Method, device and program product for evaluating a flight anti-overload hp maneuver

Abstract

The application relates to the field of intelligent medical treatment, in particular to a method, device and program product for evaluating a flight anti-overload HP action. Detection values of EIT data, plantar pressure data and electromyography data of a to-be-tested person are acquired; the EIT data comprises one or more of the following whole ventilation parameters: an inspiration value, an expiration uniformity value and an expiration flow rate value; the electromyography data comprises one or more of the following: a gastrocnemius muscle ratio, a rectus femoris muscle ratio and a rectus abdominis muscle ratio; HP action evaluation is carried out based on the detection values of the EIT data, the plantar pressure data and the electromyography data, and an evaluation result of reaching a standard or not reaching the standard is obtained, which has good application value.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent medical treatment, in particular to a method, device, program product and computer readable storage medium for evaluating HP action against overload in flight. BACKGROUND

[0002] In new training modes such as continuous free air combat and system confrontation, pilots are often in a high-G high growth rate environment, the load acting time is long, and high load acting repeatedly occurs, the incidence of G-induced loss of consciousness (G-LOC) significantly increases, which poses a serious threat to flight safety. Correct and effective anti-G straining maneuver (AGSM) is an important measure to prevent G-LOC. Commonly used AGSM includes L-I, M-1 and HP action. However, L-1 and M-1 actions are skillful, the force degree is not easy to control, and pilots are more difficult to master. Therefore, many pilots have inaccurate anti-G actions, are accustomed to their own inherent wrong actions, and have low efficiency and large physical consumption when combined with extended coverage G-suit (ECGS) and pressure breathing for +G (PBG) in the advanced and efficient anti-G system, which can easily lead to pilot fatigue. Therefore, researchers propose HP action. HP action has been widely used in air force fighter pilots and has significant anti-G effect. AGSM uses the change of eye level systolic pressure as the evaluation gold standard, but current non-invasive real-time collection of systolic pressure mainly relies on infrared plethysmography. However, the head blood vessels are located in the deep brain, and the device is difficult to accurately find the blood vessels in the brain and collect the eye level systolic pressure. Therefore, a technology is needed to replace the eye level systolic pressure to evaluate the effect of AGSM. SUMMARY

[0003] To solve the above problems, the present application provides a method for evaluating HP action against overload in flight, which specifically comprises: obtaining the detection values of EIT data, plantar pressure data and electromyography data of the subject to be tested;

[0004] The EIT data includes one or more of the following whole ventilation parameters: inspiratory volume value, expiratory uniformity value, and expiratory flow rate value. The electromyography data includes one or more of the following: gastrocnemius muscle ratio, rectus femoris muscle ratio, and rectus abdominis muscle ratio.

[0005] Based on the detection values of the EIT data, plantar pressure data and electromyography data, HP action evaluation is performed to obtain an evaluation result of reaching the standard or not reaching the standard.

[0006] The plantar pressure includes one or more of the following regional pressures: the thumb area, the first metatarsal area, the lateral area of ​​the arch, and the posterior area of ​​the heel;

[0007] Optionally, the plantar pressure area further includes one or more of the following: the second and third metatarsal areas, the fourth and fifth metatarsal areas, the medial heel area, and the lateral heel area;

[0008] Optionally, the gastrocnemius ratio is a ratio of an electromyographic signal value of the gastrocnemius muscle when the test subject performs HP action to an electromyographic signal value of the gastrocnemius muscle when the test subject is breathing quietly;

[0009] Optionally, the rectus femoris ratio is a ratio of an electromyographic signal value of the rectus femoris when the tester performs the HP action to an electromyographic signal value of the rectus femoris during quiet breathing;

[0010] Optionally, the rectus abdominis ratio is a ratio of an electromyographic signal value of the rectus abdominis when the tester performs the HP action to an electromyographic signal value of the rectus abdominis when the tester breathes quietly;

[0011] Optionally, the evaluation is performed by comparing the detection value of the EIT data with a preset threshold, the detection value of the plantar pressure data with a preset threshold, and the detection value of the electromyography data with a preset threshold; when the detection value of the EIT data, the plantar pressure data, and the electromyography data is greater than the preset threshold, it is determined that the standard is met; when any one of the detection values ​​of the EIT data, the plantar pressure data, and the electromyography data is less than the preset threshold, it is determined that the standard is not met;

[0012] Optionally, the non-compliance includes one or more of the following: EIT non-compliance, plantar pressure non-compliance, electromyographic data non-compliance, EIT and plantar pressure non-compliance, EIT and electromyographic data non-compliance, plantar pressure and electromyographic data non-compliance, EIT, plantar pressure and electromyographic data non-compliance;

[0013] Optionally, the method further includes HP action optimization. When the evaluation result is not up to standard, targeted HP action optimization is performed for the not up to standard result.

[0014] The EIT data is replaced by: inspiratory volume ratio, expiratory uniformity ratio, and expiratory flow rate ratio; the inspiratory volume ratio is the ratio of the inspiratory volume of the test subject during HP maneuvers to the inspiratory volume during quiet breathing; the expiratory uniformity ratio is the ratio of the expiratory uniformity of the test subject during HP maneuvers to the expiratory uniformity during quiet breathing; the expiratory flow rate ratio is the ratio of the expiratory flow rate of the test subject during HP maneuvers to the expiratory flow rate during quiet breathing;

[0015] Optionally, the EIT data further includes one or more of the following: inspiratory volume ratio, expiratory uniformity ratio, expiratory flow rate ratio;

[0016] The EIT data also includes one or more of the following local ventilation parameters: left and right lung ventilation, ventilation center value; optionally, the EIT data local ventilation parameters are replaced by: left and right lung ventilation ratio, ventilation center ratio; the left and right lung ventilation ratio is the ratio of the left and right lung ventilation of the tester performing HP action to the left and right lung ventilation when breathing calmly; the ventilation center ratio is the ratio of the ventilation center of the tester performing HP action to the ventilation center when breathing calmly;

[0017] Optionally, the EIT data also includes one or more of the following: left and right lung ventilation ratio, ventilation center ratio;

[0018] Optionally, when the inspiration volume in the EIT data is greater than a preset threshold, the expiration uniformity is better, the expiration flow rate is greater than a preset threshold, the ventilation center is biased towards the ventral side, and the left and right lung ventilation is biased towards the left side, it is determined to be up to standard.

[0019] The method also includes frontal lobe level oxygenated hemoglobin value, and HP action evaluation is performed based on the detection values of the EIT data, plantar pressure data, electromyography data, frontal lobe level oxygenated hemoglobin value, to obtain an evaluation result; optionally, the evaluation is performed by comparing the detection values of the EIT data, plantar pressure data, electromyography data, frontal lobe level oxygenated hemoglobin value, and a preset threshold, and when the detection values of the EIT data, plantar pressure data, electromyography data, and frontal lobe level oxygenated hemoglobin value are all greater than the preset threshold, it is determined to be up to standard; when any one of the detection values of the EIT data, plantar pressure data, electromyography data, and frontal lobe level oxygenated hemoglobin value is less than the preset threshold, it is determined to be not up to standard;

[0020] Optionally, the not up to standard includes one or more of the following: EIT not up to standard, plantar pressure not up to standard, electromyography data not up to standard, frontal lobe level oxygenated hemoglobin value not up to standard, EIT and plantar pressure not up to standard, EIT and electromyography data not up to standard, plantar pressure and electromyography data not up to standard, EIT and frontal lobe level oxygenated hemoglobin value not up to standard, plantar pressure and frontal lobe level oxygenated hemoglobin value not up to standard, electromyography data and frontal lobe level oxygenated hemoglobin value not up to standard, EIT, plantar pressure, and electromyography data not up to standard, EIT, frontal lobe level oxygenated hemoglobin value, and electromyography data not up to standard, EIT, plantar pressure, and frontal lobe level oxygenated hemoglobin value not up to standard, frontal lobe level oxygenated hemoglobin value, plantar pressure, and electromyography data not up to standard, frontal lobe level oxygenated hemoglobin value, EIT, plantar pressure, and electromyography data not up to standard.

[0021] The evaluation is replaced by: HP action evaluation is performed by an evaluation model to obtain an evaluation result; the evaluation model is obtained by training the correlation between the detection values of the EIT data, plantar pressure data, electromyography data, and high eye level systolic pressure;

[0022] Optionally, the training process of the evaluation model is:

[0023] obtaining the EIT data, the plantar pressure data, the electromyography data, and the eye level systolic pressure high value of the subject when performing the HP action;

[0024] constructing a linear regression model based on the EIT data, the plantar pressure data, the electromyography data, and the eye level systolic pressure high value to obtain the evaluation model;

[0025] Optionally, in the linear regression model, the eye level systolic pressure high value is the dependent variable, and the EIT data, the plantar pressure data, and the electromyography data are the independent variables.

[0026] Optionally, the training process of the evaluation model is replaced by:

[0027] obtaining the EIT data, the plantar pressure data, the electromyography data, and the eye level systolic pressure high value of the subject when performing the HP action;

[0028] calculating the relationship between the EIT data, the plantar pressure data, the electromyography data, and the eye level systolic pressure high value to obtain a mapping relationship;

[0029] feeding the mapping relationship into a neural network model for training to obtain the evaluation model.

