A non-contact method, device, equipment and storage medium for detecting myocardial infarction

Abstract

This invention provides a non-contact method, apparatus, device, and storage medium for detecting myocardial infarction. The non-contact method includes: acquiring radio frequency signals fed back by a target user, and determining the target user's motion state based on the radio frequency signals; the motion state includes a resting state and a state of slight body movement; reconstructing the target user's heartbeat waveform based on the target user's motion state, and extracting the heartbeat signal; segmenting the target user's heartbeat signal; extracting physiological features from the segmented heartbeat signal, and classifying the target user based on the physiological features to obtain a classification result. This invention significantly improves the detection accuracy under conditions of slight movement, solving the problem of poor accuracy in myocardial infarction detection in existing related technologies.

Description

Technical Field

[0001] This invention relates to the field of medical testing technology, and in particular to a non-contact method, device, equipment, and storage medium for detecting myocardial infarction. Background Technology

[0002] Myocardial infarction (MI), commonly known as a heart attack, is an acute illness caused by blockage of the coronary arteries, leading to insufficient oxygen supply to the heart muscle and subsequent myocardial cell death. The high mortality rate and severe sequelae of MI make early detection a crucial medical need. Traditional MI detection methods, such as electrocardiograms (ECG) and blood tests, while effective in identifying cardiac abnormalities, are increasingly showing limitations in practical applications.

[0003] In the field of intelligent health monitoring, radio frequency (RF) signals, as an emerging non-contact physiological signal sensing method, have received increasing attention. RF-based cardiac health monitoring technology transmits and receives electromagnetic waves reflected from the human body, extracting physiological information such as heart rate and respiratory rate to assess health status. Compared to traditional electrocardiogram (ECG) and blood tests, RF signal monitoring requires no physical contact, offering greater convenience and continuity. Especially for the elderly or patients with chronic illnesses, RF technology avoids the discomfort and limitations of conventional testing equipment, making health monitoring more widespread and continuous.

[0004] However, radio frequency (RF) signals face many technical challenges in application. First, RF signal processing requires complex algorithms, including multiple steps such as signal acquisition, filtering, demodulation, and feature extraction. Each step can be affected by various factors, leading to instability in heart rate detection results. For example, although RF systems perform well under static conditions, even slight user movements, such as arm shaking or leg swinging, can significantly increase noise in the signal, affecting the accuracy of heart rate extraction. Therefore, maintaining high detection accuracy even during slight user activity is a significant technical challenge for RF health monitoring systems.

[0005] Secondly, because the propagation of radio frequency signals is easily affected by physiological phenomena such as human respiration, accurately extracting heart rate signals has become the primary challenge for radio frequency cardiac monitoring systems. Traditional heart rate detection methods based on radio frequency signals rely on simple spectrum analysis techniques, but due to the influence of human movement and respiration on radio frequency signals, these methods struggle to effectively separate the heartbeat signal, especially when the user makes slight physical movements, as the signal can be severely interfered with.

[0006] To overcome these problems, researchers have proposed several improvements. For example, they have employed more advanced Frequency Modulated Continuous Wave (FMCW) radar technology, which acquires higher-resolution physiological signals by precisely measuring the phase changes of the echo. This technology can effectively capture minute chest displacements, thus reflecting the periodic fluctuations of heartbeat and respiration. However, because the frequency ranges of heartbeat and respiration overlap to some extent, these methods still struggle to accurately separate heartbeat signals in complex environments, especially when users are making slight body movements, where traditional signal processing methods exhibit poor robustness.

[0007] Furthermore, the effective application of radio frequency (RF) signals also faces the challenge of environmental adaptability. Different environmental conditions can have varying effects on the propagation of RF signals. For example, walls, furniture, and other objects may alter the signal propagation path or even introduce additional noise. Therefore, how to suppress environmental noise and extract effective physiological information through precise signal processing algorithms has become one of the key issues in RF health monitoring technology.

[0008] There is currently no effective solution to the problem of poor accuracy in myocardial infarction detection in existing related technologies. Summary of the Invention

[0009] This invention provides a non-contact method, device, equipment, and storage medium for detecting myocardial infarction, thereby addressing the shortcomings of poor accuracy in existing myocardial infarction detection technologies.

