CN117281479A - Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion - Google Patents
Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion Download PDFInfo
- Publication number
- CN117281479A CN117281479A CN202311351065.6A CN202311351065A CN117281479A CN 117281479 A CN117281479 A CN 117281479A CN 202311351065 A CN202311351065 A CN 202311351065A CN 117281479 A CN117281479 A CN 117281479A
- Authority
- CN
- China
- Prior art keywords
- chronic pain
- pain
- semg
- lower limb
- data
- 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
- 208000002193 Pain Diseases 0.000 title claims abstract description 65
- 208000000094 Chronic Pain Diseases 0.000 title claims abstract description 26
- 210000003141 lower extremity Anatomy 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000004927 fusion Effects 0.000 title claims abstract description 15
- 208000024891 symptom Diseases 0.000 claims abstract description 13
- 238000012706 support-vector machine Methods 0.000 claims abstract description 7
- 230000003183 myoelectrical effect Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000036541 health Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000007635 classification algorithm Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 230000006872 improvement Effects 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract description 8
- 238000002567 electromyography Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000008602 contraction Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 206010011878 Deafness Diseases 0.000 description 1
- 230000036982 action potential Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000001087 myotubule Anatomy 0.000 description 1
- 230000008035 nerve activity Effects 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 210000002027 skeletal muscle Anatomy 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000000451 tissue damage Effects 0.000 description 1
- 231100000827 tissue damage Toxicity 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4824—Touch or pain perception evaluation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
- A61B5/397—Analysis of electromyograms
-
- 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
-
- 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
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention belongs to the technical field of surface electromyography assessment, and provides a method, a storage medium and a device for discriminating human lower limb chronic pain based on surface electromyography multi-dimensional feature fusion. Through Gaussian noise introduction, sEMG multidimensional feature fusion and support vector machine classification learning, the accuracy of judging the chronic pain symptoms of the lower limbs can be effectively enhanced. The invention can provide objective and quantitative scientific analysis means for auxiliary diagnosis of the chronic pain symptoms of the lower limbs, improves the diagnosis work efficiency of doctors, reduces unnecessary examination and avoids the waste of medical resources.
Description
Technical Field
The invention belongs to the technical field of surface electromyography assessment, and particularly relates to a method, a storage medium and a device for discriminating chronic pain of lower limbs of a human body based on multi-dimensional feature fusion of surface electromyography signals.
Background
Pain is the most common symptom in clinic, and is a complex physiological and psychological activity. The international pain community defines pain as an unpleasant and emotional sensation, accompanied by existing or potential tissue damage. At present, pain is a fifth vital sign after four vital signs of body temperature, pulse, respiration and blood pressure, and is increasingly valued by the international society and medical community, in fact, pain is a subjective experience, traditional doctor diagnosis is very dependent on subjective statement of a patient, and if pain conditions of the patient can be analyzed through objective and scientific technical means, the pain diagnosis method has very important significance for standardizing diagnosis procedures and improving pain diagnosis accuracy.
The conventional subjective pain assessment means are usually digital assessment, visual simulation (VAS) and other methods for describing pain conditions, but the difference in distinguishing pain conditions is always caused by the difference in subjective consciousness of each person. In particular, for particular groups, such as infants, the deaf-mute, the elderly, etc., these groups present varying degrees of impediments in accurately expressing pain conditions. Besides the method, the nerve activity related to pain in the brain can be observed through an electroencephalogram (EEG) so as to evaluate the pain degree, however, the technology has higher use cost, and patients can only acquire the EEG signals in professional hospitals, so that the wide application in clinical practice is greatly limited. In addition, the judgment of pain requires expert knowledge and clinical experience of doctors, and it is difficult for experts seeking rich experience to judge pain symptoms in some areas or places with limited medical resources.
Surface electromyographic signals (semgs) are bioelectric currents produced by the contraction of human surface muscles. The nervous system controls the movement (contraction or relaxation) of the muscles, and at the same time different muscle fiber movement units on the surface skin produce mutually different signals. The acquisition of the electromyographic signals of the skin surface layer is called surface electromyographic signals, sEMG. The surface electromyographic signals are one-dimensional action potential sequences, belong to non-stable micro-electric signals, have amplitude of 0-1.5mv, useful signal frequency of 0-500HZ and main energy concentration of 20-150HZ. sEMG signals have a number of dimensional features that have important application values in research, clinical and motor physiology fields. In addition, myoelectric devices are low in cost and mature in application, and have various advantages in the pain field, and can provide important information about pain mechanisms and pain treatments.