[0030] The evaluation model is replaced by: performing HP action evaluation through a first evaluation model to obtain an evaluation result; the first evaluation model is trained based on the correlation between the EIT data, the plantar pressure data, the electromyography data, the frontal lobe level oxygenated hemoglobin value, and the eye level systolic pressure high value.

[0031] Optionally, the training process of the first evaluation model is:

[0032] obtaining the EIT data, the plantar pressure data, the electromyography data, the frontal lobe level oxygenated hemoglobin value, and the eye level systolic pressure high value of the subject when performing the HP action;

[0033] constructing a linear regression model based on the EIT data, the plantar pressure data, the electromyography data, the frontal lobe level oxygenated hemoglobin value, and the eye level systolic pressure high value to obtain the first evaluation model;

[0034] Optionally, in the regression model of the first evaluation model, the eye level systolic pressure high value is the dependent variable, and the EIT data, the plantar pressure data, the electromyography data, and the frontal lobe level oxygenated hemoglobin value are the independent variables.

[0035] Optionally, the training process of the first evaluation model is replaced by:

[0036] Obtain the EIT data, plantar pressure data, electromyographic data detection value, frontal lobe level oxygenated hemoglobin value, and eye level systolic blood pressure high value when the subject performs HP action;

[0037] Calculating the relationship between the EIT data, the plantar pressure data, the detection value of the electromyographic data, the frontal lobe level oxygenated hemoglobin value and the eye level systolic blood pressure high value to obtain a mapping relationship;

[0038] The mapping relationship is input into a neural network model for training to obtain a first evaluation model.

[0039] Optionally, the evaluation model is replaced by: performing HP action evaluation using a second evaluation model to obtain an evaluation result; the second evaluation model is obtained by training the correlation between the detection values ​​of EIT data, plantar pressure data, and electromyography data and the oxygenated hemoglobin value at the frontal lobe level;

[0040] Optionally, the training process of the second evaluation model is:

[0041] Obtain EIT data, plantar pressure data, electromyographic data detection values, and frontal lobe oxyhemoglobin values ​​when the subject performs HP movements;

[0042] A linear regression model is constructed based on the detection values ​​of the EIT data, the plantar pressure data, the electromyographic data and the frontal lobe level oxyhemoglobin value to obtain a second evaluation model.

[0043] Optionally, in the regression model of the second evaluation model, the frontal lobe level oxygenated hemoglobin value is the dependent variable, and the detection values ​​of EIT data, plantar pressure data, and electromyography data are independent variables.

[0044] The plantar pressure parameter is obtained by a plantar pressure device, which includes an insole, N pressure sensors, a signal transmission circuit, and an external circuit module; the N pressure sensors are fixed to the insole and connected to form a closed loop through the signal transmission circuit, the signal transmission circuit is connected to the external circuit module, and the external circuit module is used to process signal data, where N is a natural number greater than or equal to 4;

[0045] When the pressure sensor is subjected to pressure, a pressure signal is generated, and the pressure signal is transmitted to the external circuit module through the signal transmission circuit. The external circuit module receives the pressure signal to obtain plantar pressure data;

[0046] Optionally, the number of the pressure sensors is 4-8;

[0047] Optionally, the number of the pressure sensors is 4;

[0048] Optionally, when the number of the pressure sensors is 4, the pressure sensors are fixed at the thumb area, the first metatarsal bone area, the lateral arch area, and the rear heel area, respectively.

[0049] Optionally, when the number of the pressure sensors is 8, the pressure sensors are fixed at the thumb area, the first metatarsal bone area, the lateral arch area, the rear heel area, the second metatarsal bone area, the fourth metatarsal bone area, the medial heel area, and the lateral heel area, respectively.

[0050] The purpose of the present application is to provide a computer program product comprising a computer program or instructions thereon, which are executed by a processor to implement the above-mentioned evaluation method of flight anti-overload HP action.

[0051] The purpose of the present application is to provide a computer device comprising a memory, a processor, and a computer program or instructions stored on the memory, which are executed by the processor to implement the above-mentioned evaluation method of flight anti-overload HP action.

[0052] The purpose of the present application is to provide a computer-readable storage medium having a computer program or instructions stored thereon, which are executed by a processor to implement the above-mentioned evaluation method of flight anti-overload HP action.

[0053] Advantages of the present application:

[0054] 1. The HP action evaluation is performed by multiple parameters, including EIT parameter data, foot parameter data, and electromyographic parameter data, which comprehensively detects the tester during the HP action, forms a complete detection process and system, and helps to improve the reliability and accuracy of HP action detection.

[0055] 2. For the foot parameter, experiments show that pressure measurement in the thumb area, the first metatarsal bone area, the lateral arch area, and the rear heel area can better detect the standard degree of the tester during the HP action compared to other areas, which helps to improve the detection accuracy of HP action.

[0056] 3. The present application also proposes frontal lobe level oxygenated hemoglobin value, which is used together with EIT parameter data, foot parameter data, and electromyographic parameter data for HP action detection, increases a new dimension, and improves the reliability of HP detection. Secondly, the evaluation results are used for targeted HP action optimization and improvement. EIT parameters are used to determine whether the breathing during HP action meets the standard, foot parameter data and electromyographic parameter data are used to determine whether the foot and lower limb actions meet the standard, and frontal lobe level oxygenated hemoglobin value is used to determine whether the deoxyhemoglobin concentration change is normal to meet the HP action, which helps to train HP action.

[0057] 4. Constructing a regression model based on the frontal lobe level oxygenated hemoglobin value, EIT parameter data, foot parameter data and electromyography parameter data, and using the constructed regression equation to perform real-time and accurate evaluation on the training effect of the pilot AGSM. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed 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.

[0059] Figure 1 The evaluation method flowchart of the flight anti-overload HP action provided by the embodiment of the present application;

[0060] Figure 2 The evaluation system schematic diagram of the flight anti-overload HP action provided by the embodiment of the present application;

[0061] Figure 3 The evaluation device schematic diagram of the flight anti-overload HP action provided by the embodiment of the present application;

[0062] Figure 4 The surface electromyography electrode pasting position and foot pressure measurement insole point position schematic diagram provided by the embodiment of the present application;

[0063] Figure 5 The mean value of eye level systolic pressure during the calm breathing and HP action of the subject provided by the embodiment of the present application;

[0064] Figure 6 The EIT impedance-time curve provided by the embodiment of the present application, A: the impedance-time curve during the calm breathing and HP action of the subject; B: the impedance-time curve during the HP action of the subject. a: P<0.001, compared with the impedance value during the calm breathing; b: P<0.001, compared with the impedance value of the subject No.1; AU: arbitrary unit;

[0065] Figure 7 The inspiration volume (A) and the inspiration volume ratio (B) of different groups during the calm breathing and HP action of the subject provided by the embodiment of the present application; A: the IV point line graph during the calm breathing and HP action of the subject P1-P12 represents 12 subjects, 85.5321 and 233.4905 represent the IV mean value of 12 subjects during the calm breathing and HP action; B: the IVHP / IVPJ box plot between different groups. a: P<0.001, compared with the inspiration volume mean value during the calm breathing; b: P<0.01, compared with the d<30mmHg group; AU: arbitrary unit;

[0066] Figure 8 Exhalation evenness of the subject during HP action provided by the embodiment of the present application;

[0067] Figure 9 Exhalation flow rate of the subject during HP action provided by the embodiment of the present application;

[0068] Figure 10 Exhalation evenness of the subject during HP action provided by the embodiment of the present application;

[0069] Figure 11 Respiratory time of the subject during HP action provided by the embodiment of the present application;

[0070] Figure 12 Ventilation center mean value of the subject during HP action provided by the embodiment of the present application;

[0071] Figure 13 Left and right lung ventilation ratio mean value of the subject during HP action provided by the embodiment of the present application;

[0072] Figure 14 Three-muscle iEMG box plot of the subject during HP action provided by the embodiment of the present application;

[0073] Figure 15 Right foot plantar pressure mean value box plot of the subject provided by the embodiment of the present application, a: 5-point relaxation state compared with the rest of the point, the difference is statistically significant (p<0.05); b: 8-point relaxation state compared with the rest of the point (except 5), the difference is statistically significant (p<0.001);

[0074] Figure 16 HbO2 box plot of the subject during HP action provided by the embodiment of the present application;

[0075] Figure 17 Regression equation fitting graph provided by the embodiment of the present application;

[0076] Figure 18 Bland-Altman consistency test provided by the embodiment of the present application;

[0077] Figure 19 Single-factor linear regression scatter and fitting equation graph provided by the embodiment of the present application. DETAILED DESCRIPTION

[0078] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application.

