CN111134689B - Blood glucose concentration detection method based on time-frequency Teager-Kaiser energy - Google Patents
Blood glucose concentration detection method based on time-frequency Teager-Kaiser energy Download PDFInfo
- Publication number
- CN111134689B CN111134689B CN202010089839.2A CN202010089839A CN111134689B CN 111134689 B CN111134689 B CN 111134689B CN 202010089839 A CN202010089839 A CN 202010089839A CN 111134689 B CN111134689 B CN 111134689B
- Authority
- CN
- China
- Prior art keywords
- frequency
- time
- teager
- blood glucose
- blood sugar
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention relates to the fields of photoacoustic signal processing, human blood sugar detection application and the like. The method is mainly characterized by providing a blood glucose concentration detection algorithm with high detection precision and strong anti-interference capability, and realizing the non-invasive blood glucose detection technology. The main scheme comprises the steps of 1, inputting a blood sugar photoacoustic signal f (t) to be detected; step 2, performing S conversion on the blood sugar photoacoustic signals f (t) obtained in the step 1 to obtain time-frequency spectrums g (t, f) of the blood sugar photoacoustic signals; step 3, frequency selection is carried out on the blood sugar photoacoustic signal time frequency spectrum g (t, f) obtained in the step 2, and a refined time frequency spectrum is obtainedStep 4, the refined time frequency spectrum obtained in the step 3 is usedCalculating the energy of Teager-Kaiser, and recording as E (t); and 5, predicting the E (t) obtained in the step 4 by using a linear regression model to obtain a detection result, and outputting the detection result. The invention is used for detecting the blood sugar concentration.
Description
Technical Field
The invention relates to the field of photoacoustic signal detection and identification application, in particular to a real-time detection and measurement technology of blood glucose concentration, a time-frequency analysis technology of photoacoustic signals and the like.
Background
Diabetes has become one of the major diseases that endanger human health. By 2017, diabetics worldwide have reached 4.249 billion with 8.3% adults. Also, there is a cost of over 7200 billion dollars annually for treating diabetics worldwide. However, until now, there is no specific and effective treatment for diabetes internationally, and therefore accurate measurement of blood glucose levels in patients and appropriate management thereof are important means for ensuring the health of patients.
At present, the means for detecting blood sugar at home and abroad are mainly divided into two types of minimally invasive detection and non-invasive detection. Wherein, the minimally invasive blood sugar detection belongs to invasive detection and needs to puncture the skin of a patient and collect blood; non-invasive blood glucose detection does not require blood collection, but instead measures blood glucose concentration in blood by using techniques such as microwave, spectroscopy, and optoacoustic. Since diabetics usually need to monitor blood glucose concentration in real time, noninvasive blood glucose detection technology is gradually becoming a research hotspot and is an important research direction of blood glucose detection technology.
The non-invasive blood glucose detection technology has various measurement modes, such as blood glucose detection technology based on a microwave sensor, blood glucose detection technology based on infrared spectrum, blood glucose detection technology based on photoacoustic spectrum, and the like. Each of these measurement techniques has its own advantages and its own disadvantages, and there is no clear advantage of either technique over the others. In the microwave-based blood glucose detection technology, the microwave is not absorbed by blood glucose, so that the signal-to-noise ratio is low and the measurement accuracy is poor; the blood glucose detection technology based on the infrared spectrum cannot measure the blood concentration of the deep layer of the skin because water absorbs infrared light highly, and meanwhile, light scattering also generates great interference on measurement; the blood glucose detection technology based on the photoacoustic spectroscopy is not influenced by light scattering, but has weak signals, and expensive measurement equipment is needed to realize higher measurement precision.
At present, a great deal of detailed research is carried out on a blood glucose photoacoustic signal acquisition and measurement system, but a signal processing algorithm aiming at the blood glucose photoacoustic signal is rarely explored. The method mainly aims at the acquired blood sugar signal to perform subsequent data processing; and designing a new signal processing algorithm based on a time-frequency analysis algorithm, and establishing a signal model of the blood glucose photoacoustic signal.
