A graphene-based wearable fitness monitoring system

Abstract

The application provides a wearable graphene-based physical fitness monitoring system, and relates to the technical field of physical fitness monitoring.The system comprises a motion direction identification module, a motion amplitude monitoring module, a dynamic sensitive area adjustment module, a physical fitness state evaluation module and a physical fitness index monitoring module.The application can more finely capture the deformation differences of different levels of tissues in the motion process through the combined analysis of the skin shear strain and the subcutaneous vertical strain, so that the physical fitness monitoring is more accurate.With the aid of the strain gradient calculation method, the skin deformation direction and trend can be identified, and the motion state can be accurately described.The dynamic monitoring of the strain amplitude change trend makes the data processing more continuous, which is helpful for accurately judging the motion intensity fluctuation.In view of the change of the motion load, the weight distribution of the monitoring area is adjusted, so that the sensor resources are optimally configured, and the accuracy of the physical fitness state evaluation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of physical fitness monitoring, and particularly relates to a wearable physical fitness monitoring system based on graphene. BACKGROUND

[0002] The technical field of physical fitness monitoring includes systems and methods for measuring and analyzing physiological parameters and motion states of human body. The core of this technical field involves biological signal acquisition, motion data analysis and health status evaluation. Biological signal acquisition includes the acquisition of information such as heart rate, electro-physiological signals and skin conductance, motion data analysis involves the processing of motion parameters such as gait, acceleration and angular velocity, and health status evaluation determines the physical fitness condition of an individual based on the trend of physiological and motion data. Existing physical fitness monitoring technology mainly relies on wearable devices to complete data acquisition and analysis, and common systems include heart rate monitors based on optical sensing, pedometers based on acceleration sensing, and electrocardiogram monitoring devices based on electro-physiological signals. With the development of wearable devices, the application of flexible electronic materials, miniaturized sensors and wireless communication technology has improved the convenience and real-time performance of physical fitness monitoring.

[0003] Among them, the wearable physical fitness monitoring system based on graphene refers to a system that uses graphene materials to construct a sensing unit, and combines signal acquisition and data transmission technology to realize the monitoring of physiological and motion states of human body. The core part of the system includes a flexible sensor based on graphene, which detects bioelectric signals, skin electrical impedance or mechanical deformation information through skin contact, and converts the collected signals into electrical signals for output. High-sensitivity conductive channel structure is adopted for signal acquisition to detect small changes in skin potential or stress. Wireless communication interface is adopted for data transmission to send the collected data to a terminal device. The system can be powered by integrated micro power supply, and combined with low-power data processing circuit to complete signal preprocessing and preliminary feature extraction.

[0004] Current physical fitness monitoring mainly relies on single or a small number of biological signal sensing technologies, and there are limitations in analyzing complex motion states. Most monitoring systems only analyze heart rate, step count or single-dimensional motion parameters, and it is difficult to effectively capture the real deformation of different levels of organization during the motion process, resulting in limited monitoring accuracy. Motion state evaluation is often based on fixed monitoring areas, and cannot be optimized for individual motion patterns, resulting in monitoring data being easily affected by individual differences and reducing the accuracy of evaluation. The data fusion method mainly relies on independent parameter analysis, and cannot deeply mine the internal relationship between different monitoring indicators, making the motion load evaluation more one-sided. In practical applications, the uneven distribution of motion amplitude and load makes the monitoring device unstable in complex motion environments, and it is difficult to adapt to the dynamic changes of motion demand. The monitoring system lacks intelligent optimization means in the adjustment of regional sensitivity, and it is difficult to adaptively adjust to different motion situations, resulting in poor balance of data acquisition and affecting the reliability of the final evaluation results. SUMMARY

[0005] In order to solve the technical problems existing in the prior art, an embodiment of the present application provides a wearable physical fitness monitoring system based on graphene. The technical solution is as follows:

[0006] A wearable physical fitness monitoring system based on graphene, the system comprises: a motion direction recognition module that acquires skin surface shear strain and subcutaneous deep layer vertical strain data collected by a graphene strain sensor, calculates a skin strain gradient according to the strain change rate of the skin surface and the subcutaneous deep layer in adjacent time periods, and acquires a strain direction change state; a motion amplitude monitoring module that calculates the skin strain amplitude of adjacent time periods based on the strain direction change state, calls the skin strain gradient change value of each time period, and obtains a strain amplitude change trend; a dynamic sensitive area adjustment module that refers to the distribution deviation of the current strain data in the strain amplitude change trend and the motion load monitoring area, takes the monitoring area that exceeds a preset deviation threshold as a sensitive area, adjusts the strain weight of the sensitive area, and obtains a strain sensitive area optimization result; a physical fitness state evaluation module that judges the motion load change trend of each sensitive area in the strain sensitive area optimization result, divides the physical fitness strain response types of the same motion intensity category, and obtains a physical fitness state classification result; and a physical fitness index monitoring module that analyzes the mutual influence degree of each type of physical fitness state index based on the physical fitness state classification result, divides the physical fitness level according to the influence degree, and obtains a physical fitness monitoring evaluation result.

[0007] Optionally, the strain direction change state includes shear strain change, vertical strain change, strain gradient distribution, the strain amplitude change trend includes adjacent time period strain gradient change amplitude, skin surface layer strain change rate, subcutaneous deep layer vertical strain change rate, the skin strain sensitive area optimization result includes strain data deviation value, sensitive area adjustment threshold, correction monitoring area weight, the physical fitness state classification result includes exercise load change trend, physical fitness strain response type, exercise intensity classification, the physical fitness monitoring evaluation result includes monitoring index correlation analysis, physical fitness state evaluation, exercise load influence analysis.

[0008] Optionally, the exercise direction recognition module includes: a strain data acquisition submodule that acquires data collected by a graphene strain sensor, calculates the amount of shear strain change of the skin surface layer and the amount of vertical strain change of the subcutaneous deep layer, matches the amounts of shear strain and vertical strain change according to time series, establishes a data correspondence relationship, and obtains a matched strain data set; a strain gradient calculation submodule that extracts the difference between the amount of surface layer shear strain change and the amount of deep layer vertical strain change based on the matched strain data set, calculates the skin strain gradient value, filters out abnormal points that exceed a set strain gradient abnormal threshold according to the time series change range, calculates the gradient change average of a plurality of time series before and after the abnormal points as a reference value, corrects the abnormal points, and acquires the corrected skin strain gradient value; and a strain direction change recognition submodule that calls the corrected skin strain gradient value, calculates the direction angle change amount under a plurality of time series, judges the strain direction change trend, filters out time periods with a change rate exceeding an angle change rate threshold, classifies the change trend, and acquires the strain direction change state.

