CN110610233B - Fitness running heart rate prediction method based on domain knowledge and data driving - Google Patents
Fitness running heart rate prediction method based on domain knowledge and data driving Download PDFInfo
- Publication number
- CN110610233B CN110610233B CN201910886628.9A CN201910886628A CN110610233B CN 110610233 B CN110610233 B CN 110610233B CN 201910886628 A CN201910886628 A CN 201910886628A CN 110610233 B CN110610233 B CN 110610233B
- Authority
- CN
- China
- Prior art keywords
- heart rate
- model
- domain
- gradient
- autoregressive
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B22/00—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements
- A63B22/02—Exercising apparatus specially adapted for conditioning the cardio-vascular system, for training agility or co-ordination of movements with movable endless bands, e.g. treadmills
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B24/00—Electric or electronic controls for exercising apparatus of preceding groups; Controlling or monitoring of exercises, sportive games, training or athletic performances
- A63B24/0062—Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Physical Education & Sports Medicine (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
Abstract
The invention relates to a fitness running heart rate prediction method based on domain knowledge and data driving, which comprises the following steps of: 1) Collecting body-building running data of a sporter to obtain a training data set; 2) Establishing a domain model DM reflecting the relation between the heart rate and the movement speed and the gradient; 3) Establishing a data-driven autoregressive model ARM reflecting the relationship between the heart rate and the movement speed, the gradient and the movement time; 4) Determining parameters in the domain model and the autoregressive model by adopting a training data set to obtain an individualized domain model and an autoregressive model; 5) And (3) taking the heart rate values predicted by the autoregressive model and the field model, namely the outputs of the autoregressive model and the field model as the input of the integrated learning algorithm, and predicting through the integrated learning algorithm to obtain the final heart rate predicted value. The method is beneficial to improving the precision of the established personalized body-building running model.
Description
Technical Field
The invention relates to the technical field of fitness running modeling, in particular to a fitness running heart rate prediction method based on domain knowledge and data driving.
Background
Exercising on an indoor treadmill is not affected by seasonal weather and is simple and efficient, and becomes an important fitness mode. Most of the running machines on the market currently provide some optional exercise schemes constructed by applying domain knowledge to provide certain guidance for an exerciser in exercising and building up body. However, these exercise schemes are often established on the basis of running models of specific population or age group, and individual differences of physical functions of different exercisers are neglected, which easily results in problems of low model accuracy and inaccurate predicted heart rate value.
Disclosure of Invention
The invention aims to provide a fitness running heart rate prediction method based on domain knowledge and data driving, and the method is favorable for improving the accuracy of fitness running heart rate prediction.
In order to realize the purpose, the technical scheme of the invention is as follows: a fitness running heart rate prediction method based on domain knowledge and data driving comprises the following steps:
1) Collecting body-building running data of a sporter to obtain a training data set;
2) Establishing a domain model DM reflecting the relation between the heart rate and the movement speed and the gradient;
3) Establishing a data-driven autoregressive model ARM reflecting the relation between the heart rate and the exercise speed, the gradient and the exercise time;
4) Determining parameters in the domain model and the autoregressive model by adopting a training data set to obtain an individualized domain model and an autoregressive model;
5) And obtaining a t-time heart rate value predicted by the autoregressive model and a t-time heart rate value predicted by the field model, namely the outputs of the autoregressive model and the field model, by taking historical data before t time as the inputs of the autoregressive model and the field model, then taking the outputs of the autoregressive model and the field model as the inputs of an integrated learning algorithm, and predicting by the integrated learning algorithm to obtain a final heart rate predicted value.
Further, in step 2), the calculation formula of the domain model is as follows:
HR=a((3.5+0.2V+0.9VA)/3.5)+b (1)
wherein HR represents heart rate, V represents exercise speed, A represents gradient, and a and b are two undetermined parameters corresponding to different runners.
Further, in step 3), the calculation formula of the data-driven autoregressive model is as follows:
wherein, a 0 Representing resting heart rate without exercise, m representing the order of the regression term, a 0 ,……,a m , b 0 ,……,b m ,c 0 ,……,c m Respectively representing the undetermined parameters before the heart rate term, the velocity term and the degree term.
Further, in step 4), the method for determining the parameters a and b slope of the domain model includes: and (4) taking the motion speed and the gradient of the two tests and the corresponding measured heart rate from the training data set, substituting the motion speed and the gradient and the corresponding measured heart rate into a calculation formula of the field model, and then solving the parameters a and b.
Further, in step 4), based on the training data set, the minimum description length criterion is adopted to calculate the value of m, and the undetermined parameter a is determined by the Newton method according to the principle of minimum error 0 ,……,a m ,b 0 ,……,b m ,c 0 ,……,c m 。
Further, in the step 5, the machine learning algorithm is a random forest algorithm RF.
Compared with the prior art, the invention has the beneficial effects that: the heart rate value is predicted through the autoregression model and the field model on the basis of establishing the field model and the data-driven autoregression model, then the output of the autoregression model and the field model is used as the input of the integrated learning algorithm, and the heart rate prediction is carried out through the integrated learning algorithm, so that the accuracy of the personalized fitness running heart rate prediction is improved.
