CN115363586A - Psychological stress grade assessment system and method based on pulse wave signals - Google Patents
Psychological stress grade assessment system and method based on pulse wave signals Download PDFInfo
- Publication number
- CN115363586A CN115363586A CN202211096007.9A CN202211096007A CN115363586A CN 115363586 A CN115363586 A CN 115363586A CN 202211096007 A CN202211096007 A CN 202211096007A CN 115363586 A CN115363586 A CN 115363586A
- Authority
- CN
- China
- Prior art keywords
- pulse wave
- psychological stress
- wave signal
- target object
- features
- 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.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- 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
-
- 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
Abstract
The invention provides a psychological stress grade assessment system and method based on pulse wave signals, which relate to the technical field of physiological signal analysis, and comprise the following steps: the signal processing module is used for acquiring a pulse wave signal of the target object, and performing first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object; the characteristic extraction module is used for extracting heart rate variability characteristics of the cardiac cycle sequence; and the grade evaluation module is used for selecting the features of the heart rate variability features, constructing the feature set, inputting the feature set into a preset psychological pressure grade evaluation model, and evaluating the psychological pressure grade of the target object according to the output result of the model. By the mode, deep effective information related to psychological stress can be more comprehensively mined, and accuracy of psychological stress grade assessment is improved.
Description
Technical Field
The invention belongs to the technical field of physiological signal analysis, and particularly relates to a psychological stress level assessment system and method based on pulse wave signals.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art that is already known to a person of ordinary skill in the art.
Prolonged exposure to chronic or extreme stress can lead to a range of diseases such as cardiovascular disease, alzheimer's disease, depression. It is of great importance to assess stress conditions accurately and to identify early changes in mental state that may progress to disease, in order to intervene effectively in time.
The psychological stress grade assessment method commonly used at present is still based on a scale. Doctors make diagnosis by combining the results of inquiry and scale, but the method is greatly influenced by the subjective experience of doctors, and patients often cannot accurately describe own feelings and even hide the disease conditions due to the pubic feeling of diseases and the like. The development of early detection and early treatment of psychological stress is further limited by the limitations that professional consultants are lacked and scale survey cannot be continuously monitored.
The pulse wave signal can effectively reflect the change of the regulation state of the autonomic nervous system, and has the advantages of no wound, no damage, simple operation, low cost and the like. Most conventional methods calculate simple time domain and frequency domain characteristics, establish a relation between the characteristics and the stress level by combining a traditional machine learning algorithm, do not consider the specific nonlinear and time-frequency domain information of a human body as a complex physiological system, and do not fully excavate deep effective information related to the psychological stress, so that the psychological stress level of an individual cannot be accurately evaluated.
Disclosure of Invention
In order to solve the above problems, the present invention provides a system and a method for assessing psychological stress level based on a pulse wave signal, wherein a cardiac cycle sequence is obtained by performing first-order difference, filtering and peak identification on the pulse wave signal, and a multi-domain heart rate variability feature including a time domain feature, a frequency domain feature, a non-linear feature and a time-frequency domain feature is extracted from the cardiac cycle sequence for assessing psychological stress level. So as to fully dig deep effective information related to the psychological stress and improve the accuracy of psychological stress grade evaluation.
In order to achieve the above object, the present invention mainly includes the following aspects:
in a first aspect, an embodiment of the present invention provides a system for assessing a psychological stress level based on a pulse wave signal, including:
the signal processing module is used for acquiring a pulse wave signal of a target object, and performing first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object;
the characteristic extraction module is used for extracting heart rate variability characteristics of the cardiac cycle sequence, wherein the heart rate variability characteristics comprise time domain characteristics, frequency domain characteristics, nonlinear characteristics and time-frequency domain characteristics;
the grade evaluation module is used for selecting the heart rate variability characteristics, constructing a characteristic set, inputting the characteristic set into a preset psychological stress grade evaluation model, and evaluating the psychological stress grade of the target object according to the output result of the model; the psychological stress level evaluation model is obtained by training a classifier by a machine learning method.
In a possible implementation, the pulse wave monitoring system further comprises a data acquisition module for acquiring a pulse wave signal of the target object; the data acquisition module comprises a pulse wave piezoelectric sensor and an amplification filter which are electrically connected with each other, and the signals acquired by the pulse wave piezoelectric sensor are amplified by the amplification filter to obtain pulse wave signals of the target object.
