A biological signal processing method, device, computer device and storage medium

Abstract

This application relates to the field of signal processing, and discloses a biological signal processing method, device, computer device and storage medium. By collecting biological signals and performing preliminary filtering processing on them, a preliminarily filtered signal is obtained; the noise characteristics of the preliminarily filtered signal are analyzed, a suitable filtering method is selected according to the analysis results, and filter parameters are designed through fuzzy logic processing; the filter parameters are input into an adaptive filter to process the signal to obtain a filtered biological signal; in combination with a denoising convolutional neural network model, noise discrimination and fuzzy logic processing are performed on the filtered biological signal to dynamically adjust the filter parameters; through multiple rounds of iterative optimization until the target filtering effect is obtained, and the optimized biological signal is output. The biological signal processing method of this application effectively removes complex noise in biological signals, improves filtering accuracy, and at the same time maintains signal integrity, providing a reliable basis for subsequent biological signal analysis and processing.

Description

Technical Field

[0001] This application relates to the technical field of signal processing, and in particular, to a biological signal processing method, apparatus, computer device, and storage medium. Background Art

[0002] Biological signals (such as electrocardiogram signals, electroencephalogram signals, electromyogram signals, etc.) are widely used in medical diagnosis, health monitoring, and scientific research. However, during the acquisition process, biological signals are often interfered by noises such as power frequency interference and motion artifacts, which reduces the signal-to-noise ratio and affects the accuracy of subsequent analysis and processing.

[0003] For biological signal denoising, existing technologies mainly include analog filters, digital filters, and deep learning-based methods. Analog filters filter out noises of specific frequencies through hardware circuits such as band-stop, low-pass, and high-pass, for example, power frequency interference. Although it has strong real-time performance, its performance is easily affected by temperature changes or aging of electronic components, and the design is fixed, making it difficult to adapt to dynamically changing noises. Digital filters rely on methods such as wavelet transform and adaptive filters to process the acquired signals. Among them, wavelet transform can perform multi-resolution analysis, but it is complex to select an appropriate wavelet function and may introduce pseudo-harmonics. Although the adaptive filter can dynamically adjust the filter coefficients, it has problems such as slow convergence speed and large steady-state error. In recent years, neural network methods based on deep learning have shown potential in noise modeling and removal, but their engineering implementation is still immature, and there are certain difficulties in popularization and application.

[0004] Although the above technologies have made breakthroughs, there are still problems such as insufficient dynamic adaptability, the contradiction between filtering accuracy and signal fidelity, and weak comprehensive processing ability for multiple noise sources in practical applications. For example, traditional filters are difficult to follow power frequency noises with changing frequencies and phases, and low-pass or high-pass filters may weaken the effective frequency components of the target signal, while the performance of a single filter in a multi-noise mixed environment is poor. In addition, both wavelet transform and deep learning methods have problems of high implementation complexity and high requirements for hardware resources.

[0005] Therefore, how to efficiently remove power frequency interference and motion artifacts during the acquisition of biological signals, while maintaining signal integrity, and significantly improving filtering flexibility, stability, and accuracy has become an important problem that needs to be solved urgently. Summary of the Invention

[0006] In view of this, embodiments of this application provide a biological signal processing method, apparatus, computer device, and storage medium, which can effectively solve the problems of insufficient dynamic adaptability of filters, low noise removal accuracy, inability to fully guarantee signal integrity, and weak comprehensive processing ability for multiple noises in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a biological signal processing method, including:

[0008] Collect biological signals;

[0009] Perform preliminary filtering on the collected biological signals to obtain a preliminarily filtered signal;

[0010] Analyze the noise characteristics of the preliminarily filtered signal, select a filtering method based on the analysis results, and design the parameters of an adaptive filter through fuzzy logic processing;

[0011] Input the parameters of the adaptive filter into the adaptive filter for processing to obtain a filtered biological signal;

[0012] Use a denoising convolutional neural network model to perform repeated noise discrimination and fuzzy logic processing on the filtered biological signal, and iteratively adjust the parameters of the adaptive filter until a target filtering effect is obtained, and output an optimized biological signal.

[0013] In some embodiments, the collecting biological signals includes:

[0014] Attach at least one surface-mounted electrode as a detection electrode to different parts of the surface of the organism to capture the biological signals, and amplify the amplitude of the biological signals through a preamplifier.

[0015] In some embodiments, the performing preliminary filtering on the collected biological signals to obtain a preliminarily filtered signal includes:

[0016] Filter out frequency components below a first frequency threshold and above a second frequency threshold from the collected biological signals to obtain the preliminarily filtered signal.