[0009] Optionally, for calculating the direction angle change amount θ t , the formula is:

[0010]

[0011] wherein, Δε i,t represents the strain gradient change value of the i th monitoring point at time t, Δε i,t-1 represents the strain gradient change value of the i th monitoring point at the previous time t-1, n represents the total number of monitoring points participating in the calculation in the current time series, d j,t represents the distance measurement data of the j th monitoring point at time t, d j,t-1 represents the distance measurement data of the j th monitoring point at time t-1, and m represents the number of monitoring points participating in the calculation of distance measurement data in the current time series.

[0012] Optionally, the motion amplitude monitoring module comprises: a strain amplitude extraction submodule that calls the skin strain gradient change value of each time period in the strain direction change state, sorts the strain amplitude information of the complete time period in time sequence, and obtains the time period strain amplitude data; an adjacent time period amplitude calculation submodule that calculates the adjacent time period skin strain amplitude change value based on the time period strain amplitude data, extracts the change rate mean value of the time period whose change rate exceeds the amplitude fluctuation threshold value, sets the mutation point according to the mean value and marks the time sequence, calculates the mean value deviation of the two time periods before and after the mutation point, adjusts the mutation point data whose deviation exceeds the set deviation range, recalculates the amplitude change rate of the adjusted amplitude change rate, and obtains the adjacent time period amplitude change rate; and an amplitude change trend analysis submodule that calls the adjacent time period amplitude change rate, calculates the amplitude change trend value of a plurality of time sequences, screens the time period whose change rate continuously increases or decreases, classifies the trend mode, and obtains the strain amplitude change trend.

[0013] Optionally, for calculating the amplitude change trend value ΔV trend of different time sequences, the formula is as follows:

[0014]

[0015] wherein, V t1 represents the amplitude value at time point t1, V t1-1 represents the amplitude value at the previous time point t1-1, Δt1 represents the time interval, which is usually the measurement period, V avg represents the average value of the amplitude value in all measurement periods, T represents the length of the total time sequence, and ΔV trend represents the calculated amplitude change trend value.

[0016] Optionally, the dynamic sensitive area adjustment module comprises: a deviation calculation submodule that calls the strain amplitude change trend, calculates the deviation value of the current strain data and the motion load monitoring area distribution, calculates the deviation mean value of the area that exceeds the set deviation range, and obtains the area deviation distribution result; a sensitive area adjustment threshold setting submodule that calculates the deviation fluctuation rate of the area that exceeds the set deviation range based on the area deviation distribution result, calculates the sensitive area adjustment threshold value according to the deviation mean value and the fluctuation rate, judges the change trend of the sensitive area adjustment threshold value, adjusts the adjustment range of the abnormal area, and obtains the updated sensitive area adjustment threshold value; and a monitoring area weight optimization submodule that calls the updated sensitive area adjustment threshold value, adjusts the sensitive area weight, calculates the balance degree of the adjusted weight, screens the area whose weight changes exceed the adjustment range, and obtains the skin strain sensitive area optimization result.

[0017] Optionally, the physical state evaluation module comprises: a motion load trend analysis submodule that calls the motion load change data of each sensitive area in the skin strain sensitive area optimization result, calculates the load change rate in the time sequence, screens the areas with a change rate exceeding a set change rate threshold, and obtains the motion load change trend; a strain response classification submodule that extracts the sensitive areas with similar load change rates based on the motion load change trend, calculates the load change similarity between the areas, screens the areas with a similarity exceeding a set similarity threshold, classifies the similar load change areas, and obtains the physical strain response type; and a physical state division submodule that calls the physical strain response type, classifies the physical strain areas of the same category, calculates the load balance between the classified areas, screens the categories with a load balance deviation exceeding a load balance deviation threshold, divides a plurality of physical state areas, and obtains the physical state classification result.

[0018] Optionally, for calculating the load change similarity S i1,j1 between the areas, the formula is:

[0019]

[0020] wherein, R i1,t2 represents the load change rate of area i1 at time t2, R j1,t2 represents the load change rate of area j1 at time t2, T represents the total time sequence length, and S i1,j1 represents the load change similarity between area i1 and area j1.

[0021] Optionally, the physical index monitoring module comprises: a physical monitoring data integration submodule that extracts the corresponding monitoring data in the physical state classification result, refers to the motion load, physiological feedback and external environment parameters, matches the time sequence, eliminates the data with a synchronization error exceeding an error range, and obtains the time sequence alignment monitoring data; a monitoring index influence analysis submodule that analyzes the correlation of each monitoring index based on the time sequence alignment monitoring data, calculates the contribution degree of each index to the physical state classification, screens the indexes with a contribution degree exceeding a set contribution degree standard, induces the contribution degree index influence relationship, and obtains the monitoring index influence degree; and a physical monitoring evaluation generation submodule that calls the monitoring index influence degree, calculates the index change amplitude in each physical state, analyzes the differences of the indexes in each state category, screens the indexes with a difference exceeding a physical state difference threshold as characteristic indexes, extracts the change trend of the characteristic indexes and divides the physical grades, and obtains the physical monitoring evaluation result.

[0022] The technical scheme provided by the embodiment of the application has at least the following beneficial effects:

[0023] By combining the analysis of skin shear strain and subcutaneous vertical strain, the deformation differences of different levels of tissues during movement can be captured more finely, making the physical fitness monitoring more accurate. With the strain gradient calculation method, the skin deformation direction and trend can be identified, realizing high-precision characterization of the movement state. Dynamic monitoring of strain amplitude change trend makes data processing more continuous, which helps to accurately judge the movement intensity fluctuation. According to the change of movement load, the weight distribution of the monitoring area is adjusted, so that the sensor resources are optimized, and the accuracy of physical fitness state evaluation is improved. According to the change trend of physical fitness load, the dynamic classification of movement state can be realized, and by integrating the corresponding monitoring data, the interaction between different indicators is analyzed, the overall evaluation of physical fitness state is optimized, and the monitoring result is more in line with the actual movement demand. By accurately identifying the movement mode and physical fitness load, optimizing the distribution of physical fitness monitoring area, effectively reducing data error, and improving the adaptability of the monitoring system to complex movement scenes. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0025] Figure 1 The system flowchart of the present application;

[0026] Figure 2 The sub-module flowchart of the present application;

[0027] Figure 3 The movement direction identification module flowchart of the present application;

[0028] Figure 4 The movement amplitude monitoring module flowchart of the present application;

[0029] Figure 5 The dynamic sensitive area adjustment module flowchart of the present application;

[0030] Figure 6 The physical fitness state evaluation module flowchart of the present application;

[0031] Figure 7 The physical fitness index monitoring module flowchart of the present application. DETAILED DESCRIPTION

[0032] The technical solutions in the present application will be described below in combination with the drawings.