[0079] In some of the flowcharts described in the description, claims, and drawings of the present application, multiple operations are included in a single flowchart, and it should be apparent that the operations can be performed in other sequences and be performed in parallel or concurrently. The sequence of operations should not be construed as limiting the claims. The flowcharts can include more or fewer operations, can be performed in a different order than the described, or can be performed concurrently or in parallel. It is further noted that the descriptions of“first,”“second,” and the like in this disclosure refer to different messages, devices, modules, etc. and are not intended to denote or imply that the first and second are different types of messages, devices, modules, etc.

[0080] Figure 1 The evaluation method of the flight anti-overload HP action provided by the embodiment of the application specifically comprises the following steps: S101: acquiring detection values of EIT data, plantar pressure data, and electromyography data of a to-be-tested person;

[0081] The EIT data comprises one or more of the following overall ventilation parameters: inhalation volume, exhalation uniformity, and exhalation flow rate; and the electromyography data comprises one or more of the following: gastrocnemius muscle ratio, rectus femoris muscle ratio, and rectus abdominis muscle ratio.

[0082] In one embodiment, the plantar pressure comprises one or more of the following regional pressures: thumb region, first metatarsal region, lateral arch region, and posterior heel region.

[0083] In one embodiment, the plantar pressure further comprises one or more of the following regional pressures: second-third metatarsal region, fourth-fifth metatarsal region, medial heel region, and lateral heel region.

[0084] In one embodiment, the gastrocnemius muscle ratio is a ratio of an electromyography signal value of the gastrocnemius muscle when the to-be-tested person performs the HP action to an electromyography signal value of the gastrocnemius muscle when the to-be-tested person breathes calmly.

[0085] Optionally, the rectus femoris muscle ratio is a ratio of an electromyography signal value of the rectus femoris muscle when the to-be-tested person performs the HP action to an electromyography signal value of the rectus femoris muscle when the to-be-tested person breathes calmly.

[0086] Optionally, the rectus abdominis muscle ratio is a ratio of an electromyography signal value of the rectus abdominis muscle when the to-be-tested person performs the HP action to an electromyography signal value of the rectus abdominis muscle when the to-be-tested person breathes calmly.

[0087] In one embodiment, the EIT data is replaced by one or more of: an inspiration volume ratio, an expiration uniformity ratio, an expiration flow rate ratio; the inspiration volume ratio is a ratio of the inspiration volume of the subject performing the HP maneuver to the inspiration volume of the subject performing quiet breathing; the expiration uniformity ratio is a ratio of the expiration uniformity of the subject performing the HP maneuver to the expiration uniformity of the subject performing quiet breathing; the expiration flow rate ratio is a ratio of the expiration flow rate of the subject performing the HP maneuver to the expiration flow rate of the subject performing quiet breathing.

[0088] In one embodiment, the EIT data further comprises one or more of: an inspiration volume ratio, an expiration uniformity ratio, an expiration flow rate ratio.

[0089] The EIT data further comprises one or more of the following regional ventilation parameters: left and right lung ventilation, ventilation center value; in one embodiment, the EIT data regional ventilation parameters are replaced by: left and right lung ventilation ratio, ventilation center ratio; the left and right lung ventilation ratio is a ratio of the left and right lung ventilation of the subject performing the HP maneuver to the left and right lung ventilation of the subject performing quiet breathing; the ventilation center ratio is a ratio of the ventilation center of the subject performing the HP maneuver to the ventilation center of the subject performing quiet breathing.

[0090] In one embodiment, the EIT data further comprises one or more of: left and right lung ventilation ratio, ventilation center ratio.

[0091] In one embodiment, the plantar pressure parameters are obtained by a plantar pressure device, the plantar pressure device comprising an insole, N pressure sensors, a signal transmission circuit, an external circuit module; the N pressure sensors are fixed on the insole, and are connected to form a closed loop through the signal transmission circuit, the signal transmission circuit is connected to the external circuit module, the external circuit module is used for processing signal data, and N is a natural number greater than or equal to 4;

[0092] When the pressure sensor is subjected to pressure, a pressure signal is generated, the pressure signal is transmitted to the external circuit module through the signal transmission circuit, and the external circuit module obtains plantar pressure data by receiving the pressure signal; in one embodiment, the number of the pressure sensors is 4-8.

[0093] In one embodiment, the number of the pressure sensors is 4.

[0094] In one embodiment, when the number of the pressure sensors is 4, the pressure sensors are respectively fixed in the thumb region, the first metatarsal bone region, the lateral arch region and the heel rear region.

[0095] In one embodiment, when the number of pressure sensors is 8, the pressure sensors are fixed in the thumb area, the first metatarsal area, the lateral arch area, the rear heel area, the second and third metatarsal area, the fourth and fifth metatarsal area, the medial heel area, and the lateral heel area, respectively.

[0096] In one specific embodiment, the experiment was conducted in March 2023, and 8 healthy volunteers from the Air Force Medical University were selected as the research subjects. They had no experience with anti-G action training and were beginners. The inclusion criteria were: no history of smoking, no respiratory diseases, no serious cardiovascular and nervous system diseases, no infectious diseases, and exclusion of severe flat feet and lower extremity injuries.

[0097] Before the formal experiment began, a professional instructor (who was proficient in AGSM) guided all the subjects (i.e., beginners) to learn the essentials of HP action and L1 action. The subjects practiced AGSM repeatedly until they completely learned it and passed the test of the professional instructor. According to the chest size of the subjects, EIT electrode belts (with 16 equally spaced rubber electrodes) of consistent length were selected. After disinfecting the EIT electrode belt and the body surface with alcohol cotton, physiological saline was applied to the electrode belt. Then, the EIT electrode belt was placed horizontally between the 4th and 5th intercostal spaces of the subject, and the acquisition box was connected to the electrode belt. The EIT electrode belt numbers 1 / 16 / 8 / 9 were adhered to the skin surface using conductive glue to prevent disconnection. A lung EIT imager was used for real-time imaging of lung ventilation (the lung EIT imager uses Bluetooth to transmit data, the acquisition device has a volume of 12cm x 8cm x 3cm, the number of electrodes is 16, the acquisition frame rate is 20Hz, the excitation current is 700μA, and the imaging speed is 20 frames / second). The surface electromyography electrode patch was selected as a 3M disposable electrocardiogram electrode patch. After alcohol disinfection of the skin, it was adhered to the highest muscle belly in the parallel muscle fiber direction, with electrodes about 2cm apart, and the reference electrode was placed at the prominent bony landmark (low muscle activity). In this study, the central patella, gastrocnemius muscle, rectus femoris muscle, and rectus abdominis muscle were selected as the sticking positions. Figure 4The foot pressure measurement insole was placed in the subject's shoe, and the 8-point foot pressure measurement insole with a 50Kg range was worn, and black sports shoes were worn uniformly, and the foot rudder was changed to the ground to cover all the points of the multi-point foot pressure insole. The near-infrared headband was worn on the frontal lobe position, and the near-infrared device headband was fixed on the forehead using self-adhesive elastic bandage to prevent interference caused by movement. The subject sat in the anti-G physiological trainer (GD-KHXLY-1.1 type), was told to breathe calmly and relax, and 2 min of baseline data was collected, and 20 s of stable systolic pressure was taken for analysis; the maximum strength was used to test the maximum force, and then the HP action and L1 action were performed for 30 s each three times, and the multi-dimensional physiological parameter measurement was performed during the interval, and the interval was at least 5 min to ensure the recovery of the resting state, and the maximum change of the systolic pressure mean value of 5-25 s was taken for analysis. The non-invasive continuous blood pressure was measured by the eye level arterial pressure, and the AGSM anti-G ability was reflected by the eye level systolic pressure rise value (d). The calculation method was: the mean value of the eye level systolic pressure (SBPHP) of 5-25 s during the HP action minus the mean value of the eye level systolic pressure (SBPPJ) of 20 s of calm breathing (i.e. d = SBPHP-SBPPJ), unit: mmHg. The specific method is: connect the non-invasive continuous blood pressure measurement instrument hardware device (cuff, finger sleeve, height calibrator), perform physiological correction and reflux correction, and obtain the exact heart level blood pressure of each subject. Then, the cylindrical device (heart level height) is placed at the eye outer canthus level position, and the blood pressure converted by the hydrostatics of the calibrator is the eye level continuous blood pressure.

[0098] In one embodiment, the EIT data processing:

[0099] Matlab R2022a (The MathWorks Inc, Natick, MA, USA) was used to analyze the EIT data, and the EIDORS 2.8 platform was used to complete the reconstruction of the lung EIT image. The reconstruction method adopts the GREIT algorithm. Based on the CT image of a real adult male, a finite element model was constructed, and then the reconstruction matrix was calculated. The reconstructed EIT image is composed of 32*32 pixels. The end-expiratory time under the calm breathing state is selected as the reference frame, and the lung EIT image during the entire experiment is reconstructed. The key parameters of EIT used in this study are as follows. Inspiratory Volume (IV): Inspiratory Volume is the difference between the inspiratory EIT image and the expiratory EIT image, reflecting the change in inspiratory volume. The mean value of more than 5 respiratory cycles is used as the final value, and the calculation formula is as follows:

[0100]

[0101] wherein, IV i is the pixel i in the EIT image; N is the number of breaths included in the analysis, which is ≥5 in this study; ΔZi,Ins,n and ΔZ i,Exp,n are the pixel values of the original EIT images at the beginning of inspiration and expiration, respectively. If IV i <0, then IVi is assigned a value of 0.

