Anti-interference filtering method and system for multi-modal physiological signal acquisition equipment, terminal and storage medium

Abstract

The invention relates to the technical field of physiological signal processing, and discloses an anti-interference filtering method and system for a multi-modal physiological signal acquisition device, a terminal and a storage medium, and the method comprises the steps: carrying out the preprocessing of an acquired multi-modal physiological signal; modal recognition and feature extraction are carried out on the preprocessed multi-modal physiological signals; selecting a corresponding filter according to a modal identification result, and dynamically adjusting parameters of the filter; adjusting a filtering path and a filtering sequence based on a cascade filtering structure and a dynamic switching mechanism; adaptive interference estimation and offset are carried out based on crosstalk processing and a reference channel compensation mechanism; and performing parallel filtering according to the extracted features, comparing evaluation parameters of each filtering result based on an output result selection mechanism, and selecting and outputting a final signal according to a comparison result. According to the invention, effective suppression of multi-source interference such as power supply interference, motion artifacts, crosstalk and high-frequency noise is realized, and the real-time performance and stability of the filtering effect are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of physiological signal processing, and in particular to an anti-interference filtering method, system, terminal and storage medium for a multimodal physiological signal acquisition device. Background Art

[0002] With the rapid development of wearable devices and telemedicine, physiological signal acquisition equipment has gradually evolved from single-modality to multi-modality. Common physiological signals include electrocardiogram (ECG), electroencephalogram (EEG), galvanic skin response (EDA), electromyogram (EMG), and blood oxygen saturation (SpO2). However, these physiological signals are susceptible to various interferences during the acquisition process (such as power frequency noise, motion artifacts, muscle electrical noise, environmental electromagnetic interference, and crosstalk between signals). Therefore, after acquiring these physiological signals, specific filtering methods are required for processing.

[0003] Existing filtering methods, such as FIR filters (finite impulse response filters) / IIR filters (infinite impulse response digital filters), wavelet transforms, adaptive filters (such as LMS filters and least mean square filters), and blind source separation (ICA methods, independent component analysis noise reduction methods), although effective in certain specific situations, have the following shortcomings in multimodal signal processing: 1) Lack of targeting: It is difficult to apply to multiple signal modalities at the same time, resulting in limited filtering effects in multimodal scenarios.

[0004] 2) Poor real-time performance: Some filtering algorithms are computationally complex and cannot meet real-time processing requirements, especially in resource-constrained wearable devices.

[0005] 3) Limited filtering effect: In dynamic motion or high-interference environments, filtering quality is difficult to guarantee.

[0006] Therefore, the existing technology needs to be improved. Summary of the Invention

[0007] The technical problem to be solved by the present invention is that, in response to the defects of the existing technology, the present invention provides an anti-interference filtering method, system, terminal and storage medium for a multimodal physiological signal acquisition device to solve the problems of poor filtering effect and low efficiency of the existing filtering method in multimodal signal scenarios.

[0008] The technical solutions adopted by the present invention to solve the technical problems are as follows: In a first aspect, the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising: Preprocessing the collected multimodal physiological signals; Perform modality recognition and feature extraction on the preprocessed multimodal physiological signals; Select the corresponding filter according to the modal identification results and dynamically adjust the filter parameters; Adjust the filtering path and order based on the cascade filtering structure and dynamic switching mechanism; Adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism; Parallel filtering is performed based on the extracted features, the evaluation parameters of each filtering result are compared based on the output result selection mechanism, and the final signal is selected and output based on the comparison results.

[0009] In one implementation, the preprocessing of the collected multimodal physiological signals includes: The multimodal physiological signal is amplitude normalized, a mean removal method and a high-pass filter method are used to remove DC bias, and a standard score method, an interquartile range method, and a sliding window method are used to remove abnormal points to obtain the preprocessed multimodal physiological signal.

[0010] In one implementation, performing modality recognition and feature extraction on the preprocessed multimodal physiological signal includes: Identifying a signal category corresponding to each modality signal in the preprocessed multimodal physiological signal; The time domain signal of each modal signal is converted into a frequency domain signal by using the spectrum analysis method, the frequency component with the largest amplitude is identified, and the corresponding main frequency characteristics are obtained; The amplitude of each sampling point of each modal signal is squared and summed to obtain the corresponding waveform energy characteristics; Calculate the difference between adjacent sampling points of each modal signal, count the number of mutation points that exceed the set threshold, and calculate the ratio of the number of mutation points to the total number of sampling points to obtain the corresponding mutation rate characteristics; The ratio of the signal power to the noise power of each modal signal is calculated to obtain the corresponding signal-to-noise ratio characteristics.