[0033] In the embodiments of the present application, the words such as "example", "for example" and the like are used to represent an example, an illustration or a description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be either one of the two.

[0034] In the embodiments of the present application, sometimes the subscript such as W1 may be written in the form of non-subscript such as W1, and the meanings expressed thereby are consistent when the difference is not emphasized.

[0035] In order to make the technical problems, technical schemes and advantages to be solved by the present application more clear, the following will be described in detail in combination with the drawings and specific embodiments.

[0036] As shown in Figure 1 The present application provides a wearable body energy monitoring system based on graphene, comprising: a motion direction recognition module acquires skin surface shear strain and subcutaneous deep vertical strain data collected by a graphene strain sensor, calculates a skin strain gradient according to a strain change rate of the skin surface and the subcutaneous deep layer in adjacent time periods, and acquires a strain direction change state; a motion amplitude monitoring module calculates a skin strain amplitude of adjacent time periods based on the strain direction change state and a skin strain gradient change value of each time period, and obtains a strain amplitude change trend; a dynamic sensitive area adjustment module refers to a distribution deviation of current strain data in the strain amplitude change trend and a motion load monitoring area, regards a monitoring area exceeding a preset deviation threshold as a sensitive area, adjusts a strain weight of the sensitive area, and obtains a strain sensitive area optimization result; a body energy state evaluation module judges a motion load change trend of each sensitive area in the strain sensitive area optimization result, divides a body energy strain response type of the same motion intensity category, and obtains a body energy state classification result; and a body energy index monitoring module analyzes a mutual influence degree of each body energy state index based on the body energy state classification result, divides a body energy level according to the influence degree, and obtains a body energy monitoring evaluation result. The strain direction change state includes shear strain change, vertical strain change and strain gradient distribution, the strain amplitude change trend includes strain gradient change amplitude of adjacent time periods, skin surface strain change rate and subcutaneous deep vertical strain change rate, the skin strain sensitive area optimization result includes a strain data deviation value, a sensitive area adjustment threshold and a corrected monitoring area weight, the body energy state classification result includes a motion load change trend, a body energy strain response type and a motion intensity classification, and the body energy monitoring evaluation result includes a monitoring index correlation analysis, a body energy state evaluation and a motion load influence analysis.

[0037] Please refer to Figure 2 and Figure 3 , the motion direction recognition module comprises:

[0038] The strain data acquisition submodule acquires data collected by the graphene strain sensor, calculates the change amount of the skin surface layer shear strain and the change amount of the subcutaneous deep layer vertical strain, matches the change amounts of the shear strain and the vertical strain according to a time sequence, establishes a data correspondence relationship, and obtains a matched strain data set;

[0039] The strain data acquisition submodule is used to acquire strain data collected by the graphene strain sensor, including but not limited to a timestamp, a shear strain change amount, and a vertical strain change amount. First, the sensor acquires real-time strain data, the data format includes a sensor ID, a timestamp, a shear strain change amount, and a vertical strain change amount, and is stored in a data buffer area in chronological order. For example, the shear strain change amount collected at a certain time t1 is 0.0023, and the vertical strain change amount is 0.0011. The data is marked and stored. Then, the collected data is preprocessed to filter out abnormal data. For example, it is detected whether the data exceeds the measurement range of the sensor (assuming that the shear strain change range is -0.005-0.005, and the vertical strain change range is -0.003-0.003). If the data exceeds the range, the data point is discarded. Subsequently, the shear strain change amount and the vertical strain change amount are matched in chronological order. The data with the same timestamp is compared by indexing, and is arranged in ascending order. For example, the data point at t1 is (0.0023, 0.0011), and the data point at t2 is (0.0025, 0.0013). Finally, a matched strain data set is formed, which stores the correspondence relationship between the skin surface layer shear strain change amount and the subcutaneous deep layer vertical strain change amount at the same timestamp.

[0040] The strain gradient calculation submodule extracts the difference between the surface layer shear strain change amount and the deep layer vertical strain change amount based on the matched strain data set, calculates the skin strain gradient value, filters out abnormal points that exceed the set strain gradient abnormal threshold value according to the time sequence change range, calculates the gradient change average of a plurality of time sequences before and after the abnormal point as a reference value, corrects the abnormal point, and acquires the corrected skin strain gradient value;

[0041] The strain gradient calculation submodule is based on the matched strain data set. First, the difference between the surface layer shear strain change amount and the deep layer vertical strain change amount, i.e., the strain gradient value, is calculated. The calculation method is ΔE = ε s -ε d , where ε s represents the shear strain change amount, and ε d represents the vertical strain change amount. For example, at t1, ε s = 0.0023, and ε d= 0.0011, then Δε = 0.0023-0.0011 = 0.0012, then the strain gradient value is time-sequenced screening, and the abnormal point is determined, assuming that the strain gradient abnormal threshold is 0.002, if |Δε| exceeds the threshold, it is marked as an abnormal point, for example, the Δε of a certain time t5 is 0.0025, and the point is marked as an abnormal point, then, the abnormal point is corrected, and the average value of the gradient change of the continuous multiple time sequences before and after the abnormal point is calculated as the reference value, assuming that the average value of the previous and next 3 points is calculated, for example, the Δε of t2, t3, t4 is 0.0011, 0.0013, 0.0012 respectively, and the reference value is The strain gradient value of the abnormal point is adjusted to the reference value, and the corrected skin strain gradient value is finally obtained.

[0042] The strain direction change recognition submodule calls the corrected skin strain gradient value, calculates the direction angle change amount under multiple time sequences, judges the strain direction change trend, screens the time period whose change rate exceeds the angle change rate threshold, classifies the change trend, and obtains the strain direction change state;

[0043] The direction angle change amount θ is calculated under multiple time sequences t , using the formula:

[0044]

[0045] The direction angle change amount is calculated, the strain direction change trend is judged, the time period whose change rate exceeds the angle change rate threshold is screened, the change trend is classified, and the strain direction change state is obtained; wherein, θ t represents the direction angle change amount at time t, Δε i,t represents the strain gradient change value of the i-th monitoring point at time t, Δε i,t-1 represents the strain gradient change value of the same monitoring point at the previous time t-1, n represents the total number of monitoring points participating in the calculation in the current time sequence, d j,t represents the distance measurement data of the j-th monitoring point at time t, d j,t-1 represents the distance measurement data of the same monitoring point at time t-1, and m represents the number of monitoring points participating in the calculation of distance measurement data in the current time sequence.