[0017] In some embodiments, the analyzing the noise characteristics of the preliminarily filtered signal, selecting a filtering method based on the analysis results, and designing the parameters of an adaptive filter through fuzzy logic processing includes:

[0018] Analyze the noise characteristics of the preliminarily filtered signal to determine the corresponding filtering method;

[0019] Filter the preliminarily filtered signal according to the filtering method;

[0020] Perform sampling processing on the filtered preliminarily filtered signal to remove the noise in the preliminarily filtered signal;

[0021] Use a triangular fuzzy model to perform fuzzy processing on the preliminarily filtered signal with noise removed, and convert the amplitude value of the signal into a membership degree value;

[0022] According to the membership value, use a preset fuzzy rule to determine whether to filter the preliminary filtered signal again to output a fuzzy value;

[0023] Perform defuzzification processing on the fuzzy value, design and output the parameters of the adaptive filter.

[0024] In some embodiments, the step of using a preset fuzzy rule to determine whether to filter the preliminary filtered signal again according to the membership value includes:

[0025] When the membership value is greater than a preset threshold, determine that the preliminary filtered signal is noise and perform filtering processing.

[0026] In some embodiments, the step of inputting the parameters of the adaptive filter into the adaptive filter for processing to obtain a filtered biological signal includes:

[0027] Input the parameters of the adaptive filter into the adaptive filter for signal processing;

[0028] The adaptive filter adjusts the biological signal in real time according to the input parameters of the adaptive filter to filter out the noise components in the biological signal and obtain the filtered biological signal.

[0029] In some embodiments, the step of using the denoising convolutional neural network model to perform repeated noise identification and fuzzy logic processing on the filtered biological signal, and iteratively adjusting the parameters of the adaptive filter until a target filtering effect is obtained and an optimized biological signal is output includes:

[0030] Input the filtered biological signal into the denoising convolutional neural network model for noise identification and fuzzy processing;

[0031] Based on the processing results of the noise identification and the fuzzy processing, dynamically adjust the filter parameters; iteratively optimize until a target filtering effect is obtained and output the optimized biological signal.

[0032] In a second aspect, an embodiment of the present application provides a biological signal processing device, including:

[0033] A signal acquisition module for acquiring biological signals;

[0034] A filtering processing module for performing preliminary filtering processing on the acquired biological signal to obtain a preliminary filtered signal;

[0035] A parameter design module for analyzing the noise characteristics of the preliminary filtered signal, selecting a filtering method based on the analysis result, and designing the parameters of the adaptive filter through fuzzy logic processing;

[0036] A signal acquisition module, configured to input the parameters of the adaptive filter into the adaptive filter for processing to obtain a filtered biological signal;

[0037] A target signal acquisition module, configured to perform repeated noise discrimination and fuzzy logic processing on the filtered biological signal by using a denoising convolutional neural network model, and iteratively adjust the parameters of the adaptive filter until a target filtering effect is obtained, and output an optimized biological signal.

[0038] In a third aspect, an embodiment of the present application provides a computer device, which includes a processor and a memory. The memory stores a computer program, and the processor is configured to execute the computer program to implement the biological signal processing method in the first aspect above.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which when the computer program is executed by a processor, the biological signal processing method in the first aspect above is implemented.

[0040] The embodiments of the present application have the following beneficial effects:

[0041] The biological signal processing method of the present application can effectively remove low-frequency or high-frequency noise by performing preliminary filtering processing on the collected biological signal, retain the main components of the target signal, and thus obtain a preliminarily filtered signal. Subsequently, noise characteristic analysis is performed on the preliminarily filtered signal, the most suitable filtering method is selected based on the analysis result, and the filter parameters are designed by using fuzzy logic processing to ensure that the filter can dynamically adapt to the characteristics of different noises. The signal quality is further optimized through the processing of the adaptive filter, and the filtered signal is combined with the DNCNN model to perform repeated noise discrimination and fuzzy logic processing. By combining the powerful modeling ability of deep learning with the fast decision-making ability of fuzzy logic, the filter parameters are dynamically adjusted. After multiple rounds of iteration, the filtering effect is continuously optimized, and finally complex noises (such as power frequency interference, motion artifacts) are effectively removed, and an optimized biological signal with a high signal-to-noise ratio is output. The biological signal processing method of the present application not only significantly improves the filtering accuracy, but also has the characteristics of flexibility, self-adaptability and high efficiency, can adapt to a variety of complex noise environments, provides high-quality basic data for subsequent biological signal analysis and processing, and has important engineering application value. Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 Shows a flowchart of a biological signal processing method according to an embodiment of the present application;

[0044] Figure 2 Shows a schematic diagram of designing filter parameters in a biological signal processing method according to an embodiment of the present application;

[0045] Figure 3 Shows a schematic structural diagram of a biological signal processing method according to an embodiment of the present application;

[0046] Figure 4 Shows a schematic diagram of the working principle of the DNCNN model in a biological signal processing method according to an embodiment of the present application;

[0047] Figure 5 Shows a schematic structural diagram of a biological signal processing device according to an embodiment of the present application. Detailed implementation manners

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0049] Generally, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application claimed, but merely represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0050] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0051] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present application pertain. The terms (such as those defined in a general-use dictionary) will be interpreted as having the same meaning as their contextual meaning in the relevant technical field and will not be interpreted as having an idealized or overly formal meaning unless clearly defined in various embodiments of the present application.