[0011] In one implementation, selecting a corresponding filter according to the modal recognition result and dynamically adjusting the filter parameters includes: Select the corresponding filter combination according to the identified signal mode and dynamically adjust the filter parameters in the combination; The filter combination includes any combination of a band-stop filter, a wavelet denoising, a high-pass filter, an adaptive filter, an independent component analysis denoising, a low-pass filter, a notch filter and a Kalman filter.

[0012] In one implementation, adjusting the filtering path and order based on the cascaded filtering structure and the dynamic switching mechanism includes: Obtaining real-time signal-to-noise ratio detection results for each modal signal, and selecting a path that meets the current noise environment from the preset filtering paths based on the signal-to-noise ratio detection results; The filter order and filter parameters in the filter combination are dynamically adjusted according to the current noise characteristics of each modal signal.

[0013] In one implementation, the adaptive interference estimation and cancellation based on the crosstalk processing and reference channel compensation mechanism includes: A reference channel is constructed, and an interference signal in a main channel is estimated using a signal corresponding to the reference channel. An estimated value corresponding to the interference signal is subtracted from a signal corresponding to the main channel to cancel the interference signal.

[0014] In one implementation, performing parallel filtering based on the extracted features, comparing evaluation parameters of the filtering results based on an output result selection mechanism, and selecting and outputting a final signal based on the comparison results, includes: Perform parallel filtering processing according to the characteristics of each modal signal to generate corresponding filtering results; According to the preset strategy or algorithm, the evaluation parameters of each filtering result are compared, and the result that meets the current signal characteristics is selected as the final signal for output.

[0015] In a second aspect, the present invention provides an anti-interference filtering system for a multimodal physiological signal acquisition device, comprising: A signal preprocessing module, used to preprocess the collected multimodal physiological signals; Modality recognition and feature extraction module, used to perform modality recognition and feature extraction on preprocessed multimodal physiological signals; Adaptive filter module, used to select the corresponding filter according to the modal recognition results and dynamically adjust the filter parameters; Interference detection and dynamic adjustment module, used to adjust the filtering path and order based on the cascade filtering structure and dynamic switching mechanism; Crosstalk suppression and signal fusion module, used for adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism; The output selection and data transmission module is used to perform parallel filtering based on the extracted features, compare the evaluation parameters of each filtering result based on the output result selection mechanism, and select and output the final signal based on the comparison results.

[0016] In a third aspect, the present invention provides a terminal comprising: a processor and a memory, wherein the memory stores an anti-interference filtering program of a multimodal physiological signal acquisition device, and when the anti-interference filtering program of the multimodal physiological signal acquisition device is executed by the processor, it is used to implement the operation of the anti-interference filtering method of the multimodal physiological signal acquisition device as described in the first aspect.

[0017] In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores an anti-interference filtering program for a multimodal physiological signal acquisition device. When the anti-interference filtering program for the multimodal physiological signal acquisition device is executed by a processor, it is used to implement the operation of the anti-interference filtering method for the multimodal physiological signal acquisition device as described in the first aspect.

[0018] The present invention adopts the above technical solution to achieve the following effects: This paper proposes an anti-interference filtering method for multimodal physiological signal acquisition devices. Based on the spectral characteristics, noise types, and processing requirements of different physiological signal modalities, a modal adaptive filtering mechanism is constructed. Combined with a multi-stage filter cascade structure, this method effectively suppresses multiple interference sources, including power supply interference, motion artifacts, crosstalk, and high-frequency noise. Through interference identification and dynamic parameter adjustment mechanisms, the real-time performance and stability of the filtering effect are improved. This method exhibits excellent versatility, stability, and low computational resource usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0020] Figure 1 This is a flow chart of the anti-interference filtering method of the multimodal physiological signal acquisition device in the present invention.

[0021] Figure 2 This is a structural block diagram of the anti-interference filtering system of the multimodal physiological signal acquisition device in the present invention.