In a possible implementation manner, the signal processing module is specifically configured to perform an a/D conversion on the acquired pulse wave signal, and perform a first-order difference and filtering processing on the pulse wave signal after the a/D conversion to obtain a difference sequence; and determining the maximum value of each numerical value point in the difference sequence, taking the maximum value as an identified first peak, and respectively sliding a window forwards or backwards by taking the maximum value as a fixed point to obtain the numerical value point meeting a preset threshold value as a second peak so as to construct the cardiac cycle sequence of the target object.
In a possible implementation, the feature extraction module is configured to perform a discrete fourier transform on the sequence of cardiac cycles, calculate and extract frequency domain features.
In one possible implementation, the non-linear features include, but are not limited to, one or more of shannon entropy, approximate entropy, sample entropy, fuzzy entropy, permutation entropy, distribution entropy, poincare minor axis, major axis, minor/major axis, vector angle index, vector length index, porta index, and Guzik index.
In a possible implementation manner, the feature extraction module is configured to perform wavelet transform of a preset scale on the cardiac cycle sequence by using db4 mother wavelet, and take a mean value and a standard deviation of absolute values of detail coefficients of each layer of reconstructed signals as time-frequency domain features.
In one possible implementation, in the level evaluation module, when feature selection is performed on the heart rate variability features, a recursive elimination method based on a support vector machine is used for screening the features to obtain a feature set.
In a second aspect, an embodiment of the present invention provides a method for assessing a psychological stress level based on a pulse wave signal, including:
acquiring a pulse wave signal of a target object, and performing first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object;
extracting heart rate variability features of the cardiac cycle sequence, wherein the heart rate variability features comprise time domain features, frequency domain features, nonlinear features and time-frequency domain features;
selecting the characteristics of the heart rate variability characteristics, constructing a characteristic set, inputting the characteristic set into a preset psychological stress level assessment model, and assessing the psychological stress level of the target object according to the output result of the model; the psychological stress grade evaluation model is obtained by training a classifier through a machine learning method.
In a third aspect, an embodiment of the present invention provides a computer device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the computer device is operated, the machine-readable instructions being executed by the processor to perform the steps of the pulse wave signal-based psychological stress level assessment method as described in the second aspect above.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, performs the steps of the method for assessing a psychological stress level based on a pulse wave signal as described in the second aspect above.
The above one or more technical solutions have the following beneficial effects:
(1) Different from the existing method for establishing the relationship between the characteristics and the pressure level according to the time domain characteristics and the frequency domain characteristics of the pulse wave signals and combining the traditional machine learning algorithm, the psychological pressure grade evaluation system provided by the invention obtains the cardiac cycle sequence by carrying out first-order difference, filtering and wave crest identification processing on the pulse wave signals, extracts the multi-domain heart rate variability characteristics comprising the time domain characteristics, the frequency domain characteristics, the nonlinear characteristics and the time-frequency domain characteristics from the cardiac cycle sequence and is used for psychological pressure grade evaluation, so that deep effective information related to the psychological pressure can be more comprehensively mined, and the psychological pressure grade is more accurately evaluated.
(2) The extracted heart rate variability multi-domain features are screened by using a support vector machine-based cyclic recursion elimination method, so that features related to psychological pressure are reserved to the maximum extent, and the operation efficiency is greatly improved.
(3) Extracting multi-domain heart rate variability features based on a cardiac cycle sequence, inputting the features into a psychological pressure grade evaluation model, and evaluating a psychological pressure grade corresponding to a pulse wave signal according to an output result of the psychological pressure grade evaluation model; the multi-domain characteristics can provide more comprehensive autonomic nervous system change conditions, so that the method can provide better classification performance than the existing method, improve the accuracy of psychological stress level assessment, and effectively improve the application value of the heart rate variability analysis based on the pulse wave signals in the psychological stress level assessment.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are included to illustrate an exemplary embodiment of the invention and not to limit the invention.
Fig. 1 is a schematic structural diagram of a psychological stress level assessment system based on pulse wave signals according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for assessing a psychological stress level based on a pulse wave signal according to a second embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
The present embodiment provides a psychological stress level assessment system based on pulse wave signals, including:
the signal processing module is used for acquiring a pulse wave signal of a target object, and performing first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object;
the characteristic extraction module is used for extracting heart rate variability characteristics of the cardiac cycle sequence, wherein the heart rate variability characteristics comprise time domain characteristics, frequency domain characteristics, nonlinear characteristics and time-frequency domain characteristics;
the grade evaluation module is used for selecting the heart rate variability characteristics, constructing a characteristic set, inputting the characteristic set into a preset psychological stress grade evaluation model, and evaluating the psychological stress grade of the target object according to the output result of the model; the psychological stress level evaluation model is obtained by training a classifier by a machine learning method.
