Noise learning method and system based on HRV dynamic change

Abstract

The invention provides a noise learning method and system based on HRV dynamic change, and relates to the technical field of data processing. The method comprises the steps that original signals of two signal channels are obtained through a radar system, the standard deviation of each signal channel is calculated, a channel with the large standard deviation is selected to extract heartbeat signals, slope changes of each signal period are calculated through a derivative function, and a signal peak value is determined. Calculating a time interval between continuous peak values, determining a heartbeat interval change rate, analyzing the heartbeat interval change rate, and extracting key index features and frequency domain features of the HRV. Noise is generated through noise generation equipment, a noise environment is simulated, and target features in the noise environment are extracted; calculating a comprehensive feature change value according to the two features, and judging whether the comprehensive feature change value is smaller than a preset value or not; if yes, increasing the noise intensity to carry out noise training; otherwise, reducing the noise intensity according to an adaptive algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a noise acclimatization method and system based on the dynamic change of HRV. Background Art

[0002] In noise pollution, occupational noise-induced hearing loss has become a health problem of widespread concern globally. Personnel who are exposed to high-intensity noise environments for a long time, especially factory workers, airport ground crew, construction workers, etc., are prone to noise-induced hearing loss, and once this kind of injury occurs, it is often irreversible.

[0003] The core concept of noise acclimatization technology is to gradually improve the adaptability of the body to noise by giving low-intensity and non-destructive noise stimuli before high-intensity noise exposure, so as to reduce the temporary or permanent hearing threshold shift caused by high-intensity noise. Currently, existing noise acclimatization devices mainly focus on providing noise exposure protection for specific groups (such as workers, soldiers, etc.), and mainly focus on hearing loss detection.

[0004] However, existing noise acclimatization methods cannot be precisely adjusted according to individual differences, ignoring the biological adaptation ability of different organisms to noise exposure. At the same time, the biological feedback mechanisms such as HRV are not fully utilized to dynamically adjust the noise exposure intensity, resulting in poor safety and comfort of noise acclimatization, thus reducing the effect of noise acclimatization. Summary of the Invention

[0005] In order to solve the technical problems that existing noise acclimatization methods cannot be precisely adjusted according to individual differences, ignoring the biological adaptation ability of different organisms to noise exposure. At the same time, the biological feedback mechanisms such as HRV are not fully utilized to dynamically adjust the noise exposure intensity, resulting in poor safety and comfort of noise acclimatization, thus reducing the effect of noise acclimatization, the present invention provides a noise acclimatization method and system based on the dynamic change of HRV.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] A noise acclimatization method based on the dynamic change of HRV provided by the embodiments of the present invention includes:

[0009] S1: Obtain the original signals of the target to be noise acclimatized in two signal channels through a radar system;

[0010] S2: Calculate the standard deviation of the signal data in each signal channel, and select the signal channel with the larger standard deviation as the signal to be processed channel;

[0011] S3: Extract the heartbeat signal in the original signal in the signal to be processed channel;

[0012] S4: Calculate the slope change in each signal period using the derivative function according to the heartbeat signal to determine the signal peak;

[0013] S5: Calculate the time interval between consecutive signal peaks to determine the change rate of the inter-beat interval;

[0014] S6: Conduct statistical analysis on the change rate of the inter-beat interval to extract the first key index feature and the first frequency domain feature of HRV;

[0015] S7: Generate noise through a noise generating device to simulate a noise environment;

[0016] S8: Extract the second key index feature and the second frequency domain feature of the target to be habituated to noise in the noise environment;

[0017] S9: Calculate the comprehensive feature change value according to the first key index feature, the first frequency domain feature, the second key index feature, and the second frequency domain feature;

[0018] S10: Determine whether the comprehensive feature change value is less than a preset feature change value; if so, adjust the noise intensity through the noise generating device to perform noise habituation training; otherwise, adjust the noise intensity through the noise generating device to adaptively reduce the noise intensity.

[0019] Second aspect:

[0020] A noise habituation system based on the dynamic change of HRV provided by an embodiment of the present invention includes:

[0021] A processor;

[0022] A memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the noise habituation method based on the dynamic change of HRV as described in the first aspect is implemented.

[0023] Third aspect:

[0024] A computer-readable storage medium provided by an embodiment of the present invention, on which a computer program is stored, and when the program is executed by a processor, the noise habituation method based on the dynamic change of HRV as described in the first aspect is implemented.

[0025] The beneficial effects brought by the technical solutions provided by the embodiments of the present invention at least include:

[0026] (1) In the embodiments of the present invention, by calculating the standard deviation values of the signal data in each signal channel and selecting the signal channel with a larger standard deviation value as the channel to be processed, the heartbeat signal in the original signal is extracted in the channel to be processed. Then, the derivative function is used to calculate the slope change in each signal cycle, determine the signal peak value, and calculate the time interval between consecutive signal peak values, so as to determine the change rate of the inter-beat interval. This process can accurately capture individual differences and fully consider the biological adaptation ability of different organisms to noise exposure.