[0022] Figure 3 It is a functional principle diagram of a terminal in one implementation of the present invention.

[0023] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present invention more clear and distinct, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0025] Exemplary Methods Existing anti-interference filtering methods for single-modal physiological signal acquisition devices, such as FIR filters (finite impulse response filters) / IIR filters (infinite impulse response digital filters), wavelet transforms, adaptive filters (such as LMS filters and least mean square filters), and blind source separation (ICA analysis methods and independent component analysis noise reduction methods), although effective in certain specific situations, have the following shortcomings in multimodal signal processing: 1) Lack of targeting: It is difficult to apply to multiple signal modalities at the same time, resulting in limited filtering effects in multimodal scenarios.

[0026] 2) Poor real-time performance: Some filtering algorithms are computationally complex and cannot meet real-time processing requirements, especially in resource-constrained wearable devices.

[0027] 3) Limited filtering effect: In dynamic motion or high-interference environments, filtering quality is difficult to guarantee.

[0028] In response to the above technical problems, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, which includes: preprocessing the acquired multimodal physiological signals; performing modal identification and feature extraction on the preprocessed multimodal physiological signals; selecting a corresponding filter based on the modal identification result, and dynamically adjusting the filter parameters; adjusting the filtering path and order based on a cascade filtering structure and a dynamic switching mechanism; performing adaptive interference estimation and cancellation based on a crosstalk processing and reference channel compensation mechanism; performing parallel filtering based on the extracted features, comparing the evaluation parameters of each filtering result based on an output result selection mechanism, and selecting and outputting the final signal based on the comparison result.

[0029] The embodiments of the present invention construct a modality-adaptive filtering mechanism tailored to the spectral characteristics, noise types, and processing requirements of different physiological signal modalities. Combined with a multi-stage filter cascade structure, this effectively suppresses multiple interference sources, including power supply interference, motion artifacts, crosstalk, and high-frequency noise. Through interference identification and dynamic parameter adjustment mechanisms, the real-time and stability of the filtering effect are improved. This system exhibits excellent versatility, stability, and low computational resource usage.

[0030] like Figure 1 As shown, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising the following steps: Step S100: pre-processing the collected multimodal physiological signals.

[0031] Specifically, in one implementation of this embodiment, step S100 includes the following steps: In step S101 , the amplitude of the multimodal physiological signal is normalized, the DC bias is removed by using a mean removal method and a high-pass filter method, and outliers are removed by using a standard score method, an interquartile range method, and a sliding window method to obtain the preprocessed multimodal physiological signal.

[0032] In this embodiment, the anti-interference filtering method of the multimodal physiological signal acquisition device is implemented by the anti-interference filtering system of the multimodal physiological signal acquisition device.

[0033] like Figure 2 As shown, the anti-interference filtering system of the multimodal physiological signal acquisition device includes: a signal preprocessing module, a modal recognition and feature extraction module, an adaptive filter module, an interference detection and dynamic adjustment module, a crosstalk suppression and signal fusion module, and an output selection and data transmission module.

[0034] In this embodiment, the physiological signals of the corresponding modalities are first collected by sensors such as ECG sensors (electrocardiogram sensors), EMG sensors (electromyography sensors), EEG sensors (electroencephalogram sensors), EDA sensors (galvanic skin response) sensors and blood oxygen saturation sensors, thereby obtaining the multimodal physiological signals.

[0035] After obtaining the multimodal physiological signals, the original signals of each modality are input into the above-mentioned signal preprocessing module for data preprocessing. The specific preprocessing process is as follows: The input raw signal is amplitude normalized, and the DC bias is removed using the mean removal method and high-pass filter method. The Z-Score method (data standardization and outlier detection method), the IQR method (a statistical method for identifying outliers based on the interquartile range), and the sliding window method are used to remove outliers in the raw signals of each mode.

[0036] In this embodiment, data preprocessing is performed in the above manner to obtain the preprocessed multimodal physiological signal; of course, in other application scenarios, data preprocessing can also be performed through polynomial fitting methods, signal segmentation methods, time domain superposition methods, and noise injection methods.

[0037] like Figure 1 As shown, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising the following steps: Step S200 , performing modality recognition and feature extraction on the pre-processed multimodal physiological signal.

