A calorie calculation system and method based on a stationary bike

Abstract

This invention discloses a calorie calculation system based on a stationary bike, comprising: a data acquisition module for collecting the user's physiological information and cycling power p(i); a model building and training module connected to the data acquisition module for establishing a vital sign intensity model based on the physiological information; and a data processing and calculation module for calculating a power gain value k(i) based on the vital sign intensity model, and also for calculating the change in calorie consumption rate Δee and the calorie consumption rate ee(i) based on the cycling power p(i). The formula for calculating the calorie consumption rate ee(i) is: ee(i) = ee(i-1) + k in (i)*Δee; where k in (i) represents the inertial gain coefficient. The solution results of this invention are more accurate and the solution process is simpler; an inertial gain coefficient is designed to reduce the error of power change in calorie calculation, and the finite response of the nearest neighbor power to calories at the previous time step is added to make the calorie consumption rate calculation more stable.

Description

Technical Field

[0001] This invention relates to the technical field of motion parameter analysis, specifically to a calorie calculation system and method based on a stationary bike. Background Technology

[0002] Indoor cycling is an indoor cycling exercise. Because data such as cycling distance, speed, and elevation gain are obtained through fixed formulas and simulations, there are fewer available parameters for calculating calories burned compared to outdoor cycling. Therefore, calculating calorie consumption / expenditure rate during indoor cycling usually requires external heart rate monitoring or oxygen uptake monitoring devices, making the data collection process cumbersome and complex, and the calculation results less accurate.

[0003] In summary, there is a need to design a calorie calculation system and method based on exercise bikes to solve the above-mentioned problems in the existing technology. Summary of the Invention

[0004] This invention provides a calorie calculation system and method based on a stationary bike, which solves the problem of difficulty in calculating calorie consumption during indoor cycling in the prior art, or the complexity of data collection requiring external heart rate / oxygen uptake devices.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A calorie calculation system based on a stationary bike includes:

[0007] The data acquisition module is used to collect the user's physiological information and cycling power p(i);

[0008] The model building and training module is connected to the data acquisition module and is used to build a vital sign intensity model based on the physiological information.

[0009] The data processing and calculation module calculates the power gain value k(i) based on the vital sign intensity model, and is also used to calculate the change in calorie consumption rate Δee and the calorie consumption rate ee(i) based on the cycling power p(i).

[0010] The calorie consumption rate ee(i) is calculated using the following formula:

[0011] ee(i) = ee(i-1) + k in (i)* Δee;

[0012] Where, k in (i) is the inertial gain coefficient, i=1-n, n is the length of the time queue, and i is any time point in the time queue.

[0013] In some embodiments of the present invention, the inertial gain coefficient kin The formula for calculating (i) is:

[0014] ;

[0015] Where γ is the inertia index coefficient, obtained through the regression function.

[0016] In some embodiments of the present invention, the formula for calculating the change in calorie consumption rate Δee is as follows:

[0017] .

[0018] In some embodiments of the present invention, the physiological information includes height h, weight w, and age a; the vital sign intensity model is:

[0019] ;

[0020] Where hw is the height-to-weight ratio, and the functional models of α and β are obtained through machine learning fitting.

[0021] In some embodiments of the present invention, the method for calculating calories includes the following steps:

[0022] S1. Build a vital sign strength model based on the user's height h, weight w, age a, and power threshold FTP.

[0023] S2. Calculate the power gain value k(i) based on the vital sign intensity model in step S1:

[0024] S3. Collect the real-time cycling power p(i), and calculate the change in calorie consumption rate Δee by combining it with the power gain value k(i) in step S2.

[0025] S4. Introduce an inertial gain coefficient k based on the power variation between adjacent intervals. in (i) Calculate the calorie consumption rate ee(i).

[0026] In some embodiments of the present invention, the establishment of the vital sign intensity model in step S1 includes the following steps:

[0027] S11. Based on the oxygen uptake νo2, the total calories E are weighted and allocated to the time queue, corresponding one-to-one with the cycling power p(i):

[0028]

[0029] Where e represents the calorie time queue (let the length of the time queue be n, i = 1~n);

[0030] S12. Divide e(i) at the corresponding position by p(i) to obtain the corresponding power gain value k(i), and fit the exponential model of p(i) and k(i).