[0010] In a first aspect, the present invention provides a non-contact method for detecting myocardial infarction, comprising:

[0011] The radio frequency signals fed back by the target user are collected, and the motion state of the target user is determined based on the radio frequency signals; the motion state includes a static state and a slight body movement state.

[0012] Based on the target user's movement state, the target user's heartbeat waveform is recovered, and the heartbeat signal is extracted;

[0013] The heartbeat signal of the target user is segmented;

[0014] Physiological features are extracted from the heartbeat signal of the target user after segmentation, and the target user is classified based on the physiological features to obtain the classification result.

[0015] According to a non-contact myocardial infarction detection method provided by the present invention, the method acquires radio frequency signals fed back by the target user and determines the motion state of the target user based on the radio frequency signals, including:

[0016] Radio frequency signals modulated by the breathing and heartbeat of the target user are acquired and transmitted by pulse coherent radar; the radio frequency signals include several consecutive IQ data.

[0017] The motion amplitude between the two pulses is determined based on the phase difference between two consecutive IQ data.

[0018] The amplitude variance of the motion amplitude is compared with a preset detection threshold to determine the motion state of the target user.

[0019] According to a non-contact myocardial infarction detection method provided by the present invention, when the target user is in a resting state, the method recovers the target user's heartbeat waveform and extracts the heartbeat signal based on the target user's movement state, including:

[0020] The phase differences of the IQ data of the target user at various times are combined to obtain a phase difference sequence signal;

[0021] A fast Fourier transform is performed on the phase difference sequence signal to construct a bandpass filter for filtering the radio frequency signal;

[0022] The filtered radio frequency signal is subjected to inverse Fourier transform to obtain the target user's heartbeat waveform, and the heartbeat signal is extracted based on the heartbeat waveform.

[0023] According to a non-contact myocardial infarction detection method provided by the present invention, when the target user is in a state of slight body movement, the method recovers the target user's heartbeat waveform and extracts the heartbeat signal based on the target user's movement state, including:

[0024] The phase differences of the IQ data of the target user at various times are combined to obtain a phase difference sequence signal;

[0025] White noise is added to the phase difference sequence signal, and empirical mode decomposition is performed to obtain the intrinsic mode function sequence;

[0026] Transform each of the intrinsic mode function sequences to the frequency domain to determine the dominant frequency of each of the intrinsic mode function sequences;

[0027] The target user's heart rate range is determined based on the dominant frequency of the intrinsic mode function sequence, and the target user's heart rate signal is extracted.

[0028] According to a non-contact myocardial infarction detection method provided by the present invention, when the target user is in a resting state, the heartbeat signal of the target user is segmented, including:

[0029] The phase difference sequence signal is reversed and iterated through to determine the peak function at each point, generating a peak set.

[0030] The peak set is traversed sequentially by index, and the points in the peak set are sorted, filtered, and divided into multiple segments to form a heartbeat signal segment set.

[0031] According to a non-contact myocardial infarction detection method provided by the present invention, when the target user is in a resting state, the heartbeat signal of the target user is segmented, including:

[0032] Set a standard template for heartbeat signals;

[0033] Using a dynamic programming method, with the goal of minimizing the error between the signal segment of the heartbeat signal and the standard template, the standard template is iteratively updated until the iteration converges, thus obtaining the segmentation result of the heartbeat signal and the target template.

[0034] According to a non-contact myocardial infarction detection method provided by the present invention, physiological features are extracted from the segmented heartbeat signal of the target user, and the target user is classified based on the physiological features to obtain a classification result, including:

[0035] Physiological features are extracted from the segmented heartbeat signal;

[0036] The pre-trained classification model is invoked to classify the target user based on the extracted physiological features, thereby obtaining the detection results.

[0037] Secondly, the present invention also provides a non-contact myocardial infarction detection device, comprising:

[0038] The acquisition module is used to acquire the radio frequency signals fed back by the target user and determine the motion state of the target user based on the radio frequency signals; the motion state includes a static state and a slight body movement state;

[0039] The extraction module is used to recover the heartbeat waveform of the target user based on the target user's movement state and extract the heartbeat signal;

[0040] The segmentation module is used to segment the heartbeat signal of the target user;

[0041] The detection module is used to extract physiological features from the segmented heartbeat signal of the target user, and classify the target user based on the physiological features of the target user to obtain the classification result.

