Anesthesia sedation state monitoring system based on visual micro-expression recognition and physiological parameters

Abstract

The application discloses a kind of based on visual micro-expression recognition and physiological parameter's anesthetic sedation state monitoring system, fusion face visual expression and multiple physiological parameters are constructed multimodal comprehensive monitoring system, specifically by analyzing the change characteristics of patient facial micro-expression and the marginal spectrum of deep coding continuous feature and eeg frequency domain energy distribution and the energy proportion analysis of each waveband in specific frequency band, while combining blood pressure and blood oxygen real-time parameters to obtain comprehensive analysis result, the application constructs multimodal fusion system to realize accurate, real-time, personalized evaluation, improve individual difference accurate reflection dose level, obtain accurate detection anesthetic sedation state result.

Description

Technical Field

[0001] This invention belongs to the field of medical intelligent monitoring technology, and in particular relates to an anesthesia and sedation state monitoring system based on visual micro-expression recognition and physiological parameters. Background Technology

[0002] Accurate monitoring of anesthesia and sedation is crucial for surgical safety and patient prognosis. Monitoring based on physiological parameters has long been the traditional core technology approach, mainly achieved through three methods: First, monitoring of EEG signals, represented by BIS and entropy index, which has high specificity but poor adaptability to drug combinations and is easily interfered with; second, monitoring of circulatory and respiratory parameters such as heart rate and MAP, which has extremely low specificity and is prone to misjudgment due to individual differences and various factors; and third, monitoring of drug metabolism concentration, which can only reflect the dosage level and cannot reflect individual differences in drug efficacy, thus having limited reference value.

[0003] Existing single-parameter-dependent methods share common drawbacks: poor individual adaptability, and the inability of uniform standards to cover all clinical scenarios; signals are easily affected by surgical procedures and electromagnetic interference, resulting in lag in reliability and dynamic response, making it difficult to reflect instantaneous changes in sedation status in a timely manner. Even with multi-parameter joint monitoring, manual integration and analysis are still required, increasing the physician's workload and making them prone to errors due to human judgment, leading to incomplete control of risks related to intraoperative awareness and excessive anesthesia. Therefore, existing methods have room for improvement in accuracy, anti-interference capabilities, and individual adaptability, and there is an urgent need to introduce new monitoring dimensions and construct a multimodal fusion system to achieve accurate, real-time, and personalized assessment.

[0004] In view of this, the present invention is hereby proposed. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an anesthesia and sedation status monitoring system based on visual micro-expression recognition and physiological parameters, in order to improve the accuracy of individual differences in reflecting dosage levels and accurately detect anesthesia and sedation status.

[0006] The first aspect of this invention provides an anesthesia and sedation state monitoring system based on visual micro-expression recognition and physiological parameters, comprising: The user login and monitoring activation unit verifies the personal information of users with sedation and intoxication monitoring permissions. After successful login, users can select to start the monitoring module. The monitoring module includes a visualization sub-module that displays the patient's status. The visualization module contains the patient's basic information: age, height, weight, basic information on allergic drugs, and physiological parameters such as electrocardiogram, blood pressure, EEG, respiratory rate, and SpO2. The monitoring module further includes a facial analysis submodule, which is used for real-time, objective, and continuous assessment of sedation status during anesthesia based on facial data; The facial analysis submodule includes a facial data acquisition unit. It is used for acquiring facial micro-expression data. Specifically, in this invention, a multi-pose camera is used for video capture, and a detector locates the facial bounding box in the frame. The detector detects facial key points, specifically including the contours of eyebrows, eyes, nose, and mouth. In this invention, the detector can use Dlib, MTCNN, or other deep learning-based facial feature points; no particular limitation is made here.

[0007] The facial analysis submodule also includes a facial data normalization unit. Based on the position of both eyes, it rotates the face to a horizontal position through affine transformation, and crops the facial region by expanding it outward by a certain proportion according to the bounding box or key points. The facial image is scaled to a preset size, preferably 260x260 pixels in this invention; pixel values ​​are normalized using ImageNet, and after alignment, a standard facial image Image(t) is output.

[0008] Facial micro-expression analysis is performed based on facial data processed by normalized units. Specifically, action unit (AU) extraction and analysis are performed using the following algorithm, the formula of which is as follows:

[0009] The parameters have the following meanings: For the true value, For predicted values, The mean of the true values; The mean of the predicted values, : is the standard deviation of the true value; This represents the standard deviation of the predicted values.