[0052] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0053] Considering the problems of insufficient dynamic adaptability of filters, low noise removal accuracy, inability to fully guarantee signal integrity, and weak comprehensive processing ability for multiple noises in the prior art. Therefore, a biological signal processing method is proposed. By collecting biological signals and performing preliminary filtering processing on them, a preliminarily filtered signal is obtained; subsequently, the noise characteristics of the preliminarily filtered signal are analyzed, a suitable filtering method is selected based on the analysis results, and the filter parameters are dynamically designed using the fuzzy logic method to adapt to different noise characteristics; then, the designed filter parameters are input into an adaptive filter for signal processing to further remove complex noises; finally, in combination with a denoising convolutional neural network model (DNCNN), the filtered signal is subjected to noise discrimination and fuzzy logic processing, and the filter parameters are dynamically adjusted through iterative optimization until the target filtering effect is obtained, and a high-quality optimized biological signal is output. This method not only significantly improves the accuracy of noise removal, but also effectively guarantees the signal integrity and the comprehensive processing ability for multiple noises, has strong flexibility and adaptability, and can meet the biological signal processing requirements in a complex noise environment.

[0054] Figure 1 A flowchart of the biological signal processing method according to an embodiment of the present application is shown. Exemplarily, the method includes step S100 - step S500.

[0055] Step S100, collect biological signals.

[0056] Exemplarily, the collection of biological signals is achieved through detection electrodes. Biological signals generally refer to the signals generated by electrophysiological activities inside and outside the human body. For example, electrocardiogram (ECG), electromyogram (EMG), etc. To obtain these signals, electrodes need to be attached to the human body surface to collect the electrical signals generated by the human body. Usually, the amplitude of biological signals is small and needs to be amplified for subsequent processing. The collection of biological signals can be carried out in various ways, and appropriate collection techniques are selected according to specific application scenarios.

[0057] In this embodiment, the collected biological signal is an electrical signal, which represents the electrophysiological activities within the organism. The collection process relies on suitable detection electrodes that can sense the weak current changes on the organism's surface and convert them into electronic signals. The collected signal will serve as the basis for subsequent signal processing and can provide important data for further filtering, analysis, processing, etc.

[0058] In an alternative embodiment, in step S100, collecting the biological signal includes:

[0059] To ensure the signal quality captured from the organism's surface, at least one surface-mounted electrode is used as the detection electrode in this embodiment. The surface-mounted electrode is attached to the organism's surface in a non-invasive manner, for example, on the skin, to collect the electrical signal of the organism. The surface-mounted electrode usually has flexibility and good electrical conductivity, which can ensure good contact with the skin surface and cause no discomfort to the subject.

[0060] According to the requirements of biological signal collection, the surface-mounted electrodes are usually attached to multiple different parts of the organism's surface. For example, taking the collection of forearm electromyogram signals as an example, detection electrodes with pre-amplification functions are placed at five different positions on the forearm muscles, namely the flexor carpi radialis, flexor carpi ulnaris, flexor pollicis longus, flexor digitorum profundus, and extensor digitorum. The positions of these electrodes are selected based on the distribution characteristics of muscle electrophysiological activities, which can capture signals from different muscle parts and thus obtain more comprehensive electromyogram signal data. The distance between each two collection electrodes is 20 mm, and the collection electrodes are output through shielded wires to reduce the influence of external interference on the signal.

[0061] Since the amplitude of biological signals is usually small, the directly collected signals may be difficult to analyze effectively. To solve this problem, a pre-amplifier is used on each electrode in this embodiment to amplify the amplitude of the signal. The function of the pre-amplifier is to amplify the amplitude of the signal to a range suitable for subsequent processing, avoiding information loss caused by overly weak signals. The pre-amplifier usually has a high input impedance and a low output impedance, which can effectively reduce the noise during signal collection and improve the clarity and stability of the signal.

[0062] Through the above method, the surface-mounted electrode and the pre-amplifier work together to ensure that a biological signal with sufficient intensity can be stably and clearly collected from the organism's surface, laying a foundation for subsequent signal processing and analysis. Specifically, in this embodiment, by arranging detection electrodes with pre-amplification at multiple parts of the forearm muscles, not only can the muscle electrical signals of different parts be captured, but also the quality and intensity of signal collection can be guaranteed, providing a reliable data source for subsequent signal analysis.

[0063] Step S200, perform preliminary filtering on the collected biological signal to obtain a preliminarily filtered signal.

[0064] Exemplarily, the initial filtering process of the acquired bio-signal is to remove some unwanted components in the signal. For example, power frequency noise, motion artifacts, etc. Bio-signals usually contain useful physiological information and various noise interferences. Especially during the acquisition process, environmental noise and motion artifacts may affect the signal quality. Therefore, in order to obtain a clearer and more accurate signal, it is necessary to perform initial filtering on the signal to eliminate these unwanted noise components.