[0042] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the non-contact myocardial infarction detection method as described in the first aspect above.

[0043] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the non-contact myocardial infarction detection method as described in the first aspect above.

[0044] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the non-contact myocardial infarction detection method as described in the first aspect above.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The non-contact myocardial infarction detection method provided by this invention processes radio frequency signals differently based on the target user's movement state, which not only enhances the stability of the radio frequency signals but also significantly improves the detection accuracy under mild movement conditions, making it more closely aligned with real-life scenarios. For example, users can still monitor their heart rate changes in real time while watching TV or working. This adaptability provides great convenience for family and personal health monitoring and solves the problem of poor accuracy in myocardial infarction detection in existing related technologies. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the non-contact myocardial infarction detection method provided by the present invention;

[0049] Figure 2 This is a structural block diagram of the non-contact myocardial infarction detection device provided by the present invention;

[0050] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0052] This invention provides a non-contact method for detecting myocardial infarction. Figure 1 This is a flowchart of the non-contact myocardial infarction detection method provided by the present invention, as follows: Figure 1 As shown, the method includes the following steps:

[0053] Step S101: Collect the radio frequency signal fed back by the target user, and determine the motion state of the target user based on the radio frequency signal; the motion state includes a stationary state and a slight body movement state.

[0054] Step S102: Based on the target user's movement state, recover the target user's heartbeat waveform and extract the heartbeat signal;

[0055] Step S103: Segment the heartbeat signal of the target user;

[0056] Step S104: Extract physiological features from the segmented heartbeat signal of the target user, and classify the target user based on the physiological features to obtain the classification result.

[0057] In this method, firstly, radio frequency (RF) signals from the target user are acquired. Then, the RF signals are used to determine whether the target user is in a static or slightly moving state. Slightly moving state refers to tolerable minor physical activities during the detection process, such as reading, eating, and browsing the internet. During these activities, the target user may exhibit slight forward or backward leaning of the trunk, or small movements of the limbs. Next, based on the target user's movement state, corresponding methods are used to reconstruct the target user's heartbeat waveform and extract the heartbeat signal. Based on this, the extracted heartbeat signal is segmented to extract specific information for each heartbeat cycle. Finally, the target user's physiological characteristics are extracted from the segmented heartbeat signal, and the target user is classified based on these characteristics to determine whether the target user is a person at risk of myocardial infarction. Existing detection technologies only achieve high accuracy when the target user is stationary. However, the above process, which processes the RF signal differently based on the target user's movement state, not only enhances the stability of the RF signal but also significantly improves the detection accuracy under slightly moving conditions, making it closer to real-life scenarios. For example, users can still monitor their heart rate changes in real time while watching TV or working. This adaptability provides great convenience for family and personal health monitoring and solves the problem of poor accuracy in myocardial infarction detection in existing related technologies.

[0058] In some embodiments, step S101, acquiring radio frequency signals fed back by the target user and determining the target user's motion state based on the radio frequency signals, includes: acquiring and transmitting radio frequency signals modulated by the target user's breathing and heartbeat through pulse coherent radar; the radio frequency signals include several consecutive IQ data; determining the motion amplitude between two pulses based on the phase difference between two consecutive IQ data; and comparing the amplitude variance of the motion amplitude with a preset detection threshold to determine the target user's motion state.

[0059] For example, a pulsed coherent radar (PCR) is first used to transmit RF signals and capture reflections modulated by respiration and heartbeat. PCR can achieve high accuracy over relatively long distances. The transmitted signal of PCR is as follows:

[0060]

[0061] in, It is a rectangular pulse. It's frequency. For time indexing, It is phase. It is a pulse signal that alternates between 0 and 1. The signal received by PCR is as follows:

[0062]

[0063] in, Indicates the channel response. It's a delay. It's noise. This is indexed by time. The output of PCR is IQ data, which can be viewed as an extension of the envelope data. IQ data is typically represented as complex numbers, where the real part represents the amplitude of the radar signal and the imaginary part represents the phase of the radar signal. Let... Represents IQ data, where a and b It is a real number. It is the imaginary unit. For two consecutive IQ data samples, the motion between the two pulses is calculated based on their phase difference:

[0064]

[0065]

[0066] in, It is the phase of the signal. It's the wavelength. It is in time t Displacement distance at that location The real part of the IQ data represents the amplitude information of the signal. The imaginary part of the IQ data represents the phase information of the signal. Chest movement caused by breathing and heartbeat is a complex motion, including chest expansion, contraction, and vibration; the phase change of the signal is relative to these complex motions.