Pain is one of the most important indicators of clinical symptoms, and is important for pain treatment, and accurate pain assessment can provide the physician with the necessary assistance. In order to assist doctors in judging whether the patient has chronic pain symptoms of lower limbs, the invention collects lower limb electromyographic signals of the patient, processes and analyzes motion-induced electromyographic data, and finally gives a conclusion whether the patient has chronic pain or not through data enhancement and machine learning training models, thereby providing a novel objective evaluation means for objectively evaluating the chronic pain symptoms.
Disclosure of Invention
The invention provides a method, a storage medium and a device for discriminating chronic pain of lower limbs of a human body based on surface electromyographic signal multi-dimensional feature fusion, which comprise the following steps:
s1, selecting a plurality of subjects including N healthy volunteers and M patients with chronic pain of lower limbs. And attaching an electrode patch to a selected part of the subject, connecting a power supply, starting a self-made surface electromyographic signal acquisition device, and recording a surface electromyographic (sEMG) signal of the subject by an acquisition module according to a set frequency. The data acquisition is divided into a training set and a testing set, and the training set data is marked as 0 or 1 according to a health group and a pain group;
s2, guiding the subject to repeatedly complete multiple groups of lower limb actions, and collecting surface myoelectricity data induced by continuous actions;
s3, removing a baseline noise and high-frequency interference part through a high-pass filter on the basis of S2, and obtaining a sEMG filtering signal of 10Hz-160 Hz;
s4, on the basis of S3, converting the sEMG filtering signals into a frequency domain through short-time Fourier transform, estimating an energy spectrum, removing sEMG signal segments lower than a given energy threshold, and reserving myoelectric potentials induced by lower limb actions;
s5, on the basis of S4, gaussian noise is added to myoelectric data in a training set to artificially synthesize a myoelectric signal, and the training set data is expanded;
s6, respectively extracting the sEMG multidimensional features of the training set from the time domain and the time-frequency domain on the basis of S5;
s7, on the basis of S6, combining the sEMG multidimensional feature and a Bayesian optimization algorithm to optimize the Gaussian kernel function kernel scale for supporting a vector machine classification algorithm;
s8, on the basis of S7, carrying out two classifications on the combined characteristic data of the test set sEMG according to pain and health by adopting an optimal Gaussian kernel function and a Support Vector Machine (SVM), and calculating pain symptom estimation accuracy;
s9, randomly distributing the acquired myoelectricity data to a training set and a testing set according to a set proportion, repeating the steps S1 to S8 for a plurality of times (for example, 1000 times), calculating an average value of pain symptom estimation accuracy, and obtaining a stable estimation result.
In S5, the artificially synthesized myoelectric signal is added with specific signal-to-noise ratio and high-noise ratio only aiming at myoelectric data of a patient suffering from chronic pain of lower limbs, so that the purpose of enhancing small sample data is realized. In S6, the multi-dimensional feature extraction includes root mean square value (RMS), average value of absolute values (ABSMean), median frequency (MDF), average frequency (MNF), and the like.
Compared with the prior art, the invention has the following beneficial effects:
1. the surface electromyographic signal acquisition and storage medium and the device based on autonomous development are easy to operate, the electrode patch acquisition position is convenient to position, the design action of a subject is simple, and the device is beneficial to popularization and application to communities and household places.
2. By introducing Gaussian noise data enhancement and sEMG multidimensional feature fusion classification, the invention can effectively improve the recognition accuracy of chronic pain and enhance the recognition robustness, and can provide an effective sEMG quantitative analysis method for chronic pain diagnosis.
Drawings
FIG. 1 is a diagram showing an electromyographic signal acquisition device and an analysis structure of the present invention;
FIG. 2 is a flow chart of the myoelectric signal acquisition device of the present invention;
FIG. 3 is a flow chart of a calculation unit of the electromyographic signal acquisition device of the invention;
FIG. 4 is a schematic representation of surface myoelectricity of a healthy subject pretreated in accordance with the present invention;
FIG. 5 is a schematic representation of surface myoelectricity of a subject with pain after pretreatment in accordance with the present invention;
fig. 6 is a graph showing the contrast of the myoelectric signals of the front and rear surfaces of the gaussian noise (snr=15) introduction of the present invention;
fig. 7 is a schematic diagram of gaussian noise (snr=15) introduced gaussian kernel function optimizing process according to the present invention;
FIG. 8 is a graph showing the accuracy of pain identification on a test set under different Gaussian signal-to-noise ratios in accordance with the present invention;
FIG. 9 is a schematic diagram of a foot rest state of a subject according to the present invention;
fig. 10 is a schematic diagram of placement of an electrode patch of the electromyographic signal acquisition system of a subject according to the invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings and examples. The following examples are illustrative of the invention but are not intended to limit the scope of the invention.