[0102] expiratory uniformity (EU): calculated by the change of expiratory volume per unit time during each breath, reflecting the uniformity of expiration during quiet breathing and Gz maneuver. The mean of expiratory uniformity of more than 5 breaths was taken as the final value, and the unit time was defined as 200 ms. The formula is as follows:

[0103]

[0104] wherein, is the global impedance change in the mth unit time in the nth breath cycle; N is the number of breaths included in the analysis, which is ≥5 in this study; and the unit time is defined as 200 ms.

[0105] expiratory speed (ES): calculated by the ratio of expiratory volume to expiratory time during each breath, reflecting the flow rate of expiration during quiet breathing and Gz maneuver. The mean of expiratory uniformity of more than 5 breaths was taken as the final value. The formula is as follows:

[0106]

[0107] wherein, is the tidal impedance change in the nth breath cycle; N is the number of breaths included in the analysis, which is ≥5 in this study.

[0108] Center of ventilation (CoV): the change of CoV reflects the regional ventilation distribution change in the vertical direction of abdomen and back caused by AGSM (the weighted position of relative impedance value in the anterior-posterior coordinate), and the formula is as follows:

[0109]

[0110] wherein, TV i is the impedance change of pixel i in the fEIT image, y i is the pixel height and pixel i is scaled, so that the bottom (back) of the image is 100% and the top (abdomen) is 0%. The mean of AGSM breathing action of ≥5 breaths was taken as the final value.

[0111] Right-to-left lung ventilation ratio (RtoL): the change of RtoL reflects the regional ventilation distribution change of left and right lungs caused by AGSM, and the formula is as follows:

[0112]

[0113] wherein, ROI1-4 are the regional impedance changes of specific customized regions of interest (ROIs), ROI1, ROI3 are the regional impedance changes of the right upper and lower regions, ROI2, ROI4 are the regional impedance changes of the left upper and lower regions; N is the number of breaths included in the analysis, in the present study, ≥5.

[0114] In one embodiment, the surface electromyography data is processed;

[0115] Root mean square amplitude (RMS): RMS represents the strength of the electromyography signal, which is related to the number of motor units involved in the activity and the degree of synchronization of the discharge frequency. In practical applications, it is often used to reflect the energy size of the generated electromyography. With the deepening of fatigue, RMS has a rising trend. The calculation formula of RMS value is:

[0116]

[0117] wherein, t is the electromyography signal collection time, and xt is the electromyography signal size.

[0118] Integral electromyography value (iEMG): The integral electromyography value (iEMG) is the sum of the area under the curve per unit time after the rectified filtering of the obtained electromyography signal. It can reflect the strength change of the electromyography signal over time. iEMG is used to analyze the contraction characteristics of the muscle in a unit of time, and represents the total discharge of the motor unit involved in the muscle activity in a certain time. The calculation formula is as follows:

[0119]

[0120] wherein, t1 is the electromyography signal collection start time, t2 is the electromyography signal collection end time, and x(t) is the electromyography signal size.

[0121] In one embodiment, the near-infrared data is processed: Previous research data shows that the absorption rate of water in the blood in the near-infrared spectral window (i.e. the spectral window of 600-900 nm wavelength) is the smallest, and the absorption rate of oxygenated hemoglobin (HbO2 or HbO) and deoxyhemoglobin (Hb or HbR) is larger. The concentration of oxygenated hemoglobin and deoxyhemoglobin is related to the Lambert-Beer law. The Lambert-Beer law is a formula describing the relationship between incident light and emitted light after light is incident into a non-scattering medium, and the formula is as follows:

[0122]

[0123] The concentration change of HbO2 is calculated according to the Lambert-Beer law formula, and the calculation results are as follows:

[0124]

[0125] Where λ1 represents the incident light intensity, λ2 represents the received light intensity, DPF represents the differential path factor, HbO represents oxyhemoglobin, and HbR represents deoxyhemoglobin.

[0126] In one embodiment, statistical analysis was performed using SPSS 27.0 (IBM, USA). The Shapro-Wilk test was used to test data normality. After confirming that the data were normally distributed, the measurement data were expressed as mean ± standard deviation (x ± s). Pulmonary ventilation parameters of quiet breathing and AGSM were compared using paired sample t-tests. Plantar pressure parameters of bivariate intra-group data (i.e., quiet breathing vs. HP maneuver) were compared using independent sample t-tests. Multivariate intra-group and inter-group data, i.e., quiet breathing, maximum pedal force, and surface electromyography parameters of AGSM, were compared using one-way ANOVA tests. Post hoc comparisons were performed using the LSD test. P < 0.05 was considered statistically significant.

[0127] In a specific embodiment, the eye level systolic pressure results are: the average eye level systolic pressure during quiet breathing is (95.17±8.51) mmHg, and the average eye level systolic pressure during HP maneuver is (148.82±22.75) mmHg. The eye level systolic pressure during HP maneuver is significantly increased, and the difference is statistically significant (P<0.001, Figure 5 ). EIT results: EIT impedance-time curve comparison. The impedance-time curve of the subjects when performing HP maneuvers was significantly different from that of the subjects when performing calm breathing (P<0.001, Figure 6 The impedance-time curves of different subjects were significantly different when performing HP action (P<0.001, Figure 6 B), EIT can reflect the changes in pulmonary ventilation and realize real-time monitoring of pulmonary ventilation images.

[0128] Comparison of IV during quiet breathing and HP maneuver: Compared with quiet breathing, the inspiratory volume (IV) during HP maneuver of beginners was significantly increased, and the difference was statistically significant (P < 0.001, Figure 7 The subjects were divided into three groups according to d>60, 30~60, and <30 mmHg. The inspiratory volume ratio (IVHP / IVPJ) was the largest in the d>60 mmHg group and the smallest in the d<30 mmHg group. The difference was statistically significant (P<0.01, Figure 7 B).

[0129] Comparison of EU during quiet breathing and HP maneuver: Compared with quiet breathing, the exhalation uniformity value (EU) of beginners during HP maneuver was significantly reduced, and the exhalation was more uniform. The difference was statistically significant (P < 0.05, Figure 8 Comparison of ES during quiet breathing and HP maneuvers: Compared with quiet breathing, the expiratory flow rate (ES) during HP maneuvers for beginners was significantly faster, and the difference was statistically significant (P < 0.001, Figure 9 ).

[0130] Comparison of EU during quiet breathing and HP maneuver: Compared with quiet breathing, the exhalation uniformity value (EU) of the subjects during HP maneuver was significantly reduced, and the exhalation was more uniform, and the difference was statistically significant (P < 0.05, Figure 10 Comparison of breathing time during calm breathing and HP maneuver: Compared with calm breathing, the inhalation and exhalation time during HP maneuver for beginners were significantly shortened, and the differences were statistically significant (P < 0.001, P < 0.01, respectively). Figure 11 ), the exhalation time required by HP action is 2.0s, but the exhalation time of beginners is shorter, and the difference is statistically significant (P<0.001, Figure 11 ).

[0131] Comparison of COV during quiet breathing and HP maneuvers: Compared with quiet breathing, the center of ventilation (COV) of beginners during HP maneuvers was significantly smaller and more ventral, and the difference was statistically significant (P < 0.001, Figure 12 ).

[0132] Comparison of RtoL during quiet breathing and HP maneuver: Compared with quiet breathing, the ventilation ratio (RtoL) of the left and right lungs during HP maneuver was reduced, and the ventilation distribution was biased towards the left lung. The difference was statistically significant (P < 0.05, Figure 13 ).

[0133] sEMG results section:

[0134] The results of surface electromyography integrated electromyography (iEMG) (unit: μV·s) are as follows Figure 14As shown, in the rest state vs. HP movement, the iEMG of gastrocnemius muscle was 40.486±16.305 vs. 1154.478±756.884 (p<0.001), rectus femoris muscle was 83.844±9.688 vs. 1221.072±705.610 (p<0.001), and rectus abdominis muscle was 114.248±35.701 vs. 879.562±449.420 (p<0.001). The iEMG of the three muscles increased significantly during the HP movement. The maximum force vs. HP movement was: gastrocnemius muscle was 1211.694±779.679 vs. 1154.478±756.884, rectus femoris 1266.028±695.562 vs 1221.072±705.610, rectus abdominis 813.311±445.013 vs 879.562±449.420, the differences were not statistically significant (p>0.05), but compared with the maximum pedaling state, the surface electromyography (iEMG) of the rectus abdominis was larger during HP movement.