[0038] In this embodiment, after obtaining the preprocessed multimodal physiological signal, it is input into the above-mentioned modality recognition and feature extraction module, in which the signal type of each modality can be automatically identified, and the features of each signal can be extracted through the corresponding feature extraction method.

[0039] Specifically, in one implementation of this embodiment, step S200 includes the following steps: Step S201, identifying the signal category corresponding to each modality signal in the preprocessed multimodal physiological signal; Step S202: Convert the time domain signal of each modal signal into a frequency domain signal by using a spectrum analysis method, identify the frequency component with the largest amplitude, and obtain the corresponding main frequency feature; Step S203, square the amplitude of each sampling point of each modal signal and sum them to obtain the corresponding waveform energy feature; Step S204, calculating the difference between adjacent sampling points of each modal signal, counting the number of mutation points exceeding a set threshold, and calculating the ratio of the number of mutation points to the total number of sampling points to obtain the corresponding mutation rate feature; Step S205 , calculating the ratio of the signal power to the noise power of each modal signal to obtain a corresponding signal-to-noise ratio feature.

[0040] In this embodiment, after automatically identifying the signal type (such as ECG signal, EEG signal, etc.), a corresponding common method is selected according to the identified signal type to extract the features that best characterize this type of signal, wherein the extracted signal features include but are not limited to: main frequency features, waveform energy features, mutation rate features, and signal-to-noise ratio features.

[0041] As an example, in this embodiment, feature extraction of each modal signal can be performed in the following manner: 1) By using spectrum analysis methods, such as the fast Fourier transform (FFT) method, the time domain signal is converted into a frequency domain signal, and the frequency component with the largest amplitude is identified to obtain the main frequency characteristics.

[0042] 2) By squaring the amplitude of each sampling point of the signal and summing them up, the total energy of the signal is obtained and used as the waveform energy feature.

[0043] 3) By calculating the difference between adjacent sampling points, the number of mutation points exceeding the set threshold is counted, and the ratio of the difference to the total number of sampling points is used as the mutation rate feature.

[0044] 4) The signal-to-noise ratio feature is obtained by calculating the ratio of signal power to noise power.

[0045] In this embodiment, in addition to performing modal recognition and feature extraction on the preprocessed multimodal physiological signals in the above manner, a machine learning model can also be used to replace the above-mentioned modal recognition and feature extraction module. For example, a CNN (convolutional neural network) model, an LSTM (long short-term memory network) model, and a GRU (gated recurrent unit) model can be used for modal recognition and feature extraction.

[0046] like Figure 1 As shown, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising the following steps: Step S300: Select a corresponding filter according to the modal recognition result and dynamically adjust the filter parameters.

[0047] In this embodiment, after modal recognition and feature extraction, filter selection and adaptive parameter adjustment are performed through the above-mentioned adaptive filter module, that is, a suitable filter combination is selected according to the recognized signal modality, and the parameters are dynamically adjusted.

[0048] Specifically, in one implementation of this embodiment, step S300 includes the following steps: Step S301: Select a corresponding filter combination according to the identified signal mode, and dynamically adjust the filter parameters in the combination.

[0049] In this embodiment, anti-interference filtering is performed by dynamically adjusting and combining different filters; specifically, in the process of adjusting the filter combination, the optimal filter parameters can be adaptively selected according to the combination effect of the filters, thereby realizing the function of dynamic adjustment of the filter parameters.

[0050] As an example, the filter combination described in this embodiment includes but is not limited to: any combination of band-stop filter, wavelet denoising, high-pass filter, adaptive filter, independent component analysis denoising, low-pass filter, notch filter and Kalman filter.

[0051] In some application scenarios, the filter combination and corresponding parameters selected by the adaptive filter module in this embodiment are as follows: 1) ECG signal: band-stop filter + wavelet noise reduction; the parameters of the band-stop filter are adjusted to 50 Hz ± 2 Hz.

[0052] 2) EEG signal: high-pass filter + LMS adaptive filter (an adaptive filter that minimizes the error between the input signal and the desired signal by continuously adjusting the filter coefficients) + ICA (independent component analysis noise reduction method); the parameters of the high-pass filter are adjusted to: 1 Hz.