As shown in fig. 1 to 9:
examples: a method, a storage medium and a device for discriminating chronic pain of lower limbs of a human body based on multi-dimensional characteristic fusion of surface electromyographic signals comprise the following steps:
s1, connecting a power supply starting acquisition device, attaching an electrode patch to a selected part, and acquiring signals of the selected human body part by an electromyographic signal acquisition module at a set acquisition frequency; the system block diagram is shown in fig. 1. The electromyographic signal acquisition device and the Ag/Agcl surface electrode sheet are used for electromyographic signal acquisition, the electromyographic signal gain is 2000, the input impedance is more than 100MΩ, the sampling bandwidth is 50-1000Hz, the sensitivity is 1uV, and the signal sampling rate is 1700 times/second. The acquisition process and the calculation process are shown in fig. 2 and 3, respectively.
S2, selecting 30 healthy volunteers aged 22-30 years old and 5 male patients aged 20-30 years old with chronic pain in lower limbs. Allowing the subject to continuously and repeatedly perform 34 groups of tiptoe standing actions, collecting myoelectricity data of lower limb actions of the subject, and performing foot padding states as shown in fig. 9; the gastrocnemius muscle and hand electrode patch placement position is shown in fig. 10.
S3, removing the baseline noise and the high-frequency part through a Bart Wo Fugao pass filter on the basis of S2, and intercepting the sEMG signals of 10Hz-160 Hz. The electromyographic signals after filtration of healthy subjects and painful subjects are shown in fig. 4 and 5;
s4, on the basis of S3, converting the sEMG signals into a frequency domain through short-time Fourier transform, estimating the energy spectrum of the sEMG signals, removing sEMG signal segments lower than a given energy threshold, and retaining myoelectric potential induced by actions;
s5, on the basis of S4, artificially synthesizing a new myoelectric signal by adding Gaussian noise to myoelectric data of patients in the training set, and expanding the data quantity of the training set; the invention respectively generates artificial synthetic electromyographic signals with Gaussian signal-to-noise ratios of SNR=5, 10, 15, 20, 25, 30, 35 and 40 for verifying the influence of different signal-to-noise ratios on the classification accuracy of a small sample data set. Fig. 6 shows a graph of the artificially generated electromyographic signal versus the original electromyographic signal potential when snr=10;
s6, on the basis of S5, carrying out multi-dimensional feature extraction on a time domain and a time-frequency domain on a real original electromyographic signal and an artificially generated electromyographic signal, wherein the multi-dimensional feature extraction comprises a root mean square value (RMS), an average value of absolute values (ABSMean), a median frequency (MDF), an average frequency (MNF) and the like;
s7, optimizing the kernel scale of the Gaussian kernel function by using a Bayesian optimization algorithm on the basis of S6, wherein the iteration times are set to be 30 times. The iterative process is shown in fig. 7;
and S8, classifying the combined characteristic data of the electromyographic signals of the test set by combining the Gaussian kernel function of the optimal estimation parameter and the support vector machine SVM on the basis of S7, and finally outputting pain and health group classification results. FIG. 8 shows pain state recognition accuracy at different kernel scales of the Gaussian kernel function;
s9, repeating S1 to S8 a plurality of times (1000 times), recording each pain discrimination accuracy and calculating an average value as a stable pain symptom evaluation result.
From the above, the invention relates to a human lower limb chronic pain classification technology based on surface electromyographic signal multi-dimensional feature fusion, which can be used for carrying out two classifications (health or pain) on electromyographic signal data collected by a subject. Firstly, through a Gaussian noise data enhancement strategy, gaussian noise when the superimposed SNR is 40 is compared with the electromyographic signals of the training set patients, so that the classification accuracy of the subjects can be effectively improved (see figure 8). Secondly, using Bayesian optimization to obtain a kernel scale parameter (simply named KerS) of the Gaussian kernel function, taking integer values of 1-5 for the kernel scale parameter through an empirical value method, and finding out that the pain discrimination accuracy reaches the highest 92.77% when the KerS takes 1 through experimental results. Based on the above experimental results, it is suggested to superimpose gaussian noise with SNR of 40 on the patient myoelectric data, and the gaussian kernel scale parameter KerS is set to 1.