[0135] Multi-point plantar pressure results section:

[0136] The results of multi-point plantar pressure average (unit: Kgf) are as follows Figure 15 As shown, (1) in the quiet state, the pressure of the lateral arch area and the posterior heel area were greater than those of the eight points, and the difference was statistically significant (p < 0.05, p < 0.001); (2) in the quiet state vs. HP action: the average pressure of the four points during HP action, namely, the thumb area, the first metatarsal area, the lateral arch area, and the posterior heel area, increased significantly, and the difference was statistically significant (p < 0.01, p < 0.001). The pressure of the remaining four points, namely, the second and third metatarsal areas, the fourth and fifth metatarsal areas, the medial heel area, and the lateral heel area, increased. Near infrared results: Figure 16 As shown in the figure, the mean value of oxygenated hemoglobin (HbO2) at the frontal lobe level in the calm state was 1.54, and the mean value during HP action was 23.26, which was significantly higher than that in the calm state, and the difference was statistically significant (p < 0.001). It showed the same trend as the systolic blood pressure at the eye level, which was in line with theoretical expectations.

[0137] In one embodiment, EIT can be used for monitoring and evaluating HP action respiratory lung ventilation and respiratory muscle contraction. From the perspective of EIT overall lung ventilation, ① there is a great difference between the EIT impedance-time curve of the subject during HP action and quiet breathing. The impedance value is larger during HP action, reflecting that the lung ventilation is larger. However, for beginners, there is also a significant difference in HP action. The lung ventilation of the first tester is extremely unstable during HP action. The end-expiratory lung impedance becomes smaller and then increases and decreases again. That is, the residual volume experiences a decrease-increase-decrease change, and the range of end-inspiratory impedance change is also extremely large, thereby establishing a large fluctuation range of intrathoracic pressure. However, the lung ventilation of the second tester is relatively stable during HP action, and the end-inspiratory and end-expiratory lung impedance changes are small, thereby establishing a stable intrathoracic pressure and a more standard breathing action than the first tester. Therefore, the EIT impedance-time curve can be used as an important reference for monitoring and guiding beginners to perform correct and effective breathing action. ② Compared with quiet breathing, the inspiratory volume (IV) of the subject during HP action is significantly larger (P<0.001), which is consistent with the requirement of HP action that the subject performs moderate rapid inspiration. The grouping results show that the inspiratory volume ratio (IVHP / IVPJ) is the largest in the d>60 mmHg group and the smallest in the d<30 mmHg group, and the difference is statistically significant (P<0.01). With the increase of the eye level systolic pressure difference, IVHP / IVPJ also increases, which confirms the previous research that intrathoracic pressure increases with the increase of inspiratory volume, thereby increasing the eye level arterial pressure. At the same time, it shows that for beginners, the rapid inspiratory volume greatly affects the establishment of intrathoracic pressure. Therefore, in the AGSM training of beginners, the size of the rapid inspiratory volume (IV) should be observed. ③ Compared with quiet breathing, the expiratory flow rate (ES) of the subject during HP action is significantly faster (P<0.001), which is related to the requirement of HP action that the subject forms an expiratory segment with slightly open lips, pronounces Chinese pinyin "P" (piao), and exhales forcefully. Therefore, the expiratory flow rate (ES) can be used to evaluate the expiratory segment of HP action. ④ The inspiratory time of HP action is (0.77±0.32) s, which is slightly slower than the standard requirement of 0.5 s. The expiratory time is (1.59±0.21) s, which is faster than the standard requirement of 2.0 s, and the difference is statistically significant (P<0.001). Combined with the analysis of inspiratory volume (IV), for beginners, the problem of shallow and fast breathing is more prominent in the AGSM training of beginners.

[0138] From the perspective of EIT local lung ventilation, ① the subjects' center of ventilation (COV) during HP maneuvers was significantly smaller than that during quiet breathing, and the ventilation center was more ventral (P < 0.001). The reason may be that during HP maneuvers, chest breathing is mainly performed. Due to forced breathing, the contraction of muscles such as the external intercostal muscles increases, driving full expansion of the thorax. The spine is located in the center of the back of the thorax, and is wrapped on both sides by powerful erector spinae, latissimus dorsi, trapezius and other muscles, which limits its expansion. The lung tissue expands more ventrally, making the COV, an indicator reflecting changes in the dorsal and ventral lung ventilation distribution, smaller and the ventilation center more ventrally. Therefore, the size of COV can serve as a sensitive indicator of the forced contraction of thoracic respiratory muscles such as the external intercostal muscles. ② During HP maneuvers, the RtoL of the subjects decreased compared with that during quiet breathing, and the ventilation distribution shifted from being biased towards the right lung during quiet breathing to being biased towards the left lung (P < 0.05). That is, the ventilation volume of the right lung was slightly greater than that of the left lung during quiet breathing, while the ventilation volume of the left lung was greater than that of the right lung during HP maneuvers. The reasons for this may be that the anatomical position of the heart is biased to the left, and the right lung is slightly larger than the left lung in normal people. The trachea is divided into the left and right main bronchi. The left main bronchus is thin and long, runs obliquely, and enters the left lung through the left hilum. The right main bronchus is thick and short, runs steeply, and enters the left lung through the left hilum. The right hilum enters the right lung, so during quiet breathing, the right lung ventilation volume of a normal person is slightly larger than that of the left lung. During the HP maneuver, forced breathing increases the up and down movement of the diaphragm (the main respiratory muscle). During inhalation, the diaphragm drops more, the heart moves downward, and the left lung expands more. During exhalation, the diaphragm rises higher, the heart moves upward, compressing the left lung, making the residual volume of the left lung less than that of quiet breathing, resulting in the left lung ventilation volume being greater than the right lung during the HP maneuver. Therefore, the size of RtoL can be used as a sensitive indicator to reflect the force of contraction of respiratory muscles such as the diaphragm.

[0139] Results showed that, from a global ventilation perspective, EIT provided real-time imaging of pulmonary ventilation and reflected the magnitude of pulmonary ventilation during HP maneuvers. Compared with quiet breathing, HP maneuvers demonstrated greater inspiratory volume (IV), improved expiratory uniformity (EU), and faster expiratory flow rate (ES). From a regional ventilation perspective, HP maneuvers exhibited a more ventral center of ventilation (COV), a smaller RtoL, and a leftward distribution of ventilation compared to quiet breathing, all of which were associated with the forced contraction of respiratory muscles (external intercostal muscles, diaphragm, etc.). As a real-time pulmonary function imaging technique, EIT offers advantages such as noninvasiveness, radiation-free operation, portability, and rapid imaging, and holds great promise for application in AGSM training and monitoring.

[0140] In one embodiment, the multi-point plantar pressure-surface electromyography combined technology can be used for real-time accurate monitoring and evaluation of HP action muscle contraction. 1. When the subject is in a calm state, the foot pressure is mainly concentrated in the ⑧ posterior heel and ⑤ lateral arch area. When performing HP action, the pressure changes most significantly in the ① thumb area, ② first metatarsal area, ⑤ lateral arch area, and ⑧ posterior heel area. Therefore, during HP action training, the pilot should emphasize the force of these four areas, and the design of the landing gear of the fighter jet should fully consider the design of the landing points of these four areas to provide sufficient support for the maximum anti-G capability of the fighter pilot; 2. During HP action, the iEMG of the lower limbs and abdominal muscles is significantly increased (i.e., the muscle strength is significantly increased), but the iEMG of the rectus abdominis is lower than that of the lower limb muscles, indicating that the muscle contribution of the lower limb muscles is greater than that of the abdominal muscles. Since the abdominal fat is more than the lower limbs, it interferes with the surface electromyography signal to some extent, so this result needs to be further verified; 3. Compared with the maximum pedal force state, the iEMG of the lower limb muscles is low during HP action, but the iEMG of the rectus abdominis is increased, i.e., the muscle strength of the rectus abdominis is smaller during the maximum pedal force than during HP action. Therefore, the maximum pedal force may not be the only evaluation index for lower limb and abdominal muscle contraction, and during training, excessive attention may be paid to the pedal force size while ignoring the abdominal muscle force. Therefore, in beginners, more emphasis should be placed on the forceful contraction of the abdominal muscles.

[0141] In one embodiment, the near-infrared device can replace the eye level systolic pressure device and be integrated into the flight helmet lining for real-time monitoring of AGSM. At present, non-invasive real-time collection of systolic pressure mainly relies on infrared plethysmography, and the blood vessels in the head are located deep in the brain, so it is difficult for the device to accurately find the blood vessels and collect the eye level systolic pressure. Therefore, a technology is needed to replace the eye level systolic pressure to evaluate the effect of AGSM. In this experiment, the oxygenated hemoglobin (HbO2) calculated from the near-infrared spectroscopy signal significantly increased during AGSM, and the near-infrared device collects near-infrared spectroscopy signals, which use the intensity of the emitted and received light to reflect the changes in the concentration of oxygenated hemoglobin and deoxyhemoglobin in the frontal lobe. It can be integrated into the lining of the pilot's helmet and may become an alternative index for eye level systolic pressure for AGSM anti-G effect evaluation.