[0067] The range of chest movement caused by breathing in adults is 4 to 12 mm, while the range of movement caused by heartbeat is approximately 0.5 mm. Slight seated movements (including leaning forward and backward, leg shaking, and arm movement) do not exceed 30 cm. Two detection thresholds are set to 2 and 30 cm. If the amplitude variance is less than 2 cm, the user is considered stationary, and a stationary heartbeat segmentation algorithm is used; if the amplitude variance is greater than 2 cm but less than 30 cm, the user is considered to be performing seated movement, and a dynamic heartbeat segmentation algorithm is used; if the amplitude variation is greater than 30 cm, the user is considered to be performing significant movement, and the radio frequency signal is discarded.

[0068] In some embodiments, when the target user is in a static state, a bandpass filter is used to process the radio frequency signal. The bandpass filter filters out breathing and other low-frequency noise signals, retaining only the heartbeat frequency component, making the heartbeat waveform clearer. Specifically, step S102, based on the target user's motion state, reconstructs the target user's heartbeat waveform and extracts the heartbeat signal, including: combining the phase differences of the target user's IQ data at various times to obtain a phase difference sequence signal; performing a fast Fourier transform on the phase difference sequence signal to construct a bandpass filter to filter the radio frequency signal; performing an inverse Fourier transform on the filtered radio frequency signal to obtain the target user's heartbeat waveform, and extracting the heartbeat signal based on the heartbeat waveform.

[0069] For example, firstly, the time phase differences in the IQ data are... By combining the signals, a phase difference sequence signal is obtained. Then, for the phase difference sequence signal Perform a Fast Fourier Transform (FFT) and select the 0.8–3.6 Hz frequency band to determine the set of frequencies within this band. and the frequency of its maximum amplitude A custom narrowband bandpass filter is created by selecting the maximum amplitude and two adjacent frequency points to remove interference from other frequencies. Finally, an inverse fast fourier transform (IFFT) is performed on the filtered frequency domain data to obtain the filtered time domain data, which is the heartbeat waveform.

[0070] Based on this embodiment, step S103 involves segmenting the target user's heartbeat signal, including: reversing the phase difference sequence signal, traversing the phase difference sequence signal, determining the peak function of each point, and generating a peak set; traversing the peak set by sequential index, sorting and filtering the points in the peak set, and dividing them into multiple segments to form a heartbeat signal segment set.

[0071] For example, first, initialize the peak set. Empty, and the phase difference sequence signal Reverse. Traverse the phase difference sequence signal. Calculate the peak function at each point. = Used to determine points Is it A peak value is defined within a window of points. (Determine...) The condition for whether it is a true peak is ,in and arrays The mean and standard deviation, h This is a constant parameter, set to 3. Significant peaks are selected and added to the peak set. T For distances less than k Adjacent peak values ​​are selected, the larger value is retained, and the smaller value is removed. Finally, the processed peak signal is divided into multiple segments to form a heartbeat signal segment set. S .

[0072] In some embodiments, when the target user is in a state of slight physical movement, white noise is added to the radio frequency signal to improve the extreme value distribution of the signal, thereby reducing the occurrence of mode aliasing. Then, by performing multiple empirical mode decompositions (EMDs) on the radio frequency signal and calculating the mean, a stable intrinsic mode function (IMF) is obtained, and the heartbeat signal is extracted through filtering. Specifically, step S102, based on the target user's motion state, reconstructs the target user's heartbeat waveform and extracts the heartbeat signal, including: combining the phase differences of the target user's IQ data at various times to obtain a phase difference sequence signal; adding white noise to the phase difference sequence signal and performing empirical mode decomposition to obtain an intrinsic mode function sequence; converting each intrinsic mode function sequence to the frequency domain to determine the dominant frequency of each intrinsic mode function sequence; determining the target user's heartbeat frequency range based on the dominant frequency of the intrinsic mode function sequence, and extracting the target user's heartbeat signal.

