart rate, speed and acceleration of 30 seconds, and X9 refers to the heart rate, speed and acceleration of 1 level), and preparing for the normalization of the input format of the radial basis neural network.
In practical application, before the data of the motion parameters is cleaned to obtain the cleaned motion parameters, the method further comprises the following steps:
and sequentially carrying out baseline drift removal processing, filtering processing and feature extraction on the motion parameters to obtain the preprocessed motion parameters.
In practical application, the filtering process comprises power frequency filtering and signal filtering, wherein the power frequency filtering is used for filtering signals with the frequency of 50Hz, and the signal filtering is used for removing noise caused by motion interference and is a band-pass filter with the frequency of 5Hz-500 Hz.
The present invention also provides an athlete training system corresponding to the above method, as shown in fig. 3, the system comprising:
the acquisition module is used for acquiring the motion parameters of the athlete to be trained before training; the motion parameters include heart rate, velocity, acceleration, resting heart rate, and recovery heart rate.
The training parameter determining module is used for inputting the motion parameters before training into a radial basis function neural network to obtain training parameters, and the training parameters are used for guiding the training of athletes; the training parameters include: target heart rate, target velocity, and target acceleration.
As an optional embodiment, the athlete training system further comprises:
and the preprocessing module is used for sequentially carrying out baseline drift removal processing, filtering processing and feature extraction on the motion parameters to obtain the preprocessed motion parameters.
As an optional embodiment, the athlete training system further comprises:
and the data cleaning module is used for carrying out data cleaning on the motion parameters to obtain the cleaned motion parameters.
As an optional implementation, the filtering process in the preprocessing module includes: power frequency filtering and signal filtering.
As an alternative embodiment, the athlete training system further comprises: the wireless communication transmitting module and the wireless communication receiving module, the acquisition module and the wireless communication transmitting module form an acquisition terminal; the wireless communication receiving module, the training parameter determining module, the preprocessing module and the data cleaning module form a host; the acquisition module transmits the acquired data to the host through the wireless communication transmitting module, and the host receives and processes the data through the wireless communication receiving module, so that the determination of the training parameters of the athletes and the feedback of the training results are realized.
The invention has the technical effects that:
because the existence of the radial basis function enables the network structure to have the characteristic of local response, the proper training parameters can be obtained for different athletes, and the training effect is improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A method of training an athlete, comprising:
acquiring motion parameters of an athlete to be trained before training; the motion parameters comprise heart rate, speed, acceleration, resting heart rate and recovery heart rate;
inputting the motion parameters before training into a radial basis function neural network to obtain training parameters, wherein the training parameters are used for guiding the training of athletes; the training parameters include: target heart rate, target velocity, and target acceleration.
2. The method according to claim 1, further comprising, before inputting the motion parameters into the radial basis function neural network to obtain the training parameters:
and carrying out data cleaning on the motion parameters to obtain the cleaned motion parameters.
3. The method of claim 2, further comprising, prior to the step of data cleaning the athletic parameter to obtain the cleaned athletic parameter:
and sequentially carrying out baseline drift removal processing, filtering processing and feature extraction on the motion parameters to obtain the preprocessed motion parameters.
4. A method for athlete training according to claim 3, wherein the filtering process comprises: power frequency filtering and signal filtering.
5. An athlete training system, comprising:
the acquisition module is used for acquiring the motion parameters of the athlete to be trained before training; the motion parameters comprise heart rate, speed, acceleration, resting heart rate and recovery heart rate;
the training parameter determining module is used for inputting the motion parameters before training into a radial basis function neural network to obtain training parameters, and the training parameters are used for guiding the training of athletes; the training parameters include: target heart rate, target velocity, and target acceleration.
6. The athlete training system of claim 5, further comprising:
and the data cleaning module is used for carrying out data cleaning on the motion parameters to obtain the cleaned motion parameters.
7. The athlete training system of claim 6, further comprising:
and the preprocessing module is used for sequentially carrying out baseline drift removal processing, filtering processing and feature extraction on the motion parameters to obtain the preprocessed motion parameters.