[0046] The formula details and formula calculation derivation process: the parameter n represents the number of strain sensors used for calculation in the current time sequence, and the number of sensors obtained by field detection is 5, wherein the strain gradient values of the first sensor at time t and t-1 are Δε 1,t = 0.0020 and Δε 1,t-1 = 0.0018, and the gradient change amount is calculated as:

[0047] |Δε 1,t- Δε 1,t-1 |0.0020-0.0018|=0.0002;

[0048] Sensor No. 2 data is Δε 2,t =0.0023, Δε 2,t-1 =0.0021, calculation:

[0049] |0.0023-0.0021|=0.0002;

[0050] Sensor No. 3 data is Δε 3,t =0.0019, Δε 3,t-1 =0.0017,

[0051] |0.0019-0.0017|=0.0002;

[0052] Sensor No. 4 data is Δε 4,t =0.0021, Δε 4,t-1 =0.0020,

[0053] |0.0021-0.0020|=0.0001;

[0054] Sensor No. 5 data is Δε 5,t =0.0024, Δε 5,t-1 =0.0022,

[0055] |0.0024-0.0022|=0.0002;

[0056] Sum of absolute values of all gradient changes:

[0057] 0.0002+0.0002+0.0002+0.0001+0.0002=0.0009;

[0058] Average value:

[0059] Parameter m represents the number of distance measuring sensors, and the number of distance measuring sensors confirmed by field detection is 3. The distance measuring data of Sensor No. 1 at time t and t-1 is d 1,t =2.00mm and d 1,t-1 =2.01mm, the difference is d 1,t -d 1,t-1 =2.00-2.01=-0.01;

[0060] After squaring, it is (-0.01) 2 =0.0001;

[0061] The distance measuring data of Sensor No. 2 is d 2,t= 2.05 mm, d 2,t-1 = 2.04 mm, calculated:

[0062] (2.05-2.04) 2 = 0.0001;

[0063] The 3rd ranging data d 3,t = 1.98 mm, d 3,t-1 = 1.99 mm,

[0064] (1.98-1.99) 2 = 0.0001;

[0065] The sum of squares of all ranging variation amounts is:

[0066] 0.0001+0.0001+0.0001=0.0003;

[0067] Calculate square root:

[0068] Add 1 and take the reciprocal:

[0069] Calculate the product of the average strain gradient difference and the reciprocal of the ranging: 0.00018x0.98299=0.000177;

[0070] Finally calculate the angle variation amount: θ t = arctan(0.000177);

[0071] Since the angle variation amount is very small, the small angle approximation method can be used: θ t ≈0.000177;

[0072] The result shows that the direction angle variation amount at time sequence t is 0.000177, which indicates that the direction of the skin strain gradient has a small angle variation at this time point, and the direction variation amount is small, which means that the skin deformation trend at this time point is relatively stable. This value is further used to judge the direction variation trend. If the θ t values of consecutive multiple time points show an increasing or decreasing trend, it can be determined that the current skin strain direction has a significant change. Combined with the angle change rate threshold, the time period of the dramatic change is screened out, and the change trend is classified, so as to finally obtain the strain direction change state.

[0073] As shown in Figure 2 and Figure 4 , the motion amplitude monitoring module comprises:

[0074] The strain amplitude extraction submodule calls the skin strain gradient change value of each period in the strain direction change state, sorts according to the time sequence, records the strain amplitude information of the complete period, and obtains the period strain amplitude data;

[0075] The strain amplitude extraction submodule calls the skin strain gradient change value of each period in the strain direction change state, first, sorts the strain gradient change value of each period according to the time sequence, ensures that the data is arranged in time sequence, for example, under the time sequence t1, t2, t3, t4, the skin strain gradient change value is 0.0012, 0.0015, 0.0018, 0.0013 respectively, then the data is stored in the order of t1→t2→t3→t4, then, the strain amplitude of each period is calculated, the amplitude calculation method is the difference between the maximum gradient change value and the minimum gradient change value in the period, for example, in the t1→t3 period, the maximum value is 0.0018, the minimum value is 0.0012, then the strain amplitude of the period is 0.0018-0.0012=0.0006, then, all periods are traversed, the strain amplitude information of each complete period is recorded, and a strain amplitude data set is formed, which stores the strain amplitude values in all time periods and is arranged in time sequence order, for example, the amplitude of t1→t3 is 0.0006, and the amplitude of t2→t4 is 0.0005, and finally the period strain amplitude data is obtained.

[0076] The adjacent period amplitude calculation submodule calculates the skin strain amplitude change of adjacent periods based on the period strain amplitude data, extracts the average change rate of periods whose change rate exceeds the amplitude fluctuation threshold, sets the mutation point according to the average value and marks the time sequence, calculates the average deviation of the two periods before and after the mutation point, adjusts the mutation point data whose deviation exceeds the set deviation range, recalculates the amplitude change rate after adjustment, and obtains the adjacent period amplitude change rate;

[0077] The adjacent period amplitude calculation submodule calculates the skin strain amplitude change of adjacent periods based on the period strain amplitude data, first, the skin strain amplitude change of adjacent periods is calculated, the amplitude change is calculated as the difference between the amplitudes of adjacent periods, for example, the amplitude of t1→t3 is 0.0006, and the amplitude of t2→t4 is 0.0005, then the change is 0.0006-0.0005=0.0001, then, the periods whose change rate exceeds the amplitude fluctuation threshold are screened, assuming that the amplitude fluctuation threshold is set to 0.00015, if the change rate is greater than the threshold, the period is marked, for example, in the t3→t5 period, the amplitude change rate is calculated as If the calculation result is 0.0002, which is greater than 0.00015, the period is marked, then the mean deviation of the two periods before and after the mutation point is calculated, the mean deviation is calculated as the difference between the means of the two periods before and after the mutation point, for example, the mean of the two periods before t3 is 0.00055, and the mean of the two periods after t3 is 0.00065, then the mean deviation is 0.00065-0.00055=0.0001, then it is judged whether the deviation exceeds the set deviation range, assuming that the deviation range is set to 0.00012, if the calculation value is less than the range, it is not necessary to adjust, otherwise it is adjusted, for example, if the calculation value is 0.00014, which exceeds the range, the mutation point amplitude is adjusted to the mean of the adjacent period, for example, the mutation point data is adjusted to Finally, based on the adjusted amplitude data, the adjusted amplitude change rate is recalculated to obtain the amplitude change rate of adjacent periods.