[0010] Each state during the surgery is framed at a fixed frequency and processed through a facial data normalization unit to output a time series matrix S of AU intensity for different frames, with dimensions [T, N].

[0011]

[0012] T: number of time steps, N: number of AUs. Each element S[t, i] in the matrix represents the intensity of the i-th AU at time t.

[0013] The time-series matrix S of AU intensity is mapped to a clinically meaningful indicator, using the mean value of the patient's AU intensity over several minutes in a resting state before surgery as the original AU intensity. Each element in the time series matrix S is individually normalized to its AU intensity using an algorithm. The algorithm formula is as follows:

[0014] At each current time t, a normalized, multimodal context window data X is obtained, with dimensions [W, M].

[0015]

[0016] W: The number of time steps within the window.

[0017] M: Feature dimension (N AUs + K physiological parameters).

[0018] Furthermore, the transformer(x) is processed using the Transformer Encoder sequence modeling method, outputting a vector H.

[0019] The following formula is used to calculate the vector to determine whether the patient's anesthesia status is normal:

[0020] By calculating each element in the vector, a new continuous judgment vector lsm is obtained.

[0021]

[0022] Furthermore, the monitoring module of the present invention further includes an electroencephalogram (EEG) analysis submodule. The patient wears EEG electrodes, and EEG signals are acquired via an anesthesia monitoring device. The acquired wavebands are primarily... Wave, Wave, Wave, Wave, The signals from each waveband acquired are processed using the following algorithm steps, in order to... Taking a wave as an example, the processing steps are as follows: Step 1: Locate the original signal Find the highest value among all the extreme points. and minimum value Calculate the mean: The formula is as follows:

[0023] Extracting candidate IMFs: δF(t), the formula is as follows:

[0024] Repeat step one above to obtain all IMF vectors IMFS:

[0025] The algorithm for transforming the vector δIMFS to obtain the instantaneous amplitude δAi(t) and frequency δFi(t) is as follows:

[0026]

[0027] Where t is the time variable, τ is the integral variable, and dτ is the calculus in τ. Step 2: The marginal spectrum of the frequency domain energy distribution of the delta wave can be calculated using the instantaneous amplitude δAi(t) and frequency δFi(t). The algorithm formula is as follows:

[0028] Where N is the number of δIMFS vectors, and δ() is the Dirac function.

[0029] Step 3: Repeat steps 1 and 2 to calculate... Wave, Wave, Wave, Marginal spectrum of wave frequency domain energy distribution , , , The energy proportion of each band in a specific frequency band can be calculated through the marginal spectrum.

[0030]

[0031]

[0032]

[0033]

[0034] Based on the proportion of each band, if Wave, A higher proportion of wave amplitude indicates that the patient is awake. Wave, A higher proportion of waves indicates that the patient is over-anesthetized.

[0035] Furthermore, the monitoring system of the present invention further includes a comprehensive analysis unit, which determines the current sedation status of the patient through the output of the facial analysis submodule, the output of the electroencephalogram analysis submodule, blood pressure, and blood oxygen concentration SpO2.

[0036] By analyzing key parameters such as facial expressions, electroencephalogram (EEG), blood pressure, and blood oxygen saturation, the system will issue warnings. An orange warning will be given for insufficient sedation, and a red warning will be given for excessive sedation, to alert the anesthesiologist to take immediate action. The warnings are as follows: If the blood oxygen concentration SpO2 gradually decreases, accompanied by a continuous decrease in the vector lms value, it may be an immediate red alert caused by excessive sedation. If the patient's blood pressure continues to rise, accompanied by a continuous increase in the vector lms value, a red alert will be issued immediately. If the patient's blood pressure and heart rate are significantly elevated, accompanied by a high frequency of fluctuations in the vector lms within a certain range, and wave or wave or If the proportion of waves is high, an orange alert will be issued; If the wave ratio is high and the vector lms value is continuously decreasing, it may be an immediate red alert caused by excessive sedation. A red alert is issued if all parameters continue to decline.

[0037] Furthermore, in a second aspect, the present invention provides an electronic device, characterized in that it includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to realize the functions of the monitoring system described above.

[0038] Furthermore, in a third aspect, the present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the functions of the aforementioned monitoring system.