[0031] S13. Repeat steps S11 and S12 to obtain training samples;

[0032] S14. Using the training samples, based on the user's height h, weight w, and age a, the exponential model in step S12 is fitted in reverse to obtain parameters α and β.

[0033] In some embodiments of the present invention, the exponential model in step S12 is denoted as follows:

[0034] .

[0035] In some embodiments of the present invention, step S2 specifically includes the following steps:

[0036] S21. Input the user's physiological information into the vital sign intensity model;

[0037] S22. Determine whether this is the first time calculating the power gain value k(i). If it is the first time calculating, the formula for calculating the power gain value k(i) is: ;

[0038] Otherwise, the power gain value k(i) is calculated based on the power threshold FTP in step S1: Where ΔFTP is the change in the power threshold FTP. This is the gain coefficient.

[0039] In some embodiments of the present invention, the formula for calculating the change in the power threshold FTP, ΔFTP, is as follows:

[0040] .

[0041] In some embodiments of the present invention, the gain coefficient R is 0.02; the inertia index coefficient γ is 0.946.

[0042] The technical solution of the present invention has the following technical effects compared with the prior art:

[0043] This invention requires no external equipment. It uses only the user's physiological information and cycling power as the driving force to calculate the power gain value k(i) using the established vital sign intensity model, and then calculates the calorie consumption rate of the exercise. The calculation results are more accurate and the calculation process is simple. At the same time, since the impact of power changes on calorie consumption varies under different power levels, this invention designs an inertial gain coefficient to reduce the error of calorie calculation caused by power abrupt changes, and incorporates the finite response of the nearest neighbor power to calories in the previous time step, making the calorie consumption rate calculation more stable.

[0044] In addition, the power gain value k(i) can be adaptively calculated based on recent FTP changes during riding, i.e., it can be updated in real time to ensure that the energy conversion rate gain matches the user's actual ability. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the solution system shown in the embodiment.

[0047] Figure 2 A schematic diagram of calorie consumption rate optimized for inertial response. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0050] Example 1

[0051] Reference Figure 1As shown, a calorie calculation system based on a stationary bike includes:

[0052] The data acquisition module is used to collect the user's physiological information and cycling power p(i);

[0053] The model building and training module is connected to the data acquisition module and is used to build a vital sign intensity model based on the physiological information.

[0054] The data processing and calculation module calculates the power gain value k(i) based on the vital sign intensity model.

[0055] It is also used to calculate the change in calorie consumption rate Δee and the calorie consumption rate ee(i) based on the cycling power p(i).

[0056] The calorie consumption rate ee(i) is calculated using the following formula:

[0057] ee(i) = ee(i-1) + k in (i)* Δee;

[0058] Where, k in (i) is the inertial gain coefficient, i=1~n, n is the length of the time queue, and i is any time point in the time queue.

[0059] The inertial gain coefficient k in The formula for calculating (i) is:

[0060] ;

[0061] Wherein, γ is the inertia index coefficient, obtained through a regression function, and the value of the inertia index coefficient γ is 0.946.

[0062] The formula for calculating the change in calorie consumption rate Δee is:

[0063] .

[0064] For the calculation of the power gain value k(i), this embodiment takes into account the differences in energy conversion rate caused by differences in user physiological information. Therefore, the calculation of calorie consumption rate ee(i) only involves physiological information and cycling power p(i); where energy conversion rate and power gain value k(i) are reciprocals of each other.

[0065] For example, the inertial gain coefficient k involved in the formula for calculating the calorie consumption rate ee(i) in (i) According to its calculation formula, the inertial gain coefficient k in(i) is related to the cycling power p(i-1) at the previous moment; while the other parameter, the change in calorie consumption rate Δee, can be calculated from its formula. The change in calorie consumption rate Δee is the coarse calorie consumption rate between two adjacent time intervals.

[0066] In some embodiments of the present invention, the physiological information includes height h, weight w, and age a. Regarding the acquisition of each physiological information, users can use mobile terminals such as mobile phones to connect to the data acquisition module on the exercise bike and input the physiological information of height h, weight w, and age a.

[0067] The vital sign intensity model is as follows:

[0068] ;

[0069] Where hw is the height-to-weight ratio, and the functional models of α and β are obtained through machine learning fitting.

