CN114041786B - Ballistocardiogram signal detection method, ballistocardiogram signal detection device and ballistocardiogram signal detection equipment - Google Patents
Ballistocardiogram signal detection method, ballistocardiogram signal detection device and ballistocardiogram signal detection equipment Download PDFInfo
- Publication number
- CN114041786B CN114041786B CN202210024167.6A CN202210024167A CN114041786B CN 114041786 B CN114041786 B CN 114041786B CN 202210024167 A CN202210024167 A CN 202210024167A CN 114041786 B CN114041786 B CN 114041786B
- Authority
- CN
- China
- Prior art keywords
- ballistocardiogram
- signal
- signals
- unit
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 71
- 239000013598 vector Substances 0.000 claims abstract description 156
- 238000013441 quality evaluation Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 50
- 239000011159 matrix material Substances 0.000 claims abstract description 39
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 52
- 238000012545 processing Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 14
- 230000000877 morphologic effect Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000000737 periodic effect Effects 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 8
- 150000001875 compounds Chemical class 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000000747 cardiac effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 230000001020 rhythmical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 201000002859 sleep apnea Diseases 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 101150021336 torI gene Proteins 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1102—Ballistocardiography
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Cardiology (AREA)
- Dentistry (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application relates to a ballistocardiogram signal detection method, a ballistocardiogram signal detection device, ballistocardiogram signal detection equipment and a storage medium, wherein the method comprises the following steps: acquiring a ballistocardiogram signal of a user, and dividing the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length; performing multi-dimensional feature extraction on the plurality of ballistocardiogram unit signals to obtain multi-dimensional feature vectors; reconstructing the multi-dimensional eigenvectors to obtain an eigenvector matrix corresponding to the ballistocardiogram unit signals, and obtaining quality evaluation results corresponding to a plurality of ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model; responding to the detection instruction, wherein the detection instruction comprises ballistocardiogram signals of the user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results.
Description
Technical Field
The present invention relates to the field of signal processing technologies, and in particular, to a ballistocardiogram signal detection method, device, apparatus, and storage medium.
Background
Ballistocardiogram (BCG) describes the weak tremor of the body caused by the process of cardiac ejection and has been shown to be effective in monitoring the heart. The BCG signal is a weak force signal, and can be converted into an electric signal through the pressure sensor under the condition of non-direct contact, so that the interference-free collection of the vital sign signals of the user is realized.
However, due to the weak nature of BCG signals, the morphology of BCG signals is also susceptible to interference, and in practical application scenarios, the signals are subject to interference such as respiration, motion artifacts, sensor removals, environmental noise, and the like, resulting in inconsistent monitoring signal quality, and thus equivalent analysis and application cannot be performed. When the signal quality is poor, the physiological information contained in the signal form cannot be effectively extracted, so that the quality of the signal acquired by the ballistocardiogram is controlled, data with relatively better quality is selected from the signal, and the method has important significance on subsequent data processing and analysis (such as signal positioning, HRV analysis, sleep staging, sleep apnea and the like).
Disclosure of Invention
Based on the above, the invention provides a ballistocardiogram signal detection method, a ballistocardiogram signal detection device and a storage medium, wherein the ballistocardiogram signal is obtained from the ballistocardiogram signal according to a quality evaluation model by analyzing the form, time domain and nonlinear domain multidimensional characteristics of the ballistocardiogram signal, objective factors influencing the quality of the ballistocardiogram signal are fully considered, and the ballistocardiogram signal acquisition precision under a complex application scene is improved, and the technical method comprises the following steps:
in a first aspect, an embodiment of the present application provides a ballistocardiogram signal detection method, including the following steps:
the method comprises the steps of obtaining a ballistocardiogram signal of a user, and dividing the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length;
extracting the multidimensional characteristics of the ballistocardiogram unit signals to obtain multidimensional characteristic vectors, wherein the multidimensional characteristic vectors comprise morphological characteristic vectors, time domain characteristic vectors and nonlinear domain characteristic vectors;
reconstructing the multi-dimensional feature vector to obtain a feature vector matrix corresponding to the ballistocardiogram unit signal;
obtaining quality evaluation results corresponding to the plurality of ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model;
responding to a detection instruction, wherein the detection instruction comprises ballistocardiogram signals of a user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results.
In a second aspect, an embodiment of the present application provides a ballistocardiogram signal detection apparatus, including:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a ballistocardiogram signal of a user and dividing the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length;
the feature extraction module is used for performing multi-dimensional feature extraction on the ballistocardiogram unit signals to obtain multi-dimensional feature vectors, wherein the multi-dimensional feature vectors comprise morphological feature vectors, time domain feature vectors and nonlinear domain feature vectors;
the reconstruction module is used for reconstructing the multi-dimensional characteristic vector to obtain a characteristic vector matrix corresponding to the ballistocardiogram unit signal;
the evaluation module is used for obtaining quality evaluation results corresponding to the ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model;
and the processing module is used for responding to a detection instruction, the detection instruction comprises ballistocardiogram signals of a user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results.
In a third aspect, an embodiment of the present application provides a computer device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor; the computer program, when executed by the processor, implements the steps of the method of detecting a ballistocardiogram signal according to the first aspect.
In a fourth aspect, the present application provides a storage medium storing a computer program, which when executed by a processor implements the steps of the ballistocardiogram signal detection method according to the first aspect.