[0039] Compared with the prior art, the present invention has the following technical effects: To address the technical deficiencies in existing technologies, an anesthesia and sedation status monitoring system based on visual micro-expression recognition and physiological parameters is proposed. Specifically, it analyzes the deep coding features of continuous changes in the patient's facial micro-expressions, the marginal spectrum of the energy distribution in the frequency domain of electroencephalography (EEG), and the energy proportion analysis of each band in a specific frequency band. Combined with real-time blood pressure and blood oxygen parameters, a comprehensive analysis result is obtained. This invention constructs a multimodal fusion system to achieve accurate, real-time, and personalized assessment, improves the accuracy of individual differences in reflecting dosage levels, and obtains accurate results for detecting anesthesia and sedation status. Attached Figure Description

[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0041] Figure 1 This is a diagram illustrating the architecture of the monitoring system according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0042] 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. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0043] Reference Appendix Figure 1 The first aspect provides a monitoring system for anesthesia and sedation status based on visual micro-expression recognition and physiological parameters, including: The user login and monitoring activation unit verifies the personal information of users with sedation and intoxication monitoring permissions. After successful login, users can select to start the monitoring module. The monitoring module includes a visualization sub-module that displays the patient's status. The visualization module contains the patient's basic information: age, height, weight, basic information on allergic drugs, and physiological parameters such as electrocardiogram, blood pressure, EEG, respiratory rate, and SpO2. The monitoring module further includes a facial analysis submodule, which is used for real-time, objective, and continuous assessment of sedation status during anesthesia based on facial data; The facial analysis submodule includes a facial data acquisition unit. It is used for acquiring facial micro-expression data. Specifically, in this invention, a multi-pose camera is used for video capture, and a detector locates the facial bounding box in the frame. The detector detects facial key points, specifically including the contours of eyebrows, eyes, nose, and mouth. In this invention, the detector can use Dlib, MTCNN, or other deep learning-based facial feature points; no particular limitation is made here.

[0044] The facial analysis submodule also includes a facial data normalization unit. Based on the position of both eyes, it rotates the face to a horizontal position through affine transformation, and crops the facial region by expanding it outward by a certain proportion according to the bounding box or key points. The facial image is scaled to a preset size, preferably 260x260 pixels in this invention; pixel values ​​are normalized using ImageNet, and after alignment, a standard facial image Image(t) is output.

[0045] Facial micro-expression analysis is performed based on facial data processed by normalized units. Specifically, action unit (AU) extraction and analysis are performed using the following algorithm, the formula of which is as follows:

[0046] The parameters have the following meanings: For the true value, For predicted values, The mean of the true values; The mean of the predicted values, : is the standard deviation of the true value; This represents the standard deviation of the predicted values.

[0047] Each state during the surgery is framed at a fixed frequency and processed through a facial data normalization unit to output a time series matrix S of AU intensity for different frames, with dimensions [T, N].

[0048]

[0049] T: number of time steps, N: number of AUs. Each element S[t, i] in the matrix represents the intensity of the i-th AU at time t.

[0050] The time-series matrix S of AU intensity is mapped to a clinically meaningful indicator, using the mean value of the patient's AU intensity over several minutes in a resting state before surgery as the original AU intensity. Each element in the time series matrix S is individually normalized to its AU intensity using an algorithm. The algorithm formula is as follows:

[0051] At each current time t, a normalized, multimodal context window data X is obtained, with dimensions [W, M].

[0052]

[0053] W: The number of time steps within the window.

[0054] M: Feature dimension (N AUs + K physiological parameters).

[0055] Furthermore, the transformer(x) is processed using the Transformer Encoder sequence modeling method, outputting a vector H.

[0056] The following formula is used to calculate the vector to determine whether the patient's anesthesia status is normal:

[0057] By calculating each element in the vector, a new continuous judgment vector lsm is obtained.

[0058]

[0059] Furthermore, the monitoring module of the present invention further includes an electroencephalogram (EEG) analysis submodule. The patient wears EEG electrodes, and EEG signals are acquired via an anesthesia monitoring device. The acquired wavebands are primarily... Wave, Wave, Wave, Wave, The signals from each waveband acquired are processed using the following algorithm steps, in order to... Taking a wave as an example, the processing steps are as follows: Step 1: Locate the original signal Find the highest value among all the extreme points. and minimum value Calculate the mean: The formula is as follows:

[0060] Extracting candidate IMFs: δF(t), the formula is as follows:

[0061] Repeat step one above to obtain all IMF vectors IMFS:

[0062] The algorithm for transforming the vector δIMFS to obtain the instantaneous amplitude δAi(t) and frequency δFi(t) is as follows:

[0063]

[0064] Where t is the time variable, τ is the integral variable, and dτ is the calculus in τ. Step 2: The marginal spectrum of the frequency domain energy distribution of the delta wave can be calculated using the instantaneous amplitude δAi(t) and frequency δFi(t). The algorithm formula is as follows:

[0065] Where N is the number of δIMFS vectors, and δ() is the Dirac function.