[0070] Continue to refer to Figure 1 As shown, the basic solution process of this solution system is as follows:

[0071] In the physical strength model, the user's physiological data (including height h, weight w, and age a) are first input. If it is the first calculation, the physiological data is fitted to obtain the power gain value k(i). If it is not the first calculation, the power gain value k(i) is iterated based on the FTP output after the previous cycling, so that the power gain value k(i) matches the user's physical fitness.

[0072] During the user's ride on the exercise bike, the cycling power is collected in real time to obtain the power change value between adjacent time intervals. At the same time, an inertial gain coefficient k is introduced based on the cycling power at the previous moment. in (i), thereby realizing the calculation of calorie consumption rate; when the user finishes riding, the output power threshold FTP is fed back to the physical strength model to iteratively update the power gain value k(i).

[0073] In some embodiments of the present invention, the method for calculating calories includes the following steps:

[0074] S1. Build a vital sign strength model based on the user's height h, weight w, age a, and power threshold FTP.

[0075] Specifically, the input to this vital sign intensity model is the user's physiological information, and the output is the power gain value k(i); the model parameters are obtained through machine learning fitting. A large amount of user physiological information (height h, weight w, age a), cycling power p(i) sequence, and total calories E were obtained using extensive indoor cycling test data. (Here, the calorie sequence serves as the model's output control value, obtained by combining heart rate hr and oxygen uptake.) (The data is obtained through calculation). After obtaining the batch training data, the vital sign intensity model is trained as follows:

[0076] S11. Based on the oxygen uptake νo2, the total calories E are weighted and allocated to the time queue, corresponding one-to-one with the cycling power p(i):

[0077]

[0078] Where e represents the calorie time queue (let the length of the time queue be n, i = 1~n);

[0079] S12. Divide e(i) at the corresponding position by p(i) to obtain the corresponding power gain value k(i). This power gain value k(i) is the reciprocal of the energy conversion rate. Fit the exponential model of p(i) and k(i) as follows:

[0080] ;

[0081] Store α and β from the model with the minimum mean squared error, and store them in correspondence with the user's body information;

[0082] S13. Repeat steps S11 and S12 to obtain a large number of training samples; as the basis for constructing the vital sign intensity model, the dataset is denoted as {data(i) = [h (i),w (i),a (i),a(i),b(i)]; i = 1~m} (Note: the dataset contains m samples).

[0083] S14. Using the training samples, based on the user's height h, weight w, and age a, the exponential model in step S12 is fitted in reverse, that is, the fitting parameters α and β.

[0084] S2. Calculate the power gain value k(i) based on the vital sign intensity model in step S1:

[0085] Specifically, the following steps are included:

[0086] S21. Input the user's physiological information into the vital sign intensity model;

[0087] S22. Determine whether this is the first time calculating the power gain value k(i). If it is the first time calculating, the formula for calculating the power gain value k(i) is: ;

[0088] Otherwise, the power gain value k(i) is calculated based on the power threshold FTP in step S1: Where ΔFTP is the change in the power threshold FTP. This is the gain coefficient.

[0089] The formula for calculating the change in the power threshold FTP, ΔFTP, is as follows:

[0090] .

[0091] The gain coefficient R is 0.02.

[0092] In other words, the initial calculation of the power gain value k(i) is derived directly from the vital signs intensity model based on the user's physiological parameters; while subsequent calculations of the power gain value k(i) are updated in real time based on the changes in the power threshold FTP of recent cycling, which can ensure that the power gain value k(i) matches the user's actual ability.

[0093] S3. Collect the real-time cycling power p(i), and calculate the change in calorie consumption rate Δee by combining it with the power gain value k(i) in step S2.

[0094] The calculation formula is:

[0095] Δee is the change in calorie consumption rate obtained without optimization through the inertial response module, that is, the change in power calorie consumption rate between two adjacent time intervals;

[0096] Among them, crude calorie consumption rate ;

[0097] The crude calorie expenditure rate is simply the real-time power multiplied by a conversion factor. This causes the gain trend of the crude calorie expenditure rate to be strongly coupled with the power, resulting in poor stability of the obtained calorie expenditure rate. (Refer to...) Figure 2 The broad calorie consumption rate represented by the dotted line in the middle, although its overall trend is consistent with the calorie consumption value, has a significantly different amplitude.

[0098] S4. Due to the instability of the crude calorie consumption rate, this embodiment sets an inertial response function based on a power time queue to improve the stability of the calorie consumption rate calculation.