[0053] 3) EMG signal: high-pass filter + low-pass filter; the parameters of the high-pass filter are adjusted to: >20Hz; the parameters of the low-pass filter are adjusted to: <500Hz.

[0054] 4) EDA signal: A low-pass filter is used to remove rapid disturbances. The parameters of the low-pass filter are adjusted to <5 Hz.

[0055] 5) SpO2 signal: Notch filter + Kalman filter dynamically compensates for illumination artifacts.

[0056] In addition to the above filter combinations and parameter adjustment methods in this embodiment, in some application scenarios, wavelet denoising can be replaced by the empirical mode decomposition (EMD) method for denoising, or the LMS adaptive filter can be replaced by the RLS algorithm (an adaptive filtering algorithm based on the least squares method), or a separate modal corresponding optimization algorithm can be selected for different modal usage scenarios to achieve corresponding filtering methods and parameter adjustments.

[0057] In this embodiment, by adopting a multi-modal adaptive filtering strategy, the filtering structure can be intelligently matched according to the signal type; and by adopting a cascade adjustable filtering mechanism, different filter combinations can be used to form an adjustable processing chain.

[0058] like Figure 1 As shown, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising the following steps: Step S400: adjusting the filtering path and order based on the cascade filtering structure and the dynamic switching mechanism.

[0059] In this embodiment, after filter selection and adaptive parameter adjustment, based on the above-mentioned interference detection and dynamic adjustment module, the cascade filtering structure and dynamic switching mechanism are used to adjust the filtering path and filtering order to adapt to different noise environments.

[0060] Specifically, in one implementation of this embodiment, step S400 includes the following steps: Step S401: obtaining a real-time signal-to-noise ratio detection result of each modal signal, and selecting a path that meets the current noise environment from the preset filtering paths according to the signal-to-noise ratio detection result; Step S402 : Dynamically adjust the filter order and filter parameters in the filter combination according to the current noise characteristics of each modal signal.

[0061] In this embodiment, based on the real-time SNR (signal-to-noise ratio) measurements of each modal signal, the system selects the path from among the preset filtering paths that best suits the current noise environment. For example, in a high-noise environment, the system might select a path that includes an adaptive filter to more effectively suppress noise. Furthermore, the order of the filters is dynamically adjusted based on the current noise characteristics. For example, in the presence of strong periodic interference, a notch filter is prioritized to remove noise at a specific frequency.

[0062] This embodiment adopts a dynamic interference identification and switching mechanism, and can use SNR analysis to adjust the filtering path, thereby achieving the functions of dynamic adjustment of the filtering structure and adaptive adjustment of parameters.

[0063] like Figure 1 As shown, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising the following steps: Step S500 : performing adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism.

[0064] In this embodiment, in addition to adjusting the filtering path and order based on the cascade filtering structure and dynamic switching mechanism, adaptive interference estimation and cancellation are also performed through crosstalk processing and reference channel compensation mechanism; wherein, the crosstalk processing and reference channel compensation mechanism are implemented by the above-mentioned crosstalk suppression and signal fusion module.

[0065] Specifically, in one implementation of this embodiment, step S500 includes the following steps: Step S501: construct a reference channel, use a signal corresponding to the reference channel to estimate an interference signal in a main channel, and subtract an estimated value corresponding to the interference signal from the signal corresponding to the main channel to cancel the interference signal.

[0066] In this example, a reference channel for each modality must first be constructed. In a signal acquisition system, a reference channel is used to capture signals related to interference sources in the main channel. For example, in electrocardiogram (ECG) signal processing, to eliminate myoelectric interference, additional electrodes can be placed near areas of muscle activity to specifically collect myoelectric signals as reference channel input. This reference signal should be highly correlated with the interference components in the main channel but not contain the target signal components.

[0067] After the reference channel is constructed, the interference signal in the main channel can be estimated using the signal corresponding to the reference channel, and signal cancellation can be performed based on the estimated value of the interference signal.

[0068] As an example, this embodiment uses the LMS algorithm for interference cancellation. The LMS algorithm iteratively adjusts filter coefficients to minimize the error between the output signal and the desired signal. During interference cancellation, the LMS algorithm uses the reference channel signal to estimate the interference component in the main channel and subtracts this estimate from the main channel signal, thereby extracting a purer target signal. This process does not require prior knowledge of the specific characteristics of the interference and can adapt to changes in interference in real time, improving the robustness of signal processing.