[0066] Step 3: Repeat steps 1 and 2 to calculate... Wave, Wave, Wave, Marginal spectrum of wave frequency domain energy distribution , , , The energy proportion of each band in a specific frequency band can be calculated through the marginal spectrum.

[0067]

[0068]

[0069]

[0070]

[0071] Based on the proportion of each band, if Wave, A higher proportion of wave amplitude indicates that the patient is awake. Wave, A higher proportion of waves indicates that the patient is over-anesthetized.

[0072] Furthermore, the monitoring system of the present invention further includes a comprehensive analysis unit, which determines the current sedation status of the patient through the output of the facial analysis submodule, the output of the electroencephalogram analysis submodule, blood pressure, and blood oxygen concentration SpO2.

[0073] By analyzing key parameters such as facial expressions, electroencephalogram (EEG), blood pressure, and blood oxygen saturation, the system will issue warnings. An orange warning will be given for insufficient sedation, and a red warning will be given for excessive sedation, to alert the anesthesiologist to take immediate action. The warnings are as follows: If the blood oxygen concentration SpO2 gradually decreases, accompanied by a continuous decrease in the vector lms value, it may be an immediate red alert caused by excessive sedation. If the patient's blood pressure continues to rise, accompanied by a continuous increase in the vector lms value, a red alert will be issued immediately. If the patient's blood pressure and heart rate are significantly elevated, accompanied by a high frequency of fluctuations in the vector lms within a certain range, and wave or wave or If the proportion of waves is high, an orange alert will be issued; If the wave ratio is high and the vector lms value is continuously decreasing, it may be an immediate red alert caused by excessive sedation. A red alert is issued if all parameters continue to decline.

[0074] Furthermore, in a second aspect, the present invention provides an electronic device, characterized in that it includes a processor and a memory, the memory storing computer-executable instructions executable by the processor, the processor executing the computer-executable instructions to realize the functions of the monitoring system described above.

[0075] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 100 includes: a processor 110, a memory 111, a bus 112, and a communication interface 113. The processor 110, the communication interface 113, and the memory 111 are connected through the bus 112. The processor 110 is used to execute executable modules, such as computer programs, stored in the memory 111.

[0076] The memory 111 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 113 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0077] Bus 112 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0078] The memory 111 is used to store programs. After receiving an execution instruction, the processor 110 executes the program. The method executed by the device for defining the flow process disclosed in any of the foregoing embodiments of the present invention can be applied to the processor 110 or implemented by the processor 110.

[0079] Processor 110 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 110 or by instructions in software form. Processor 110 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 111, and processor 110 reads the information in memory 111 and, in conjunction with its hardware, completes the steps of the above method.

[0080] Furthermore, in a third aspect, the present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the functions of the aforementioned monitoring system.

[0081] The computer program product of the readable storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the foregoing method embodiments. For specific implementation, please refer to the foregoing method embodiments, which will not be repeated here.

[0082] It should be noted that the terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of this application. As shown in this specification, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitations, an element defined by the phrase "comprising an..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0083] It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," "linked," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0084] 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring system for anesthesia and sedation status based on visual micro-expression recognition and physiological parameters, characterized in that, include: The user login and monitoring activation unit verifies the personal information of users with the authority to monitor intoxicated and sedative states and allows them to log in. After successful login verification, select to start the monitoring module; The monitoring module further includes a facial analysis submodule, which is used to continuously assess the sedation state during anesthesia based on facial data. The action unit (AU) is extracted and analyzed using the following algorithm, and frames are drawn at a fixed frequency. All frames are processed through a facial data normalization unit to output a time series matrix S of AU intensity for different frames. A new continuous judgment vector lsm is then obtained through a Transformer Encoder. The monitoring module further includes an EEG analysis submodule, which calculates... Wave, Wave, Wave, Marginal spectrum of wave frequency domain energy distribution , , , The energy percentage of each band in a specific frequency band can be calculated through the marginal spectrum; The monitoring system further includes a comprehensive analysis unit, which determines the current sedation status of the patient through the output of the facial analysis submodule, the output of the electroencephalogram (EEG) analysis submodule, blood pressure, and blood oxygen saturation (SpO2).