Disclosure of Invention
The invention aims at solving the problem of whether the correlation exists between the blood glucose concentration and the signal characteristics in the blood glucose photoacoustic signal detection, provides a blood glucose concentration detection method with high detection precision and strong anti-interference capability, and provides a feasible thought for the design of the implementation method of the non-invasive blood glucose detection technology.
In order to solve the technical problems and achieve the aim, the invention adopts the following technical scheme:
a blood sugar concentration detection method based on time-frequency Teager-Kaiser energy is characterized by comprising the following steps:
step 4, the refined time frequency spectrum obtained in the step 3 is usedCalculating the energy of Teager-Kaiser, and recording as E (t);
in the above technical solution, the specific process of step 2 is as follows: performing S conversion on the blood sugar photoacoustic signal f (t) obtained in the step 1, wherein the formula is as follows:
wherein g (t, f) represents the result of S conversion, f (τ) represents the blood glucose photoacoustic signal, f represents the frequency, and t represents the time.
In the above technical solution, the specific process in step 3 is as follows: using the initial frequency f to the time frequency spectrum g (t, f) obtained in the step 2sAnd a cut-off frequency fePerforming truncation processing, i.e. refining the time spectrumContains only the frequencies in the time spectrum g (t, f) higher than the starting frequency fsAnd below the cut-off frequency fePart (c) of (a).
Wherein the starting frequency fsAnd a cut-off frequency feThe selection rule of (1) is: the frequency band formed by the start frequency and the cut-off frequency needs to contain more than 90% of effective value in the time spectrum g (t, f), wherein the effective value is | g (t, f) & gtLiquid2A value greater than 0.
In the above technical solution, the specific process of step 4 is as follows: using the refined time-frequency spectrum obtained in step 3The Teager-Kaiser energy was calculated. Let T be aT, f be b/NT, a represents the a-th time sample point, b represents the b-th frequency sample point, where T is the sampling interval, N is the signal sampling length, then the time-frequency spectrumIn discrete form ofThe Teager-Kaiser energy calculation formula is therefore:
wherein, Re [ ·]The representation takes the real part, Im [. cndot]The representation takes the imaginary part, ΨR(a, b) and ΨI(a, b) represent the real and imaginary parts of the Teager-Kaiser energy, respectively, for a single frequency slice, and the total Teager-Kaiser energy Ψ (a), which is formulated as
In the above technical solution, the specific process in the step 5 is as follows: predicting the blood glucose concentration of the Teager-Kaiser energy E (t) of the photoacoustic signal of the blood glucose to be detected obtained in the step (4) by using a linear regression model, and outputting a detection result;
the prediction method of the linear regression model comprises the following specific steps: the linear regression model that this patent used is first order polynomial model, and specific formula is:
wherein, x represents an input variable,respectively representing the slope and intercept in the model, and y representing the predicted value.
The prediction method of the linear regression model is to use the trained model parametersBy mixing t0Teager-Kaiser energy E (t) at time0) Substituted into(5) In the method, a predicted value can be calculated, and the prediction of the blood glucose concentration is completed; wherein, t0The time is determined empirically, and the Teager-Kaiser energy e (t) maximum position is typically chosen.
The model parameter training method of the linear regression model is as follows:
firstly, selecting a blood sugar photoacoustic signal N group with known concentration, and recording the ith blood sugar photoacoustic signal as fi(t) and the corresponding blood glucose concentration is ni. For each blood sugar photoacoustic signal fi(t) processing according to the steps 1 to 4 to obtain corresponding Teager-Kaiser energy E (t, n)i). Finally, the least square method is utilized to carry out the treatment on N groups of blood sugar concentrations NiAnd the corresponding Teager-Kaiser energy E (t, n)i) Using linear regression model to carry out data fitting to obtain model parameter slope and intercept
Compared with the prior art, the invention has the following beneficial effects:
the invention applies S transformation in time-frequency analysis technology to the blood sugar photoacoustic signal, and extracts the time-frequency spectrum of the signal; and aiming at the characteristics of blood sugar photoacoustic signals, Teager-Kaiser energy characteristics in a time frequency spectrum are extracted for representing the height of blood sugar concentration, so that the blood sugar concentration can be accurately reflected when the signal-to-noise ratio is low; finally, a linear regression model is used for quantitatively measuring the blood glucose concentration of the blood glucose photoacoustic signal with unknown concentration.