In this embodiment, a ballistocardiogram signal detection method, a ballistocardiogram signal detection device, a ballistocardiogram signal detection apparatus, and a storage medium are provided, and by analyzing the form, time domain, and nonlinear domain multidimensional features of the ballistocardiogram signal, a target ballistocardiogram signal is obtained from the ballistocardiogram signal according to a quality evaluation model, objective factors affecting the quality of the ballistocardiogram signal are fully considered, and accuracy and efficiency of obtaining the ballistocardiogram signal in a complex application scene are improved.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting ballistocardiogram signals according to a first embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of a method for detecting ballistocardiogram signals according to a second embodiment of the present disclosure;
fig. 3 is a schematic flowchart of S2 in the method for detecting a ballistocardiogram signal according to the first embodiment of the present application;
FIG. 4 is a schematic flow chart of a method for detecting ballistocardiogram signals according to a third embodiment of the present disclosure;
FIG. 5 is a schematic flow chart of a method for detecting ballistocardiogram signals according to a fourth embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a ballistocardiogram signal detection device according to a fifth embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device according to a sixth embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if/if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for detecting a ballistocardiogram signal according to a first embodiment of the present application, including the following steps:
s1: the method comprises the steps of obtaining a ballistocardiogram signal of a user, and dividing the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length.
The main execution subject of the ballistocardiogram signal detection method of the present application is a detection device (hereinafter referred to as a detection device) of the ballistocardiogram signal detection method.
In an alternative embodiment, the detection device may be a computer device, may be a server, or a server cluster formed by combining a plurality of computer devices.
The ballistocardiogram signal bcg (ballistocardiogram) is used for heart rate detection, heart rate variability monitoring, cardiac contractility and cardiac output variation monitoring, etc.
In an optional embodiment, the detection device may obtain the ballistocardiogram signal of the user by querying in a preset database, and in another optional embodiment, the detection device may obtain the human body microvibration signal of the user by using a piezoelectric sensor, convert the human body microvibration signal into a digital signal according to an analog-to-digital conversion module, analyze the digital signal according to a data processing module, and extract the physiological signal of the user from the digital signal; wherein, the physiological signal is a human body characteristic signal, including a ballistocardiogram signal;
since the energy of the physiological signal is mainly 0 to 50Hz, wherein the energy spectrum range of the ballistocardiogram signal is mainly 1 to 10Hz, the detection device can filter the physiological signal by means of filtering to separate the ballistocardiogram signal from the physiological signal.
The piezoelectric sensor can be a piezoelectric ceramic sensor, a piezoelectric film sensor and the like, can be placed below the heart in the lying position, and can also be placed below the pillow to acquire a human body micro-vibration signal of a user.
The analog-to-digital conversion module can adopt an external chip, and can also adopt a corresponding internal analog-to-digital conversion interface to convert the human body micro-vibration signal into a digital signal.
The data processing module may adopt a dsp (digital Signal processing) or an arm (advanced RISC machines) processor to analyze the digital Signal and extract the physiological Signal of the user from the digital Signal.
In this embodiment, a detection device obtains a ballistocardiogram signal of a user, performs windowing on the ballistocardiogram signal according to a preset signal length, and divides the ballistocardiogram signal into a plurality of ballistocardiogram unit signals, where the ballistocardiogram unit signals include a plurality of ts segments, and each segment has t × 1000 sampling points.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for detecting a ballistocardiogram signal according to a second embodiment of the present application, further including step S6, where the step S6 is performed before step S2 as follows:
s6: and preprocessing the ballistocardiogram signal, removing power frequency interference and baseline offset in the ballistocardiogram signal, and acquiring a processed ballistocardiogram signal.
In this embodiment, because aliasing breathing noise, power frequency noise, motion artifact and other interferences exist in the ballistocardiogram signal, the detection device removes the power frequency interference and baseline shift in the ballistocardiogram signal in a filtering manner, and obtains the processed ballistocardiogram signal.
S2: and extracting the multidimensional characteristics of the ballistocardiogram unit signals to obtain multidimensional characteristic vectors, wherein the multidimensional characteristic vectors comprise morphological characteristic vectors, time domain characteristic vectors and nonlinear domain characteristic vectors.
The morphological feature vector comprises a consistency feature vector, a fluctuation feature vector, a periodicity feature vector and a signal-to-noise ratio feature vector;
the time domain feature vector comprises a kurtosis feature vector and a skewness feature vector;
the non-linear domain feature vector comprises a sample entropy feature vector.
Referring to fig. 3, fig. 3 is a schematic flow chart of S2 in the method for detecting a ballistocardiogram signal according to the first embodiment of the present application, which includes steps S201 to S208, and specifically includes the following steps:
s201: and acquiring BCG positioning parameters corresponding to the ballistocardiogram unit signals, and acquiring consistency characteristic vectors according to the BCG positioning parameters and a consistency characteristic vector algorithm.
It has been found from prior studies that a typical ballistocardiogram signal includes a plurality of peaks such as H, I, J, K, L, M. In a BCG waveform, a J peak is the most obvious peak of a heart state, most of the current positioning algorithms position a ballistocardiogram according to the characteristics of the J peak, and subsequent data analysis such as HRV analysis, sleep staging and the like needs to use positioning results. Therefore, whether the J peak shape in the ballistocardiogram signal is clear is an important factor for measuring the BCG signal. In the signals with good quality, the J peak features are obvious, the J peak can be accurately positioned by different algorithms, and the results have high consistency. In a signal with poor quality, the noise frequency is overlapped with the effective signal frequency, so that the signal is deformed or even distorted, and the positioning results of different algorithms are different. Therefore, different BCG signal positioning methods are used for positioning the same BCG signal, the positioning result is obtained, the consistency of the detection of the positioning result is improved, and the quality of the signal can be effectively reflected.