The psychological stress grade evaluation system provided by the embodiment of the invention comprises a signal processing module, a characteristic extraction module and a grade evaluation module, wherein a cardiac cycle sequence is obtained by carrying out first-order difference, filtering and peak identification processing on a pulse wave signal of a target object, and then multi-domain heart rate variability characteristics of the cardiac cycle sequence, including time domain characteristics, frequency domain characteristics, nonlinear characteristics, time-frequency domain characteristics and the like, are extracted, and further the heart rate variability characteristics are selected in the grade evaluation module to construct a characteristic set for evaluating the psychological stress grade of the target object.
In an implementation, as shown in fig. 1, the psychological stress level assessment system further includes a data acquisition module for acquiring a pulse wave signal of the target subject; the data acquisition module comprises a pulse signal acquisition unit 1, the pulse signal acquisition unit 1 is specifically a pulse wave piezoelectric sensor and an amplification filter which are electrically connected with each other, and signals acquired by the pulse wave piezoelectric sensor are amplified by the amplification filter to obtain pulse wave signals of a target object. In the evaluation process of the pulse wave signals, the data acquisition module is used for acquiring the pulse wave signals of the target object; in the training process of the psychological pressure grade evaluation model, the data acquisition module is used for acquiring the pulse wave signals as sample data. In a specific application, the pulse signal acquisition unit 1 is placed at the index finger end of a target object to acquire a pulse wave signal.
The characteristic extraction module comprises an A/D conversion unit 2 and a preprocessing unit 3, wherein the A/D conversion unit 2 is used for carrying out A/D conversion on the acquired pulse wave signals; the preprocessing unit 3 is used for performing first-order difference and filtering processing on the pulse wave signals after the A/D conversion to obtain a difference sequence, identifying wave crests of the pulse wave first-order difference sequence and constructing a cardiac cycle time sequence. In a specific application, a fourth-order Butterworth band-pass filter is used for carrying out band-pass filtering of 0.5-10 Hz. The peak identification mode is to determine the maximum value of each numerical point in the difference sequence, take the maximum value as an identified first peak, and respectively slide a window forwards or backwards by taking the first peak as a fixed point to obtain the numerical point meeting a preset threshold value as a second peak so as to construct the cardiac cycle sequence of the target object.
The feature extraction module 4 is configured to extract multi-domain heart rate variability features of the cardiac cycle sequence, such as a time domain, a frequency domain, nonlinearity, a time-frequency domain, and the like.
In a specific implementation, the method of extracting heart rate variability features comprises:
1. for the preprocessed cardiac cycle sequence, 22 time domain statistical characteristics such as interval mean mRR, median medRR, standard deviation SDNN, standard deviation-to-mean ratio HRVC, kurtosis St, skewness Kt, cumulative Area, 20 quantile Q20, 80 quantile Q80, quartile QD, mean mSD, standard deviation SDSD and RMSSD of adjacent interval differences, NN50 of adjacent interval differences larger than 50ms, pNN50, pNN25, pNN20 and pNN10 of adjacent interval differences larger than 50ms, 25ms, 20ms and 10ms accounting for the percentage of the sinus heartbeat number, heart rate mean mrh and standard deviation stdHR, trigonometric index TRI, triangular interpolation TINN of histograms are calculated as the time domain characteristics of the cardiac cycle sequence.
2. And performing discrete Fourier transform on the preprocessed cardiac cycle sequence, and calculating and extracting frequency domain characteristics. The frequency domain features include 19 features such as the spectral sequence mean meanFreq, standard deviation stdFreq, skewness skewFreq and kurtFreq, very low frequency (0.0033-0.04 Hz) power VLF, low frequency (0.04-0.15 Hz) power LF, high frequency (0.15-0.4 Hz) power HF, total power (0.0033-0.4 Hz) TF, normalized low frequency power LFn, normalized high frequency power HFn, low high frequency power ratio LF/HF, low high frequency Energy ratio LH _ Energy, low frequency power ratio Per _ LF, high frequency power ratio Per _ HF, very low frequency power ratio Per _ f, coherence ratio CR, frequency peak in very low frequency range VLF _ peak, frequency peak in low frequency range LF _ peak, frequency peak in high frequency range LF _ peak, etc.