The invention uses the time-frequency analysis technology, can simultaneously extract the time domain information and the frequency domain information of the signal compared with the traditional method, and simultaneously extracts the Teager-Kaiser energy based on the time-frequency spectrum, can accurately reflect the blood sugar concentration under the low signal-to-noise ratio, and obtains higher measurement precision.
The method is based on S transformation and Teager-Kaiser energy operator, combines the characteristics of the blood sugar photoacoustic signal, and carries out blood sugar concentration detection on the blood sugar photoacoustic signal with the concentration to be detected. Because the S transformation can simultaneously extract the time domain information and the frequency domain information of the signals, and the blood sugar photoacoustic signals belong to non-stationary signals, the time frequency spectrum of the blood sugar photoacoustic signals is extracted by the S transformation, and then the Teager-Kaiser energy attribute is extracted from the time frequency spectrum, so that the concentration of blood sugar can be well represented. A large number of data tests show that the blood glucose concentration and the Teager-Kaiser energy have strong linear relation, and meanwhile, compared with the traditional method, the method has higher detection accuracy and can still ensure higher accuracy under the condition of low signal-to-noise ratio. The invention provides a blood glucose concentration detection algorithm with high detection precision and strong anti-interference capability aiming at the problem of whether correlation exists between blood glucose concentration and signal characteristics in blood glucose photoacoustic signal detection, and provides a feasible thought for algorithm design of a non-invasive blood glucose detection technology.
Drawings
FIG. 1: an algorithm design flow chart;
FIG. 2: blood glucose photoacoustic original signals;
FIG. 3: a complete time frequency spectrum;
FIG. 4: a single frequency spectrum;
FIG. 5: blood glucose concentration and time-frequency Teager-Kaiser energy curve.
Detailed Description
The invention will be further described with reference to the accompanying drawings and specific embodiments.
Inputting a photoacoustic signal f (t) of blood sugar to be detected;
s conversion is carried out on the blood sugar photoacoustic signals f (t) obtained in the step 1 to obtain time frequency spectrums g (t, f) of the blood sugar photoacoustic signals;
thirdly, frequency selection is carried out on the blood sugar photoacoustic signal time frequency spectrum g (t, f) obtained in the step 2, and a refined time frequency spectrum is obtainedThe starting frequency and the cut-off frequency here are usually taken as empirical values;
fourthly, the refined time frequency spectrum obtained in the step 3 is usedCalculating the energy of Teager-Kaiser, and recording as E (t);
predicting the E (t) obtained in the step (4) by using a linear regression model to obtain a detection result, and outputting the detection result;
in the invention, the step two is specifically as follows: performing S conversion on the blood glucose photoacoustic signal f (t) obtained in the step I, wherein the formula is as follows:
wherein g (t, f) represents the result of S conversion, f (τ) represents the blood glucose photoacoustic signal, f represents the frequency, and t represents the time.
In the invention, the step III is specifically as follows: using the initial frequency f for the time frequency spectrum g (t, f) obtained in the step IIsAnd a cut-off frequency fePerforming truncation processing, i.e. refining the time spectrumContains only the frequencies in the time spectrum g (t, f) higher than the starting frequency fsAnd below the cut-off frequency fePart (c) of (a).
Wherein the starting frequency fsAnd a cut-off frequency feThe selection rule of (1) is: the frequency band formed by the start frequency and the cut-off frequency needs to contain more than 90% of effective value in the time spectrum g (t, f), wherein the effective value is | g (t, f) & gtLiquid2A value greater than 0.