[0027] (2) In the embodiments of the present invention, by extracting the key index features and frequency domain features of the HRV of the heartbeat signal and analyzing them in combination with the HRV features in the noise environment, the comprehensive feature change value is calculated. According to the comprehensive feature change value, the physiological state of an individual is dynamically evaluated, so as to adaptively adjust the noise intensity according to the feedback situation, ensure the safety and comfort of the noise adaptation process, and improve the effect of noise adaptation. Description of the Drawings

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0029] Figure 1 It is a schematic flowchart of a noise adaptation method based on the dynamic change of HRV provided by the embodiments of the present invention;

[0030] Figure 2 It is a schematic structural diagram of a noise adaptation system based on the dynamic change of HRV provided by the embodiments of the present invention. Detailed Embodiments

[0031] The following describes the technical solutions in the present invention with reference to the drawings.

[0032] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0033] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same. "Of", "corresponding", and "corresponding to" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same.

[0034] In the embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, their intended meanings are the same.

[0035] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0036] Refer to the attached Figure 1 illustrates a schematic flowchart of a noise adaptation method based on the dynamic change of HRV provided by an embodiment of the present invention.

[0037] The embodiments of the present invention provide a noise adaptation method based on the dynamic change of HRV. This method can be implemented by a noise adaptation device based on the dynamic change of HRV. The noise adaptation device based on the dynamic change of HRV can be a terminal or a server. The processing flow of the noise adaptation method based on the dynamic change of HRV can include the following steps:

[0038] S1: Through a radar system, obtain the original signals of the target to be noise-adapted in two signal channels.

[0039] Among them, the radar system (RADAR, Radio Detection and Ranging) is a technology that uses electromagnetic waves (usually radio waves or microwaves) to detect the position, speed, and other characteristics of objects. It works by emitting electromagnetic waves and receiving the reflected signals of these waves.

[0040] In a possible implementation manner, S1 specifically includes:

[0041] S101: Use an oscillator to generate a transmitted signal and transmit the transmitted signal through the radar to the chest of the target to be noise-adapted:

[0042] Among them, an oscillator is an electronic circuit that can generate a periodic waveform. It is usually used to generate different types of waveforms such as sine waves, square waves, triangular waves, or sawtooth waves. Oscillators are widely used in fields such as communication, signal processing, audio equipment, clock generation, and power control.

[0043] T(t) = Acos(2πft)

[0044] Among them, T(t) represents the amplitude of the signal transmitted at time t, A represents the amplitude of the signal, f represents the frequency of the signal, and t represents time.

[0045] In the present invention, by adjusting the frequency and amplitude of the oscillator, the transmission frequency of the signal can be precisely controlled, thereby improving the detection ability and accuracy of the radar system.

[0046] S102: Receive the reflected signal through the receiving antenna:

[0047] x r (t) = x(t - ψ(t))

[0048] Among them, x r (t) represents the received reflected signal, x(t) represents the transmitted signal, and ψ(t) represents the signal delay.

[0049] S103: Calculate the signal delay of the received reflected signal:

[0050]

[0051] Among them, c represents the speed of light, d0 represents the initial distance between the radar and the target, and v(t) represents the velocity function of the target.

[0052] In the present invention, through the signal delay, the radar system can accurately calculate the distance of the target and improve the accuracy of signal acquisition.

[0053] S104: Rewrite the received signal according to the signal delay to obtain the actual received signal:

[0054]

[0055] In the present invention, by rewriting the received signal, the error caused by the signal delay can be reduced, thereby optimizing the effect of signal processing.

[0056] S105: Multiply the actual received signal by the transmitted signal to determine the original signals of the two signal channels:

[0057]

[0058] Among them, I(t) represents the original signal of the I channel at time t, Q(t) represents the original signal of the Q channel at time t, s(t) represents the displacement function of the target at time t, d0 represents the initial distance between the radar and the target, λ represents the wavelength of the signal, and θ represents the phase shift.

[0059] It should be noted that the continuous wave radar acquires the signals of the I channel and the Q channel. At this time, the radar will capture the reflected signal, and the reflected signal contains the body displacement caused by breathing and heartbeat.

[0060] Specifically, the received original radar signal includes two signal channels. Then, a single-channel signal is selected for the next processing. The selected channel signal is filtered by a low-pass filter, using a finite impulse response (FIR) filter with a cut-off frequency of 3 Hz. This filter is used to eliminate the high-frequency components of the heartbeat and noise, while retaining the respiratory component. Then, the filtered signal is transmitted to a convolutional filter to extract the respiratory component. The convolutional filter removes the residual components of the noise and heartbeat, generating the respiratory component and noise. By subtracting the original signal from the respiratory component and noise, a signal containing noise and heartbeat is obtained.

[0061] In the present invention, by eliminating signal delay, extracting the dynamic information of the target (such as displacement, velocity), and optimizing the signal processing, it is ensured that the radar can achieve efficient and accurate target detection and analysis in a complex environment.

[0062] S2: Calculate the standard deviation of the signal data in each signal channel, and select the signal channel with the larger standard deviation as the signal channel to be processed.