[0142] In one embodiment, the AGSM real-time accurate monitoring and evaluation method is constructed. The experiment was conducted in June 2024, and 66 students who were proficient in AGSM were selected as the research object. The students had previously undergone AGSM system learning and training and were qualified and excellent according to the professional teacher's examination. The general data were as follows: age (21.3±1.06) years old; height (176.6±4.52) cm; weight (74.0±10.13) kg. The inclusion and exclusion criteria and experimental methods were the same as above. The key indicators in the multi-dimensional physiological parameter experiment during AGSM were verified and modeled. As with beginners, the inspiratory volume (IV), expiratory flow rate (ES), left and right lung ventilation ratio (RtoL), and ventilation center (COV) during AGSM were significantly different (p<0.001, p<0.01), so they can be used as key indicators for modeling analysis of AGSM respiratory action monitoring and evaluation. Compared with the calm state, the gastrocnemius, rectus femoris, and rectus abdominis surface electromyography iEMG during AGSM were significantly increased, and the difference was statistically significant (all p<0.001), so they can be used as key indicators for modeling analysis of AGSM muscle contraction degree monitoring and evaluation. Compared with the calm state, the average of the 8-point plantar pressure during AGSM was significantly increased, and the difference was statistically significant (p<0.001, p<0.01), so it can be used as a key indicator for modeling analysis of AGSM lower limb force degree monitoring and evaluation.

[0143] The horizontal systolic blood pressure difference (d-SBP) and IV ratio (IVHP / IVPJ), ES ratio (ESHP / ESPJ), COV ratio (COVHP / COVPJ), RtoL ratio (RtoLHP / RtoLPJ), gastrocnemius, rectus femoris, rectus abdominis iEMG ratio (iEMGHP / iEMGPJ), and multi-point plantar pressure 8-point difference (d-1-d8) variable scatter plot showed a roughly linear trend. With d-SBP as y value (dependent variable), and IV ratio (x1), ES ratio (x2), COV ratio (x3), RtoL ratio (x4), gastrocnemius-iEMG ratio (x5), rectus femoris-iEMG ratio (x6), rectus abdominis-iEMG ratio (x7), d-1 (x8), d-2 (x9), d-3 (x10), d-4 (x11), d-5 (x12), d-6 (x13), d-7 (x14), and d-8 (x15) as 15 variables for x value (independent variable), the multi-factor linear regression equation was constructed as follows:

[0144] d-SBP = 24.23981 + 0.17675xl - 1.00423x2 - 7.66907x3 + 13.69225x4 + 0.21246x5 + 0.21986x6 + 0.42098x7 0.12854x8 + 0.123775x9 + 0.26601x10 + 0.25644xl l - 2.07761-4x12 + 1.48067x13 - 0.55104x14 + 0.79442x15 Model fitness test results showed that the determination coefficient (adjusted R2) was 0.864, which proved to be a good fit to the real situation, and the D-W test value was 1.601 (between 1-4), and the independence was met. Regression model hypothesis test results showed that F = 28.478, P < 0.001, and the regression equation was statistically significant.

[0145] Considering the multiple and complex independent variables, combined with the standardized coefficient β value (i.e. contribution degree), significance, collinearity and expert opinions, the multi-point plantar pressure (1, 2, 5, 6, 7) difference independent variables were removed for model optimization. The optimized multi-factor linear regression equation is as follows:

[0146] d-SBP = 14.5707 + 0.71223xl - 0.74873x2 + 9.58953x3 + 8.97892x4 + 0.1628x5 + 0.11345x6 + 0.43536x7 - 0.5264x8 + 0.20822x9 + 0.59163x10. The optimization model fitness test results showed that the determination coefficient (adjusted R2) was 0.850, which proved to be a good fit to the real situation, and the D-W test value was 1.636 (between 1-4), and the independence was met. Regression model hypothesis test results showed that F = 37.702, P < 0.01, and the regression equation was also statistically significant, as shown in Figure 17 As shown in Figure 18 As shown in

[0147] In one specific embodiment, the correlation analysis and regression equation construction of the eye level systolic blood pressure elevation value (d-SBP) and the oxygenated hemoglobin elevation value (d-Hb02) are as follows: Figure 19As shown in the scatter plot of the eye level systolic pressure elevation value (d-SBP, dependent variable) and the oxygenated hemoglobin elevation value (d-HbO2, x value, independent variable), the two values are approximately linearly distributed. Pearson correlation analysis shows that r=0.95677, P<0.001, indicating that the two values are highly closely related. A single-factor linear regression equation is constructed. Model fitting goodness test results show that the determination coefficient (adjusted R2) is 0.914, proving that the equation is highly fitted to the real situation.

[0148] The regression model is subjected to variance analysis, F=692.594, P<0.0001, the regression equation is statistically significant, and the modeling is successful. When the pilot performs anti-G action, the local cerebral blood flow and oxygen metabolic rate increase, the oxygenated hemoglobin (HbO2) increases, and the deoxygenated hemoglobin (HHb) decreases. Although previous studies have researched the relationship between the cerebral blood flow velocity, cerebral cortex activity, and oxygen and blood oxygen protein changes in the hypergravity environment, the relationship between oxygenated hemoglobin and eye level systolic pressure is rarely studied. This study is based on this background. After the test, it is found that there is a very close relationship between the frontal lobe level oxygenated hemoglobin and the eye level systolic pressure change value (AGSM anti-G effect evaluation gold standard), and there is a high positive correlation.

[0149] In one embodiment, the two regression equations are combined to construct a regression equation with oxygenated hemoglobin as the dependent variable (i.e., YHbO2), and 10 key indicators as independent variables, including IV ratio (x1), ES ratio (x2), COV ratio (x3), RtoL ratio (x4), peroneal-iEMG ratio (x5), femoral-iEMG ratio (x6), abdominal-iEMG ratio (x7), d-3 (x8), d-4 (x9), and d-8 (x10).

[0150] S102: Perform HP action evaluation based on the detection values of the EIT data, plantar pressure data, and electromyography data to obtain an evaluation result of reaching the standard or not reaching the standard.

[0151] In one embodiment, the evaluation is performed by comparing the sizes of the detection values of the EIT data, the detection values of the plantar pressure data, and the detection values of the electromyography data with preset threshold values. When the detection values of the EIT data, the plantar pressure data, and the electromyography data are greater than the preset threshold values, it is determined that the standard is reached. When any one of the detection values of the EIT data, the plantar pressure data, and the electromyography data is less than the preset threshold value, it is determined that the standard is not reached.

[0152] In one embodiment, the not reaching the standard includes one or more of the following: EIT not reaching the standard, plantar pressure not reaching the standard, electromyography data not reaching the standard, EIT and plantar pressure not reaching the standard, EIT and electromyography data not reaching the standard, plantar pressure and electromyography data not reaching the standard, EIT, plantar pressure, and electromyography data not reaching the standard.

[0153] In one embodiment, the method further comprises HP action optimization, when the evaluation result is substandard, the substandard result is targeted for HP action optimization.

[0154] In one embodiment, when the gastrocnemius muscle ratio, rectus femoris muscle ratio, rectus abdominis muscle ratio in the electromyography data are greater than a preset threshold, it is determined to be up to standard.

[0155] In one embodiment, when the pressure value of any one or several regions in the plantar pressure data is greater than a preset threshold, it is determined to be up to standard, the regions being a thumb region, a first metatarsal region, a lateral arch region, a rear lateral heel region, a second and third metatarsal region, a fourth and fifth metatarsal region, a medial heel region, and a lateral heel region.

[0156] In one embodiment, when the inspiration volume in the EIT data is greater than a preset threshold, the expiration uniformity is better, the expiration flow rate is greater than a preset threshold, the ventilation center is biased towards the abdominal side, and the left and right lung ventilation is biased towards the left side, it is determined to be up to standard.

[0157] In one embodiment, the method further comprises a frontal lobe level oxygenated hemoglobin value, and the HP action evaluation is performed based on the detection values of the EIT data, the plantar pressure data, the electromyography data, and the frontal lobe level oxygenated hemoglobin value, to obtain an evaluation result.

[0158] In one embodiment, the evaluation is performed by comparing the sizes of the detection values of the EIT data, the plantar pressure data, the electromyography data, and the frontal lobe level oxygenated hemoglobin value with preset thresholds, when the detection values of the EIT data, the plantar pressure data, the electromyography data, and the frontal lobe level oxygenated hemoglobin value are all greater than the preset thresholds, it is determined to be up to standard, and when any one of the detection values of the EIT data, the plantar pressure data, the electromyography data, and the frontal lobe level oxygenated hemoglobin value is less than the preset threshold, it is determined to be substandard.

[0159] In one embodiment, the substandard includes one or more of the following: EIT substandard, plantar pressure substandard, electromyography data substandard, frontal lobe level oxygenated hemoglobin value substandard, EIT and plantar pressure substandard, EIT and electromyography data substandard, plantar pressure and electromyography data substandard, EIT and frontal lobe level oxygenated hemoglobin value substandard, plantar pressure and frontal lobe level oxygenated hemoglobin value substandard, electromyography data and frontal lobe level oxygenated hemoglobin value substandard, EIT, plantar pressure, and electromyography data substandard, EIT, frontal lobe level oxygenated hemoglobin value, and electromyography data substandard, EIT, plantar pressure, and frontal lobe level oxygenated hemoglobin value substandard, frontal lobe level oxygenated hemoglobin value, plantar pressure, and electromyography data substandard, frontal lobe level oxygenated hemoglobin value, EIT, plantar pressure, and electromyography data substandard.