Drawings
FIG. 1 is a flow chart of an implementation of an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and specific embodiments.
The invention provides a fitness running heart rate prediction method based on domain knowledge and data driving, which comprises the following steps as shown in figure 1:
1) The body-building running data of the sporter is collected to obtain a training data set.
2) And establishing a domain model DM reflecting the relation between the heart rate and the movement speed and the gradient.
The calculation formula of the domain model is as follows:
HR=a((3.5+0.2V+0.9VA)/3.5)+b (1)
wherein, HR represents heart rate in bpm, V represents movement speed in m/min, A represents gradient in%, and a and b represent two undetermined parameters corresponding to different runners.
3) And establishing a data-driven autoregressive model ARM reflecting the relation between the heart rate and the exercise speed, the gradient and the exercise time.
The calculation formula of the data-driven autoregressive model is as follows:
wherein, a 0 Representing the resting heart rate without exercise, and the heart rate during exercise increases with increasing intensity on the basis of the resting heart rate, m representing the order of the regression term, a 0 ,……,a m ,b 0 ,……,b m ,c 0 ,……,c m Respectively representing the undetermined parameters before the heart rate term, the velocity term and the degree term.
4) And determining parameters in the domain model and the autoregressive model by adopting the training data set to obtain an individualized domain model and an autoregressive model.
The method for determining the parameters a and b of the field model comprises the following steps: and (4) taking the motion speed and the gradient of the two tests and the corresponding measured heart rate from the training data set, substituting the motion speed and the gradient and the corresponding measured heart rate into a calculation formula of the field model, and then solving the parameters a and b. Based on a training data set, solving the value of m by adopting a minimum description length criterion (MDL), and determining the undetermined parameter a by adopting a Newton method according to the principle of minimum error 0 ,……,a m ,b 0 ,……,b m ,c 0 ,……,c m 。
5) And obtaining a t-time heart rate value predicted by the autoregressive model and a t-time heart rate value predicted by the field model, namely the outputs of the autoregressive model and the field model, by taking historical data before t time as the inputs of the autoregressive model and the field model, then taking the outputs of the autoregressive model and the field model as the inputs of an integrated learning algorithm, and predicting by the integrated learning algorithm to obtain a final heart rate predicted value.
The ensemble learning algorithm may be a feedforward neural network (BPNN), a Support Vector Regression (SVR) or a random forest algorithm (RF). In this embodiment, the ensemble learning algorithm is a random forest algorithm RF.
The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.
Claims (4)
1. A fitness running heart rate prediction method based on domain knowledge and data driving is characterized by comprising the following steps:
1) Acquiring body-building running data of a sporter to obtain a training data set;
2) Establishing a domain model DM reflecting the relation between the heart rate and the movement speed and the gradient;
3) Establishing a data-driven autoregressive model ARM reflecting the relationship between the heart rate and the movement speed, the gradient and the movement time;
4) Determining parameters in the domain model and the autoregressive model by adopting a training data set to obtain an individualized domain model and an autoregressive model;
5) Obtaining a t-time heart rate value predicted by the autoregressive model and a t-time heart rate value predicted by the domain model, namely the outputs of the autoregressive model and the domain model, by taking historical data before t time as the inputs of the autoregressive model and the domain model, then taking the outputs of the autoregressive model and the domain model as the inputs of an integrated learning algorithm, and predicting by the integrated learning algorithm to obtain a final heart rate predicted value;
in step 2), the calculation formula of the domain model is as follows:
HR=a((3.5+0.2V+0.9VA)/3.5)+b (1)
wherein HR represents heart rate, V represents movement speed, A represents gradient, and a and b are two undetermined parameters corresponding to different runners;
in step 3), the calculation formula of the data-driven autoregressive model is as follows:
wherein, a 0 Representing resting heart rate without exercise, m representing the order of the regression term, a 0 ,……,a m ,b 0 ,……,b m ,c 0 ,……,c m Respectively representing the undetermined parameters before the heart rate term, the speed term and the gradient term.
2. The fitness running heart rate prediction method based on domain knowledge and data driving according to claim 1, wherein in the step 4), the parameters a and b of the domain model are determined by: and (4) taking the motion speed and the gradient of the two tests and the corresponding measured heart rate from the training data set, substituting the motion speed and the gradient and the corresponding measured heart rate into a calculation formula of the field model, and then solving the parameters a and b.