[0065] The purpose of the initial filtering process is to preprocess the signal through a certain filtering method to make it suitable for subsequent signal analysis and processing. The role of the filter here is to selectively attenuate or remove certain frequency components in the signal through frequency, so as to achieve the effect of reducing noise. The initially filtered signal is the signal after this stage of processing. It will be clearer and purer than the original signal and can provide a better basis for subsequent signal processing.

[0066] In an alternative embodiment, in step S200, the acquired bio-signal is subjected to an initial filtering process to obtain an initially filtered signal, including:

[0067] In this embodiment, the specific filtering method is to use a band-pass filter. A band-pass filter is a frequency-selective filter that can allow signals within a specific frequency range to pass through while suppressing signals outside this range. In bio-signal processing, especially in the processing of signals such as electromyogram (EMG) and electroencephalogram (EEG), noise in certain frequency ranges (such as power frequency noise) will affect the analysis of the signal.

[0068] The working principle of the band-pass filter is to define the passband range by setting two thresholds: the first frequency threshold and the second frequency threshold. These two thresholds represent the lowest and highest frequency ranges that the signal is allowed to pass through respectively. Frequency components below the first frequency threshold will be filtered out, and frequency components above the second frequency threshold will also be suppressed. In this way, the band-pass filter can effectively remove low-frequency and high-frequency noise in the signal and only retain the frequency components useful for the analysis of bio-signals, so that the filtered signal becomes the initially filtered signal.

[0069] In this embodiment, the passband frequency range of the active band-pass filter is set to 20Hz - 500Hz and is implemented through a hardware circuit. In the hardware design, the resistance values of filter resistors R1 and R2 are 40kΩ and 2.5kΩ respectively, the values of capacitors C1 and C2 are both 0.1μF, and the operational amplifier selects the OPA227 chip. Through this design, it can be ensured that the filter has good frequency selectivity and stability.

[0070] After the filtering operation is completed, the signal undergoes AD conversion through the STM32 chip to quantize the analog signal into a digital signal for use by the subsequent signal processing unit. This hardware implementation method ensures the accuracy and efficiency of signal filtering.

[0071] For example, in the processing of electromyogram (EMG) signals, it is usually necessary to retain the frequency range from 20 Hz to 500 Hz and remove the low-frequency noise below 20 Hz and the high-frequency noise above 500 Hz. The active band-pass filter can effectively eliminate these unwanted noises according to the set passband range to obtain a preliminary filtered signal, making the signal clearer and providing more reliable basic data for further analysis.

[0072] By means of band-pass filtering and combined with the precise design of hardware implementation, it can ensure that only the frequency components of the useful signal are retained, and the irrelevant noises are eliminated, thus providing cleaner and more accurate signal data for subsequent processing and analysis.

[0073] Step S300: Analyze the noise characteristics of the preliminary filtered signal, select a filtering method based on the analysis results, and design the parameters of the adaptive filter through fuzzy logic processing.

[0074] In this embodiment, in order to optimize the preliminary filtered signal, the noise characteristics of the signal are first analyzed. By analyzing the statistical characteristics of the noise (such as Gaussian distribution, uniform distribution, or random distribution), the main characteristic parameters of the noise (such as mean, variance, or frequency distribution) are identified, so as to select a suitable filtering method, such as single-value filtering, multi-value filtering, or adaptive filtering. Subsequently, the parameters of the adaptive filter are dynamically designed by combining the method of fuzzy logic processing. Fuzzy logic processing can convert the signal amplitude value into a membership degree value, use the preset fuzzy rules to effectively judge the noise components in the signal, and calculate the target parameters of the filter (such as cut-off frequency, gain, or filtering range) through the membership degree value. Finally, the designed filter parameters can significantly improve the noise removal effect in the subsequent filtering process while maximizing the retention of the integrity and accuracy of the signal.

[0075] In an alternative embodiment, in step S300, analyzing the noise characteristics of the preliminary filtered signal, selecting a filtering method based on the analysis results, and designing the parameters of the adaptive filter through fuzzy logic processing includes:

[0076] In this embodiment, as Figure 2 shown, in order to achieve efficient denoising of the preliminary filtered signal and optimize the design of the adaptive filter, the following steps are specifically carried out:

[0077] Analyze the noise characteristics of the preliminary filtered signal. By analyzing the statistical characteristics of the noise (e.g., Gaussian distribution or uniform distribution), determine the type of noise in the signal and its main characteristic parameters (e.g., variance and mean). Based on the analysis results of the noise characteristics, select a suitable filtering method. For example, use multi-value filtering for Gaussian noise and single-value filtering for uniform noise, etc.

[0078] According to the selected filtering method, perform filtering processing on the preliminary filtered signal. For example, use multi-value filtering to smooth the signal, thereby reducing the interference of random noise.

[0079] Perform sampling processing on the filtered preliminary filtered signal, and further remove the remaining noise by extracting the characteristic values of the signal. For example, smooth the signal by means of average sampling and periodic sampling, and reduce the influence of non-linear noise on the signal.

[0080] Use a triangular fuzzy model to perform fuzzy processing on the sampled signal. Specifically, convert the amplitude value of the signal into a membership value, where the membership value represents the possibility of the signal corresponding to specific noise characteristics.