[0160] In one embodiment, the evaluation is replaced by: performing HP action evaluation by an evaluation model to obtain an evaluation result; the evaluation model is obtained by training the correlation between the detection values of EIT data, plantar pressure data, and muscle electromyography data and the high value of eye level systolic pressure.

[0161] In one embodiment, the training process of the evaluation model is:

[0162] Obtain the detection values of EIT data, plantar pressure data, and muscle electromyography data, and the high value of eye level systolic pressure when the subject performs HP action; construct a linear regression model based on the detection values of EIT data, plantar pressure data, and muscle electromyography data and the high value of eye level systolic pressure to obtain an evaluation model.

[0163] In one embodiment, the high value of eye level systolic pressure in the linear regression model is the dependent variable, and the detection values of EIT data, plantar pressure data, and muscle electromyography data are the independent variables.

[0164] In one embodiment, the training process of the evaluation model is replaced by:

[0165] Obtain the detection values of EIT data, plantar pressure data, and muscle electromyography data, and the high value of eye level systolic pressure when the subject performs HP action; calculate the mapping relationship between the detection values of EIT data, plantar pressure data, and muscle electromyography data and the high value of eye level systolic pressure; input the mapping relationship into a neural network model for training to obtain an evaluation model.

[0166] In one embodiment, the evaluation is replaced by: performing HP action evaluation by a first evaluation model to obtain an evaluation result; the first evaluation model is obtained by training the correlation between the detection values of EIT data, plantar pressure data, and muscle electromyography data, and the high value of eye level systolic pressure. In one embodiment, the training process of the first evaluation model is:

[0167] Obtain the detection values of EIT data, plantar pressure data, and muscle electromyography data, and the high value of eye level systolic pressure when the subject performs HP action;

[0168] Construct a linear regression model based on the detection values of EIT data, plantar pressure data, and muscle electromyography data, and the high value of eye level systolic pressure to obtain a first evaluation model.

[0169] In one embodiment, the high value of eye level systolic pressure in the regression model of the first evaluation model is the dependent variable, and the detection values of EIT data, plantar pressure data, and muscle electromyography data are the independent variables.

[0170] In one embodiment, the training process of the first evaluation model is replaced by:

[0171] Obtaining the EIT data, plantar pressure data, electromyography data detection value, frontal lobe level oxygenated hemoglobin value and eye level systolic pressure high value of the subject when performing the HP action;

[0172] Calculating the mapping relationship between the EIT data, plantar pressure data, electromyography data detection value, frontal lobe level oxygenated hemoglobin value and eye level systolic pressure high value;

[0173] The mapping relationship is input into the neural network model for training to obtain the first evaluation model.

[0174] In one embodiment, the evaluation model is replaced by: performing HP action evaluation by a second evaluation model to obtain an evaluation result; and the second evaluation model is obtained by training the correlation between the EIT data, plantar pressure data, electromyography data detection value and frontal lobe level oxygenated hemoglobin value.

[0175] In one embodiment, the training process of the second evaluation model is:

[0176] Obtaining the EIT data, plantar pressure data, electromyography data detection value and frontal lobe level oxygenated hemoglobin value of the subject when performing the HP action;

[0177] Constructing a linear regression model based on the EIT data, plantar pressure data, electromyography data detection value and frontal lobe level oxygenated hemoglobin value to obtain the second evaluation model.

[0178] The present application also discloses a computer program product or system, comprising a computer program which, when executed by a processor, implements the steps of the above-mentioned evaluation method for flight anti-overload HP action.

[0179] Figure 2 The evaluation system for flight anti-overload HP action provided by the embodiments of the present application specifically comprises: an acquisition unit for acquiring the EIT data, plantar pressure data and electromyography data detection value of the subject;

[0180] The EIT data comprises one or more of the following whole ventilation parameters: inhalation volume value, exhalation uniformity value and exhalation flow rate value; and the electromyography data comprises one or more of the following: gastrocnemius muscle ratio, rectus femoris muscle ratio and rectus abdominis muscle ratio.

[0181] An evaluation unit for performing HP action evaluation based on the EIT data, plantar pressure data and electromyography data detection value to obtain an evaluation result of reaching the standard or not.

[0182] Figure 3The flight anti-overload HP action evaluation device provided by the embodiment of the application specifically comprises: a memory and a processor; the memory is used for storing program instructions; and the processor is used for calling the program instructions, so as to implement any one of the flight anti-overload HP action evaluation methods.

[0183] The embodiment of the application further discloses a computer readable storage medium, which stores a computer program, and the computer program is used for implementing any one of the flight anti-overload HP action evaluation methods when executed by a processor.

[0184] The verification result of the verification embodiment shows that the performance of the method can be improved by assigning inherent weights to the syndromes relative to the default settings. It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms. The units described as separated components can be or can not be physical separate units, and the units shown as separate components can be or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments. In addition, each functional unit in the embodiments of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be in the form of hardware or software function unit. Those skilled in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by a program instructing related hardware, and the program can be stored in a computer readable storage medium, and the storage medium can include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0185] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment methods can be instructed by programs to relevant hardware, and the programs can be stored in a computer readable storage medium, such as a read-only memory, a magnetic disk or an optical disk.

[0186] The computer device provided by the present application is described in detail above. For those skilled in the art, the specific implementation and application range of the embodiment of the present application can be changed according to the idea of the embodiment of the present application. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for evaluating flight anti-overload HP action, characterized in that: include: Obtain the test values ​​of the subject's EIT data, plantar pressure data, and electromyographic data; The EIT data includes one or more of the following overall ventilation parameters: inspiratory volume value, expiratory uniformity value, expiratory flow rate value; the electromyographic data includes one or more of the following: gastrocnemius ratio, rectus femoris ratio, rectus abdominis ratio; Performing an HP action assessment based on the detection values ​​of the EIT data, plantar pressure data, and electromyographic data to obtain an assessment result of whether it meets the standard or not; The plantar pressure includes one or more of the following area pressures: thumb area, first metatarsal area, lateral arch area, posterior heel area, second and third metatarsal areas, fourth and fifth metatarsal areas, medial heel area, and lateral heel area; The gastrocnemius ratio is the ratio of the electromyographic signal value of the gastrocnemius muscle when the test subject performs the HP action to the electromyographic signal value of the gastrocnemius muscle when the test subject is breathing quietly; The rectus femoris ratio is the ratio of the electromyographic signal value of the rectus femoris when the tester performs the HP action to the electromyographic signal value of the rectus femoris when the tester breathes quietly; The rectus abdominis ratio is the ratio of the electromyographic signal value of the rectus abdominis when the tester performs the HP action to the electromyographic signal value of the rectus abdominis when the tester breathes quietly.

2. The method for evaluating flight anti-overload HP action according to claim 1, characterized in that: The evaluation is performed by comparing the EIT data detection value with a preset threshold, the plantar pressure data detection value with a preset threshold, and the electromyography data detection value with a preset threshold. When the detection values ​​of the EIT data, the plantar pressure data, and the electromyography data are greater than the preset threshold, it is determined that the standard is met; when any one of the detection values ​​of the EIT data, the plantar pressure data, and the electromyography data is less than the preset threshold, it is determined that the standard is not met.

3. The method for evaluating flight anti-overload HP action according to claim 2, characterized in that: The non-compliance includes one or more of the following: EIT does not meet the standard, plantar pressure does not meet the standard, electromyographic data does not meet the standard, EIT and plantar pressure do not meet the standard, EIT and electromyographic data do not meet the standard, plantar pressure and electromyographic data do not meet the standard, EIT, plantar pressure and electromyographic data do not meet the standard.

4. The method for evaluating flight anti-overload HP action according to claim 1, characterized in that: The method further includes HP action optimization. When the evaluation result is not up to standard, targeted HP action optimization is performed for the not up to standard result.

5. The flight anti-overload HP action evaluation method according to claim 1, characterized in that: The overall ventilation parameters of the EIT data are replaced by: inspiratory volume ratio, expiratory uniformity ratio, and expiratory flow rate ratio; the inspiratory volume ratio is the ratio of the inspiratory volume of the test subject during HP maneuver to the inspiratory volume during quiet breathing; the expiratory uniformity ratio is the ratio of the expiratory uniformity of the test subject during HP maneuver to the expiratory uniformity during quiet breathing; the expiratory flow rate ratio is the ratio of the expiratory flow rate of the test subject during HP maneuver to the expiratory flow rate during quiet breathing.

6. The method for evaluating flight anti-overload HP action according to claim 1, characterized in that: The EIT data also includes one or more of the following overall ventilation parameters: inspiratory volume ratio, expiratory uniformity ratio, and expiratory flow rate ratio.

7. The method for evaluating flight anti-overload HP action according to claim 1, characterized in that: The EIT data also includes one or more of the following local ventilation parameters: left and right lung ventilation, and ventilation center value.