[0069] In other application scenarios of this embodiment, an AI-assisted judgment mechanism can be added to realize dynamic interference prediction, and a deep neural network can be used for unified modeling and processing of the entire solution.

[0070] like Figure 1 As shown, an embodiment of the present invention provides an anti-interference filtering method for a multimodal physiological signal acquisition device, comprising the following steps: Step S600 , performing parallel filtering according to the extracted features, comparing the evaluation parameters of the filtering results based on the output result selection mechanism, and selecting and outputting the final signal according to the comparison result.

[0071] In this embodiment, after adaptive interference estimation and cancellation, in the actual filtering process, multiple modal signals can be filtered through parallel processing. Moreover, for each modal signal, parallel processing is also adopted to filter using multiple filters. Then, by evaluating each filter scheme, the result that best meets the current noise environment and current signal characteristics is selected as the final output.

[0072] Specifically, in one implementation of this embodiment, step S600 includes the following steps: Step S601, performing parallel filtering processing according to the characteristics of each modal signal to generate corresponding filtering results; Step S602: Compare the evaluation parameters of the filtering results according to a preset strategy or algorithm, and select the result that meets the current signal characteristics as the final signal for output.

[0073] In this embodiment, the parallel filtering processing method is: the original signal is processed by multiple filters at the same time, for example, a bandpass filter, a notch filter, an adaptive filter, etc., and then multiple filtering results are generated.

[0074] Furthermore, each filtering result is evaluated by feature evaluation, wherein the feature evaluation method is: for each filtering result, its key parameters such as SNR (signal-to-noise ratio), energy distribution, and spectral characteristics are calculated.

[0075] Optimal selection: Based on the preset strategy or algorithm, the evaluation parameters of each filtering result are compared and the result that best matches the current signal characteristics is selected as the final output.

[0076] In this embodiment, the above technical solution significantly improves the signal-to-noise ratio of multimodal signals (by an average of 8-15 dB); and the filtering delay is controlled within 10 ms, making it suitable for real-time systems.

[0077] It is worth mentioning that the above technical solution of this embodiment supports the deployment of edge computing platforms (such as ESP32 platform and STM32 platform), and can maintain high stability in dynamic motion or high interference environments.

[0078] As an example, the technical solution of this embodiment can be deployed in the following ways: 1) Deployed on the STM32H7 platform, the filtering algorithm is implemented using CMSIS-DSP.

[0079] 2) Run FreeRTOS on the ESP32-S3 platform and dynamically switch between the LMS algorithm and the FIR algorithm.

[0080] 3) Combine AI models to identify interference types and call specific filtering solutions (such as edge neural networks to determine whether there is power frequency interference).

[0081] As an application prospect of this embodiment, the anti-interference filtering method of the multimodal physiological signal acquisition device can be deployed in combination with edge AI to improve the accuracy of interference identification; and it can be expanded to a multi-user, multi-channel remote physiological monitoring system; and it has good adaptability in the Internet of Things (IoT) and can be used as the core algorithm of the health management platform.

[0082] This embodiment achieves the following technical effects through the above technical solution: This embodiment proposes an anti-interference filtering method for multimodal physiological signal acquisition devices. Based on the spectral characteristics, noise types, and processing requirements of different physiological signal modalities, a modal adaptive filtering mechanism is constructed. Combined with a multi-stage filter cascade structure, this method effectively suppresses multiple sources of interference, including power supply interference, motion artifacts, crosstalk, and high-frequency noise. Through interference identification and dynamic parameter adjustment mechanisms, the real-time performance and stability of the filtering effect are improved. This embodiment exhibits excellent versatility, stability, and low computational resource utilization.

[0083] Exemplary devices Based on the above embodiments, the present invention further provides an anti-interference filtering system for a multimodal physiological signal acquisition device, comprising: A signal preprocessing module, used to preprocess the collected multimodal physiological signals; Modality recognition and feature extraction module, used to perform modality recognition and feature extraction on preprocessed multimodal physiological signals; Adaptive filter module, used to select the corresponding filter according to the modal recognition results and dynamically adjust the filter parameters; Interference detection and dynamic adjustment module, used to adjust the filtering path and order based on the cascade filtering structure and dynamic switching mechanism; Crosstalk suppression and signal fusion module, used for adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism; The output selection and data transmission module is used to perform parallel filtering based on the extracted features, compare the evaluation parameters of each filtering result based on the output result selection mechanism, and select and output the final signal based on the comparison results.