2. The monitoring system according to claim 1, characterized in that... The EEG analysis submodule is specifically used to process the signals of each acquired band using the following algorithm steps: Step 1: Find the original signal Find the highest value among all the extreme points. and minimum value Calculate the mean: Repeat step one above to obtain all IMF vectors (IMFS). Step 2: The marginal spectrum of the frequency domain energy distribution of the δ wave can be calculated using the instantaneous amplitude δAi(t) and frequency δFi(t). Step 3: Repeat steps 1 and 2 to calculate... Wave, Wave, Wave, Marginal spectrum of wave frequency domain energy distribution , , , The energy percentage of each band in a specific frequency band can be calculated using the marginal spectrum.

3. The monitoring system according to claim 1, characterized in that... The comprehensive analysis unit determines the patient's current sedation status through the output of the facial analysis submodule, the output of the electroencephalogram (EEG) analysis submodule, blood pressure, and SpO2 blood oxygen concentration. The system will issue warnings: an orange warning for insufficient sedation and a red warning for excessive sedation, to remind the anesthesiologist to take immediate measures.

4. The monitoring system according to claim 3, characterized in that, The warning judgment is as follows: If the blood oxygen concentration SpO2 gradually decreases, accompanied by a continuous decrease in the vector lms value, it may be an immediate red alert caused by excessive sedation. If the patient's blood pressure continues to rise, accompanied by a continuous increase in the vector lms value, a red alert will be issued immediately. If the patient's blood pressure and heart rate are significantly elevated, accompanied by a high frequency of fluctuations in the vector lms within a certain range, and wave or wave or If the proportion of waves is high, an orange alert will be issued; If the wave ratio is high and the vector lms value is continuously decreasing, it may be an immediate red alert caused by excessive sedation. A red alert is issued if all parameters continue to decline.

5. The monitoring system according to claim 1, characterized in that... In the facial analysis submodule Facial micro-expression analysis is performed on data processed by facial data normalization units. Specifically, action unit (AU) extraction and analysis are performed using the following algorithm, the formula of which is as follows: The parameters have the following meanings: For the true value, For predicted values, The mean of the true values; The mean of the predicted values, : is the standard deviation of the true value; The standard deviation of the predicted values; Each state during the surgery is framed at a fixed frequency and processed through a facial data normalization unit to output a time series matrix S of AU intensity for different frames, with dimensions [T, N]. T: number of time steps, N: number of AUs, and each element S[t, i] in the matrix represents the intensity of the i-th AU at time t.

6. The monitoring system according to claim 3, characterized in that, Furthermore, the transformer(x) is processed using the Transformer Encoder sequence modeling method, outputting a vector H: The following formula is used to calculate the vector to determine whether the patient's anesthesia status is normal: By calculating each element in the vector, a new continuous judgment vector lsm is obtained: 。 7. The monitoring system according to claim 2, characterized in that... The signals of each band acquired by the EEG analysis sub-model are processed using the following algorithm steps: Step 1: Locating the original signal Find the highest value among all the extreme points. and minimum value Calculate the mean: The formula is as follows: Extracting candidate IMFs: δF(t), the formula is as follows: Repeat step one above to obtain all IMF vectors IMFS: The algorithm for transforming the vector δIMFS to obtain the instantaneous amplitude δAi(t) and frequency δFi(t) is as follows: Where t is the time variable, τ is the integral variable, and dτ is the calculus in τ. Step 2: The marginal spectrum of the frequency domain energy distribution of the delta wave can be calculated using the instantaneous amplitude δAi(t) and frequency δFi(t). The algorithm formula is as follows: Where N is the number of δIMFS vectors, and δ() is the Dirac function; Step 3: Repeat steps 1 and 2 to calculate... Wave, Wave, Wave, Marginal spectrum of wave frequency domain energy distribution , , , The energy proportion of each band in a specific frequency band can be calculated through the marginal spectrum. 。 8. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the functions of the monitoring system according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the functions of the monitoring system according to any one of claims 1 to 7.

Images