The BCG positioning parameters are acquired according to a BCG signal positioning method and comprise a first J peak number, a second J peak number and a third J peak number; the first J peak number is the J peak number obtained by positioning the J peaks of the ballistocardiogram unit signals through any one BCG signal positioning algorithm, the second J peak number is the J peak number obtained by positioning the J peaks of the ballistocardiogram unit signals through another BCG positioning algorithm, and the third J peak number is the J peak number obtained by positioning the J peaks of the ballistocardiogram unit signals through two BCG positioning algorithms and having the same position.
The consistency feature vector algorithm comprises the following steps:
in the formula, bSQI is a consistency coefficient; a is the first J peak number in the BCG positioning parameters, b is the second J peak number in the BCG positioning parameters, AmatchLocating a third number of J peaks in the parameters for the BCG;
in this embodiment, the detection device obtains BCG positioning parameters corresponding to the plurality of ballistocardiogram unit signals, and obtains bSQI values of the ballistocardiogram unit signals as consistency feature vectors according to the BCG positioning parameters and a bSQI feature vector algorithm.
S202: and acquiring JJ interval data corresponding to the signals of the ballistocardiogram units, and acquiring a fluctuation feature vector according to the JJ interval data and a fluctuation feature vector algorithm.
In this embodiment, the detection device locates the J peaks of the ballistocardiogram unit signals, and obtains peak coordinate data, where the peak coordinate data includes first peak coordinate data and second peak coordinate data.
The first peak coordinate data is peak coordinate data location _ J1 obtained by any BCG signal positioning algorithm, and is recorded as:
in the formula, ja-1Coordinate data for the a-1 th J peak;
according to the first peak coordinate data, first JJ interval data JJI1 corresponding to the first peak coordinate data is obtained, and is recorded as:
wherein c is coordinate data of the c-th J peak.
The second peak coordinate data is peak coordinate data location _ J2 obtained by another BCG signal positioning algorithm, and is recorded as:
according to the second peak coordinate data, second JJ interval data JJI2 corresponding to the second peak coordinate data is obtained and recorded as:
and sorting the first JJ interval data and the second JJ interval data from large to small according to the interval size, and acquiring the sorted first JJ interval data and second JJ interval data.
In normal metabolic activity, the heart rate of a normal person generally remains steady for a period of time, and in a resting situation the instantaneous heart rate fluctuates up and down with breathing in a rhythmic and small amplitude. Therefore, the quality of the signal can be effectively reflected by the JJ interval values of the top 20% of the sequence and the JJ interval values of the top 80% of the sequence in the JJ interval data.
The detection device acquires iSBI 1 values corresponding to the signals of the plurality of ballistocardiogram units according to the sorted first JJ interval data and a fluctuation eigenvector algorithm, wherein the iSBI 1 is a fluctuation coefficient based on the sorted first JJ interval data;
acquiring iSBI 2 values corresponding to the signals of the plurality of ballistocardiogram units according to the sorted second JJ interval data and a fluctuation feature vector algorithm, wherein the iSBI 2 is a fluctuation coefficient based on the sorted second JJ interval data;
taking the iSBI 1 and iSBI 2 as fluctuation feature vectors, wherein the fluctuation feature vector algorithm is as follows:
wherein iSQI is the fluctuation coefficient, JJ20%Sorting the top 20% of JJ interval values, JJ, in the JJ interval data80%Sorting the top 80% of the JJ interval values in the JJ interval data.
S203: and acquiring ECG signals corresponding to the plurality of ballistocardiogram unit signals, and reconstructing the ballistocardiogram unit signals corresponding to the ECG signals according to the ECG signals to acquire a plurality of reconstructed ballistocardiogram unit signals.
The ECG signal is an Electrocardiogram (ECG), which is an electrical signal obtained by the change of the potential of the heart; ECG signals may be acquired by a single lead electrocardiograph device.
In this embodiment, the detection device acquires an ECG signal acquired synchronously with the ballistocardiogram signal, analyzes the ECG signal, acquires an R peak of the ECG signal, and acquires J peak coordinate data J _ peak corresponding to the ballistocardiogram unit signal according to the R peak of the ECG signal, which is recorded as:
in the formula, jp-1Coordinate data of the p-1J peak acquired based on the ECG signal.
And selecting r seconds before and after the central store to reconstruct the ballistocardiogram unit signals corresponding to the ECG signals by taking the coordinate position of the J peak as a central point according to the coordinate data of the J peak and the preset signal duration r, and acquiring a plurality of reconstructed ballistocardiogram unit signals.
S204: and acquiring the periodic feature vector according to the plurality of ballistocardiogram unit signals, the reconstructed ballistocardiogram unit signals and a periodic feature vector algorithm.
The BCG signal is a body vibration signal generated by the beating of the human heart, so the BCG signal has obvious pseudo periodicity, and the form of each BCG waveform has stronger correlation under the condition of good signal quality; when the signal quality is poor and the signal is affected by noise, motion artifacts and the like, the waveform of the signal is deformed or distorted, and the correlation of the waveform is obviously weakened at the moment. Therefore, the average correlation coefficient of all BCG signals is calculated as one of the characteristics measuring the signal quality using a fixed time scale.
The periodic feature vector algorithm is as follows:
wherein tSQI is the average correlation coefficient, k is the number of the reconstructed ballistocardiogram unit signals,
representing the covariance between the ith ballistocardiogram cell signal and the jth reconstructed ballistocardiogram cell signal;
in this embodiment, the detection device obtains a tSQI value corresponding to a reconstructed ballistocardiogram unit signal as the periodic feature vector according to the ballistocardiogram unit signal, the reconstructed ballistocardiogram unit signal and a periodic feature vector algorithm.
S205: and constructing a plurality of reconstructed ballistocardiogram unit signal groups according to the plurality of reconstructed ballistocardiogram unit signals, and acquiring the signal-to-noise ratio characteristic vector according to the reconstructed ballistocardiogram unit signal groups and a signal-to-noise ratio characteristic vector algorithm.