3. And calculating nonlinear characteristics of the preprocessed cardiac cycle sequence, wherein the nonlinear characteristics comprise 13 characteristics such as shannon entropy, approximate entropy, sample entropy, fuzzy entropy, arrangement entropy, distribution entropy, poincare short axis, long axis, short axis/long axis, vector angle index, vector length index, porta index and Guzik index.
Specifically, the process of calculating the sample entropy and the fuzzy entropy is as follows:
step 3.1.1: normalizing the cardiac cycle sequence using the subtracted mean divided by the standard deviation;
step 3.1.2: for the sequence { u ] obtained in the above step i I ≦ N = u (i), 1 ≦ i ≦ N }, and the following spatial vector is reconstructed
Where m is the reconstruction dimension and N is the time series length.
Step 3.1.3:definition of
And
the distance d between is:
computing
If the sample entropy is calculated, A () is a Havesseld step function; if fuzzy entropy is calculated, then
Is a gaussian function.
Step 3.1.4: calculating out
And taking the logarithm, i.e.:
step 3.1.5: increasing the reconstruction dimension to m +1, repeating steps 3.1.2 to 3.1.4, calculating statistical features
By
And respectively solving the sample entropy and the fuzzy entropy according to the difference of A ().
In this embodiment, the process of calculating the distribution entropy is:
step 3.2.1: the cardiac cycle sequence was normalized using the subtracted mean divided by the standard deviation.
Step 3.2.2: for the sequence { u ] obtained in the above step i I ≦ N ≦ 1 ≦ u (i), and reconstruct the following space vector
Where m is the reconstruction dimension and N is the time series length.
Step 3.2.3: definition matrix
Is composed of
And
a distance therebetween
The matrix is formed, wherein i is more than or equal to 1 and less than or equal to N-m +1, and j is more than or equal to 1 and less than or equal to N-m +1.
Step 3.2.4: in the [0,1 ]]On the interval, estimation is carried out by using a histogram method
Except for the main diagonal (i.e., i = j), the empirical probability density function of all elements. The number of the histograms is predefined as B, and the probability p of the elements falling into each histogram is counted k (1≤k≤B)。
Step 3.2.5: by the formula
And solving the distribution entropy.
4. And calculating the time-frequency domain characteristics of the preprocessed cardiac cycle sequence. Performing 5-scale wavelet transform on the sequence by using db4 mother wavelet, and taking the average value of the absolute values of detail coefficients of each layer of reconstructed signalAnd standard deviation as 10 time-frequency domain characteristics, denoted as meand i And stdd i (i＝1，2，...，5)。
The grade evaluation module 5 is used for selecting the heart rate variability characteristics, constructing a characteristic set, inputting the characteristic set into a preset psychological stress grade evaluation model, and evaluating the psychological stress grade of the target object according to an output result of the model. The psychological pressure grade evaluation model adopts a recursive elimination method of a support vector machine to screen characteristics; and verifying the result by using a k-fold cross verification method.
The method for generating the psychological stress level assessment model comprises the following steps: obtaining a heart cycle sequence sample of pulse wave sample data, extracting heart rate variability characteristics of the heart cycle sequence sample, including time domain characteristics, frequency domain characteristics, nonlinear characteristics, time-frequency domain characteristics and the like, and performing characteristic selection on the heart rate variability characteristics to obtain a characteristic selection result; and constructing a sample feature set according to the feature selection result, training a classifier by a machine learning method, and obtaining a psychological stress grade evaluation model.
In the grade evaluation module, when the heart rate variability features are selected in the grade evaluation module, the features are screened by a recursive elimination method based on a support vector machine to obtain a feature set. In specific implementation, each iteration eliminates the feature with the minimum contribution rate in the feature set, and the optimal feature set with the specified number is obtained through multiple loop iterations. The best feature set obtained: the combined analysis of mRR, medRR, HRVC, mSD, Q20, TRI, mHR, stdHR, skewfeq, kurtFreq, per _ VLF, VLF _ peak, stdd1, and mead 2 features identified high performance for the stress and health groups.
According to the embodiment of the invention, the multi-domain features based on the preprocessed cardiac cycle sequence are extracted, the features are input into the trained psychological stress level assessment model after feature selection, and the output result of the model provides information reference for the psychological stress level assessment aspect.