[0063] Optionally, the standard deviation is calculated as follows:

[0064]

[0065] where σ represents the standard deviation, N represents the number of data points, x i represents the i-th data point, and μ represents the mean of the channel signal.

[0066] In the present invention, the channel selection method based on the standard deviation helps to improve the sensitivity of the system to signal fluctuations, ensure the processing of effective signals, while suppressing noise and irrelevant signals, thereby improving the overall performance of the system and the efficiency of signal processing.

[0067] S3: Extract the heartbeat signal from the original signal in the signal channel to be processed.

[0068] In a possible implementation, S3 specifically includes:

[0069] S301: Set the sampling rate and perform filtering processing using a band-pass filter to determine the frequency range of the original signal.

[0070] Among them, a band-pass filter is a filter that allows signals within a specific frequency range to pass through while blocking signals outside other frequency ranges. It combines the characteristics of a low-pass filter and a high-pass filter, and can pass signals within a specific frequency range while suppressing signals outside the frequency range.

[0071] S302: Perform a fast Fourier transform on the original signal after band-pass filtering to obtain a frequency-domain signal.

[0072] Among them, the Fast Fourier Transform (FFT) is an efficient algorithm of the Fourier transform, which is used to convert a signal from the time domain to the frequency domain. It is a fundamental tool in many fields such as signal processing, digital audio, communication, image analysis, and radar.

[0073] S303: Estimate the heart rate frequency based on the position corresponding to the maximum value of the frequency-domain signal.

[0074] S304: Calculate the average heart rate period according to the heart rate frequency. The average heart rate period is used to determine the smoothing length.

[0075] S305: Create a convolution vector to smooth the original signal according to the smoothing length.

[0076] Among them, the convolution vector generally refers to a vector used in the convolution operation. It is convolved with the input signal to generate the output signal. In fields such as signal processing, image processing, and deep learning, convolution is a very common operation. The convolution vector is an important concept of the convolution kernel or filter, which defines how to weight the input signal and generate the output.

[0077] In the present invention, by using the convolution vector (filter) to smooth the signal and remove the respiratory signal, the noise interference can be effectively reduced, and then a more pure heartbeat signal can be extracted, improving the accuracy of the signal.

[0078] S306: Convolve the original signal with the convolution vector to obtain the respiratory signal.

[0079] S307: Remove the respiratory signal from the original signal to obtain the heartbeat signal.

[0080] In the present invention, the respiratory signal and the heartbeat signal usually have significant differences in frequency. By using the combination of the band-pass filter and the convolution vector, the low-frequency part of the respiratory signal can be effectively suppressed, and only the frequency range corresponding to the heartbeat signal is retained, reducing the interference of other physiological signals (such as respiration), and improving the signal-to-noise ratio of the heartbeat signal. At the same time, by removing the respiratory signal from the original signal, the accuracy of the heartbeat signal can be significantly improved, the smoothness of the signal can be enhanced, and the efficiency and quality of signal processing can be improved.

[0081] S4: According to the heartbeat signal, use the derivative function to calculate the slope change in each signal period to determine the signal peak.

[0082] Among them, the signal peak refers to the point with the maximum amplitude in the waveform of the signal. The peak is an important concept in signal processing and is usually used to describe the maximum value of the instantaneous change in the signal.

[0083] In a possible implementation, S4 specifically includes:

[0084] S401: Perform derivative processing on the heartbeat signal.

[0085] S402: Calculate the slope of the heartbeat signal:

[0086] y(n) = λ1x(n - 2) + λ2x(n - 1) + λ3x(n) + λ4x(n + 1) + λ5x(n + 2)

[0087] where y(n) represents the slope value of the heartbeat signal calculated at time n, x(n - 2) represents the heartbeat signal value at time n - 2, λ1 represents the weight of the heartbeat signal value at time n - 2, x(n - 1) represents the heartbeat signal value at time n - 1, λ2 represents the weight of the heartbeat signal value at time n - 1, x(n) represents the heartbeat signal value at time n, λ3 represents the weight of the heartbeat signal value at time n, x(n + 1) represents the heartbeat signal value at time n + 1, λ4 represents the weight of the heartbeat signal value at time n + 1, x(n + 2) represents the heartbeat signal value at time n + 2, and λ5 represents the weight of the heartbeat signal value at time n + 2.

[0088] S403: Determine the position corresponding to the maximum slope as the signal peak.

[0089] In the present invention, by calculating the slope, that is, the rate of signal change, the peak of the signal can be more accurately located. The peak usually appears at the position where the signal change rate is the largest. Through the derivative (slope) method, the rapidly changing region can be identified, thereby more precisely detecting the peak of the heartbeat signal.

[0090] S5: Calculate the time interval between consecutive signal peaks and determine the change rate of the inter-beat interval.

[0091] In a possible implementation, S5 specifically includes:

[0092] S501: Calculate the time interval between consecutive signal peaks to obtain the inter-beat interval between each signal peak:

[0093]

[0094] where IBI i represents the i-th inter-beat interval, represents the time point of the (i + 1)-th signal peak, represents the time point of the i-th signal peak.