The SNR is a signal-to-noise ratio coefficient, which is an important index for measuring the effectiveness of a signal, and specifically, the SNR value is a ratio of effective signal energy to random noise on a signal segment, which can effectively reflect the degree of influence of the noise on the effective signal. When the SNR value is high, the signal is less influenced by noise, and the morphological characteristics of the signal are relatively obvious; when the SNR value is low, the signal is greatly affected by noise, the signal may be distorted or distorted due to the influence of the noise, and the signal quality is poor.
The signal-to-noise ratio feature vector algorithm is as follows:
wherein SNR is the signal-to-noise ratio coefficient, BCGKIs the kth set of reconstructed ballistocardiogram unit signals,
is an average signal segment of K reconstructed ballistocardiogram unit signal groups, K is the number of the reconstructed ballistocardiogram unit signal groups;
in this embodiment, the detection device constructs a plurality of reconstructed ballistocardiogram unit signal groups according to the plurality of reconstructed ballistocardiogram unit signals, and acquires SNR values corresponding to the reconstructed ballistocardiogram unit signal groups according to the reconstructed ballistocardiogram unit signal groups and a signal-to-noise ratio eigenvector algorithm, and the SNR values serve as the signal-to-noise ratio eigenvectors.
S206: and acquiring kurtosis values corresponding to the ballistocardiogram unit signals according to the ballistocardiogram unit signals and a kurtosis feature vector algorithm, and taking the kurtosis values as kurtosis feature vectors.
The kurtosis represents the steepness degree of the peak of a section of signal and reflects the sharpness of each peak of the BCG signal, namely whether the main characteristic peak of the BCG signal is clear or not. In the signals with relatively good quality, the J peak amplitude of the BCG signal is obviously higher than the peaks at other moments, the peak value of the signal is larger than the peak value of the signal when the human body is far away from the sensor, when the signal is influenced by motion artifacts, the BCG signal can generate violent jitter, and the kurtosis of the signal is much larger than that of a normal BCG signal section, so that for the signals with different qualities, a relatively obvious boundary line is also formed by utilizing the kurtosis, and a certain effect is also realized on the quality control of the BCG signal.
The kurtosis feature vector algorithm is as follows:
in the formula, Kurtosis is the Kurtosis value, E [ ] is an expectation function, X is a ballistocardiogram unit signal group with the length of N, mu is the expectation of the ballistocardiogram unit signal group with the length of N, and sigma is the standard deviation of the ballistocardiogram unit signal group with the length of N;
in this embodiment, the detection device obtains kurtosis values corresponding to the ballistocardiogram unit signals according to the ballistocardiogram unit signals and a kurtosis feature vector algorithm, and uses the kurtosis values as the kurtosis feature vector.
S207: and acquiring skewness values corresponding to the plurality of ballistocardiogram unit signals according to the plurality of ballistocardiogram unit signals and a skewness feature vector algorithm, and taking the skewness values as skewness feature vectors.
The skewness feature vector algorithm is as follows:
wherein Skewness is the Skewness value;
in this embodiment, the detection device obtains, according to the ballistocardiogram unit signals and the skewness feature vector algorithm, skewness values corresponding to the ballistocardiogram unit signals as skewness feature vectors.
S208: and acquiring sample entropy values corresponding to the plurality of ballistocardiogram unit signals as sample entropy characteristic vectors.
In this embodiment, the detecting device reconstructs the ballistocardiogram unit signal set with the length of N, and obtains the reconstructed ballistocardiogram unit signal set with the length of N
Ballistocardiogram unit signal group
Thereby constructing
Dimension embedding space, whose expression is:
in the formula (I), the compound is shown in the specification,
for the reconstructed length to be
First in the ballistocardiogram unit signal groupiAnd reconstructing the ballistocardiogram unit signal.
Calculating the absolute value of the maximum difference of the distances between the reconstructed ballistocardiogram unit signal groups
And is recorded as:
in the formula (I), the compound is shown in the specification,
is 0 to
The number of the integer (c) of (d),
is another reconstructed length of
The ballistocardiogram unit signal set.
Statistics of
Is less than the number of length thresholds r, and is recorded as
Wherein, in the step (A),r=0.2 std, std being of length
Is calculated by dividing the standard deviation of the ballistocardiogram cell signal by the total distance
The method comprises the following steps:
wherein the total distance is
。
Counting the distances among all the reconstructed ballistocardiogram unit signals in the reconstructed ballistocardiogram unit signal group to be less than or equal torIs counted as the total number of distances and divided by the total number of distances
The method comprises the following steps:
increasing the dimension of the embedding space to
Repeating the above steps to obtain
Acquiring sample entropy values corresponding to the ballistocardiogram unit signals according to a preset sample entropy calculation algorithm, wherein the sample entropy values serve as sample entropy characteristic vectors, and the sample entropy calculation algorithm is as follows:
in the formula (I), the compound is shown in the specification,
to calculate the length of
Sample entropy of the ballistocardiogram cell signal.
S3: and reconstructing the multi-dimensional characteristic vector to obtain a characteristic vector matrix corresponding to the ballistocardiogram unit signal.
In this embodiment, the detection device obtains a multidimensional feature vector of the sample ballistocardiogram unit signal according to the sample ballistocardiogram unit signal, reconstructs the multidimensional feature vector of the sample ballistocardiogram unit signal, and obtains a feature vector matrix corresponding to the sample ballistocardiogram unit signal, where an expression of the feature vector matrix corresponding to the sample ballistocardiogram unit signal is:
in the formula (I), the compound is shown in the specification,Wfor the matrix of feature vectors is described,
for the bSQI value of the first sample ballistocardiogram cell signal,
is the sample entropy value of the first sample ballistocardiogram unit signal.