In the invention, the specific flow of the step (iv) is as follows: using the refined time frequency spectrum obtained in the step (c)The Teager-Kaiser energy was calculated. Let T be aT, f be b/NT, a represents the a-th time sample point, b represents the b-th frequency sample point, where T is the sampling interval, N is the signal sampling length, then the time-frequency spectrumIn discrete form ofThe Teager-Kaiser energy calculation formula is therefore:
wherein, Re [ ·]The representation takes the real part, Im [. cndot]The representation takes the imaginary part, ΨR(a, b) and ΨI(a, b) represent the real and imaginary parts of the Teager-Kaiser energy, respectively, for a single frequency slice, and the total Teager-Kaiser energy Ψ (a), which is formulated as
In the invention, the concrete flow of the fifth step is as follows: predicting the blood sugar concentration of the Teager-Kaiser energy E (t) of the photoacoustic signal of the blood sugar to be detected, which is obtained in the step (IV), by using a linear regression model, and outputting a detection result;
the prediction method of the linear regression model comprises the following specific steps: the linear regression model that this patent used is first order polynomial model, and specific formula is:
wherein, x represents an input variable,respectively representing the slope and intercept in the model, and y representing the predicted value.
The prediction method of the linear regression model is to use the trained model parametersBy mixing t0Teager-Kaiser energy E (t) at time0) Substituting into formula (5), calculating predicted value, and completing prediction of blood glucose concentration; wherein, t0The time is determined empirically, and the Teager-Kaiser energy e (t) maximum position is typically chosen.
The model parameter training method of the linear regression model is as follows:
firstly, selecting a blood sugar photoacoustic signal N group with known concentration, and recording the ith blood sugar photoacoustic signal as fi(t) and the corresponding blood glucose concentration is ni. For each blood sugar photoacoustic signal fi(t) processing according to the steps 1 to 4 to obtain corresponding Teager-Kaiser energy E (t, n)i). Finally, the least square method is utilized to carry out the treatment on N groups of blood sugar concentrations NiAnd the corresponding Teager-Kaiser energy E (t, n)i) Using linear regression model to carry out data fitting to obtain model parameter slope and intercept
Claims (5)
1. A blood sugar concentration detection method based on time-frequency Teager-Kaiser energy is characterized by comprising the following steps:
step 1, inputting a photoacoustic signal f (t) of blood sugar to be detected;
step 2, performing S conversion on the blood sugar photoacoustic signals f (t) obtained in the step 1 to obtain time-frequency spectrums g (t, f) of the blood sugar photoacoustic signals;
step 3, frequency selection is carried out on the blood sugar photoacoustic signal time frequency spectrum g (t, f) obtained in the step 2, and a refined time frequency spectrum is obtained
Step 4, the refined time frequency spectrum obtained in the step 3 is usedCalculating the energy of Teager-Kaiser, and recording as E (t);
step 5, predicting the E (t) obtained in the step 4 by using a linear regression model to obtain a detection result, and outputting the detection result;
the specific process of the step 5 is as follows: predicting the blood glucose concentration of the Teager-Kaiser energy E (t) of the photoacoustic signal of the blood glucose to be detected obtained in the step (4) by using a linear regression model, and outputting a detection result;
the prediction method of the linear regression model comprises the following specific steps: the linear regression model used is a first-order polynomial model, and the specific formula is as follows:
wherein, x represents an input variable,respectively representing the slope and intercept in the model, and y representing a predicted value;
the prediction method of the linear regression model is to use the trained model parametersBy mixing t0Teager-Kaiser energy E (t) at time0) Substituting into formula (5), calculating predicted value, and completing prediction of blood glucose concentration; wherein, t0The time is determined empirically, and the Teager-Kaiser energy e (t) maximum position is typically chosen.