[0073] For example, firstly, the time phase differences in the IQ data are... By combining the signals, a phase difference sequence signal is obtained. Then, the initial white noise in the time domain... Perform a Fast Fourier Transform to obtain its spectrum. .Will Converted into a spectrum with sinusoidal amplitude. The specific formula is as follows:

[0074]

[0075] in, The sampling rate is represented by this formula, which ensures that the amplitude of the spectrum varies in the form of a sine wave, making the generated noise frequency-regular and helping to smooth the distribution of signal extrema during the decomposition process. Then, the adjusted spectrum... Performing an inverse Fourier transform yields the noise in the time domain. And added to the phase difference sequence signal Then, empirical mode decomposition is performed on the noisy signal to obtain the first... mSecondary decomposition results: Eigenmode functions Repeat the above steps. M Each time, different white noise is added to the decomposition, among which... M =1000. Calculate the ensemble mean of the IMF for each intrinsic mode function. conduct M The average of the results from all experiments yields the final IMF:

[0076]

[0077] This step ensures that each IMF reflects the true frequency characteristics of the signal, avoiding mode aliasing issues. Finally, an FFT analysis is performed on each IMF to identify those whose frequencies primarily fall within the range of 0.8 Hz to 3.6 Hz (i.e., the heartbeat frequency range), and these IMFs are denoted as [IMF name missing]. This refers to the heartbeat signal.

[0078] Based on this embodiment, step S103 involves segmenting the heartbeat signal of the target user, including: setting a standard template for the heartbeat signal; using a dynamic programming method, with the goal of minimizing the error between the signal segment of the heartbeat signal and the standard template, iteratively updating the standard template until the iteration converges, thereby obtaining the segmentation result of the heartbeat signal and the target template.

[0079] For example, first, initialize the standard template and segmentation parameters. Set the standard template... Set it as the zero vector, and set the iteration counter. Then, update the segmentation results. Using dynamic programming, based on the current template... Heartbeat sequence Perform segmentation to obtain the segmentation results. Update the template again. Based on the latest segmentation results, the template is recalculated. Repeat the above steps until the segmentation result is obtained. S and templates u Convergence. Upon convergence, the final segmentation result is returned. S and templates u .

[0080] In some embodiments, step S104, extracting physiological features from the segmented heartbeat signal of the target user and classifying the target user based on the physiological features to obtain a classification result, includes: extracting physiological features from the segmented heartbeat signal; calling a pre-trained classification model to classify the target user according to the extracted physiological features to obtain a classification result.

[0081] In this embodiment, physiological features mainly include heart rate variability (HRV) and heart rate cycle. These features will be used as input to the classification model. Based on the extracted features, a disease classification subsystem assesses the user's risk of myocardial infarction. The classification module uses the trained model to map the input features to a healthy or myocardial infarction state, ultimately outputting the detection result. If the detection result indicates a risk of myocardial infarction, further medical examination will be suggested.

[0082] For example, first, heart rate variability characteristics are calculated, which are excellent at distinguishing healthy individuals from MI patients, including:

[0083] Time domain characteristics:

[0084] SDNN: Standard deviation of normal heartbeat intervals, representing the overall variation in heartbeat intervals.

[0085] RMSSD: Root mean square of the difference between adjacent heartbeats, used to measure the fluctuation of heartbeat intervals.

[0086] NN50 and pNN50: represent the number of times and the percentage of consecutive heartbeats with an interval of more than 50 milliseconds, respectively.

[0087] Frequency domain characteristics: including low-frequency (LF) and high-frequency (HF) energy, as well as the LF / HF ratio, these metrics are calculated through power spectrum estimation.

[0088] Due to the small sample size, directly using all features might lead to overfitting. Therefore, L1-SVM was used as the classification model, automatically selecting the features most correlated with myocardial infarction (MI), removing redundant features, and optimizing model performance. The selected features and their importance levels are as follows: SDNN: 26:4%; RMSSD: 15:3%; NN50: 4:7%; PNN50: 2:9%. Finally, the classification model was used to detect myocardial infarction and obtain the detection results for the target user.

[0089] In summary, unlike traditional electrocardiograms (ECG) or blood tests, this method achieves completely contactless detection. This means users do not need to wear sensors, connect wires, or undergo invasive procedures such as blood tests, thus avoiding physical discomfort. Because it does not require direct contact with the human body, the system can monitor heart rate anytime in everyday environments, making it particularly suitable for home use. Users can continuously and for extended periods monitor their heart health at home, detecting early signs of myocardial infarction (MI), thereby significantly increasing the likelihood of disease prevention.

