CN116458845A - Wearable traditional chinese medical science physique evaluation system of intelligence - Google Patents
Wearable traditional chinese medical science physique evaluation system of intelligence Download PDFInfo
- Publication number
- CN116458845A CN116458845A CN202310366362.1A CN202310366362A CN116458845A CN 116458845 A CN116458845 A CN 116458845A CN 202310366362 A CN202310366362 A CN 202310366362A CN 116458845 A CN116458845 A CN 116458845A
- Authority
- CN
- China
- Prior art keywords
- peak
- point
- wave
- pulse wave
- physique
- 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
- 238000011156 evaluation Methods 0.000 title abstract description 6
- 239000003814 drug Substances 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000000630 rising effect Effects 0.000 claims description 16
- 208000031975 Yang Deficiency Diseases 0.000 claims description 8
- 208000031971 Yin Deficiency Diseases 0.000 claims description 8
- 230000000284 resting effect Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 201000010099 disease Diseases 0.000 abstract description 17
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 17
- 208000017667 Chronic Disease Diseases 0.000 abstract description 10
- 238000003745 diagnosis Methods 0.000 abstract description 10
- 238000011160 research Methods 0.000 abstract description 5
- 238000011161 development Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 244000062645 predators Species 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 210000004369 blood Anatomy 0.000 description 7
- 239000008280 blood Substances 0.000 description 7
- 230000006872 improvement Effects 0.000 description 6
- 230000001174 ascending effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000036541 health Effects 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000002861 ventricular Effects 0.000 description 4
- 230000003321 amplification Effects 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000037213 diet Effects 0.000 description 3
- 235000005911 diet Nutrition 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000003199 nucleic acid amplification method Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 206010062717 Increased upper airway secretion Diseases 0.000 description 2
- 210000000709 aorta Anatomy 0.000 description 2
- 230000004872 arterial blood pressure Effects 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006806 disease prevention Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000474 nursing effect Effects 0.000 description 2
- 208000026435 phlegm Diseases 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 210000001765 aortic valve Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 210000000624 ear auricle Anatomy 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000003811 finger Anatomy 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000005240 left ventricle Anatomy 0.000 description 1
- 230000033001 locomotion Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 210000005259 peripheral blood Anatomy 0.000 description 1
- 239000011886 peripheral blood Substances 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 229940126532 prescription medicine Drugs 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 210000000707 wrist Anatomy 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
- A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
-
- 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
-
- 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
- A61B5/021—Measuring pressure in heart or blood vessels
- A61B5/02108—Measuring pressure in heart or blood vessels from analysis of pulse wave characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Cardiology (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Behavior & Ethology (AREA)
- Primary Health Care (AREA)
- Physiology (AREA)
- Epidemiology (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Vascular Medicine (AREA)
- Alternative & Traditional Medicine (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses an intelligent wearable traditional Chinese medicine physique evaluation system, and relates to the field of electrophysiological sensors and biomedical signal processing and classification. The invention is beneficial to the informatization of individual physique and the construction of a traditional Chinese medicine physique information base. The establishment of the constitution information base can provide help for the biological characteristic research of constitution so as to promote the national medical care level and construct the personalized diagnosis and treatment system of traditional Chinese medicine. The diagnosis and treatment means of helping hand development "no disease is treated first" can help the user to condition the constitution of the deviation in time, find and clear away chronic diseases of the body of the predator as early as possible, prevent the occurrence of diseases related to constitution, and enable the organism to be restored to the healthy state of "yin-yang-secret". Realizing intelligent Chinese medicine pulse taking. The method for acquiring the vital sign of the patient by analyzing the pulse wave characteristics can replace or assist the pulse taking of the traditional Chinese medicine to a certain extent, so that the detection result is more objective, and the result is convenient to store and quantitatively analyze.
Description
Technical Field
The present invention relates to the field of electrophysiological sensors, biomedical signal processing and classification.
Background
Constitutions refer to the inherent characteristics of individuals, such as comprehensive and relatively stable morphological structure, physiological function and psychological state, which are formed on the basis of inheritance in the first day and acquisition in the last day, and the constitution of people is classified into nine types by the ninth-minute method of constitution in traditional Chinese medicine: mild, qi deficiency, yin deficiency, yang deficiency, blood stasis, damp heat, phlegm dampness, qi depression and specific properties. Each body constitution has different physical characteristics, psychological characteristics, adaptability to the external environment and specific attack tendency. The traditional Chinese medicine physique takes the artificial research of life individuals as a starting point, and aims to research the composition characteristics, evolution rules, influence factors and classification standards of different physiques; moreover, the field of traditional Chinese medicine physique is regarded as the source of many diseases, and the theory of traditional Chinese medicine is expected to be used as a guide, and a basis is provided for preventing and treating diseases of each type of the biased physique by a physique identification method, so that a personalized health care method for different physiques is formulated.