[0084] This embodiment achieves the following technical effects through the above technical solution: This embodiment proposes an anti-interference filtering system for multimodal physiological signal acquisition devices. This system employs a modal adaptive filtering mechanism tailored to the spectral characteristics, noise types, and processing requirements of different physiological signal modalities. Combined with a multi-stage filter cascade structure, it effectively suppresses multiple sources of interference, including power supply interference, motion artifacts, crosstalk, and high-frequency noise. Through interference identification and dynamic parameter adjustment, the real-time performance and stability of the filtering effect are improved. This embodiment exhibits excellent versatility, stability, and low computational resource usage.

[0085] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be shown as follows: Figure 3 shown.

[0086] The terminal includes: a processor, memory, interface, display screen and communication module connected via a system bus; wherein the processor of the terminal is used to provide computing and control capabilities; the memory of the terminal includes a computer-readable storage medium and an internal memory; the computer-readable storage medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and computer program in the computer-readable storage medium; the interface is used to connect to external devices; the display screen is used to display corresponding information; and the communication module is used to communicate with a cloud server or other devices.

[0087] When the computer program is executed by a processor, it is used to implement the operation of the anti-interference filtering method of the multimodal physiological signal acquisition device.

[0088] It will be understood by those skilled in the art that Figure 3The principle block diagram shown in the figure is only a block diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the terminal to which the solution of the present invention is applied. The specific terminal may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0089] In one embodiment, a terminal is provided, which includes: a processor and a memory, wherein the memory stores an anti-interference filtering program of a multimodal physiological signal acquisition device, and when the anti-interference filtering program of the multimodal physiological signal acquisition device is executed by the processor, it is used to implement the operation of the anti-interference filtering method of the multimodal physiological signal acquisition device as described above.

[0090] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores an anti-interference filtering program for a multimodal physiological signal acquisition device. When the anti-interference filtering program for the multimodal physiological signal acquisition device is executed by a processor, it is used to implement the operation of the anti-interference filtering method for the multimodal physiological signal acquisition device as described above.

[0091] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile storage medium. When executed, the computer program can include the processes in the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include both non-volatile and volatile memory.

[0092] In summary, the present invention provides an anti-interference filtering method, system, terminal, and storage medium for a multimodal physiological signal acquisition device, including: preprocessing the acquired multimodal physiological signals; performing modal identification and feature extraction on the preprocessed multimodal physiological signals; selecting a corresponding filter based on the modal identification result, and dynamically adjusting the filter parameters; adjusting the filtering path and order based on a cascaded filtering structure and a dynamic switching mechanism; performing adaptive interference estimation and cancellation based on a crosstalk processing and reference channel compensation mechanism; performing parallel filtering based on the extracted features, comparing the evaluation parameters of each filtering result based on an output result selection mechanism, and selecting and outputting the final signal based on the comparison result. The present invention effectively suppresses multi-source interference such as power supply interference, motion artifacts, crosstalk, and high-frequency noise, and improves the real-time and stability of the filtering effect.

[0093] It should be understood that the application of the present invention is not limited to the above examples. For those skilled in the art, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. An anti-interference filtering method for a multimodal physiological signal acquisition device, characterized in that: include: Preprocessing the collected multimodal physiological signals; Perform modality recognition and feature extraction on the preprocessed multimodal physiological signals; Select the corresponding filter according to the modal identification results and dynamically adjust the filter parameters; Adjust the filtering path and order based on the cascade filtering structure and dynamic switching mechanism; Adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism; Parallel filtering is performed based on the extracted features, the evaluation parameters of each filtering result are compared based on the output result selection mechanism, and the final signal is selected and output based on the comparison results.

2. The anti-interference filtering method of the multimodal physiological signal acquisition device according to claim 1, characterized in that: The preprocessing of the collected multimodal physiological signals includes: The multimodal physiological signal is amplitude normalized, a mean removal method and a high-pass filter method are used to remove DC bias, and a standard score method, an interquartile range method, and a sliding window method are used to remove abnormal points to obtain the preprocessed multimodal physiological signal.