[0081] According to the membership value, make a judgment using preset fuzzy rules. For example, if the membership value is higher than a certain threshold, it is judged that there may still be noise in the signal, and then filtering is required again; otherwise, directly output the fuzzy value. Obtain the tuning parameters of the filter through fuzzy reasoning.

[0082] Perform defuzzification processing on the fuzzy value, calculate and output the final parameters of the adaptive filter. For example, calculate the cut-off frequency or gain range of the filter through defuzzification and use it to dynamically adjust the filter to complete the final optimization of the signal.

[0083] Through the above specific steps, it is possible to effectively cope with different types of noise characteristics, realize the dynamic adjustment of the filter parameters, thereby improving the filtering accuracy and the signal-to-noise ratio of the signal, and providing a reliable data basis for subsequent signal analysis.

[0084] In an alternative embodiment, making a judgment using preset fuzzy rules according to the membership value includes:

[0085] In this embodiment, when further processing the preliminary filtered signal, a decision-making mechanism based on fuzzy logic is adopted. Specifically, during the processing, fuzzy processing and fuzzy reasoning methods are used to analyze the signal, judge whether it is noise, and decide whether further filtering processing is required. One of the key steps in this decision-making process is the calculation of the membership value, which reflects whether the signal conforms to the noise characteristics.

[0086] First, after the previous filtering step, the preliminary filtered signal will undergo fuzzification to convert its amplitude value into a membership degree value. The main function of fuzzification is to transform the data of the input signal into corresponding membership degrees, which are used to analyze the degree to which the signal belongs to a certain category (e.g., noise or valid signal). In this embodiment, a triangular fuzzy model is used to perform fuzzification on the filtered signal. Specifically, the function definition of the triangular fuzzy model can map the signal amplitude value to the membership degree value interval [0, 1]. Among them, 0 indicates that the signal does not belong to noise at all, and 1 indicates that the signal completely belongs to noise. Since the signal output from the previous stage is already a digital signal, the value of the amplitude mean is 0 or 1, and these values are fuzzified through the triangular fuzzy model to generate corresponding membership degree values.

[0087] Next, according to the membership degree value, fuzzy inference is performed using preset fuzzy rules. The specific method is to calculate the membership degree values u0 and u1 of the signal amplitude sampling value with respect to 0 and 1, where u0 represents the membership degree value of the sampling value with respect to amplitude 0, and u1 represents the membership degree value of the sampling value with respect to amplitude 1. When u0 > u1, the system outputs 0 during defuzzification, indicating that the signal is relatively clean; when u0 < u1, the defuzzification output is 1, indicating that the signal contains relatively large noise and needs further filtering.

[0088] To achieve more efficient filtering operations, supplementary rules are designed to determine the maximum filtering noise threshold value. Specifically, when the rightmost parameter of the 0 membership degree function of the filtering noise is equal to the leftmost parameter of the 1 membership degree function, it is the maximum filtering threshold value. In this embodiment, the maximum threshold value of the triangular distribution is set to 0.204. In addition, by sampling multiple times within a period and combining single-value filtering, the signal can be further smoothed and the periodic noise components can be removed.

[0089] For example, in practical applications, assume that the preset membership degree threshold is 0.5. When the membership degree value of the signal exceeds this threshold, the system determines that the signal contains relatively strong noise components and needs further filtering; when the membership degree value is less than the threshold, it is considered that the signal is relatively clean and no further processing is required. This dynamic decision-making mechanism based on the membership degree value can flexibly adjust the filtering strategy, thereby effectively removing the noise in the signal.

[0090] Through the above method, this embodiment can combine the processing methods of fuzzification, fuzzy inference, and defuzzification to accurately judge and process the noise in the signal. Finally, the filtered signal output by the system has a higher signal-to-noise ratio and better quality, can adapt to the signal processing requirements in various noise environments, and at the same time has strong flexibility and adaptability.

[0091] Step S400, input the parameters of the adaptive filter into the adaptive filter for processing to obtain the filtered biological signal.

[0092] Exemplarily, the design of the filter parameters is based on the analysis of the noise characteristics of the preliminary filtered signal and the results of fuzzy logic reasoning. These parameters are designed to optimize the performance of the filter to meet the requirements of complex noise environments in biological signal processing. The filter and the adaptive filter are the same filter, and the adaptive filter can dynamically adjust its behavior according to the input parameters, thereby achieving efficient signal processing.

[0093] The unity of the filter and the adaptive filter ensures a simplified design of the system, that is, the core algorithm and physical structure of the filter remain unchanged, but the parameters are adjusted in real time to adapt to different noise characteristics. By inputting the designed filter parameters into the adaptive filter, the filter can further process the biological signal according to these parameters, filter out the noise in the signal, and retain the useful biological information.