S4: and obtaining quality evaluation results corresponding to the plurality of ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model.
The quality evaluation model comprises a classification module and an evaluation module, in this embodiment, an XGboost (extreme Gradient boosting) classifier is adopted as the classification module of the quality evaluation model by the detection equipment, wherein the XGboost classifier is one of Gradient lifting models and comprises a loss function and an objective function, the loss function is subjected to second-order Taylor expansion, so that the calculation precision is higher, meanwhile, regularization is added into the objective function, overfitting of the model is effectively prevented while the complexity of the model is controlled, and the quality evaluation model has a better effect on physiological signals with various signal forms.
The evaluation module is preset with a classification threshold corresponding to the classification value output by the classification module,
and obtaining a classification value output by a classification module of the quality evaluation model according to the eigenvector matrix corresponding to the ballistocardiogram unit signals and the quality evaluation model, and comparing according to a classification threshold of the evaluation module to obtain quality evaluation results corresponding to the ballistocardiogram unit signals.
Referring to fig. 4, fig. 4 is a schematic flow chart of a method for detecting a ballistocardiogram signal according to a third embodiment of the present application, further including step S7, where the step S7 is performed before the step S4 as follows:
s7: acquiring a feature vector matrix after normalization processing according to the feature vector matrix and a normalization algorithm, wherein the normalization algorithm is as follows:
in the formula (I), the compound is shown in the specification,
in order to normalize the processed feature vector matrix,
for the minimum value of each feature in the feature vector matrix,
is the maximum value of each feature in the feature vector matrix.
In this embodiment, the detection device obtains the feature vector matrix after normalization processing according to the feature vector matrix and the normalization algorithm.
Referring to fig. 5, fig. 5 is a schematic flow chart of a method for detecting a ballistocardiogram signal according to a fourth embodiment of the present application, including steps S8-S9, where steps S8-S9 are as follows before step S4:
s8: acquiring a sample data set, wherein the sample data set comprises sample ballistocardiogram unit signals and corresponding label data.
The method comprises the steps that the detection equipment obtains ballistocardiogram signals of a plurality of healthy tested users as sample ballistocardiogram signals, and divides the sample ballistocardiogram signals into a plurality of sample ballistocardiogram unit signals according to preset signal length.
Each sample ballistocardiogram unit signal corresponds to a tag data, the tag data is used for determining the quality of the corresponding sample ballistocardiogram unit signal, wherein the tag data comprises an A-type tag type, a B-type tag type and a C-type tag type, the A-type tag type is that the corresponding sample ballistocardiogram unit signal has no obvious noise and motion artifact interference, the BCG signal morphology is obvious, and the J peak is obviously higher than other peaks; the type of the B-type label is that two conditions occur to corresponding sample ballistocardiogram unit signals, namely, firstly, no motion artifact exists, but the BCG signal form obviously presents periodicity but changes under the influence of noise, and the J peak is not necessarily a local maximum value; motion artifacts appear, but the duration of the motion artifacts is lower than 30% of a window, and other signal waveforms are obvious or periodic; the type of the C-type label is that the corresponding sample ballistocardiogram unit signal has obvious motion artifact and the duration of the motion artifact exceeds 30 percent of the length of the signal or the BCG signal cannot be seen due to waveform disorder caused by noise interference.
In this embodiment, the detection device acquires the sample ballistocardiogram unit signal and the corresponding tag data, and constructs the sample data set.
S9: and inputting the characteristic vector matrix corresponding to the sample ballistocardiogram unit signal and the corresponding label data into a quality evaluation model to be trained for training to obtain the quality evaluation model.
The quality evaluation model to be trained comprises an objective function, and the objective function is as follows:
in the formula (I), the compound is shown in the specification,
in order to be said objective function, the method comprises the steps of,
in order to be able to do so with the complexity,vfor the number of sample ballistocardiogram cell signals,
is the value to which the tag data corresponds,
is as followst-1 output value of model prediction,
is as followstThe output value of the secondary model prediction;
is the value to which the feature vector matrix corresponds,
is a preset constant value.
The detection equipment inputs the characteristic vector matrix corresponding to the sample ballistocardiogram unit signal into a quality evaluation model to be trained, obtains output values of model prediction for a plurality of times, trains the quality evaluation model to be trained according to label data corresponding to the sample ballistocardiogram unit signal and an objective function, and obtains the quality evaluation model.
S5: responding to a detection instruction, wherein the detection instruction comprises ballistocardiogram signals of a user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results.
The detection instruction is sent by a user and received by the detection equipment.
The method comprises the steps that detection instructions sent by a user are obtained by detection equipment, quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected are obtained according to the initial ballistocardiogram signals of the user to be detected, and the quality evaluation results comprise A-type label type results, B-type label type results and C-type label type results.
The detection instruction further comprises a target label type, wherein the target label type comprises an A-type label type, a B-type label type and a C-type label type, the detection equipment acquires the ballistocardiogram unit signal of the A-type label type, the ballistocardiogram unit signal of the B-type label type and the ballistocardiogram unit signal of the C-type label type of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation result, and acquires ballistocardiogram unit signals meeting the target label type as target ballistocardiogram signals according to the target label type.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a ballistocardiogram signal detection apparatus according to a fifth embodiment of the present application, which may implement all or part of a ballistocardiogram signal detection method through software, hardware, or a combination of the two, where the apparatus 6 includes:
the acquisition module 61 is configured to acquire a ballistocardiogram signal of a user, and divide the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length;
the feature extraction module 62 is configured to perform multi-dimensional feature extraction on the ballistocardiogram unit signals to obtain multi-dimensional feature vectors, where the multi-dimensional feature vectors include morphological feature vectors, time domain feature vectors, and nonlinear domain feature vectors;
a reconstruction module 63, configured to reconstruct the multidimensional feature vector to obtain a feature vector matrix corresponding to the ballistocardiogram unit signal;
the evaluation module 64 is configured to obtain quality evaluation results corresponding to the ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model;
the processing module 65 is configured to respond to a detection instruction, where the detection instruction includes a ballistocardiogram signal of a user to be detected, obtain a quality evaluation result corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to an initial ballistocardiogram signal of the user to be detected, and obtain a target ballistocardiogram signal of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation result.