[0078] The amplitude change trend analysis submodule calls the amplitude change rate of adjacent periods, calculates the amplitude change trend value of multiple time series, filters the time periods with continuously increasing or decreasing change rates, classifies the trend patterns, and obtains the strain amplitude change trend;

[0079] The amplitude change trend value of different time series is calculated using the formula:

[0080]

[0081] The amplitude change trend value is calculated, the time periods with continuously increasing or decreasing change rates are filtered, the trend patterns are classified, and the strain amplitude change trend is obtained;

[0082] Wherein, V t1 represents the amplitude value at time point t1, V t1-1 represents the amplitude value at the previous time point t1-1, Δt1 represents the time interval, usually the measurement period, V avg represents the average value of the amplitude value in all measurement periods, T represents the length of the total time series, ΔV trend represents the calculated amplitude change trend value;

[0083] Formula details and formula calculation derivation process:

[0084] Consider a practical scenario in which a time series (T=4 time points) of strain amplitudes is measured. Assume that the time interval Δt1 is 1 second, and the amplitude values V t1 The records at consecutive four time points t1=1, 2, 3, 4 are 2.0, 2.5, 3.0, and 2.8 units respectively. First, calculate the amplitude change rate at each time point, then calculate the weight of each rate, and finally obtain the trend value.

[0085] Calculate the amplitude change rate at each time point: from t1=1 to t1=2:

[0086] From t1=2 to t1=3: From t1=3 to t1=4:

[0087] Calculate the average amplitude value V avg :

[0088] Calculate the weighted amplitude change rate: |V2-V avg | = |2.5-2.575| = 0.075;

[0089] |V3-V avg | = |3.0-2.575| = 0.425;

[0090] |V4-V avg = |2.8-2.575| = 0.225;

[0091] Apply the formula to calculate the trend value AV trend :

[0092]

[0093] The results show that the average amplitude change trend value is 0.0683, which reflects the weighted value of the average change rate of the entire time series, considering the degree of amplitude deviation from the average value of each rate. This numerical trend shows that the strain amplitude as a whole presents a gradually increasing trend in the considered time period, especially at t=3, the strain amplitude is much higher than the average, contributing the most to the overall trend. In this way, the model can effectively classify and identify the time period of continuous growth or decline, and further help to analyze the overall change dynamics of the strain amplitude.

[0094] As shown in Figure 2 and Figure 5 , the dynamic sensitive area adjustment module comprises:

[0095] The deviation calculation submodule calls the strain amplitude change trend to calculate the deviation value of the current strain data and the motion load monitoring area distribution, calculates the deviation mean value of the area exceeding the set deviation range, and obtains the area deviation distribution result;

[0096] The deviation calculation sub-module calls the strain amplitude change trend to calculate the deviation value of the current strain data and the motion load monitoring area distribution. First, the current strain data is determined, and the data format includes the time stamp, the strain amplitude change trend value, and the corresponding monitoring area number. For example, the strain amplitude change trend value at time t1 is 0.0008, and the monitoring area number is A1. Second, the historical distribution data of the motion load monitoring area is extracted, which stores the strain amplitude mean and variance of the area at multiple time sequences in the past. For example, the historical mean of area A1 is 0.0006, and the variance is 0.0001. Then, the deviation value of the current strain data and the historical distribution data of the area is calculated. The deviation value calculation method is |ε 当前 -ε 历史均值 |, where ε 当前 represents the current strain amplitude change trend value, and ε 历史均值 represents the historical mean of the area. For example, |0.0008-0.0006| = 0.0002. If the deviation value exceeds the set deviation range, the area is marked as an exceeding area. Subsequently, the deviation mean of all areas exceeding the set deviation range is calculated. The deviation mean calculation method is the average of the deviation values of the exceeding areas. For example, the deviation values of areas A1, A2, and A3 are 0.0002, 0.0003, and 0.00025, respectively. The deviation mean is Finally, the area deviation distribution result is obtained.

[0097] The sensitive area adjustment threshold setting sub-module calculates the deviation fluctuation rate of the area exceeding the set deviation range based on the area deviation distribution result. The sensitive area adjustment threshold is calculated based on the deviation mean and the fluctuation rate. The change trend of the sensitive area adjustment threshold is judged, the adjustment range of the abnormal area is adjusted, and the updated sensitive area adjustment threshold is obtained.

[0098] The sensitive area adjustment threshold setting sub-module calculates the deviation fluctuation rate of the area exceeding the set deviation range based on the area deviation distribution result. First, all areas exceeding the deviation range are determined, and the deviation values of the area at multiple time sequences before and after are extracted. For example, the deviation values of area A1 at times t1, t2, and t3 are 0.0002, 0.00015, and 0.0003, respectively. Then, the deviation fluctuation rate is calculated. The calculation method is the ratio of the change amount of the adjacent time deviation value to the time interval. For example, Assuming Δt = 0.2s, the fluctuation rate is Next, the sensitive area adjustment threshold is calculated based on the deviation mean and the fluctuation rate. The adjustment threshold calculation method is K·ε 偏差均值 +B·ε 波动速率wherein K, B are adjustment coefficients, assuming that K = 2 and B = 1 are set, the adjustment threshold is 2x0.00025 + 1x0.00075 = 0.00125, then the trend of the adjustment threshold of the sensitive area is judged, the trend judgment method is the change direction of the adjustment threshold of adjacent time points, for example, the adjustment thresholds of t1, t2, t3 are 0.001, 0.0012, 0.00125 respectively, then it is judged that the trend is rising, if the adjustment threshold of a certain region appears abnormal fluctuation, the adjustment range of the region is adjusted, the adjustment method is to smooth the adjustment threshold of the abnormal region to the mean value of the adjacent regions, for example, the mean value of the threshold of the adjacent regions is 0.0011, then the abnormal region is adjusted to 0.0011, and finally the updated sensitive area adjustment threshold is obtained.