The pulse diagnosis system of Chinese traditional medicine in China is very dependent on subjective judgment of doctors, can not quantify diagnosis results, and lacks scientific and accurate modern medical expression; the research on traditional Chinese medicine physique evaluation is less, the detection means of the traditional Chinese medicine physique identifier which is put into the market or is being researched and developed is single, most users fill out questionnaires to obtain self physique results, and the physical information of the traditional Chinese medicine is not really used for informatization and digital processing; and the selling price varies from seven thousand to forty thousand yuan, and the size is 65 multiplied by 55 multiplied by 130 (cm). Therefore, the traditional Chinese medicine physique identifier used at present is huge, heavy and expensive, user data can be input only through an inefficient query means, the result lacks scientificity and objectivity, the functions of real-time monitoring, rapid analysis of the physique of the user and instant reporting of the result cannot be realized, the delay time is long, the use is inconvenient, a large number of users cannot be attracted, and the early-finding early-warning function without disease treatment cannot be applied to a sufficiently reliable and wide platform.
Disclosure of Invention
Aiming at the technical problems, the invention aims to establish an intelligent wearable traditional Chinese medicine physique evaluation system which is extremely low in cost, judges the traditional Chinese medicine physique of a user by using the acquired physiological signal indexes of the user, and proposes personalized physique improvement and adjustment suggestions for users with different physiques.
The technical scheme of the invention is as follows: an intelligent wearable traditional Chinese medicine physique assessment system, the system comprising: the system comprises a wearing end and a cloud end, wherein the wearing end acquires photoelectric volume pulse wave signals in a target resting state and then sends the photoelectric volume pulse wave signals to the cloud end, and the cloud end classifies target physique by analyzing the acquired photoelectric volume pulse wave signals; the classification includes: mild, yin deficiency, yang deficiency, damp heat;
after the wearing end collects the photoelectric volume pulse wave signals in the target resting state, the signals are filtered and amplified firstly, and then the processed signals are transmitted to the cloud;
the cloud firstly establishes a clustering center, and a sample database is acquired through a wearing end, wherein the sample database comprises the following components: the goals of mild constitutions, yin deficiency constitutions, yang deficiency constitutions and damp heat constitutions, and each constitutions includes multiple goals; after the cloud receives the sample database acquired and processed by the wearing end, extracting the characteristics of each signal in the database, wherein the extracted characteristics comprise: pulse wave main peak value, rising branch slope, waveform area and pulse rate; reducing dimensions of the extracted four features by adopting a main component analysis method based on JavaScript to obtain two-dimensional features, and splicing the four two-dimensional features to obtain a target feature; the target features obtained by the sample database are gathered into 4 classes, 4 clustering centers are obtained, and the 4 classes are respectively: mild, yin deficiency, yang deficiency, damp heat;
setting a WebSocket at a wearing end to realize real-time two-way communication with a cloud; after each time new data arrives and clustering operation is carried out, euclidean distances between the target features of the new data points and four new clustering center points are calculated, and physique corresponding to the shortest distance center point is the physique type of the tester; therefore, the data of the user can be collected in real time, the data volume is increased, the database is expanded, and the accuracy of physique classification is improved;
and then returning the classification result of the cloud to the wearing end.