In the embodiment of the application, a ballistocardiogram signal of a user is obtained through an obtaining module, and the ballistocardiogram signal is divided into a plurality of ballistocardiogram unit signals according to a preset signal length; performing multi-dimensional feature extraction on the ballistocardiogram unit signals through a feature extraction module to obtain multi-dimensional feature vectors, wherein the multi-dimensional feature vectors comprise morphological feature vectors, time domain feature vectors and nonlinear domain feature vectors; reconstructing the multi-dimensional characteristic vector through a reconstruction module to obtain a characteristic vector matrix corresponding to the ballistocardiogram unit signal; obtaining quality evaluation results corresponding to the ballistocardiogram unit signals through an evaluation module according to the eigenvector matrix and a preset quality evaluation model; responding to a detection instruction through a processing module, wherein the detection instruction comprises ballistocardiogram signals of a user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results. According to the method and the device, the morphology, the time domain and the nonlinear domain multidimensional characteristics of the ballistocardiogram signal are analyzed, the target ballistocardiogram signal is obtained from the ballistocardiogram signal according to the quality evaluation model, the factors influencing the quality objective of the ballistocardiogram signal are fully considered, and the accuracy and the efficiency of obtaining the ballistocardiogram signal in a complex application scene are improved.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer device according to a sixth embodiment of the present application, where the computer device 7 includes: a processor 71, a memory 72, and a computer program 73 stored on the memory 72 and operable on the processor 71; the computer device may store a plurality of instructions, where the instructions are suitable for being loaded by the processor 71 and executing the method steps in the embodiments described in fig. 1 to 5, and a specific execution process may refer to specific descriptions of the embodiments described in fig. 1 to 5, which are not described herein again.
The Memory 72 may include a Random Access Memory (RAM) 72 or a Read-Only Memory (Read-Only Memory) 72. Optionally, the memory 72 includes a non-transitory computer-readable medium. The memory 72 may be used to store instructions, programs, code sets, or instruction sets. The memory 72 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 72 may alternatively be at least one memory device located remotely from the processor 71.
The embodiment of the present application further provides a storage medium, where the storage medium may store a plurality of instructions, where the instructions are suitable for being loaded by a processor and being executed in the method steps of the first to third embodiments, and a specific execution process may refer to specific descriptions of the embodiments shown in fig. 1 to fig. 5, which is not described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.
Claims (8)
1. A method of detecting ballistocardiogram signals, comprising the steps of:
the method comprises the steps of obtaining a ballistocardiogram signal of a user, and dividing the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length;
extracting the multidimensional characteristics of the ballistocardiogram unit signals to obtain multidimensional characteristic vectors, wherein the multidimensional characteristic vectors comprise morphological characteristic vectors, time domain characteristic vectors and nonlinear domain characteristic vectors, and the morphological characteristic vectors comprise consistency characteristic vectors, fluctuation characteristic vectors, periodic characteristic vectors and signal-to-noise ratio characteristic vectors; the time domain feature vector comprises a kurtosis feature vector and a skewness feature vector; the non-linear domain feature vector comprises a sample entropy feature vector;
the step of obtaining the morphological feature vector is as follows:
acquiring BCG positioning parameters corresponding to the ballistocardiogram unit signals, and acquiring consistency characteristic vectors according to the BCG positioning parameters and a consistency characteristic vector algorithm, wherein the consistency characteristic vector algorithm is as follows:
in the formula, bSQI is a consistency coefficient; a is the first J peak number in the BCG positioning parameters, b is the second J peak number in the BCG positioning parameters, AmatchA third number of J peaks in the BCG positioning parameters, wherein the BCG positioning parameters are obtained according to a BCG signal positioning method, the first number of J peaks is the number of J peaks obtained by positioning the J peaks of the ballistocardiogram unit signals through any one BCG signal positioning algorithm, the second number of J peaks is the number of J peaks obtained by positioning the J peaks of the ballistocardiogram unit signals through another BCG positioning algorithm, and the third number of J peaks is the number of J peaks with the same position obtained by positioning the J peaks of the ballistocardiogram unit signals through two BCG positioning algorithms;
acquiring JJ interval data corresponding to the signals of the ballistocardiogram units, and acquiring a fluctuation feature vector according to the JJ interval data and a fluctuation feature vector algorithm, wherein the fluctuation feature vector algorithm comprises the following steps:
wherein i SQI is the coefficient of variation, JJ20%Sorting the top 20% of JJ interval values, JJ, in the JJ interval data80%Sorting the top 80% of the JJ interval values in the JJ interval data;
acquiring ECG signals corresponding to the ballistocardiogram unit signals, and reconstructing the ballistocardiogram unit signals corresponding to the ECG signals according to the ECG signals to acquire a plurality of reconstructed ballistocardiogram unit signals;
obtaining the periodic feature vector according to the ballistocardiogram unit signals, the reconstructed ballistocardiogram unit signals and a periodic feature vector algorithm, wherein the periodic feature vector algorithm is as follows:
wherein tSQI is the average correlation coefficient, k is the number of the reconstructed ballistocardiogram unit signals,
representing the covariance between the ith ballistocardiogram cell signal and the jth reconstructed ballistocardiogram cell signal;
constructing a plurality of reconstructed ballistocardiogram unit signal groups according to the plurality of reconstructed ballistocardiogram unit signals, and acquiring the signal-to-noise ratio characteristic vector according to the reconstructed ballistocardiogram unit signal groups and a signal-to-noise ratio characteristic vector algorithm, wherein the signal-to-noise ratio characteristic vector algorithm is as follows:
wherein SNR is the signal-to-noise ratio coefficient, BCGKIs the kth set of reconstructed ballistocardiogram unit signals,
is an average signal segment of K reconstructed ballistocardiogram unit signal groups, K is the number of the reconstructed ballistocardiogram unit signal groups;
reconstructing the multi-dimensional feature vector to obtain a feature vector matrix corresponding to the ballistocardiogram unit signal;
obtaining quality evaluation results corresponding to the plurality of ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model;
responding to a detection instruction, wherein the detection instruction comprises ballistocardiogram signals of a user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results.