In conclusion, the method for judging the chronic pain of the lower limb of the human body based on the multi-dimensional characteristic fusion of the surface electromyographic signals has the following effects:
1. the surface electromyographic signal acquisition and storage medium and the device based on autonomous development are easy to operate, the electrode patch acquisition position is convenient to position, the design action of a subject is simple, and the device is beneficial to popularization and application to communities and household places.
2. By introducing Gaussian noise data enhancement and sEMG multidimensional feature fusion classification, the invention can effectively improve the recognition accuracy of chronic pain symptoms and enhance the robustness of an algorithm, and can provide an effective sEMG quantitative analysis method for chronic pain diagnosis; the invention is beneficial to intelligent pain assessment, reduces unnecessary examination and avoids waste of medical resources.
While embodiments of the present invention have been shown and described above for purposes of illustration and description, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (4)
1. A method, a storage medium and a device for discriminating chronic pain of lower limbs of a human body based on multi-dimensional characteristic fusion of surface electromyographic signals are characterized in that: the method comprises the following steps:
s1, selecting a plurality of subjects including N healthy volunteers and M patients with chronic pain of lower limbs. And attaching an electrode patch to a selected part of the subject, connecting a power supply, starting a self-made surface electromyographic signal acquisition device, and recording a surface electromyographic (sEMG) signal of the subject by an acquisition module according to a set frequency. The data acquisition is divided into a training set and a testing set, and the training set data is marked as 0 or 1 according to a health group and a pain group;
s2, guiding the subject to repeatedly complete multiple groups of lower limb actions, and collecting surface myoelectricity data induced by continuous actions;
s3, removing a baseline noise and high-frequency interference part through a high-pass filter on the basis of S2, and obtaining a sEMG filtering signal of 10Hz-160 Hz;
s4, on the basis of S3, converting the sEMG filtering signals into a frequency domain through short-time Fourier transform, estimating an energy spectrum, removing sEMG signal segments lower than a given energy threshold, and reserving myoelectric potentials induced by lower limb actions;
s5, on the basis of S4, gaussian noise is added to myoelectric data in a training set to artificially synthesize a myoelectric signal, and the training set data is expanded;
s6, respectively extracting the sEMG multidimensional features of the training set from the time domain and the time-frequency domain on the basis of S5;
s7, on the basis of S6, combining the sEMG multidimensional feature and a Bayesian optimization algorithm to optimize the Gaussian kernel function kernel scale for supporting a vector machine classification algorithm;
s8, classifying the test set sEMG combined characteristic data according to a pain group and a health group by adopting an optimal Gaussian kernel function and a Support Vector Machine (SVM) on the basis of S7, and calculating pain symptom estimation accuracy;
s9, randomly distributing the acquired myoelectricity data to a training set and a testing set according to a set proportion, repeating the steps S1 to S8 for a plurality of times (for example, 1000 times), calculating an average value of pain symptom estimation accuracy, and obtaining a stable estimation result.
2. The method, the storage medium and the device for distinguishing the chronic pain of the lower limb of the human body based on the multi-dimensional feature fusion of the surface electromyographic signals as claimed in claim 1 are characterized in that: in S5, the artificially synthesized myoelectric signal is added with specific signal-to-noise ratio and high-noise ratio only aiming at myoelectric data of a patient with lower limb chronic pain, so that the purpose of enhancing small sample data is realized.
3. The method, the storage medium and the device for distinguishing the chronic pain of the lower limb of the human body based on the multi-dimensional feature fusion of the surface electromyographic signals as claimed in claim 1 are characterized in that: in S6, the multi-dimensional feature extraction includes a root mean square value (RMS), an average value of absolute values (ABSMean), a median frequency (MDF), an average frequency (MNF), and the like.