3. The fitness running heart rate prediction method based on domain knowledge and data driving of claim 1, wherein in the step 4), m is obtained by using a minimum description length criterion based on a training data set, and the parameter a to be determined is determined by Newton's method according to a principle of minimum error 0 ,……,a m ,b 0 ,……,b m ,c 0 ,……,c m 。
4. The fitness running heart rate prediction method based on domain knowledge and data driving of claim 1, wherein in the step 5, the ensemble learning algorithm is a random forest algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910886628.9A CN110610233B (en) | 2019-09-19 | 2019-09-19 | Fitness running heart rate prediction method based on domain knowledge and data driving |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910886628.9A CN110610233B (en) | 2019-09-19 | 2019-09-19 | Fitness running heart rate prediction method based on domain knowledge and data driving |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110610233A CN110610233A (en) | 2019-12-24 |
CN110610233B true CN110610233B (en) | 2023-04-07 |
Family
ID=68893006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910886628.9A Active CN110610233B (en) | 2019-09-19 | 2019-09-19 | Fitness running heart rate prediction method based on domain knowledge and data driving |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110610233B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113837512B (en) * | 2020-06-23 | 2024-08-13 | 中国移动通信集团辽宁有限公司 | Abnormal user identification method and device |
CN113730892A (en) * | 2021-09-30 | 2021-12-03 | 天津工业大学 | Athlete training method and system |
CN113893516B (en) * | 2021-10-19 | 2023-02-28 | 成都拟合未来科技有限公司 | Mirror surface display method and system based on fitness information acquisition |
CN114092855A (en) * | 2021-11-15 | 2022-02-25 | 长春理工大学 | Non-contact intelligent human body heart rate prediction method based on deep learning |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942445B (en) * | 2014-04-30 | 2017-02-15 | 福建师范大学 | Method for generating jogging exercising plan |
CN105286842B (en) * | 2015-11-06 | 2018-04-03 | 深圳风景网络科技有限公司 | A kind of method and device based on acceleration transducer predicted motion process heart rate |
CN105447304B (en) * | 2015-11-10 | 2018-09-07 | 重庆邮电大学 | A kind of early warning system and mobile terminal based on self-learning algorithm |
KR101827108B1 (en) * | 2016-05-04 | 2018-02-07 | 두산중공업 주식회사 | Plant fault detection learning method and system |
US20190188611A1 (en) * | 2017-12-14 | 2019-06-20 | Business Objects Software Limited | Multi-step time series forecasting with residual learning |
CN108926338B (en) * | 2018-05-31 | 2019-06-18 | 中南民族大学 | Heart rate prediction technique and device based on deep learning |
-
2019
- 2019-09-19 CN CN201910886628.9A patent/CN110610233B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN110610233A (en) | 2019-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110610233B (en) | Fitness running heart rate prediction method based on domain knowledge and data driving | |
CN104573359B (en) | A kind of mass-rent labeled data integration method of task based access control difficulty and mark person's ability | |
US9526430B2 (en) | Method and system to estimate day-long calorie expenditure based on posture | |
CN102110191B (en) | exercise guidance system | |
CN101201980B (en) | Remote Chinese language teaching system based on voice affection identification | |
US20200179757A1 (en) | Method, an apparatus and a software product for providing a training program | |
CN103942445B (en) | Method for generating jogging exercising plan | |
KR102245338B1 (en) | Self Fitness Management System and Method Based on Wearable Device | |
US10820810B2 (en) | Method and a system for determining the maximum heart rate of a user of in a freely performed physical exercise | |
US20190009134A1 (en) | Methods, systems, and non-transitory computer readable media for estimating maximum heart rate and maximal oxygen uptake from submaximal exercise intensities | |
Novatchkov et al. | Machine learning methods for the automatic evaluation of exercises on sensor-equipped weight training machines | |
CN106669134A (en) | Method for generating music for exercise training | |
KR20110044113A (en) | Health management system and method | |
CN111569397B (en) | Handle motion counting method and terminal | |
CN113780811B (en) | Musical instrument performance evaluation method, device, equipment and storage medium | |
CN106037703A (en) | Cardiorespiratory endurance indirect testing method based on intelligent exercise bicycle | |
CN113457108B (en) | Cognitive characterization-based exercise performance improving method and device | |
CN114886433A (en) | Exercise load evaluation method with environment adaptability | |
CN102836543A (en) | Fitness sport recognizing method and related devices | |
CN105467826A (en) | Sports smart watch and best running speed acquisition method | |
CN115565639A (en) | Exercise heart rate prediction method, device and equipment | |
US11850470B2 (en) | System and method for improving cardio machine capabilities by dynamically adapting workouts to an athlete | |
CN114299925A (en) | Method and system for obtaining importance measurement index of dysphagia symptom of Parkinson disease patient based on voice | |
Dziomdziora et al. | Running Pace Adjustment and Training Distance Fitting with Fuzzy Logic and Machine Learning | |
Ludwig et al. | A convolution model for prediction of physiological responses to physical exercises |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230615 Address after: Building 5, 6 and 7, Yimei Intelligent Industrial Park, No. 30, Wisdom Avenue, Nanyu Town, High tech Zone, Fuzhou City, 350109, Fujian Province Patentee after: Fujian Yimei Intelligent Technology Co.,Ltd. Address before: Building 15, Juyuanzhoucangshan Garden, Jinshan Industrial Zone, Cangshan District, Fuzhou City, Fujian Province 350007 Patentee before: FUJIAN EZON INFORMATION TECHNOLOGY Co.,Ltd. |