2. The ballistocardiogram signal detecting method according to claim 1, wherein the obtaining of the ballistocardiogram signal of the user further comprises the steps of:
and preprocessing the ballistocardiogram signal, removing power frequency interference and baseline offset in the ballistocardiogram signal, and obtaining the processed ballistocardiogram signal.
3. The ballistocardiogram signal detection method according to claim 1, wherein the multi-dimensional feature extraction is performed on the ballistocardiogram unit signals to obtain a multi-dimensional feature vector, comprising the steps of:
acquiring JJ interval data corresponding to the signals of the ballistocardiogram units, and acquiring a fluctuation feature vector according to the JJ interval data and a fluctuation feature vector algorithm, wherein the fluctuation feature vector algorithm comprises the following steps:
wherein i SQI is the coefficient of variation, JJ20%Sorting the top 20% of JJ interval values, JJ, in the JJ interval data80%Sorting the top 80% of the JJ interval values in the JJ interval data;
according to the ballistocardiogram unit signals and the kurtosis feature vector algorithm, obtaining kurtosis values corresponding to the ballistocardiogram unit signals, and using the kurtosis values as kurtosis feature vectors, wherein the kurtosis feature vector algorithm is as follows:
in the formula, Kurtosis is the Kurtosis value, E [ ] is an expectation function, X is a ballistocardiogram unit signal group with the length of N, mu is the expectation of the ballistocardiogram unit signal group with the length of N, and sigma is the standard deviation of the ballistocardiogram unit signal group with the length of N;
according to the ballistocardiogram unit signals and a skewness feature vector algorithm, obtaining skewness values corresponding to the ballistocardiogram unit signals as skewness feature vectors, wherein the skewness feature vector algorithm is as follows:
wherein Skewness is the Skewness value;
and acquiring sample entropy values corresponding to the plurality of ballistocardiogram unit signals as sample entropy characteristic vectors.
4. The method for detecting ballistocardiogram signals according to claim 1, wherein the reconstructing the multi-dimensional eigenvector obtains an eigenvector matrix corresponding to the ballistocardiogram unit signals, further comprising the steps of:
acquiring a feature vector matrix after normalization processing according to the feature vector matrix and a normalization algorithm, wherein the normalization algorithm is as follows:
in the formula (I), the compound is shown in the specification,
in order to normalize the processed feature vector matrix,
for the matrix of feature vectors is described,
for the minimum value of each feature in the feature vector matrix,
is the maximum value of each feature in the feature vector matrix.
5. The method for detecting ballistocardiogram signals according to claim 1, wherein before obtaining the quality evaluation results corresponding to the plurality of ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model, the method comprises the steps of:
acquiring a sample data set, wherein the sample data set comprises a sample ballistocardiogram unit signal and corresponding label data;
and inputting the characteristic vector matrix corresponding to the sample ballistocardiogram unit signal and the corresponding label data into a quality evaluation model to be trained for training to obtain the quality evaluation model.
6. A ballistocardiogram signal detecting apparatus to which the ballistocardiogram signal detecting method according to any one of claims 1 to 5 is applied, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a ballistocardiogram signal of a user and dividing the ballistocardiogram signal into a plurality of ballistocardiogram unit signals according to a preset signal length;
the feature extraction module is used for performing multi-dimensional feature extraction on the ballistocardiogram unit signals to obtain multi-dimensional feature vectors, wherein the multi-dimensional feature vectors comprise morphological feature vectors, time domain feature vectors and nonlinear domain feature vectors, and the morphological feature vectors comprise consistency feature vectors, fluctuation feature vectors, periodic feature vectors and signal-to-noise ratio feature vectors; the time domain feature vector comprises a kurtosis feature vector and a skewness feature vector; the non-linear domain feature vector comprises a sample entropy feature vector;
the reconstruction module is used for reconstructing the multi-dimensional characteristic vector to obtain a characteristic vector matrix corresponding to the ballistocardiogram unit signal;
the evaluation module is used for obtaining quality evaluation results corresponding to the ballistocardiogram unit signals according to the eigenvector matrix and a preset quality evaluation model;
and the processing module is used for responding to a detection instruction, the detection instruction comprises ballistocardiogram signals of a user to be detected, acquiring quality evaluation results corresponding to a plurality of ballistocardiogram unit signals of the user to be detected according to the initial ballistocardiogram signals of the user to be detected, and acquiring target ballistocardiogram signals of the user to be detected from the plurality of ballistocardiogram unit signals according to the quality evaluation results.