Example two
As shown in fig. 2, an embodiment of the present invention further provides a method for assessing a psychological stress level based on a pulse wave signal, which specifically includes the following steps:
s201: obtaining a pulse wave signal of a target object, and carrying out first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object;
s202: extracting heart rate variability features of the cardiac cycle sequence, wherein the heart rate variability features comprise time domain features, frequency domain features, nonlinear features and time-frequency domain features;
s203: selecting the characteristics of the heart rate variability characteristics, constructing a characteristic set, inputting the characteristic set into a preset psychological stress level assessment model, and assessing the psychological stress level of the target object according to the output result of the model; the psychological stress grade evaluation model is obtained by training a classifier through a machine learning method.
The method for assessing a psychological stress level based on a pulse wave signal according to this embodiment is obtained based on the system for assessing a psychological stress level based on a pulse wave signal, and specific embodiments of the method for assessing a psychological stress level based on a pulse wave signal according to this embodiment can be found in the foregoing section of the system for assessing a psychological stress level based on a pulse wave signal, and are not described herein again.
EXAMPLE III
The embodiment of the invention also provides computer equipment, which comprises a processor, a memory and a bus.
The memory stores machine-readable instructions executable by the processor, when a computer device runs, the processor and the memory communicate through a bus, and when the machine-readable instructions are executed by the processor, the steps of the method for assessing a psychological stress level based on a pulse wave signal in the embodiment of the method shown in fig. 2 may be performed.
Example four
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the method for assessing a psychological stress level based on a pulse wave signal according to the above method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A psychological stress level evaluation system based on a pulse wave signal, comprising:
the signal processing module is used for acquiring a pulse wave signal of a target object, and performing first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object;
the characteristic extraction module is used for extracting heart rate variability characteristics of the cardiac cycle sequence, wherein the heart rate variability characteristics comprise time domain characteristics, frequency domain characteristics, nonlinear characteristics and time-frequency domain characteristics;
the grade evaluation module is used for selecting the heart rate variability characteristics, constructing a characteristic set, inputting the characteristic set into a preset psychological stress grade evaluation model, and evaluating the psychological stress grade of the target object according to the output result of the model; the psychological stress level evaluation model is obtained by training a classifier by a machine learning method.
2. The pulse wave signal-based psychological stress level assessing system according to claim 1, further comprising a data collecting module for collecting the pulse wave signal of the target subject; the data acquisition module comprises a pulse wave piezoelectric sensor and an amplification filter which are electrically connected with each other, and the signals acquired by the pulse wave piezoelectric sensor are amplified by the amplification filter to obtain pulse wave signals of the target object.
3. The system according to claim 1, wherein the signal processing module is specifically configured to perform a/D conversion on the acquired pulse wave signal, and perform a first-order difference and filtering on the a/D converted pulse wave signal to obtain a difference sequence; and determining the maximum value of each numerical value point in the difference sequence, taking the maximum value as an identified first peak, and respectively sliding a window forwards or backwards by taking the maximum value as a fixed point to obtain the numerical value point meeting a preset threshold value as a second peak so as to construct the cardiac cycle sequence of the target object.
4. The pulse wave signal-based psychological stress level assessment system according to claim 1, wherein the feature extraction module is configured to perform a discrete fourier transform on the cardiac cycle sequence, calculate and extract frequency domain features.
5. The pulse wave signal-based psychological stress level assessment system according to claim 1, wherein the non-linear characteristics include, but are not limited to, one or more of shannon entropy, approximate entropy, sample entropy, fuzzy entropy, permutation entropy, distribution entropy, poincare minor axis, major axis, minor/major axis, vector angle index, vector length index, porta index, and Guzik index.
6. The pulse wave signal-based psychological stress level assessment system according to claim 1, wherein said feature extraction module is configured to perform a wavelet transform of a preset scale on said cardiac cycle sequence using db4 mother wavelet, and take the mean and standard deviation of the absolute value of detail coefficient of each layer of reconstructed signal as the time-frequency domain feature.
7. The system for psychological stress rating assessment based on pulse wave signals according to claim 1, wherein in the rating assessment module, when feature selection is performed on the heart rate variability features, a recursive elimination method based on a support vector machine is used for screening the features to obtain the feature set.
8. A psychological stress level evaluation method based on a pulse wave signal, comprising:
obtaining a pulse wave signal of a target object, and carrying out first-order difference, filtering and peak identification processing on the pulse wave signal to obtain a cardiac cycle sequence of the target object;
extracting heart rate variability features of the cardiac cycle sequence, wherein the heart rate variability features comprise time domain features, frequency domain features, nonlinear features and time-frequency domain features;
selecting the heart rate variability features, constructing a feature set, inputting the feature set into a preset psychological stress grade assessment model, and assessing the psychological stress grade of the target object according to an output result of the model; the psychological stress level evaluation model is obtained by training a classifier by a machine learning method.