[0099] The monitoring area weight optimization submodule calls the updated sensitive area adjustment threshold, adjusts the weight of the sensitive area, calculates the balance degree of the adjusted weight, screens the regions whose weight changes exceed the adjustment range, and obtains the optimization result of the skin strain sensitive area;

[0100] The monitoring area weight optimization submodule calls the updated sensitive area adjustment threshold, adjusts the weight of the sensitive area, first, the weight of each monitoring area is calculated according to the updated adjustment threshold, and the weight calculation method is For example, if the adjustment threshold of a certain region is 0.00125, the weight calculation is Then, the balance degree of the adjusted weight is calculated, and the balance degree calculation method is the standard deviation of the weight of all regions, for example, the weights of regions A1, A2 and A3 are 800, 850 and 780 respectively, and the standard deviation is calculated as Then, the regions whose weight changes exceed the adjustment range are screened, and the screening method is to judge whether the weight change of a certain region exceeds the set weight fluctuation threshold, assuming that the weight fluctuation threshold is set to 30, if the weight change of a certain region is greater than 30, the region is marked, for example, the weight of a certain region changes from 780 to 850, the change is 70, which is greater than 30, so the region is marked, finally, the weight of the marked region is adjusted to tend to the mean value of the adjacent regions, for example, the mean value of the adjacent regions is 815, so the weight of the region is adjusted to 815, and finally the optimization result of the skin strain sensitive area is obtained.

[0101] As shown in Figure 2 and Figure 6 The physical state evaluation module includes:

[0102] The exercise load trend analysis submodule calls the exercise load change data of each sensitive area in the skin strain sensitive area optimization result, calculates the load change rate under the time sequence, screens the regions whose change rates exceed the set change rate threshold, and obtains the exercise load change trend.

[0103] The motion load trend analysis submodule calls the motion load change data of each sensitive area in the skin strain sensitive area optimization result. First, the motion load data of each sensitive area is extracted, and the data format includes a timestamp, an area number, and a load value of the area at the time point. For example, at time point t1, the motion load value of area A1 is 5.2 N, and the load value of area A2 is 4.8 N. Then, the load change rate in the time sequence is calculated. The calculation method is the ratio of the load value change amount between adjacent time points to the time interval, that is, wherein F t1 ,F t2 represent the load values at t1 and t2 respectively. Assuming that Δt = 0.5 s, if F t1 = 5.2 N and F t2 = 5.5 N, then the load change rate is Next, the areas with a change rate exceeding a set change rate threshold are screened. The threshold is set to 0.5 N / s. If the calculation result is greater than the threshold, the area is marked. For example, the change rate of area A1 is 0.6 N / s, which exceeds the threshold, so area A1 is marked. All areas are traversed, and all time periods exceeding the threshold are recorded. Finally, the motion load change trend is obtained.

[0104] The strain response classification submodule extracts sensitive areas with similar load change rates based on the motion load change trend, calculates the load change similarity between the areas, screens the areas with a similarity exceeding a set similarity threshold, classifies the similar load change areas, and obtains the physical fitness strain response type.

[0105] The load change similarity S ij between the areas is calculated using the formula:

[0106] The load change similarity is calculated, the areas with a similarity exceeding a set similarity threshold are screened, the similar load change areas are classified, and the physical fitness strain response type is obtained.

[0107] wherein R i1,t2 represents the load change rate of area i1 at time t2, R j1,t2 represents the load change rate of area j1 at time t2, T represents the total time sequence length, and S i1,j1 represents the load change similarity between area i1 and area j1. The calculation method is based on the improved Jaccard similarity. The minimum and maximum values of the load rates of the two areas are calculated at each time point t2, and the ratio in the entire time sequence is accumulated. When the change trends of the two areas are similar, a higher similarity score is obtained. If the load change value of one of the areas is large for a long time, the similarity is reduced. This ensures that the local matching of the change trend is more sensitive, and at the same time, the dependence on the absolute numerical value by the Euclidean distance method is avoided.

[0108] Formula details and formula calculation derivation process: load change rate R of area A and area B in time sequence T = 5 time points i,t Through sensor data acquisition, the unit is Newton per second, and the data is as follows: R A,t2 = [2.5, 3.2, 2.9, 3.5, 3.1]; R B,t2 = [2.7, 3.0, 2.8, 3.6, 3.3];

[0109] Calculate the minimum load change rate at each time point in the time sequence: min(2.5, 2.7) = 2.5; min(3.2, 3.0) = 3.0; min(2.9, 2.8) = 2.8;

[0110] min(3.5, 3.6) = 3.5; min(3.1, 3.3) = 3.1;

[0111] Sum = 2.5 + 3.0 + 2.8 + 3.5 + 3.1 = 14.9;

[0112] Calculate the maximum load change rate at each time point in the time sequence: max(2.5, 2.7) = 2.7; max(3.2, 3.0) = 3.2; max(2.9, 2.8) = 2.9; max(3.5, 3.6) = 3.6; max(3.1, 3.3) = 3.3; Sum = 2.7 + 3.2 + 2.9 + 3.6 + 3.3 = 15.7;

[0113] Calculate the load change similarity S ij :

[0114] The results show that the load change trend of area A and area B at 5 time points is highly similar, with a similarity of 0.948, close to 1, meaning that the load change rates of the two regions have strong consistency in the time sequence. This value can be used to screen similar load change regions. If the value exceeds the set similarity threshold, it can be determined that the two regions belong to the same load change type, and then classified into the corresponding physical strain response type.

[0115] The physical state division sub-module calls the physical strain response type, classifies the physical strain regions of the same category, calculates the load balance between the classified regions, screens the categories with load balance deviation exceeding the load balance deviation threshold, divides multiple physical state regions, and obtains the physical state classification result;

[0116] The physical condition state division module calls the physical strain response type, and the same type of physical strain area is classified. First, the load balance between the classified areas is calculated. The calculation method is the standard deviation of the load values of all classified areas. For example, the load values of areas A1, A2, and A3 are 5.2 N, 5.4 N, and 5.1 N, respectively. The standard deviation is calculated as Then, the categories with a load balance deviation exceeding the load balance deviation threshold are screened. Assuming that the threshold is set to 0.15 N, if the standard deviation is less than the threshold, it is determined that the load balance of the category is good, otherwise, the category is divided. For example, the standard deviation of a certain category is 0.18 N, which is greater than the threshold, so the category needs to be further divided. Then, according to the load balance, multiple physical condition state areas are divided. If the load deviation of the internal area of a category is large, the category is divided into two independent categories. For example, the original category B1 includes areas A1, A2, and A3, but the load balance of area A3 exceeds the range, so B1 and B2 are divided. Finally, the physical condition state classification result is obtained.