2. The method for detecting the blood glucose concentration based on the time-frequency Teager-Kaiser energy according to claim 1, wherein the specific process in the step 2 is as follows: performing S conversion on the blood sugar photoacoustic signal f (t) obtained in the step 1, wherein the formula is as follows:
wherein g (t, f) represents the result of S conversion, f (τ) represents the blood glucose photoacoustic signal, f represents the frequency, and t represents the time.
3. The method for detecting the blood glucose concentration based on the time-frequency Teager-Kaiser energy according to claim 1, wherein the specific process in the step 3 is as follows: using the initial frequency f to the time frequency spectrum g (t, f) obtained in the step 2sAnd a cut-off frequency fePerforming truncation processing, i.e. refining the time spectrumContains only the frequencies in the time spectrum g (t, f) higher than the starting frequency fsAnd below the cut-off frequency feA moiety of (a);
wherein the starting frequency fsAnd a cut-off frequency feThe selection rule of (1) is: the frequency band formed by the start frequency and the cut-off frequency needs to contain more than 90% of effective value in the time spectrum g (t, f), wherein the effective value is | g (t, f) & gtLiquid2A value greater than 0.
4. The method for detecting the blood glucose concentration based on the time-frequency Teager-Kaiser energy according to claim 1, wherein the specific process of the step 4 is as follows: using the refined time-frequency spectrum obtained in step 3Calculating Teager-Kaiser energy;
let T be aT, f be b/NT, where T is the sampling interval, N is the signal sampling length, a represents the a-th time sample, and b represents the b-th frequency sample, then the time-frequency spectrumIn discrete form ofThe Teager-Kaiser energy calculation formula is therefore:
wherein, Re [ ·]The representation takes the real part, Im [. cndot]The representation takes the imaginary part, ΨR(a, b) and ΨI(a, b) represent the real and imaginary parts of the Teager-Kaiser energy, respectively, for a single frequency slice, and the total Teager-Kaiser energy Ψ (a), which is formulated as
5. The method for detecting blood glucose concentration based on time-frequency Teager-Kaiser energy according to claim 1, wherein the method for training model parameters of the linear regression model is as follows:
firstly, selecting a blood sugar photoacoustic signal N group with known concentration, and recording the ith blood sugar photoacoustic signal as fi(t) and the corresponding blood glucose concentration is niFor each blood glucose photoacoustic signal fi(t) processing according to the steps 1 to 4 to obtain corresponding Teager-Kaiser energy E (t, n)i) Finally, the least square method is utilized to carry out the treatment on N groups of blood sugar concentrations NiAnd the corresponding Teager-Kaiser energy E (t, n)i) Using linear regression model to carry out data fitting to obtain model parameter slopeAnd intercept
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010089839.2A CN111134689B (en) | 2020-03-31 | 2020-03-31 | Blood glucose concentration detection method based on time-frequency Teager-Kaiser energy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010089839.2A CN111134689B (en) | 2020-03-31 | 2020-03-31 | Blood glucose concentration detection method based on time-frequency Teager-Kaiser energy |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111134689A CN111134689A (en) | 2020-05-12 |
CN111134689B true CN111134689B (en) | 2021-05-14 |
Family
ID=70527415
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010089839.2A Active CN111134689B (en) | 2020-03-31 | 2020-03-31 | Blood glucose concentration detection method based on time-frequency Teager-Kaiser energy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111134689B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113295674B (en) * | 2021-04-29 | 2022-10-14 | 中国科学院沈阳自动化研究所 | Laser-induced breakdown spectroscopy characteristic nonlinear processing method based on S transformation |
CN114081482B (en) * | 2021-11-23 | 2023-04-18 | 电子科技大学 | Blood glucose concentration detection method and device based on waveform evidence regression |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106814393A (en) * | 2015-11-27 | 2017-06-09 | 中国石油化工股份有限公司 | A kind of evaluation method of stratum quality factor q |