[0095] S502: Determine the change rate of the inter-beat interval according to each inter-beat interval:

[0096]

[0097] Among them, represents the change rate of the inter-beat interval, IBI i+1 represents the (i + 1)-th inter-beat interval.

[0098] In the present invention, by calculating and real-time monitoring the change rate of the inter-beat interval, abnormal fluctuations in the cardiac rhythm can be detected more timely, providing real-time health feedback. Avoiding potential health hazards caused by excessive noise for the noise adaptation target.

[0099] S6: Statistically analyze the change rate of the inter-beat interval, and extract the first key index features and the first frequency domain features of HRV.

[0100] In a possible implementation manner, the first key index features include: the standard deviation of the inter-beat interval and the root mean square of the differences between adjacent inter-beat intervals.

[0101] It should be noted that the standard deviation of the inter-beat interval is a common index for describing cardiac rhythm variability. It refers to the standard deviation of adjacent normal inter-beat intervals, and is usually used to measure the autonomic nerve function of the heart and the cardiac health status. A higher standard deviation of the inter-beat interval usually means better cardiac health, being able to flexibly respond to different physiological and environmental changes. A lower standard deviation of the inter-beat interval may indicate poorer cardiac health, especially in some cardiac diseases or stressful states.

[0102] The first frequency domain features include: the low-frequency power related to sympathetic nerve activity and the high-frequency power related to parasympathetic nerve activity.

[0103] It should be noted that the low-frequency power mainly reflects sympathetic nerve activity, and its increase is usually related to factors such as physiological stress, anxiety, and exercise. The high-frequency power mainly reflects parasympathetic nerve activity, and its increase is usually related to relaxation states such as relaxation, meditation, and deep breathing.

[0104] The calculation method of the standard deviation of the inter-beat interval is:

[0105]

[0106] Among them, SDNN represents the standard deviation of the inter-beat interval, N represents the total number of inter-beat intervals, IBI i represents the i-th inter-beat interval, represents the average value of the inter-beat intervals.

[0107] The calculation method of the root mean square of the differences between adjacent inter-beat intervals is:

[0108]

[0109] Among them, RMSSD represents the root mean square of the differences between adjacent inter-beat intervals, IBIi-1 represents the (i - 1)-th cardiac cycle interval.

[0110] In the present invention, by extracting the standard deviation of the cardiac cycle intervals and the root mean square of the differences between adjacent cardiac cycle intervals, the cardiac variability can be deeply analyzed to reveal the regulatory ability of the autonomic nervous system.

[0111] The determination method of the first frequency domain feature is as follows:

[0112] Divide the signal into short time segments (such as each cardiac cycle or a fixed time window).

[0113] Apply a window function to each segment.

[0114] Apply FFT to each weighted segment of the window function to obtain the frequency domain features of each segment.

[0115] Calculate the average value of the frequency domain features of each segment to obtain the overall frequency domain feature.

[0116] In the present invention, by extracting the frequency domain features, the activity levels of the sympathetic nerve and the parasympathetic nerve can be quantitatively evaluated.

[0117] Specifically, various characteristic parameters of HRV are extracted from the preprocessed electrocardiogram signal, such as the standard deviation of the RR intervals, the root mean square of the differences between adjacent RR intervals, the ratio of the low-frequency component to the high-frequency component, etc. These parameters can quantitatively reflect the activity state of the autonomic nervous system.

[0118] In summary, by extracting HRV features such as the standard deviation of the cardiac cycle intervals, the root mean square of the differences between adjacent cardiac cycle intervals, and the low-frequency power and high-frequency power, the functional state of the autonomic nervous system and the cardiac health can be deeply understood, the stress response can be effectively detected, the body's recovery ability can be evaluated, the accuracy of HRV analysis is improved, and the training effect of noise habituation is further enhanced.

[0119] S7: Generate noise through a noise generating device to simulate a noise environment.

[0120] Specifically, the noise generating device is equipped with various types of noise generating devices, which can generate noises with different frequencies, intensities, and durations, such as white noise, pink noise, traffic noise, etc., to simulate various noise environments in real life. At the same time, the noise generating device also includes an intensity adjustment device, which can accurately adjust the intensity of the noise according to the feedback result of the HRV analysis module to achieve personalized noise habituation training. The intensity adjustment range should be wide enough to meet the needs of different individuals and different training stages. A duration control unit can set the duration of noise exposure, reasonably arrange the noise duration of each training according to the training plan and the individual's tolerance, and gradually increase the duration to improve the individual's adaptability to noise.

[0121] In the present invention, by using a noise generating device to simulate various noise environments and combining precise adjustment of intensity and duration, the noise adaptation ability of an individual can be effectively improved. Personalized noise acclimation training not only helps an individual increase their tolerance to noise, but also can avoid physiological discomfort caused by excessive exposure, support a long-term and effective adaptation process, and ultimately improve the quality of life and health status of the individual in a complex noise environment.