[0090] Furthermore, traditional radio frequency monitoring systems require users to remain stationary for accurate heart rate detection. This method innovatively designs a signal processing algorithm that tolerates slight physical activity. These activities include reading, eating, and browsing the internet, during which users may exhibit slight forward or backward leaning of the torso, or minor limb movements. This method not only enhances signal stability but also significantly improves the system's detection accuracy under slight movement conditions, making it more closely resemble real-life scenarios. For example, the system can still monitor heart rate changes in real time while a user is watching TV or working. This adaptability provides significant convenience for home and personal health monitoring.

[0091] Furthermore, this method utilizes commercially available pulse coherent radar technology. This radar equipment is inexpensive and requires no customized hardware support, giving the system a significant cost advantage. The system's affordability and ease of use make it accessible to ordinary home users, and the lack of complex installation or setup makes it ideal for home applications. Users simply install the device in their room, and the system continuously monitors their cardiac health, providing a low-cost solution for the early detection of myocardial infarction.

[0092] The present invention also provides a non-contact myocardial infarction detection device. The non-contact myocardial infarction detection device provided by the present invention will be described below. The non-contact myocardial infarction detection device described below can be referred to in correspondence with the non-contact myocardial infarction detection method described above. Figure 2 This is a structural block diagram of the non-contact myocardial infarction detection device provided by the present invention, as shown below. Figure 2 As shown, the device includes:

[0093] The acquisition module 201 is used to acquire the radio frequency signals fed back by the target user and determine the motion state of the target user based on the radio frequency signals; the motion state includes a static state and a slight body movement state.

[0094] Extraction module 202 is used to recover the heartbeat waveform of the target user based on the target user's motion state and extract the heartbeat signal;

[0095] The segmentation module 203 is used to segment the heartbeat signal of the target user;

[0096] The detection module 204 is used to extract physiological features from the segmented heartbeat signal of the target user and classify the target user based on the physiological features of the target user to obtain the classification result.

[0097] In use, this device first acquires the radio frequency (RF) signal from the target user, then determines whether the user is at rest or in a state of slight body movement. Slight body movement refers to tolerable minor physical activity during the detection process, such as reading, eating, or browsing the internet. During these activities, the user may exhibit slight forward or backward leaning of the trunk, or small movements of the limbs. Next, the extraction module 202 reconstructs the target user's heartbeat waveform and extracts the heartbeat signal based on their movement state. Then, the segmentation module 203 further segments the extracted heartbeat signal to extract specific information for each heartbeat cycle. Finally, the detection module 204 extracts the target user's physiological characteristics from the segmented heartbeat signal and classifies the user based on these characteristics to determine if they are at risk of myocardial infarction. Current detection technologies only achieve high accuracy when the target user remains at rest. In the aforementioned process, different processing of the radio frequency signal is applied according to the target user's motion state. This not only enhances the stability of the radio frequency signal but also significantly improves the detection accuracy under mild motion conditions, making it more closely resemble real-life scenarios. For example, users can still monitor their heart rate changes in real time while watching TV or working. This adaptability provides great convenience for family and personal health monitoring and solves the problem of poor accuracy in myocardial infarction detection in existing related technologies.

[0098] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other via the communication bus 304. The processor 301 can call logical instructions in the memory 303 to execute a non-contact myocardial infarction detection method, which includes:

[0099] The radio frequency signals fed back by the target user are collected, and the motion state of the target user is determined based on the radio frequency signals; the motion state includes a static state and a slight body movement state.

[0100] Based on the target user's movement status, the target user's heartbeat waveform is recovered and the heartbeat signal is extracted;

[0101] The heartbeat signal of the target user is segmented and processed;

[0102] Physiological features are extracted from the segmented heartbeat signals of the target users, and the target users are classified based on these physiological features to obtain the classification results.

[0103] Furthermore, the logical instructions in the aforementioned memory 303 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the 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 cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0104] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to perform the non-contact myocardial infarction detection method provided by the above methods, the method comprising:

[0105] The radio frequency signals fed back by the target user are collected, and the motion state of the target user is determined based on the radio frequency signals; the motion state includes a static state and a slight body movement state.