8. The flight anti-overload HP action evaluation method according to claim 7, characterized in that: The local ventilation parameters of the EIT data are replaced by: left-right lung ventilation ratio and ventilation center ratio; the left-right lung ventilation ratio is the ratio of the left-right lung ventilation when the tester performs HP maneuvers to the left-right lung ventilation during quiet breathing; the ventilation center ratio is the ratio of the ventilation center when the tester performs HP maneuvers to the ventilation center during quiet breathing.

9. The method for evaluating flight anti-overload HP action according to claim 7, characterized in that: EIT data also includes one or more of the following regional ventilation parameters: left-right lung ventilation ratio, ventilation center ratio.

10. The flight anti-overload HP action evaluation method according to claim 7, characterized in that: The EIT data is judged to meet the standard when the inspiratory volume is greater than a preset threshold, the exhalation uniformity is better, the exhalation flow rate is greater than a preset threshold, the ventilation center is biased to the ventral side, and the left and right lung ventilation is biased to the left.

11. The method for evaluating flight anti-overload HP action according to claim 1, characterized in that: The method further includes a frontal lobe level oxygenated hemoglobin value, and HP action evaluation is performed based on the EIT data, plantar pressure data, detection values ​​of electromyography data, and the frontal lobe level oxygenated hemoglobin value to obtain an evaluation result.

12. The method for evaluating flight anti-overload HP action according to claim 11, characterized in that: The assessment is performed by comparing the EIT data detection value with a preset threshold, the plantar pressure data detection value with a preset threshold, the electromyographic data detection value with a preset threshold, and the frontal lobe level oxygenated hemoglobin value with a preset threshold. When the EIT data, the plantar pressure data, the electromyographic data detection value, and the frontal lobe level oxygenated hemoglobin value are all greater than the preset threshold, it is determined that the standard is met; when any one of the EIT data, the plantar pressure data, the electromyographic data detection value, and the frontal lobe level oxygenated hemoglobin value is less than the preset threshold, it is determined that the standard is not met.

13. The method for evaluating flight anti-overload HP action according to claim 12, characterized in that: The non-compliance includes one or more of the following: EIT does not meet the standard, plantar pressure does not meet the standard, electromyographic data does not meet the standard, frontal lobe level oxyhemoglobin value does not meet the standard, EIT and plantar pressure do not meet the standard, EIT and electromyographic data do not meet the standard, plantar pressure and electromyographic data do not meet the standard, EIT and frontal lobe level oxyhemoglobin value does not meet the standard, plantar pressure and frontal lobe level oxyhemoglobin value does not meet the standard, electromyographic data and frontal lobe level oxyhemoglobin value does not meet the standard, EIT, plantar pressure and electromyographic data do not meet the standard, EIT, frontal lobe level oxyhemoglobin value and electromyographic data do not meet the standard, EIT, plantar pressure and frontal lobe level oxyhemoglobin value does not meet the standard, frontal lobe level oxyhemoglobin value, plantar pressure and electromyographic data do not meet the standard, frontal lobe level oxyhemoglobin value, EIT, plantar pressure and electromyographic data do not meet the standard.

14. The method for evaluating flight anti-overload HP action according to claim 2, characterized in that: The evaluation is replaced by: performing HP action evaluation through an evaluation model to obtain an evaluation result; the evaluation model is obtained by training the correlation between the detection values ​​of EIT data, plantar pressure data, and electromyography data and the high value of eye-level systolic blood pressure.

15. The flight anti-overload HP action evaluation method according to claim 14, characterized in that: The training process of the evaluation model is as follows: Obtain the EIT data, plantar pressure data, electromyographic data detection value, and eye level systolic blood pressure high value when the subject performs HP action; A linear regression model is constructed based on the detection values ​​of the EIT data, plantar pressure data, electromyography data and the high value of eye-level systolic blood pressure to obtain an evaluation model.

16. The method for evaluating flight anti-overload HP action according to claim 15, characterized in that: In the linear regression model, the high value of eye level systolic pressure is the dependent variable, and the detection values ​​of EIT data, plantar pressure data, and electromyography data are the independent variables.

17. The method for evaluating flight anti-overload HP action according to claim 15, characterized in that: The training process of the evaluation model is replaced by: Obtain the EIT data, plantar pressure data, electromyographic data detection value, and eye level systolic blood pressure high value when the subject performs HP action; Calculating the relationship between the detection values ​​of the EIT data, the plantar pressure data, and the electromyographic data and the high value of the eye-level systolic blood pressure to obtain a mapping relationship; The mapping relationship is input into a neural network model for training to obtain an evaluation model.

18. The method for evaluating flight anti-overload HP action according to claim 14, characterized in that: The evaluation model is replaced by: HP action evaluation is performed through a first evaluation model to obtain an evaluation result; the first evaluation model is obtained by training the detection values ​​of EIT data, plantar pressure data, electromyography data, and the correlation between the frontal lobe level oxygenated hemoglobin value and the eye level systolic blood pressure high value.

19. The method for evaluating flight anti-overload HP action according to claim 18, characterized in that: The training process of the first evaluation model is: Obtain the EIT data, plantar pressure data, electromyographic data detection values, frontal lobe level oxyhemoglobin value and eye level systolic blood pressure high value when the subject performs HP action; A linear regression model is constructed based on the EIT data, plantar pressure data, detection values ​​of electromyography data, frontal lobe level oxyhemoglobin value and eye level systolic blood pressure high value to obtain a first evaluation model.

20. The flight anti-overload HP action evaluation method according to claim 19, characterized in that: In the regression model of the first evaluation model, the high eye level systolic blood pressure value is the dependent variable, and the detection values ​​of EIT data, plantar pressure data, electromyography data, and frontal lobe level oxyhemoglobin value are independent variables.

21. The method for evaluating flight anti-overload HP action according to claim 19, characterized in that: The training process of the first evaluation model is replaced by: Obtain the EIT data, plantar pressure data, electromyographic data detection value, frontal lobe level oxygenated hemoglobin value, and eye level systolic blood pressure high value when the subject performs HP action; Calculating the relationship between the EIT data, the plantar pressure data, the detection value of the electromyographic data, the frontal lobe level oxygenated hemoglobin value and the eye level systolic blood pressure high value to obtain a mapping relationship; The mapping relationship is input into a neural network model for training to obtain a first evaluation model.

22. The method for evaluating flight anti-overload HP action according to claim 14, characterized in that: The evaluation model is replaced by: HP action evaluation is performed through a second evaluation model to obtain an evaluation result; the second evaluation model is obtained by training the correlation between the detection values ​​of EIT data, plantar pressure data, and electromyography data and the oxygenated hemoglobin value at the frontal lobe level.

23. The method for evaluating flight anti-overload HP action according to claim 22, characterized in that: The training process of the second evaluation model is: Obtain EIT data, plantar pressure data, electromyographic data detection values, and frontal lobe oxyhemoglobin values ​​when the subject performs HP movements; A linear regression model is constructed based on the detection values ​​of the EIT data, the plantar pressure data, the electromyographic data and the frontal lobe level oxyhemoglobin value to obtain a second evaluation model.

24. The method for evaluating flight anti-overload HP action according to claim 1, characterized in that: The plantar pressure data is obtained by a plantar pressure device, which includes an insole, N pressure sensors, a signal transmission circuit, and an external circuit module; the N pressure sensors are fixed to the insole and connected to form a closed loop via the signal transmission circuit, the signal transmission circuit is connected to the external circuit module, and the external circuit module is used to process the signal data, where N is a natural number greater than or equal to 4; When the pressure sensor is subjected to pressure, a pressure signal is generated, and the pressure signal is transmitted to the external circuit module through the signal transmission circuit. The external circuit module receives the pressure signal to obtain plantar pressure data.

25. The method for evaluating flight anti-overload HP action according to claim 24, characterized in that: The number of the pressure sensors is 4-8.

26. The method for evaluating flight anti-overload HP action according to claim 24, characterized in that: The number of the pressure sensors is 4.

27. The method for evaluating flight anti-overload HP action according to claim 24, characterized in that: When the number of the pressure sensors is four, the pressure sensors are respectively fixed on the thumb area, the first metatarsal area, the outer side area of ​​the arch, and the back area of ​​the heel.

28. The method for evaluating flight anti-overload HP action according to claim 24, characterized in that: When the number of the pressure sensors is 8, the pressure sensors are respectively fixed on the thumb area, the first metatarsal area, the lateral arch area, the posterior heel area, the second and third metatarsal areas, the fourth and fifth metatarsal areas, the medial heel area, and the lateral heel area.

29. A computer program product comprising a computer program or instructions, characterized in that: The computer program or instructions are executed by a processor to implement the flight anti-overload HP action evaluation method described in any one of claims 1-28.

30. A computer device comprising a memory, a processor, and a computer program or instruction stored in the memory, wherein: The computer program or instructions are executed by a processor to implement the flight anti-overload HP action evaluation method described in any one of claims 1-28.

31. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instructions are executed by a processor to implement the flight anti-overload HP action evaluation method described in any one of claims 1-28.

Images