[0122] S8: Extract the second key index features and the second frequency domain features of the target to be acclimated to noise in a noise environment.

[0123] It should be noted that by extracting the second key index features and the second frequency domain features of the target to be acclimated to noise in a noise environment in real time, the HRV in the noise state can be compared with the HRV in the normal state, and the change of HRV can be detected in real time, providing a strong basis for noise acclimation training.

[0124] S9: Calculate the comprehensive feature change value according to the first key index features, the first frequency domain features, the second key index features, and the second frequency domain features.

[0125] In a possible implementation manner, the calculation method of the comprehensive feature change value is specifically as follows:

[0126] ΔHRV total = w1·ΔSDNN + w2·ΔRMSSD + w3·ΔLF + w4·ΔHF

[0127] Wherein, ΔHRV total represents the comprehensive feature change value, ΔSDNN represents the change in the standard deviation of the heart rate interval, w1 represents the weight represented by the change in the standard deviation of the heart rate interval, ΔRMSSD represents the change in the root mean square of the difference between adjacent heart rate intervals, w2 represents the weight represented by the change in the root mean square of the difference between adjacent heart rate intervals, ΔLF represents the change in the low-frequency power related to sympathetic nerve activity, w3 represents the weight represented by the change in the low-frequency power related to sympathetic nerve activity, ΔHF represents the change in the high-frequency power related to parasympathetic nerve activity, and w4 represents the weight represented by the change in the high-frequency power related to parasympathetic nerve activity.

[0128] In the present invention, by calculating and comprehensively considering the change values of multiple key index features and frequency domain features, more comprehensive and accurate health monitoring results can be provided. Especially in the training or stress state, the autonomous regulation ability of the heart is often affected, and the comprehensive feature change value can reflect these complex changes, improving the early warning ability for health abnormalities. At the same time, by assigning different weights to each feature, personalized health assessment and feedback can be achieved. The adjustment of the weights enables flexible adaptation to the physiological state changes of different individuals, thereby providing more accurate and personalized health advice and intervention measures.

[0129] S10: Determine whether the comprehensive feature change value is less than a preset feature change value; if so, adjust the noise intensity through a noise generating device to perform noise habituation training; otherwise, adjust the noise intensity through the noise generating device to adaptively reduce the noise intensity.

[0130] In a possible implementation, S10 specifically includes:

[0131] S1001: When the comprehensive feature change value is less than the preset feature change value, after a preset duration, increase the noise intensity by a preset decibel increment to perform noise habituation training.

[0132] It should be noted that those skilled in the art can set the values of the preset duration and the preset decibel increment according to actual needs, and the present invention does not limit this here.

[0133] S1002: When the comprehensive feature change value is greater than or equal to the preset feature change value, calculate the adjusted noise intensity through the following formula, and adaptively reduce the noise intensity through the noise generating device according to the adjusted noise intensity:

[0134]

[0135] where N new represents the adjusted noise intensity, N current represents the current noise intensity, α represents the adjustment factor, ΔHRV total represents the comprehensive feature change value, and T desired represents the preset feature change value.

[0136] In the present invention, by dynamically adjusting the noise intensity according to the change of HRV, the intensity of the noise stimulus can be adjusted in real time according to the physiological state of the individual. This personalized adjustment method ensures that the noise intensity is neither too low to effectively stimulate adaptation nor too high to avoid physiological overload. At the same time, by setting the adjustment factor α, the degree of change of the noise intensity can be flexibly controlled, so that the noise adjustment can vary flexibly according to the physiological feedback of different individuals. The introduction of the adjustment factor makes the training more adaptable, and the noise intensity can be finely adjusted according to the adaptation situation of the individual at different training stages.

[0137] Specifically, the user wears the device and starts the training program. The noise generation and control module generates noise according to the set scheme, while the physiological signal acquisition module continuously acquires electrocardiogram signals, and the HRV analysis module analyzes the change of HRV in real time. During the training process, the feedback and intervention module gives the user visual and auditory feedback in a timely manner according to the change of HRV, and automatically adjusts the noise intensity or duration as needed.

[0138] After each training session, the HRV analysis module comprehensively analyzes the HRV data during the training process, compares it with the data from the initial assessment, and evaluates the training effect. According to the evaluation results, the subsequent training plan is adjusted, such as increasing the noise intensity, extending the training duration, etc., to gradually improve the individual's adaptability to noise.

[0139] In the present invention, by analyzing the HRV changes and feedback in real time, the system can dynamically adjust the noise intensity and duration, making the training more personalized. Individuals can gradually adapt to the noise according to their own physiological responses, thereby effectively enhancing their tolerance and avoiding discomfort reactions caused by excessive noise. At the same time, through the comprehensive analysis after each training session and comparison with the initial assessment data, the system can evaluate the training effect and adjust the subsequent training plan according to the evaluation results, ensuring that each individual can undergo adaptation training at an appropriate intensity.

[0140] In one possible implementation, the adjustment factor is optimized by improving the particle swarm optimization algorithm.