3. The anti-interference filtering method of the multimodal physiological signal acquisition device according to claim 1, characterized in that: The modality recognition and feature extraction of the pre-processed multimodal physiological signals include: Identifying a signal category corresponding to each modality signal in the preprocessed multimodal physiological signal; The time domain signal of each modal signal is converted into a frequency domain signal by using the spectrum analysis method, the frequency component with the largest amplitude is identified, and the corresponding main frequency characteristics are obtained; The amplitude of each sampling point of each modal signal is squared and summed to obtain the corresponding waveform energy characteristics; Calculate the difference between adjacent sampling points of each modal signal, count the number of mutation points that exceed the set threshold, and calculate the ratio of the number of mutation points to the total number of sampling points to obtain the corresponding mutation rate characteristics; The ratio of the signal power to the noise power of each modal signal is calculated to obtain the corresponding signal-to-noise ratio characteristics.

4. The anti-interference filtering method of the multimodal physiological signal acquisition device according to claim 1, characterized in that: The method of selecting a corresponding filter according to the modal recognition result and dynamically adjusting the filter parameters includes: Select the corresponding filter combination according to the identified signal mode and dynamically adjust the filter parameters in the combination; The filter combination includes any combination of a band-stop filter, a wavelet denoising, a high-pass filter, an adaptive filter, an independent component analysis denoising, a low-pass filter, a notch filter and a Kalman filter.

5. The anti-interference filtering method of the multimodal physiological signal acquisition device according to claim 1, characterized in that: The method of adjusting the filtering path and order based on the cascade filtering structure and the dynamic switching mechanism includes: Obtaining real-time signal-to-noise ratio detection results for each modal signal, and selecting a path that meets the current noise environment from the preset filtering paths based on the signal-to-noise ratio detection results; The filter order and filter parameters in the filter combination are dynamically adjusted according to the current noise characteristics of each modal signal.

6. The anti-interference filtering method of the multimodal physiological signal acquisition device according to claim 1, characterized in that: The adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism includes: A reference channel is constructed, and an interference signal in a main channel is estimated using a signal corresponding to the reference channel. An estimated value corresponding to the interference signal is subtracted from a signal corresponding to the main channel to cancel the interference signal.

7. The anti-interference filtering method of the multimodal physiological signal acquisition device according to claim 1, characterized in that: The parallel filtering is performed based on the extracted features, the evaluation parameters of each filtering result are compared based on the output result selection mechanism, and the final signal is selected and outputted based on the comparison result, including: Perform parallel filtering processing according to the characteristics of each modal signal to generate corresponding filtering results; According to the preset strategy or algorithm, the evaluation parameters of each filtering result are compared, and the result that meets the current signal characteristics is selected as the final signal for output.

8. An anti-interference filtering system for a multimodal physiological signal acquisition device, characterized in that: include: A signal preprocessing module, used to preprocess the collected multimodal physiological signals; Modality recognition and feature extraction module, used to perform modality recognition and feature extraction on preprocessed multimodal physiological signals; Adaptive filter module, used to select the corresponding filter according to the modal recognition results and dynamically adjust the filter parameters; Interference detection and dynamic adjustment module, used to adjust the filtering path and order based on the cascade filtering structure and dynamic switching mechanism; Crosstalk suppression and signal fusion module, used for adaptive interference estimation and cancellation based on crosstalk processing and reference channel compensation mechanism; The output selection and data transmission module is used to perform parallel filtering based on the extracted features, compare the evaluation parameters of each filtering result based on the output result selection mechanism, and select and output the final signal based on the comparison results.

9. A terminal, characterized in that: include: A processor and a memory, wherein the memory stores an anti-interference filtering program for a multimodal physiological signal acquisition device, and when the anti-interference filtering program for the multimodal physiological signal acquisition device is executed by the processor, it is used to implement the operation of the anti-interference filtering method for the multimodal physiological signal acquisition device as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an anti-interference filtering program of a multimodal physiological signal acquisition device, which, when executed by a processor, is used to implement the operation of the anti-interference filtering method of the multimodal physiological signal acquisition device as described in any one of claims 1 to 7.

Images