CN107708528A (en) * | 2015-06-25 | 2018-02-16 | 皇家飞利浦有限公司 | Apparatus and method for the physiological status of monitoring object |
CN110623678A (en) * | 2018-06-22 | 2019-12-31 | 深圳市游弋科技有限公司 | Blood glucose measuring device, data processing method thereof and storage medium |
CN110811636A (en) * | 2019-10-29 | 2020-02-21 | 四川知周光声医疗科技有限公司 | Photoacoustic noninvasive blood glucose detector |
-
2020
- 2020-03-31 CN CN202010089839.2A patent/CN111134689B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107708528A (en) * | 2015-06-25 | 2018-02-16 | 皇家飞利浦有限公司 | Apparatus and method for the physiological status of monitoring object |
CN106814393A (en) * | 2015-11-27 | 2017-06-09 | 中国石油化工股份有限公司 | A kind of evaluation method of stratum quality factor q |
CN110623678A (en) * | 2018-06-22 | 2019-12-31 | 深圳市游弋科技有限公司 | Blood glucose measuring device, data processing method thereof and storage medium |
CN110811636A (en) * | 2019-10-29 | 2020-02-21 | 四川知周光声医疗科技有限公司 | Photoacoustic noninvasive blood glucose detector |
Non-Patent Citations (2)
Title |
---|
Brazilian deep water carbonate reservoir study using the wavelet transform;Marcílio Castro de Matos et al.;《SEG Technical Program Expanded Abstracts》;20080131;第1-5页 * |
基于连续小波变换Teager-Kaiser能量在储层预测中的应用;尹继尧 等;《地球物理学进展》;20140831;第1863-1866页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111134689A (en) | 2020-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018107915A1 (en) | General noninvasive blood glucose prediction method based on timing analysis | |
CN110338813B (en) | Noninvasive blood glucose detection method based on spectrum analysis | |
EP1250082B1 (en) | Classification and characterization of tissue through features related to adipose tissue | |
CN111134689B (en) | Blood glucose concentration detection method based on time-frequency Teager-Kaiser energy | |
CN101206463B (en) | Method and system for on-line monitoring medicaments production mixing process | |
CN107228904B (en) | Photoinduced ultrasonic blood glucose noninvasive detection device and method | |
CN108652640B (en) | Non-invasive blood glucose detection method and system based on electrocardiosignals | |
CN103149177A (en) | Device and method for detecting biological tissue of pressure modulation near infrared spectrum | |
CN113662538A (en) | Non-invasive blood glucose detection method based on time-frequency domain comprehensive analysis | |
CN108324286B (en) | Infrared noninvasive blood glucose detection device based on PCA-NARX correction algorithm | |
CN106691410B (en) | Pulse and red blood cell concentration monitor and method | |
CN103027669A (en) | Method and equipment for judging floating and sinking degree of pulse condition | |
Shulei et al. | Non-invasive blood glucose measurement scheme based on near-infrared spectroscopy | |
CN116327188B (en) | Blood oxygen analysis method based on finger-clip type oximeter | |
CN117017297A (en) | Method for establishing prediction and identification model of driver fatigue and application thereof | |
CN113974618B (en) | Noninvasive blood glucose testing method based on water peak blood glucose correction | |
CN114886421A (en) | Near-infrared-based high-precision noninvasive blood glucose concentration detection system and method | |
CN114145725A (en) | PPG sampling rate estimation method based on noninvasive continuous blood pressure measurement | |
CN114081483A (en) | Tissue blood flow and blood oxygen saturation measuring method based on deep learning diffusion correlation spectrum | |
CN114081482B (en) | Blood glucose concentration detection method and device based on waveform evidence regression | |
Li et al. | Research on multi-parameter fusion non-invasive blood glucose detection method based on machine learning. | |
CN114795288A (en) | Human body osteoporosis detection method based on ultrasonic guided wave frequency dispersion curve | |
CN113208586A (en) | Noninvasive blood glucose rapid diagnosis differential Raman spectroscopy system | |
CN110974250B (en) | Terahertz spectrum-based blood glucose detection method and device and computer storage medium | |
CN211022696U (en) | Portable noninvasive blood glucose detection device based on near-infrared optics |
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 |