[0141] Optionally, a target function is constructed:

[0142]

[0143] where f represents the target function, min represents minimization, N new,i represents the i-th adjusted noise intensity, N current,i represents the current noise intensity at the i-th sample point, and N represents the total number of data points.

[0144] Aiming to minimize the target function, it is optimized by improving the particle swarm optimization algorithm.

[0145] Optionally, the improvement of the particle swarm optimization algorithm specifically includes:

[0146] S1101: Initialize the particle swarm. The particle swarm contains multiple particles, and each particle represents a possible solution to the adjustment factor parameters.

[0147] S1102: Improve the fitness function of the particle swarm optimization algorithm with the reciprocal of the target function.

[0148] S1103: Calculate the fitness function value for each particle in the particle swarm.

[0149] S1104: Update the particle with the highest fitness value to the global optimal position.

[0150] S1105: Determine the neighborhood of each particle, and based on the particle information within the neighborhood, determine the particle with the highest fitness value within the neighborhood as the local best position.

[0151] In the present invention, through the guidance of the local optimal position and the sharing of neighborhood information, the search ability of particles in the local area can be improved. The particles adjust their positions according to the particle with the highest fitness value in the neighborhood, thereby improving the accuracy of local search.

[0152] S1106: Update the velocity and position of the particle through the following formula:

[0153] V u = ωV u + c1r1(Pbset u - X u ) + c2r2(Gbset - X u )

[0154] where, V u represents the velocity of the particle, ω represents the inertia weight, c1 and c2 represent the acceleration constants, r1 and r2 represent random numbers, Pbest u represents the historical best position of the u-th particle, and Gbest represents the global best position.

[0155] S1107: Generate a random number and determine whether the currently generated random number is less than the preset mutation probability. If so, enter S1108. Otherwise, enter S1109.

[0156] S1108: Use the mutation operation to update the position of the particle through the following formula and enter S1112:

[0157] T uv = X uv + A(Lbest - X uv )

[0158] where, T uv represents the position of the u-th particle after mutation in the v-th dimension, X uv represents the current position information of the u-th particle in the v-th dimension, and A represents the amplification factor.

[0159] In the present invention, the mutation operation broadens the search range of the particles, enabling the particles to conduct a more extensive search in the global scope. This helps to explore a broader solution space, enhance the global search ability, and ensure that the optimization process is not confined to a narrow area.

[0160] S1109: Apply a random permutation function to the local best position to increase the diversity of the solution space:

[0161] Lbest := permuting(Lbest)

[0162] Among them, Lbest represents the optimal solution position found by the particle in its neighborhood, and permuting() represents the random permutation function.

[0163] In the present invention, through the random permutation of the local solution space, the diversity of the solution space can be maintained during the optimization process, the global search ability can be enhanced, and a better solution can be found.

[0164] S1110: Generate the trial position of the particle through the following formula:

[0165] Mutant = X + F(Lbest - X)

[0166] Among them, Mutant represents the position of the mutated particle, X represents the current position of the particle, Lbest represents the local best position, and F represents the amplification parameter.

[0167] In the present invention, by amplifying the distance between the current position of the particle and the local best position (controlled by the amplification parameter F), the particle can jump out of the current local optimal region during update, thereby expanding its search range. This operation can enhance the exploratory ability of the particle swarm algorithm, avoid the premature convergence of the particle swarm to the local optimal solution, and improve the global search ability.

[0168] S1111: Perform a crossover operation on the current particle using the crossover operator to generate the solution of the next generation, and enter 1112.

[0169] S1112: Calculate the fitness of each particle and update the global best position according to the fitness of the particle.

[0170] S1113: Determine whether the maximum number of iterations is satisfied. If so, output the adjustment factor corresponding to the optimal result. Otherwise, return to S1105.

[0171] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0172] (1) In the embodiment of the present invention, by calculating the standard deviation value of the signal data in each signal channel and selecting the signal channel with a larger standard deviation value as the channel to be processed, the heartbeat signal in the original signal is extracted from the channel to be processed. Then, the derivative function is used to calculate the slope change in each signal cycle, determine the signal peak value, and calculate the time interval between consecutive signal peak values, so as to determine the change rate of the heartbeat interval. This process can accurately capture individual differences and fully consider the biological adaptation ability of different organisms to noise exposure.

[0173] (2) In the embodiments of the present invention, by extracting the HRV key index features and frequency domain features of the heartbeat signal, and analyzing in combination with the HRV features in the noise environment, the comprehensive feature change value is calculated. According to the comprehensive feature change value, the physiological state of the individual is dynamically evaluated, so as to adaptively adjust the noise intensity according to the feedback situation, ensure the safety and comfort of the noise acclimatization process, and improve the effect of noise acclimatization.

[0174] Refer to the attached Figure 2 figures, which show a schematic structural diagram of a noise acclimatization system based on the dynamic change of HRV provided by the present invention.

[0175] The present invention also provides a noise acclimatization system 20 based on the dynamic change of HRV, which is applied to the above-mentioned noise acclimatization method based on the dynamic change of HRV, and includes:

[0176] A processor 201.