[0094] For example, if the input filter parameters specify a band-pass filtering range (e.g., 20 Hz to 500 Hz), the adaptive filter will perform filtering operations within this range to remove low-frequency noise below 20 Hz and high-frequency noise above 500 Hz, while retaining the meaningful signal components. Through this process, the adaptive filter can effectively improve the quality of biological signals, laying a foundation for subsequent signal analysis.

[0095] In an alternative embodiment, in step S400, inputting the parameters of the adaptive filter into the adaptive filter for processing to obtain the filtered biological signal includes:

[0096] In the specific implementation process, the filter parameters are input into the adaptive filter in real time. These parameters include but are not limited to the type of filter (e.g., band-pass filter or low-pass filter), cut-off frequencies (e.g., high-frequency and low-frequency thresholds), gain, etc. These parameters are determined through the previous fuzzy logic analysis and noise characteristic analysis, aiming to optimize the performance of the filter so that it can adapt to the dynamic changes of the signal.

[0097] The core characteristic of the adaptive filter is its ability to adjust its behavior in real time according to the input parameters. For example, when power frequency noise (e.g., 50 Hz) is detected in the signal, the adaptive filter can automatically adjust its filtering parameters to specifically suppress the 50 Hz frequency band without affecting other frequency components. When the noise characteristics change (e.g., an increase in random noise), the adaptive filter can adapt to the new noise environment by dynamically adjusting the gain or frequency range.

[0098] During the signal processing, the adaptive filter continuously updates and optimizes the filtering parameters to ensure the filtering effect. For example, the filter analyzes the frequency distribution and intensity of the input signal in each sampling period, and adjusts the cut-off frequency range so that it can more accurately filter out the noise. This dynamic adjustment mechanism ensures that the filter can always efficiently process the noise in the biological signal and output a signal with higher quality.

[0099] Finally, after being processed by the adaptive filter, the filtered biological signal is output. These signals not only remove the interference components, but also retain the useful information in the original signal to the greatest extent, providing higher-quality data input for subsequent signal analysis.

[0100] Step S500: Use the denoising convolutional neural network model to repeatedly perform noise discrimination and fuzzy logic processing on the filtered biological signal, and adjust the parameters of the adaptive filter through iteration until the target filtering effect is obtained, and then output the optimized biological signal.

[0101] To further improve the signal quality, the denoising convolutional neural network model (Denoising Convolutional Neural Network, abbreviated as DNCNN) is used to process the filtered biological signal again. The denoising convolutional neural network is a signal optimization method based on deep learning, which can accurately model and remove complex noise, and is especially suitable for non-linear or random noise that is difficult to handle by traditional filtering methods. The principle and working process of the model are introduced as follows Figure 4 shown:

[0102] 1. The filtered biological signal x is input into the DNCNN model. The goal is to calculate the denoised signal v by learning the noise signal n, and the relationship is: v = x - n;

[0103] Among them, x represents the filtered noisy signal, n is the residual noise signal predicted by the model, and v is the output signal after denoising.

[0104] 2. Through end-to-end training, the DNCNN model learns the residual noise in the signal and optimizes the denoising effect through residual connections. The calculation formula for each layer of the network is:

[0105]

[0106] Among them, represents the convolution and deconvolution operations, represents the L-th neuron of the i-th input layer. represents the scale of the filter, represents the bias value, and f represents the activation function;

[0107] The model predicts the noise signal through a residual learning mechanism, and the formula for residual learning is:

[0108] x = F(x1) + x1

[0109] where F(x1) represents the residual prediction function;

[0110] 3. The length of each layer of the signal is dynamically adjusted according to the step size S, and the calculation formula is:

[0111]

[0112] where: represents the length of the signal of the L-th layer; S: step size.

[0113] 4. The output of each layer is processed through batch normalization (Batch Normalization), and the formula is:

[0114]

[0115] where: BNγ,β: is the batch normalization function; γ,β: are trainable normalization parameters.

[0116] 5. During the optimization process of the model, the discriminator of the generative adversarial network (GAN) is combined to compare the denoised signal and the original clean signal. Through the feedback mechanism, the network parameters of the DnCNN are adjusted to optimize the denoising effect.

[0117] 6. Based on the DnCNN, a diffusion model with weighted anisotropy is combined for image signal denoising. The reconstructed signal is classified by the discriminator, and the signal optimization process is gradually completed under the feedback of the discriminator, so as to achieve the optimal denoising effect.

[0118] 7. Through multiple rounds of iteration, the DnCNN model continuously adjusts the filter parameters to optimize the denoising effect of the signal. The model dynamically adjusts the diffusion coefficient threshold K and stops updating the threshold K until the denoising effect reaches the optimal.

[0119] Through the above process, the DnCNN model can accurately identify and remove complex noises in biological signals (such as power frequency interference and motion artifacts), dynamically optimize the filter parameters, and significantly improve the signal-to-noise ratio of the signal. The finally output optimized signal not only has significantly reduced noise components, but also can retain the integrity of the original signal to the greatest extent, ensuring the reliability and accuracy of subsequent signal analysis.