7. A computer device comprising a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method of detecting ballistocardiogram signals according to any one of claims 1 to 5 when executing the computer program.
8. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the steps of the method of detection of a ballistocardiogram signal according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210024167.6A CN114041786B (en) | 2022-01-11 | 2022-01-11 | Ballistocardiogram signal detection method, ballistocardiogram signal detection device and ballistocardiogram signal detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210024167.6A CN114041786B (en) | 2022-01-11 | 2022-01-11 | Ballistocardiogram signal detection method, ballistocardiogram signal detection device and ballistocardiogram signal detection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114041786A CN114041786A (en) | 2022-02-15 |
| CN114041786B true CN114041786B (en) | 2022-04-26 |
Family
ID=80213652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210024167.6A Active CN114041786B (en) | 2022-01-11 | 2022-01-11 | Ballistocardiogram signal detection method, ballistocardiogram signal detection device and ballistocardiogram signal detection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114041786B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116671885A (en) * | 2022-02-22 | 2023-09-01 | Oppo广东移动通信有限公司 | Heart rate detection method and device, computer readable storage medium and electronic equipment |
| CN115381438B (en) * | 2022-08-24 | 2023-04-18 | 华南师范大学 | Method and device for reconstructing vital sign signals, computer equipment and storage medium |
| CN116369907B (en) * | 2023-03-20 | 2024-02-13 | 华南师范大学 | Ballistocardiogram signal positioning method |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108042141B (en) * | 2017-11-17 | 2020-11-10 | 深圳和而泰智能控制股份有限公司 | Signal processing method and device |
| CN108256457B (en) * | 2018-01-09 | 2021-06-04 | 东北大学 | Heart impact signal deep bottleneck characteristic extraction method based on deep neural network |
| CN108968946A (en) * | 2018-06-20 | 2018-12-11 | 广州中科新知科技有限公司 | A kind of female incretion management system based on HRV analysis |
| CN109431482A (en) * | 2018-11-13 | 2019-03-08 | 杭州菲诗奥医疗科技有限公司 | A kind of mattress and its detection method based on contactless detection heart rate variability |
| EP3900610A4 (en) * | 2019-02-03 | 2022-01-12 | Huawei Technologies Co., Ltd. | Atrial fibrillation screening method and device |
| CN110420019B (en) * | 2019-07-29 | 2021-04-20 | 西安电子科技大学 | Deep regression heart rate estimation method for ballistocardiogram signals |
| CN111938621B (en) * | 2020-06-29 | 2023-04-11 | 杨铭轲 | Heart rate detection method and device, computer equipment and readable storage medium |
| CN112971770B (en) * | 2021-02-10 | 2022-10-18 | 北京邮电大学 | Method and system for controlling and processing quality of cardiac shock signal |
-
2022
- 2022-01-11 CN CN202210024167.6A patent/CN114041786B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114041786A (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114041786B (en) | Ballistocardiogram signal detection method, ballistocardiogram signal detection device and ballistocardiogram signal detection equipment | |
| JP6367442B2 (en) | Method and system for disease analysis based on conversion of diagnostic signals | |
| Wang et al. | Arrhythmia classification algorithm based on multi-head self-attention mechanism | |
| CN111035367B (en) | Signal detection system for judging sleep apnea | |
| CN110338786B (en) | Epileptic discharge identification and classification method, system, device and medium | |
| US8543194B2 (en) | System and method of detecting abnormal movement of a physical object | |
| WO2019234458A1 (en) | Detecting abnormalities in ecg signals | |
| Banerjee et al. | PhotoECG: Photoplethysmographyto estimate ECG parameters | |
| CN106175754B (en) | Waking state detection device in sleep state analysis | |
| CN105550659A (en) | Real-time electrocardiogramclassification method based on random projection | |
| KR20130092849A (en) | Method and apparatus for eliminating motion artifact of biosignal using personalized biosignal pattern | |
| CN112674782B (en) | Device and method for detecting epileptic-like electrical activity of epileptic during inter-seizure period | |
| CN112971770B (en) | Method and system for controlling and processing quality of cardiac shock signal | |
| CN115486849A (en) | Electrocardiosignal quality evaluation method, device and equipment | |
| Wartzek et al. | Modeling of motion artifacts in contactless heart rate measurements | |
| CN115553784B (en) | Coronary heart disease assessment method and system based on electrocardio and heart sound signal coupling analysis | |
| CN116712099A (en) | Fetal heart state detection method based on multi-mode data, electronic equipment and storage medium | |
| CN106361327B (en) | Waking state detection method and system in sleep state analysis | |
| CN110580448B (en) | Heart sound classification model construction and classification method and device | |
| CN112168167B (en) | Magnetoencephalogram single auditory evoked signal detection method and electronic device | |
| CN116369911B (en) | Heart information detection method, device and equipment based on physiological signals | |
| WO2020064469A1 (en) | Method and device for determining cardiophysiological characteristics using a mechanocardiograph device | |
| CN115316985B (en) | Heart information detection method, device and equipment based on physiological signals | |
| Akhbardeh et al. | Ballistocardiogram classification using a novel transform so-called AliMap and biorthogonal wavelets | |
| CN117017233B (en) | Sleep apnea detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240128 Address after: Building 2, No. 38 Junfeng Road, Huangpu District, Guangzhou City, Guangdong Province, 510000 Patentee after: GUANGDONG JUNFENG BFS INDUSTRY CO.,LTD. Country or region after: China Address before: School of physics and telecommunication engineering, South China Normal University, No. 378, Waihuan West Road, Panyu District, Guangzhou City, Guangdong Province, 510006 Patentee before: SOUTH CHINA NORMAL University Country or region before: China |
|
| TR01 | Transfer of patent right |