9. A computer device, comprising: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when a computer device is operated, the machine readable instructions when executed by the processor performing the steps of the pulse wave signal based psychological stress level assessment method according to claim 8.
10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, performs the steps of the pulse wave signal-based mental stress level assessment method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211096007.9A CN115363586A (en) | 2022-09-08 | 2022-09-08 | Psychological stress grade assessment system and method based on pulse wave signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211096007.9A CN115363586A (en) | 2022-09-08 | 2022-09-08 | Psychological stress grade assessment system and method based on pulse wave signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115363586A true CN115363586A (en) | 2022-11-22 |
Family
ID=84070976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211096007.9A Pending CN115363586A (en) | 2022-09-08 | 2022-09-08 | Psychological stress grade assessment system and method based on pulse wave signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115363586A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116616708A (en) * | 2023-05-22 | 2023-08-22 | 深圳市腾进达信息技术有限公司 | Vital sign data processing method and system based on intelligent wearable device |
| CN116919372A (en) * | 2023-09-14 | 2023-10-24 | 北京觉心健康科技有限公司 | Pressure peak time identification method and system based on heart rate variability |
-
2022
- 2022-09-08 CN CN202211096007.9A patent/CN115363586A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116616708A (en) * | 2023-05-22 | 2023-08-22 | 深圳市腾进达信息技术有限公司 | Vital sign data processing method and system based on intelligent wearable device |
| CN116919372A (en) * | 2023-09-14 | 2023-10-24 | 北京觉心健康科技有限公司 | Pressure peak time identification method and system based on heart rate variability |
| CN116919372B (en) * | 2023-09-14 | 2023-12-22 | 北京觉心健康科技有限公司 | Pressure peak time identification method and system based on heart rate variability |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109171712B (en) | Atrial fibrillation identification method, atrial fibrillation identification device, atrial fibrillation identification equipment and computer readable storage medium | |
| Çınar et al. | Classification of normal sinus rhythm, abnormal arrhythmia and congestive heart failure ECG signals using LSTM and hybrid CNN-SVM deep neural networks | |
| CN109276241B (en) | Pressure identification method and equipment | |
| CN115363586A (en) | Psychological stress grade assessment system and method based on pulse wave signals | |
| Altan et al. | A new approach to early diagnosis of congestive heart failure disease by using Hilbert–Huang transform | |
| CN109077715A (en) | A kind of electrocardiosignal automatic classification method based on single lead | |
| CN110037668B (en) | System for judging age, health state and malignant arrhythmia identification by combining pulse signal time-space domain with model | |
| US20140371610A1 (en) | Method and apparatus for beat-space frequency domain prediction of cardiovascular death after acute coronary event | |
| CN109948396B (en) | Heart beat classification method, heart beat classification device and electronic equipment | |
| Panigrahy et al. | Detection of ventricular fibrillation rhythm by using boosted support vector machine with an optimal variable combination | |
| CN104840186A (en) | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) | |
| CN113995419B (en) | Atrial fibrillation risk prediction system based on heartbeat rhythm signal and application thereof | |
| Raj et al. | Automated recognition of cardiac arrhythmias using sparse decomposition over composite dictionary | |
| WO2022233027A1 (en) | Wearable device-based method and system for motion fatigue detection | |
| CN110623678A (en) | Blood glucose measuring device, data processing method thereof and storage medium | |
| CN111956210B (en) | Electrocardiosignal R wave identification method based on EEMD and signal structure analysis | |
| Song et al. | Extracting features for cardiovascular disease classification based on ballistocardiography | |
| CN113349793A (en) | Arrhythmia classification method based on layered attention model | |
| Bruun et al. | Automatic atrial fibrillation detection: A novel approach using discrete wavelet transform and heart rate variability | |
| Lee et al. | A real-time abnormal beat detection method using a template cluster for the ECG diagnosis of IoT devices | |
| CN113116300A (en) | Physiological signal classification method based on model fusion | |
| CN117017297A (en) | Method for establishing prediction and identification model of driver fatigue and application thereof | |
| CN112037906A (en) | Method and system for expanding sample data of long-time physiological signal time sequence | |
| Lucena et al. | The performance of short-term heart rate variability in the detection of congestive heart failure | |
| Karimian et al. | Noise assessment framework for optimizing ecg key generation |
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 |