[0120] In an alternative embodiment, in step S500, the denoising convolutional neural network model is used to perform repeated noise discrimination and fuzzy logic processing on the filtered biological signal. By iteratively adjusting the parameters of the adaptive filter until the target filtering effect is obtained, and the optimized biological signal is output, including:

[0121] To further improve the quality of the filtered biological signal, a denoising convolutional neural network model (DNCNN) is used to perform noise discrimination and fuzzy processing on the signal. First, the filtered biological signal is input into the DNCNN model. Using its deep learning ability, the residual noise in the signal is discriminated, and at the same time, the signal amplitude value is fuzzified through fuzzy logic processing, the membership degree value of the signal is calculated, and the signal is classified and analyzed in combination with the preset fuzzy rules. Based on the results of noise discrimination and fuzzy processing, the parameters of the filter are dynamically adjusted, such as the cut-off frequency, filtering gain or noise threshold value, to adapt to the characteristics of the current signal.

[0122] This process adopts an iterative optimization method, that is, after each noise discrimination and fuzzy processing, the filter parameters are updated, and the biological signal is processed again to gradually reduce the residual noise and improve the signal-to-noise ratio and quality of the biological signal. The target filtering effect refers to the effect of removing noise, retaining signal integrity and improving the signal-to-noise ratio by dynamically adjusting the parameters of the adaptive filter during multiple rounds of iteration. Through multiple cyclic processes, the filtering effect is continuously optimized under the synergistic effect of the DNCNN model and the fuzzy logic system until the noise is fully removed and the quality of the biological signal reaches the preset standard. Finally, the output biological signal has a higher signal-to-noise ratio and integrity, providing reliable basic data for subsequent analysis and processing.

[0123] The method of the embodiment of the present application realizes the efficient acquisition and dynamic optimization filtering of biological signals by combining the method of fuzzy logic and the denoising convolutional neural network model (DNCNN), such as Figure 3As shown below: First, the collected bio-signal is preprocessed through preliminary filtering to eliminate some low-frequency and high-frequency noises, and the signal quality is initially improved. Second, the filter parameters are dynamically designed through noise characteristic analysis and fuzzy logic processing, enabling the filter to adaptively adjust to different noise types (e.g., Gaussian noise, random noise, or uniformly distributed noise), thereby improving the filtering accuracy. At the same time, the adaptive filter dynamically adjusts using the designed parameters to further filter out complex noise components. Finally, a denoising convolutional neural network (DNCNN) model is introduced to perform repeated noise discrimination and fuzzy logic processing on the filtered signal. Through the deep learning ability of the neural network, the residual noise is accurately identified, and the filter parameters are iteratively optimized to form a closed-loop optimization mechanism. This solution can not only effectively remove noise in a complex and diverse noise environment, significantly improve the signal-to-noise ratio of the signal, but also dynamically adjust the filtering strategy to meet the signal processing requirements under different noise conditions. The finally output bio-signal has high precision and integrity, providing a reliable basis for subsequent bio-signal analysis and processing. This method has high flexibility and strong adaptability, and has important practical application value.

[0124] Figure 5 FIG. shows a schematic structural diagram of a bio-signal processing device according to an embodiment of the present application. Exemplarily, the device includes:

[0125] A signal acquisition module 51 for acquiring bio-signals;

[0126] A filtering processing module 52 for performing preliminary filtering processing on the acquired bio-signal to obtain a preliminarily filtered signal;

[0127] A parameter design module 53 for performing noise characteristic analysis on the preliminarily filtered signal, selecting a filtering method based on the analysis result, and designing the parameters of the adaptive filter through fuzzy logic processing;

[0128] A signal acquisition module 54 for inputting the parameters of the adaptive filter into the adaptive filter for processing to obtain a filtered bio-signal;

[0129] A target signal acquisition module 55 for performing repeated noise discrimination and fuzzy logic processing on the filtered bio-signal using a denoising convolutional neural network model, and iteratively adjusting the parameters of the adaptive filter until a target filtering effect is obtained, and outputting an optimized bio-signal.

[0130] It can be understood that the device in this embodiment corresponds to the method in the above embodiment, and the optional items in the above embodiment also apply to this embodiment, so they will not be repeated here.

[0131] The present application also provides a computer device. Exemplarily, the computer device includes a processor and a memory. Among them, the memory stores a computer program, and the processor executes the computer program to enable the computer device to perform the functions of the above-mentioned method or each module in the above-mentioned device.

[0132] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0133] The memory can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the memory is used to store the computer program, and after receiving the execution instruction, the processor can execute the computer program accordingly.

[0134] The present application also provides a computer-readable storage medium for storing the computer program used in the above-mentioned computer device. For example, the computer-readable storage medium can include, but is not limited to: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0135] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and structural diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structural diagram and / or flowchart, as well as the combination of blocks in the structural diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0136] In addition, each functional module or unit in various embodiments of this application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0137] If the described functions are implemented in the form of software functional modules and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, 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 to enable a computer device (which can be a smart phone, 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 this application.