[0099] An inertial gain coefficient k is introduced based on the power variation between adjacent intervals. in(i) Calculate the calorie consumption rate ee(i), as described above, calorie consumption rate ee(i) is calculated according to the following formula: ee(i) = ee(i-1) + k in (i)* Δee;

[0100] Reference Figure 2 The calorie consumption rate ee(i) shown by the dashed line not only follows the same overall trend as the calorie consumption label, but also has a roughly the same amplitude. The inertial gain coefficient k designed in this embodiment... in (i) reduces the error of power mutation in calorie calculation and incorporates the finite response of the nearest neighbor power to calories in the previous time step, making the calorie consumption rate calculation more stable.

[0101] The technical solution of the present invention has the following technical effects compared with the prior art:

[0102] This invention requires no external devices. It uses only the user's physiological information and cycling power as the driving force to calculate the power gain value k(i) using an established vital sign intensity model, thereby calculating the calorie consumption rate of the exercise on a stationary bike. The calculation results are more accurate and the process is simpler. Furthermore, since the impact of power changes on calorie consumption varies at different power levels, this invention…

[0103] In addition, the power gain value k(i) can be adaptively calculated based on recent FTP changes during riding, i.e., it can be updated in real time to ensure that the energy conversion rate gain matches the user's actual ability.

[0104] In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0105] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A calorie calculation system based on a stationary bike, characterized in that, include: The data acquisition module is used to collect the user's physiological information and cycling power p(i); The model building and training module is connected to the data acquisition module and is used to build a vital sign intensity model based on the physiological information. The data processing and calculation module calculates the power gain value k(i) based on the vital sign intensity model, and is also used to calculate the change in calorie consumption rate Δee and the calorie consumption rate ee(i) based on the cycling power p(i). The calorie consumption rate ee(i) is calculated using the following formula: ； Where, k in (i) represents the inertial gain coefficient, i = 1 - n, where n is the length of the time queue and i is any time point in the time queue; the inertial gain coefficient k in The formula for calculating (i) is: ； Wherein, γ is the inertia exponent coefficient, obtained through the regression function; The formula for calculating the change in calorie consumption rate Δee is: ； The physiological information includes height h, weight w, and age a; the vital sign intensity model is: ； Where hw is the height-to-weight ratio, and the functional model of α and β is obtained by fitting through machine learning; If this is the first calculation, the formula for calculating the power gain value k(i) is: ； Otherwise, the power gain value k(i) is calculated based on the power threshold FTP: , where ΔFTP is the change in the power threshold FTP, and R is the gain coefficient.

2. The calorie calculation method for a calorie calculation system based on a stationary bike according to claim 1, characterized in that, Includes the following steps: S1. Build a vital sign strength model based on the user's height h, weight w, age a, and power threshold FTP. S2. Calculate the power gain value k(i) based on the vital sign intensity model in step S1: S3. Collect the real-time cycling power p(i), and calculate the change in calorie consumption rate Δee by combining it with the power gain value k(i) in step S2. S4. Introduce an inertial gain coefficient k based on the power variation between adjacent intervals. in (i) Calculate the calorie consumption rate ee(i).

3. The calorie calculation method according to claim 2, characterized in that, The establishment of the vital sign intensity model in step S1 includes the following steps: S11. Based on the oxygen uptake νo2, the total calories E are weighted and allocated to the time queue, corresponding one-to-one with the cycling power p(i): ； Where e represents the calorie time queue, and the length of the time queue is n, i = 1~n; S12. Divide e(i) at the corresponding position by p(i) to obtain the corresponding power gain value k(i), and fit the exponential model of p(i) and k(i). S13. Repeat steps S11 and S12 to obtain training samples; S14. Using the training samples, based on the user's height h, weight w, and age a, the exponential model in step S12 is fitted in reverse to obtain parameters α and β.

4. The calorie calculation method according to claim 3, characterized in that, The exponential model in step S12 is denoted as follows: 。 5. The calorie calculation method according to claim 2, characterized in that, The formula for calculating the change in the power threshold FTP, ΔFTP, is as follows: ∆FTP = FTP(j) - FTP(j-1).

6. The calorie calculation method according to claim 2, characterized in that, The gain coefficient R is 0.02; the inertia index coefficient γ is 0.946.

Images