[0177] A memory 202, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor 201, the noise acclimatization method based on the dynamic change of HRV as in the method embodiment is realized.

[0178] The noise acclimatization system 20 based on the dynamic change of HRV provided by the present invention can execute the above-mentioned noise acclimatization method based on the dynamic change of HRV and achieve the same or similar technical effects. To avoid repetition, the present invention will not be elaborated herein.

[0179] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0180] (1) In the embodiments of the present invention, by calculating the standard deviation value of the signal data in each signal channel, and selecting the signal channel with a larger standard deviation value as the channel to be processed, the heartbeat signal in the original signal is extracted in the channel to be processed. Then, the slope change in each signal period is calculated by using the derivative function, the signal peak value is determined, and the time interval between consecutive signal peak values is calculated to determine the heart rate variability. This process can accurately capture individual differences and fully consider the biological adaptation ability of different organisms to noise exposure.

[0181] (2) In the embodiments of the present invention, by extracting the HRV key index features and frequency domain features of the heartbeat signal, and analyzing in combination with the HRV features in the noise environment, the comprehensive feature change value is calculated. According to the comprehensive feature change value, the physiological state of the individual is dynamically evaluated, so as to adaptively adjust the noise intensity according to the feedback situation, ensure the safety and comfort of the noise acclimatization process, and improve the effect of noise acclimatization.

[0182] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0183] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0184] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0185] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context before and after.

[0186] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0187] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0188] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0189] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0190] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0191] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0192] In addition, the functional units in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0193] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0194] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the noise adaptation method based on the dynamic change of HRV as described in the method embodiment.

[0195] The computer-readable storage medium provided by the present invention can implement the steps and effects of the noise adaptation method based on the dynamic change of HRV in the above method embodiment. To avoid repetition, the present invention will not elaborate further.

[0196] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0197] (1) In the embodiment of the present invention, by calculating the standard deviation value of the signal data in each signal channel and selecting the signal channel with a larger standard deviation value as the channel to be processed, the heartbeat signal in the original signal is extracted in the channel to be processed. Then, the derivative function is used to calculate the slope change in each signal cycle, determine the signal peak value, and calculate the time interval between consecutive signal peak values, so as to determine the change rate of the heart rate interval. This process can accurately capture individual differences and fully consider the biological adaptation ability of different organisms to noise exposure.

[0198] (2) In the embodiment of the present invention, by extracting the HRV key index features and frequency domain features of the heartbeat signal, and analyzing them in combination with the HRV features in the noise environment, the comprehensive feature change value is calculated. According to the comprehensive feature change value, the physiological state of an individual is dynamically evaluated, and thus the noise intensity is adaptively adjusted according to the feedback situation to ensure the safety and comfort of the noise adaptation process and improve the effect of noise adaptation.

[0199] As described above, this is only the specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily conceive of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0200] The following points need to be explained:

[0201] (1) The attached drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the general design.

[0202] (2) For clarity, in the attached drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn according to the actual scale. It can be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intermediate elements.

[0203] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0204] As mentioned above, this is only the specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A noise acclimatization method based on HRV dynamic changes, characterized in that: include: S1: Obtain the original signals of the target to be noise acclimated in two signal channels through the radar system; S2: Calculate the standard deviation of the signal data in each signal channel, and select the signal channel with the largest standard deviation as the signal channel to be processed; S3: extracting the heartbeat signal from the original signal in the signal to be processed channel; S4: according to the heartbeat signal, using a derivative function to calculate the slope change in each signal cycle to determine the signal peak value; S5: Calculate the time interval between consecutive signal peaks to determine the heartbeat interval change rate; S6: Performing statistical analysis on the heart rate interval change rate to extract a first key indicator feature and a first frequency domain feature of HRV; S7: Generate noise through a noise generating device to simulate a noise environment; S8: extracting a second key indicator feature and a second frequency domain feature of the target to be noise acclimated in the noise environment; S9: Calculate a comprehensive feature change value according to the first key indicator feature, the first frequency domain feature, the second key indicator feature, and the second frequency domain feature; S10: Determine whether the comprehensive characteristic change value is less than a preset characteristic change value; if so, adjust the noise intensity through the noise generating device to perform noise acclimatization training; otherwise, adjust the noise intensity through the noise generating device to adaptively reduce the noise intensity.

2. The noise acclimatization method based on HRV dynamic changes according to claim 1 is characterized in that: The S1 specifically includes: S101: using an oscillator to generate a transmission signal, and transmitting the transmission signal to the chest of the target to be noise acclimated through a radar; S102: receiving a reflected signal through a receiving antenna; S103: Calculating the signal delay of the received reflected signal; S104: rewriting the received signal according to the signal delay to obtain an actual received signal; S105: Multiply the actual received signal by the transmitted signal to determine the original signals of the two signal channels: Where I(t) represents the original signal of the I channel at time t, Q(t) represents the original signal of the Q channel at time t, s(t) represents the displacement function of the target at time t, d0 represents the initial distance between the radar and the target, λ represents the wavelength of the signal, and θ represents the phase offset.