[0138] As described above, the above are only the specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. A biological signal processing method, characterized in that: The method comprises: Collect biological signals; Performing preliminary filtering processing on the collected biological signal to obtain a preliminary filtered signal; Performing noise characteristic analysis on the preliminary filtered signal, selecting a filtering method based on the analysis result, and designing parameters of the adaptive filter through fuzzy logic processing; Inputting the parameters of the adaptive filter into the adaptive filter for signal processing to obtain a filtered biological signal, including: The adaptive filter adjusts the biological signal in real time according to the input parameters of the adaptive filter to filter out noise components in the biological signal to obtain the filtered biological signal; The denoising convolutional neural network model is used to repeatedly perform noise identification and fuzzy logic processing on the filtered biological signal, and the parameters of the adaptive filter are dynamically adjusted through multiple rounds of iterations until the target filtering effect is obtained, and the optimized biological signal is output, including: Inputting the filtered biological signal into the denoising convolutional neural network model to perform noise identification and fuzzy processing; The denoising convolutional neural network predicts and removes residual noise through residual learning, and uses end-to-end training and feedback mechanisms to optimize the noise removal effect; the noise identification is used to predict the residual noise in the signal; the fuzzy processing is used to fuzzify the filtered biological signal, perform fuzzy reasoning according to preset fuzzy rules, and fuse it with the noise identification result output by the denoising convolutional neural network; Based on the processing results of the noise identification and the fuzzy processing, the parameters of the adaptive filter are dynamically adjusted, and multiple rounds of iterative optimization processing are performed until the target filtering effect is obtained, and the optimized biological signal is output.

2. The biological signal processing method according to claim 1, characterized in that: The collecting of biological signals comprises: At least one surface-mounted electrode is attached to different parts of the biological body surface as a detection electrode to capture the biological signal, and the amplitude of the biological signal is amplified by a preamplifier.

3. The biological signal processing method according to claim 1, characterized in that: The performing preliminary filtering processing on the collected biological signal to obtain a preliminary filtered signal includes: The frequency components below the first frequency threshold and above the second frequency threshold are filtered out from the collected biological signal to obtain the preliminary filtered signal.

4. The biological signal processing method according to claim 1, characterized in that: The performing of noise characteristic analysis on the preliminary filtered signal, selecting a filtering method based on the analysis result, and designing the parameters of the adaptive filter through fuzzy logic processing includes: Performing noise characteristic analysis on the preliminary filtered signal to determine a corresponding filtering method; According to the filtering method, filtering is performed on the preliminary filtered signal; Performing sampling processing on the filtered preliminary filtered signal to remove noise in the preliminary filtered signal; Using a triangular fuzzy model to perform fuzzy processing on the preliminary filtered signal after noise removal, and converting the amplitude value of the signal into a membership value; According to the membership value, using a preset fuzzy rule to determine whether to filter the preliminary filtered signal again to output a fuzzy value; The fuzzy value is defuzzified, and the parameters of the adaptive filter are designed and output.

5. The biological signal processing method according to claim 4, characterized in that: The step of using a preset fuzzy rule to determine whether to filter the preliminary filtered signal again according to the membership value includes: When the membership value is greater than a preset threshold, the preliminary filtered signal is determined to be noise and filtering is performed.

6. A biological signal processing device, characterized in that: The device comprises: A signal acquisition module, used for collecting biological signals; A filtering processing module, used for performing preliminary filtering processing on the collected biological signal to obtain a preliminary filtered signal; A parameter design module, used to analyze the noise characteristics of the preliminary filtered signal, select a filtering method based on the analysis results, and design the parameters of the adaptive filter through fuzzy logic processing; A signal acquisition module, used for inputting the parameters of the adaptive filter into the adaptive filter for processing to obtain a filtered biological signal, comprising: The adaptive filter adjusts the biological signal in real time according to the input parameters of the adaptive filter to filter out noise components in the biological signal to obtain the filtered biological signal; The target signal acquisition module is used to perform repeated noise identification and fuzzy logic processing on the filtered biological signal using a denoising convolutional neural network model, dynamically adjust the parameters of the adaptive filter through multiple rounds of iterations until the target filtering effect is obtained, and output the optimized biological signal, including: Inputting the filtered biological signal into the denoising convolutional neural network model to perform noise identification and fuzzy processing; The denoising convolutional neural network predicts and removes residual noise through residual learning, and uses end-to-end training and feedback mechanisms to optimize the noise removal effect; the noise identification is used to predict the residual noise in the signal; the fuzzy processing is used to fuzzify the filtered biological signal, perform fuzzy reasoning according to preset fuzzy rules, and fuse it with the noise identification result output by the denoising convolutional neural network; Based on the processing results of the noise identification and the fuzzy processing, the parameters of the adaptive filter are dynamically adjusted, and multiple rounds of iterative optimization processing are performed until the target filtering effect is obtained, and the optimized biological signal is output.

7. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the biological signal processing method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The device stores a computer program, which, when executed on a processor, implements the biological signal processing method according to any one of claims 1 to 5.

Images