[0117] As shown in Figure 2 and Figure 7 , the physical index monitoring module includes:

[0118] The physical monitoring data integration submodule extracts the corresponding monitoring data in the physical condition state classification result, refers to the exercise load, physiological feedback, and external environment parameters, and matches the time sequence to obtain time sequence alignment monitoring data by excluding data with synchronization error exceeding the error range.

[0119] The physical monitoring data integration submodule extracts the corresponding monitoring data in the physical condition state classification result. First, the monitoring data under each physical condition state category is extracted. The data format includes timestamp, exercise load value, physiological feedback parameters (such as heart rate, blood oxygen saturation, etc.), and external environment parameters (such as temperature, humidity, etc.). For example, at a certain time t1, the monitoring data includes a load value of 6.2 N, a heart rate of 80 bpm, a blood oxygen saturation of 97, and an environment temperature of 25°C. Second, all monitoring data is matched according to the time sequence to ensure that each data source corresponds at the same timestamp. For example, at time point t1, the values of each parameter are 6.2 N, 80 bpm, and 97, respectively. Third, the synchronization error between the data is calculated. The calculation method is the time deviation between different data sources. For example, if the recording time of the exercise load data is t1 = 10:00:00 and the recording time of the physiological feedback data is t1' = 10:00:02, then the synchronization error is t1' - t1 = 2 s. Then, data with an error exceeding the set error range is screened. Assuming that the error range is set to 1 s, if the data error exceeds the range, the data point is excluded. For example, if the error of a certain data point is 3 s, the data is excluded. All time points are traversed and data with an error exceeding the range is excluded. Finally, the time sequence alignment monitoring data is obtained.

[0120] The monitoring index influence analysis submodule analyzes the correlation of each monitoring index based on the time series aligned monitoring data, calculates the contribution of each index to the physical state classification, screens the indexes with contribution exceeding the set contribution standard, induces the contribution index influence relationship, and obtains the monitoring index influence degree;

[0121] The monitoring index influence analysis submodule analyzes the correlation of each monitoring index based on the time series aligned monitoring data. First, the correlation coefficient between each monitoring index is calculated, and the calculation method is Pearson correlation coefficient where Cov(X, Y) is the covariance of indexes X and Y, σ X ,σ Y are the standard deviations of indexes X and Y, for example, the correlation coefficient of heart rate and load is 0.85, indicating that there is a strong positive correlation between them. Then, the contribution of each index to the physical state classification is calculated, and the contribution is the discrimination of the index in different physical state categories, and the calculation method is where μ1, μ2 are the means of the index in two categories, and σ is the standard deviation. For example, in physical state 1 and state 2, the mean heart rate is 80bpm and 90bpm, and the standard deviation is 5, so the contribution is Then, the indexes with contribution exceeding the set contribution standard are screened. Assuming that the set standard is 1.5, if the contribution of an index is greater than the standard, the index is screened. For example, the contribution of heart rate is 2.0, which is greater than 1.5, so the index is selected. All indexes are traversed and the contribution index influence relationship is induced, and finally the monitoring index influence degree is obtained.

[0122] The physical monitoring evaluation generation submodule calls the monitoring index influence degree, calculates the index change amplitude in each physical state, analyzes the difference of the index in each state category, screens the indexes with difference exceeding the physical state difference threshold as feature indexes, extracts the change trend of the feature indexes and divides the physical level, and obtains the physical monitoring evaluation result.

[0123] The physical fitness monitoring evaluation generation submodule calls the monitoring index influence degree, calculates the index change amplitude under each physical fitness state, first, calculates the change range of each index in different physical fitness state categories, the calculation method is the difference between the maximum value and the minimum value, for example, in the physical fitness state 1, the heart rate range is 75-85bpm, then the change amplitude is 85-75=10bpm, then, analyze the difference of the index under each state category, the calculation method is the difference value of the index mean in different categories, for example, the heart rate mean of state 1 is 80bpm, the heart rate mean of state 2 is 90bpm, then the difference value is 90-80=10bpm, then, screen the indexes with the difference exceeding the physical fitness state difference threshold as the characteristic indexes, assuming that the threshold is set to 8bpm, if the difference value of an index is greater than the threshold, it is selected as a characteristic index, for example, the difference value of heart rate is 10bpm, which is greater than 8bpm, so it is screened out, then, extract the change trend of the characteristic index, calculate the trend value as the change rate of adjacent time points, for example If Δt=2s, the change rate is Finally, according to the change trend of the characteristic index, the physical fitness level is divided, for example, if the heart rate change trend exceeds 1.2bpm / s, it is classified as high intensity state, otherwise it is classified as medium intensity state, and finally the physical fitness monitoring evaluation result is obtained.