4. The method, the storage medium and the device for distinguishing the chronic pain of the lower limb of the human body based on the multi-dimensional feature fusion of the surface electromyographic signals as claimed in claim 1 are characterized in that: in S7, the gaussian kernel function kernel scale is selected and iteratively selected by using a bayesian optimization algorithm, where the bayesian optimization algorithm includes the following steps:
defining a search range of which the super parameters comprise a kernel scale (KerS) and a frame constraint level, wherein the search range is 0.001-1000;
secondly, selecting a model classification error as an objective function and minimizing the error, inputting the model classification error as a super-parameter value, and outputting the model classification error as a classification error;
randomly initializing super parameters and establishing a prior probability distribution by using a Gaussian process, wherein the distribution is used for predicting an objective function value;
(IV) selecting Expected Improvement acquisition functions, allocating a score to each possible super-parameter combination, and then selecting the super-parameter combination with the highest score as the next super-parameter evaluation value. And simultaneously transmitting the evaluation value to an objective function for error calculation. The above steps are iterated continuously until the maximum iteration number is reached or convergence is complete.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351065.6A CN117281479A (en) | 2023-10-18 | 2023-10-18 | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351065.6A CN117281479A (en) | 2023-10-18 | 2023-10-18 | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117281479A true CN117281479A (en) | 2023-12-26 |
Family
ID=89257113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311351065.6A Pending CN117281479A (en) | 2023-10-18 | 2023-10-18 | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117281479A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117653042A (en) * | 2024-01-31 | 2024-03-08 | 中船凌久高科(武汉)有限公司 | Multi-mode-based cared person pain level judging method and testing device |
| CN117653042B (en) * | 2024-01-31 | 2024-04-26 | 中船凌久高科(武汉)有限公司 | Multi-mode-based cared person pain level judging method and testing device |
-
2023
- 2023-10-18 CN CN202311351065.6A patent/CN117281479A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117653042A (en) * | 2024-01-31 | 2024-03-08 | 中船凌久高科(武汉)有限公司 | Multi-mode-based cared person pain level judging method and testing device |
| CN117653042B (en) * | 2024-01-31 | 2024-04-26 | 中船凌久高科(武汉)有限公司 | Multi-mode-based cared person pain level judging method and testing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Karthikeyan et al. | Analysis of stroop color word test-based human stress detection using electrocardiography and heart rate variability signals | |
| CN106407733A (en) | Depression risk screening system and method based on virtual reality scene electroencephalogram signal | |
| Sobahi | Denoising of EMG signals based on wavelet transform | |
| CN105147248A (en) | Physiological information-based depressive disorder evaluation system and evaluation method thereof | |
| CN109674468A (en) | It is a kind of singly to lead brain electricity sleep mode automatically method by stages | |
| CN204931634U (en) | Based on the depression evaluating system of physiologic information | |
| CN111708978B (en) | Multi-scale time-frequency inter-muscle coupling analysis method | |
| Pauk | 419. Different techniques for EMG signal processing. | |
| Islam et al. | Probability mapping based artifact detection and wavelet denoising based artifact removal from scalp EEG for BCI applications | |
| Chu et al. | Physiological signals based quantitative evaluation method of the pain | |
| Abedi et al. | Investigating the effect of traditional Persian music on ECG signals in young women using wavelet transform and neural networks | |
| CN117281479A (en) | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion | |
| Duhan et al. | Study of signal processing techniques for EMG analysis | |
| Ugarte et al. | An algorithm to measure the stress level from EEG, EMG and HRV signals | |
| CN115067942A (en) | Psychological state assessment method, device, medium and product based on multi-physiological parameter intelligent analysis | |
| CN114098768A (en) | Cross-individual surface electromyographic signal gesture recognition method based on dynamic threshold and easy TL | |
| CN107440687B (en) | Pain grade evaluation method and pain grade evaluation device adopting same | |
| Ni et al. | Extracting heartbeat intervals using self-adaptive method based on ballistocardiography (BCG) | |
| Qi | Algorithms benchmarking for removing EOG artifacts in brain computer interface | |
| Kilby et al. | Continuous wavelet analysis and classification of surface electromyography signals | |
| Majid et al. | Performance assessment of the optimum feature extraction for upper-limb stroke rehabilitation using angular separation method | |
| CN113974652B (en) | Muscle control accuracy determining method based on cortical muscle function network model | |
| Srinagesh et al. | ECG wireless telemetry | |
| Duraisamy et al. | A systematic approach for pulse diagnosis based on siddha medical procedures | |
| Zhang et al. | Research on the method of evaluating psychological stress by EEG |
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 |