[0106] Based on the target user's movement status, the target user's heartbeat waveform is recovered and the heartbeat signal is extracted;

[0107] The heartbeat signal of the target user is segmented and processed;

[0108] Physiological features are extracted from the segmented heartbeat signals of the target users, and the target users are classified based on these physiological features to obtain the classification results.

[0109] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the non-contact myocardial infarction detection method provided by the methods described above, the method comprising:

[0110] The radio frequency signals fed back by the target user are collected, and the motion state of the target user is determined based on the radio frequency signals; the motion state includes a static state and a slight body movement state.

[0111] Based on the target user's movement status, the target user's heartbeat waveform is recovered and the heartbeat signal is extracted;

[0112] The heartbeat signal of the target user is segmented and processed;

[0113] Physiological features are extracted from the segmented heartbeat signals of the target users, and the target users are classified based on these physiological features to obtain the classification results.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A non-contact myocardial infarction detection device, characterized in that, include: The acquisition module is used to acquire radio frequency signals fed back by the target user and determine the motion state of the target user based on the radio frequency signals; the motion state includes a static state and a slight body movement state; The extraction module is used to recover the heartbeat waveform of the target user based on the target user's movement state and extract the heartbeat signal; The segmentation module is used to segment the heartbeat signal of the target user; The detection module is used to extract physiological features from the segmented heartbeat signal of the target user, and classify the target user based on the physiological features of the target user to obtain the classification result; Acquiring radio frequency signals fed back by the target user, and determining the motion state of the target user based on the radio frequency signals, including: Radio frequency signals modulated by the breathing and heartbeat of the target user are acquired and transmitted by pulse coherent radar; the radio frequency signals include several consecutive IQ data. The motion amplitude between the two pulses is determined based on the phase difference between two consecutive IQ data. The amplitude variance of the motion amplitude is compared with a preset detection threshold to determine the motion state of the target user; When the target user is in a static state, the heartbeat waveform of the target user is recovered based on the target user's movement state, and the heartbeat signal is extracted, including: The phase differences of the IQ data of the target user at various times are combined to obtain a phase difference sequence signal; A fast Fourier transform is performed on the phase difference sequence signal to construct a bandpass filter for filtering the radio frequency signal; The filtered radio frequency signal is subjected to inverse Fourier transform to obtain the heartbeat waveform of the target user, and the heartbeat signal is extracted based on the heartbeat waveform; When the target user is in a state of slight body movement, the heartbeat waveform of the target user is recovered based on the target user's movement state, and the heartbeat signal is extracted, including: The phase differences of the IQ data of the target user at various times are combined to obtain a phase difference sequence signal; White noise is added to the phase difference sequence signal, and empirical mode decomposition is performed to obtain the intrinsic mode function sequence; Transform each of the intrinsic mode function sequences to the frequency domain to determine the dominant frequency of each of the intrinsic mode function sequences; The heart rate range of the target user is determined based on the dominant frequency of the intrinsic mode function sequence, and the heart rate signal of the target user is extracted. When the target user is in a static state, the target user's heartbeat signal is segmented, including: The phase difference sequence signal is reversed and iterated through to determine the peak function at each point, generating a peak set. The peak set is traversed sequentially by index, the points in the peak set are sorted and filtered, and divided into multiple segments to form a heartbeat signal segment set; When the target user is in a static state, the target user's heartbeat signal is segmented, including: Set a standard template for heartbeat signals; Using a dynamic programming approach, with the goal of minimizing the error between the signal segment of the heartbeat signal and the standard template, the standard template is iteratively updated until the iteration converges, thus obtaining the segmentation result of the heartbeat signal and the target template.

2. The non-contact myocardial infarction detection device according to claim 1, characterized in that, Physiological features are extracted from the segmented heartbeat signal of the target user, and the target user is classified based on these physiological features to obtain a classification result, including: Physiological features are extracted from the segmented heartbeat signal; The pre-trained classification model is invoked to classify the target user based on the extracted physiological features, and the classification result is obtained.

3. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the detection method of the non-contact myocardial infarction detection device as described in any one of claims 1 to 2.

4. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the detection method of the non-contact myocardial infarction detection device as described in any one of claims 1 to 2.

Images