[0124] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any skilled person in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A wearable physical fitness monitoring system based on graphene, characterized in that: The system includes: The motion direction recognition module acquires the shear strain of the skin surface and the vertical strain of the subcutaneous layer collected by the graphene strain sensor. It calculates the skin strain gradient based on the strain change rate of the skin surface and subcutaneous layer in adjacent time periods to obtain the strain direction change state. The motion direction recognition module includes: The strain data acquisition submodule acquires data collected by the graphene strain sensor, calculates the change in shear strain on the skin surface and the change in vertical strain in the deep subcutaneous layer, matches the changes in shear strain and vertical strain based on the time series, establishes the data correspondence, and obtains the matched strain dataset. Based on the matched strain dataset, the strain gradient calculation submodule extracts the difference between the surface shear strain change and the deep vertical strain change, calculates the skin strain gradient value, filters out abnormal points that exceed the set strain gradient abnormality threshold according to the time series change range, calculates the average gradient change of multiple consecutive time series before and after the abnormal point as the benchmark value, corrects the abnormal point, and obtains the corrected skin strain gradient value. The strain direction change identification submodule calls the corrected skin strain gradient value, calculates the change in direction angle under multiple time series, judges the strain direction change trend, filters time periods where the change rate exceeds the angle change rate threshold, classifies the change trend, and obtains the strain direction change status. For calculating the change in direction angle θ over multiple time series t The formula used is: Where, Δε i,t Δε represents the strain gradient change value of the i-th monitoring point at time t. i,t-1 The value represents the strain gradient change of the i-th monitoring point at the previous time t-1, n represents the number of monitoring points participating in the calculation in the current time series, and d j,t d represents the ranging data of the j-th monitoring point at time t. j,t-1 represents the ranging data of the j-th monitoring point at time t-1, and m represents the number of monitoring points whose ranging data are used in the calculation in the current time series; Based on the state of strain direction change, the motion amplitude monitoring module calls the skin strain gradient change value for each time period, calculates the skin strain amplitude for adjacent time periods, and obtains the strain amplitude change trend. The motion amplitude monitoring module includes: The strain amplitude extraction submodule calls the skin strain gradient change value for each time period in the strain direction change state, sorts it according to the time series, records the strain amplitude information of the complete time period, and obtains the strain amplitude data of the time period. The adjacent time period amplitude calculation submodule calculates the change in skin strain amplitude between adjacent time periods based on the strain amplitude data of the time periods, extracts the average change rate of the time periods when the change rate exceeds the amplitude fluctuation threshold, sets abrupt change point based on the average value and marks the time sequence, calculates the mean deviation between the two time periods before and after the abrupt change point, adjusts the abrupt change point data where the deviation exceeds the set deviation range, recalculates the adjusted amplitude change rate, and obtains the amplitude change rate between adjacent time periods. The amplitude change trend analysis submodule calls the amplitude change rate of the adjacent time period, calculates the amplitude change trend value of multiple time series, filters the time period with continuous increase or decrease in change rate, classifies the trend pattern, and obtains the strain amplitude change trend. For calculating the amplitude trend value ΔV of multiple time series trend The formula used is: Among them, V t1 V represents the amplitude value at time point t1. t1-1 V represents the amplitude value at the previous time point t1-1, Δt1 represents the time interval, usually the measurement period, and V avg ΔV represents the average amplitude value across all measurement periods, T represents the total length of the time series, and ΔV trend This represents the calculated trend value of the magnitude change. The dynamic sensitive area adjustment module refers to the distribution deviation between the current strain data and the motion load monitoring area in the strain amplitude change trend, and takes the monitoring area that exceeds the preset deviation threshold as the sensitive area, adjusts the strain weight of the sensitive area, and obtains the strain sensitive area optimization result. The physical fitness assessment module determines the trend of exercise load change in each sensitive area in the optimization results of the strain-sensitive area, classifies the physical fitness strain response type of the same exercise intensity category, and obtains the physical fitness classification results. Based on the physical fitness status classification results, the physical fitness index monitoring module analyzes the degree of mutual influence of each type of physical fitness status index, classifies physical fitness levels according to the degree of influence, and obtains physical fitness monitoring and evaluation results.

2. The wearable physical fitness monitoring system based on graphene according to claim 1, characterized in that: The strain direction change states include shear strain change, vertical strain change, and strain gradient distribution. The strain amplitude change trend includes the strain gradient change amplitude in adjacent time periods, the skin surface strain change rate, and the subcutaneous deep vertical strain change rate. The skin strain sensitive area optimization results include strain data deviation values, sensitive area adjustment thresholds, and corrected monitoring area weights. The physical fitness status classification results include exercise load change trends, physical fitness strain response types, and exercise intensity classifications. The physical fitness monitoring and evaluation results include correlation analysis of monitoring indicators, physical fitness status assessment, and analysis of the impact of exercise load.

3. The wearable physical fitness monitoring system based on graphene according to claim 1, characterized in that: The dynamic sensitive area adjustment module includes: The deviation calculation submodule calls the strain amplitude change trend to calculate the deviation value between the current strain data and the distribution of the motion load monitoring area, calculates the average deviation value of the area that exceeds the set deviation range, and obtains the regional deviation distribution result. The sensitive area adjustment threshold setting submodule calculates the deviation fluctuation rate of areas exceeding the set deviation range based on the regional deviation distribution results, calculates the sensitive area adjustment threshold based on the mean deviation and fluctuation rate, judges the changing trend of the sensitive area adjustment threshold, adjusts the adjustment range of abnormal areas, and obtains the updated sensitive area adjustment threshold. The monitoring area weight optimization submodule calls the updated sensitive area adjustment threshold, adjusts the sensitive area weight, calculates the weight balance after adjustment, filters areas where the weight change exceeds the adjustment range, and obtains the skin strain sensitive area optimization results.

4. The wearable physical fitness monitoring system based on graphene according to claim 1, characterized in that: The physical fitness assessment module includes: The exercise load trend analysis submodule calls the exercise load change data of each sensitive area in the optimization results of the skin strain sensitive area, calculates the load change rate under the time series, filters the areas whose change rate exceeds the set change rate threshold, and obtains the exercise load change trend. Based on the trend of the change in exercise load, the strain response classification submodule extracts sensitive areas with similar load change rates, calculates the load change similarity between areas, filters areas with similarity exceeding a set similarity threshold, classifies similar load change areas, and obtains the physical strain response type. The physical fitness status classification submodule calls the physical fitness strain response type to classify the physical fitness strain regions of the same category, calculates the load balance between the classified regions, filters the categories whose load balance deviation exceeds the load balance deviation threshold, divides multiple physical fitness status regions, and obtains the physical fitness status classification results.

5. The wearable physical fitness monitoring system based on graphene according to claim 4, characterized in that: For the load change similarity S between calculation regions i1,j1 The formula used is: Among them, R i1,t2 R represents the rate of load change in region i1 at time t2. j1,t2 The load change rate of region j1 ​​at time t2 represents the total time series length, and S represents the load change rate of region j1 ​​at time t2. i1,j1 This represents the similarity of load changes between region i1 and region j1.

6. The wearable physical fitness monitoring system based on graphene according to claim 1, characterized in that: The physical fitness indicator monitoring module includes: The physical fitness monitoring data integration submodule extracts the corresponding monitoring data from the physical fitness status classification results, refers to exercise load, physiological feedback and external environmental parameters, matches the time series, removes data with synchronization error exceeding the error range, and obtains time-aligned monitoring data; The monitoring indicator impact analysis submodule analyzes the correlation of each monitoring indicator based on the time-series aligned monitoring data, calculates the contribution of each indicator to the classification of physical fitness status, filters indicators whose contribution exceeds the set contribution standard, summarizes the influence relationship of contribution indicators, and obtains the degree of influence of monitoring indicators. The physical fitness monitoring and assessment generation submodule calls the influence degree of the monitoring indicators, calculates the change range of the indicators under each physical fitness state, analyzes the differences of the indicators under each state category, selects indicators whose differences exceed the physical fitness state difference threshold as feature indicators, extracts the change trend of the feature indicators and classifies the physical fitness level, and obtains the physical fitness monitoring and assessment results.

Images