8. The athlete training system of claim 7, wherein the filtering process in the preprocessing module comprises: power frequency filtering and signal filtering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111158240.0A CN113730892A (en) | 2021-09-30 | 2021-09-30 | Athlete training method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111158240.0A CN113730892A (en) | 2021-09-30 | 2021-09-30 | Athlete training method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113730892A true CN113730892A (en) | 2021-12-03 |
Family
ID=78742016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111158240.0A Pending CN113730892A (en) | 2021-09-30 | 2021-09-30 | Athlete training method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113730892A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090287070A1 (en) * | 2008-05-16 | 2009-11-19 | Nellcor Puritan Bennett Llc | Estimation Of A Physiological Parameter Using A Neural Network |
| CN107737439A (en) * | 2017-10-18 | 2018-02-27 | 徐�明 | One kind enters stepwise physical training system and method |
| US20190147372A1 (en) * | 2017-11-15 | 2019-05-16 | Uber Technologies, Inc. | Systems and Methods for Object Detection, Tracking, and Motion Prediction |
| CN110610233A (en) * | 2019-09-19 | 2019-12-24 | 福建宜准信息科技有限公司 | Fitness running heart rate prediction method based on domain knowledge and data driving |
| CN111564197A (en) * | 2020-04-14 | 2020-08-21 | 南京学立安教育科技有限公司 | Intelligent analysis system and method for physical exercise |
-
2021
- 2021-09-30 CN CN202111158240.0A patent/CN113730892A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090287070A1 (en) * | 2008-05-16 | 2009-11-19 | Nellcor Puritan Bennett Llc | Estimation Of A Physiological Parameter Using A Neural Network |
| CN107737439A (en) * | 2017-10-18 | 2018-02-27 | 徐�明 | One kind enters stepwise physical training system and method |
| US20190147372A1 (en) * | 2017-11-15 | 2019-05-16 | Uber Technologies, Inc. | Systems and Methods for Object Detection, Tracking, and Motion Prediction |
| CN110610233A (en) * | 2019-09-19 | 2019-12-24 | 福建宜准信息科技有限公司 | Fitness running heart rate prediction method based on domain knowledge and data driving |
| CN111564197A (en) * | 2020-04-14 | 2020-08-21 | 南京学立安教育科技有限公司 | Intelligent analysis system and method for physical exercise |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106108889B (en) | Electrocardiogram classification method based on deep learning algorithm | |
| CN104200234B (en) | Human action models and recognition methods | |
| EP3086320A1 (en) | Method and device for associating frames in a video of an activity of a person with an event | |
| CN105326500B (en) | Action identification method and equipment based on surface electromyogram signal | |
| CN105877766A (en) | Mental state detection system and method based on multiple physiological signal fusion | |
| CN107479702A (en) | A kind of human emotion's dominance classifying identification method using EEG signals | |
| CN112465059A (en) | Multi-person motor imagery identification method based on cross-brain fusion decision and brain-computer system | |
| CN107292296A (en) | A kind of human emotion wake-up degree classifying identification method of use EEG signals | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN112541415B (en) | Brain muscle function network motion fatigue detection method based on symbol transfer entropy and graph theory | |
| Novatchkov et al. | Machine learning methods for the automatic evaluation of exercises on sensor-equipped weight training machines | |
| CN110074779A (en) | A kind of EEG signal identification method and device | |
| KR20190047648A (en) | Method and wearable device for providing feedback on action | |
| CN109091126A (en) | A kind of human body physiological state differentiation method for visualizing and equipment based on multisensor | |
| CN116561589B (en) | Attendance training management method and system based on intelligent wearable equipment | |
| CN115105056A (en) | Method and system for recognizing user action | |
| CN115474901A (en) | Non-contact living state monitoring method and system based on wireless radio frequency signals | |
| CN109740418B (en) | Yoga action identification method based on multiple acceleration sensors | |
| Wenyuan et al. | From Lens to Prism: Device-free modeling and recognition of multi-part activities | |
| CN113408397B (en) | Domain-adaptive cross-subject motor imagery electroencephalogram signal identification system and method | |
| Mekruksavanich et al. | Badminton activity recognition and player assessment based on motion signals using deep residual network | |
| CN114469041A (en) | Heart rate change data characteristic analysis method in exercise process | |
| CN113730892A (en) | Athlete training method and system | |
| CN112370058A (en) | Method for identifying and monitoring emotion of user based on mobile terminal | |
| CN105147249B (en) | The wearable or implantable devices evaluation system of one kind and method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211203 |
|
| RJ01 | Rejection of invention patent application after publication |