3. The noise acclimatization method based on HRV dynamic change according to claim 1, characterized in that: The S3 specifically includes: S301: setting a sampling rate and performing filtering processing using a bandpass filter to determine a frequency range of the original signal; S302: Perform fast Fourier transform on the original signal after bandpass filtering to obtain a frequency domain signal; S303: estimating the heart rate frequency according to the position corresponding to the maximum value of the frequency domain signal; S304: Calculating an average heart rate cycle according to the heart rate frequency, wherein the average heart rate cycle is used to determine a smoothing length; S305: creating a convolution vector to perform a smoothing operation on the original signal according to the smoothing length; S306: Convolve the original signal with the convolution vector to obtain a breathing signal; S307: removing the breathing signal from the original signal to obtain the heartbeat signal.

4. The noise acclimatization method based on HRV dynamic change according to claim 1, characterized in that: The S4 specifically includes: S401: Performing derivative processing on the heartbeat signal; S402: Calculate the slope of the heartbeat signal: y(n)=λ1x(n-2)+λ2x(n-1)+λ3x(n)+λ4x(n+1)+λ5x(n+2) Wherein, y(n) represents the slope value of the heartbeat signal calculated at time n, x(n-2) represents the heartbeat signal value at time n-2, λ1 represents the weight of the heartbeat signal value at time n-2, x(n-1) represents the heartbeat signal value at time n-1, λ2 represents the weight of the heartbeat signal value at time n-1, x(n) represents the heartbeat signal value at time n, λ3 represents the weight of the heartbeat signal value at time n, x(n+1) represents the heartbeat signal value at time n+1, λ4 represents the weight of the heartbeat signal value at time n+1, x(n+2) represents the heartbeat signal value at time n+2, and λ5 represents the weight of the heartbeat signal value at time n+2; S403: Determine the position corresponding to the maximum slope as the signal peak.

5. The noise acclimatization method based on HRV dynamic changes according to claim 4 is characterized in that: The S5 specifically includes: S501: Calculate the time interval between consecutive signal peaks to obtain the heartbeat interval between each of the signal peaks: Among them, IBI i represents the i-th heartbeat interval, represents the time point of the i+1th signal peak, represents the time point of the i-th signal peak; S502: Determine the heartbeat interval change rate according to each of the heartbeat intervals: in, Indicates the rate of change of heart beat interval, IBI i+1 Represents the i+1th heartbeat interval.

6. The noise acclimatization method based on HRV dynamic changes according to claim 1, characterized in that: The first key indicator features include: standard deviation of heartbeat intervals and root mean square of differences between adjacent heartbeat intervals; The first frequency domain feature includes: low frequency power associated with sympathetic nerve activity and high frequency power associated with parasympathetic nerve activity.

7. The noise acclimatization method based on HRV dynamic change according to claim 6, characterized in that: The calculation method of the comprehensive feature change value is specifically as follows: <h2 style=";text-align:left;direction:ltr">ΔHRV<h2 style=";text-align:left;direction:ltr"> total <h2 style=";text-align:left;direction:ltr"> = w1 ΔSDNN + w2 ΔRMSSD + w3 ΔLF + w4 ΔHF Where ΔHRV total represents the comprehensive feature change value, ΔSDNN represents the change in the standard deviation of the heartbeat interval, w1 represents the weight represented by the change in the standard deviation of the heartbeat interval, ΔRMSSD represents the change in the root mean square of the difference between adjacent heartbeat intervals, w2 represents the weight represented by the change in the root mean square of the difference between adjacent heartbeat intervals, ΔLF represents the change in low-frequency power related to sympathetic nerve activity, w3 represents the weight represented by the change in low-frequency power related to sympathetic nerve activity, ΔHF represents the change in high-frequency power related to parasympathetic nerve activity, and w4 represents the weight represented by the change in high-frequency power related to parasympathetic nerve activity.

8. The noise acclimatization method based on HRV dynamic changes according to claim 1, characterized in that: The S10 specifically includes: S1001: When the comprehensive characteristic change value is less than the preset characteristic change value, after a preset time period, the noise intensity is increased by a preset decibel increase to perform noise acclimatization training; S1002: When the comprehensive characteristic change value is greater than or equal to the preset characteristic change value, the adjusted noise intensity is calculated by the following formula, and according to the adjusted noise intensity, the noise generating device is used to adaptively reduce the noise intensity: Among them, N new Represents the adjusted noise intensity, N current represents the current noise intensity, α represents the adjustment factor, ΔHRV total Represents the comprehensive feature change value, T desired Indicates the preset feature change value.

9. The noise acclimatization method based on HRV dynamic changes according to claim 8, characterized in that: The adjustment factor is optimized by improving the particle swarm optimization algorithm.

10. A noise acclimatization system based on HRV dynamic changes, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the noise acclimatization method based on HRV dynamic changes as described in any one of claims 1 to 9 is implemented.

Images