Further, the method for extracting the characteristics comprises the following steps:
step 1: calculating a trough point;
traversing each point of the acquired pulse wave curve, comparing the amplitude values of each point, and if the amplitude value of a certain point is smaller than the amplitude values of the left and right points, marking the point as a pulse wave valley point and recording the point data; dividing the pulse wave to obtain the period of the corresponding pulse wave, and further obtaining the pulse rate;
step 2: calculating a peak point;
traversing and comparing the amplitude values of each point in the pulse wave curve, and marking the pulse wave curve as a peak point if the amplitude value of one point is larger than the amplitude values of the left and right points; extracting a main wave peak point by adopting a threshold method, setting a fixed threshold value, comparing the amplitude values of all wave peak points marked before with the main wave peak point, wherein the wave peak point is the main wave peak point which is larger than the fixed threshold value, and further extracting the wave peak;
step 3: screening wave peaks, and calculating rising branch slope and pulse wave area;
extracting peak points by adopting a dynamic amplitude threshold method, firstly taking a conventional main wave peak value as an initial threshold value of a first period to carry out first screening, if the number of the peak points is 1, indicating that the threshold value is properly set, calibrating the threshold value as the main wave peak point, and entering a next period; if the number of peak points is greater than 1, the threshold value is smaller Yu Chongbo, and the occurrence time of the peak points screened out is compared with the peak value of the tide wave peak, and because the peak point which occurs earliest in one period is the peak point of the main wave peak, calibration is carried out, and the next period is entered; if the number of the peak points is zero, firstly decreasing the initial threshold value by taking five as a gradient until the number of the peak points is greater than zero, and repeating the two steps; according to the cycle, a main wave crest peak point of each cycle is obtained, and the rising time is calculated by utilizing the difference between the occurrence time of the main wave crest peak point and the occurrence time of the initial wave trough of the cycle; dividing each main wave crest peak value by the corresponding rising time to obtain rising branch slope; and calculating the corresponding pulse wave area by combining the trough valley values obtained by marking through the divided pulse wave periods.
Compared with the existing traditional Chinese medicine physique identifier, the system has the following technical advantages:
is beneficial to the informatization of individual physique and the construction of a traditional Chinese medicine physique information base. The establishment of the constitution information base can provide help for the biological characteristic research of constitution so as to promote the national medical care level and construct the personalized diagnosis and treatment system of traditional Chinese medicine. In the diagnosis and treatment activities of clinical diseases, the prevention and treatment measures and the treatment measures of the diseases are based on the constitution identification, and the system can help doctors to quickly acquire constitution characteristics of patients and take corresponding treatment measures.
The diagnosis and treatment means for helping hand development of 'no disease first treatment' can help users to timely condition the deviated physique, discover and clear away chronic diseases of the bodies of predators as early as possible, prevent the occurrence of physique related diseases, enable organisms to recover to the healthy state of 'yin-yang secret', discover disease high risk groups through a physique analysis system, provide early discovery and early warning grippers for the chronic disease high risk groups, realize the prevention, control and mouth-opening forward movement of the chronic diseases, solve the problem of disease screening in accurate medicine, guide the prevention, diagnosis, recovery and health maintenance of diseases, improve the health level and life quality, and are key items of 'no disease treatment' in traditional Chinese medicine.
Realizing intelligent Chinese medicine pulse taking. The method for acquiring the vital sign of the patient by analyzing the pulse wave characteristics can replace or assist the pulse taking of the traditional Chinese medicine to a certain extent, so that the detection result is more objective, and the result is convenient to store and quantitatively analyze. The information is utilized to push the traditional Chinese medicine to the world, and the new technologies such as artificial intelligence, big data and the like are utilized to excavate and summarize the diagnosis and treatment rules of the traditional Chinese medicine, so that the technology is energized, and the traditional Chinese medicine is changed into digital medicine.
Drawings
FIG. 1 is a standard pulse wave waveform diagram for a healthy adult;
FIG. 2 is a graph of the result of a system split period sample according to the present invention;
FIG. 3 is a flow chart of the dynamic amplitude thresholding method of the system of the present invention;
FIG. 4 is a main wave crest sign chart of four types of constitutions of the system;
FIG. 5 is a graph of systematic clustering results according to the present invention;
FIG. 6 is a flow chart of the system design of the present invention;
FIG. 7 is a diagram of a hardware circuit connection of the present invention;
FIG. 8 is a flow chart of the sensor operation of the present invention;
fig. 9 is a diagram illustrating a user's use in an embodiment of the present invention.
Detailed Description
The user adjusts the respiration, measures own pulse wave for three minutes through the sensor under the resting state, the data Bluetooth is transmitted to the computer, four characteristic values of the user are obtained through program analysis, the Euclidean distance from the characteristic values to the center points of the four samples is calculated and compared to judge the physique type of the user, the user goes to a recommendation system website to check the physique by himself after obtaining the physique type, corresponding nursing suggestions of life, diet, exercise and the like are obtained, and physique improvement is carried out. The related physique judgment is obtained after diagnosis by a professional traditional Chinese medical doctor, so that the doctor gives advice. Therefore, whether the two results are identical or not is judged, and the effect of the project is tested. In future experiments, the sample is expanded, the rest five physique features can be extracted continuously, the physique information database is enriched, and the accuracy of physique assessment is further improved. In order to build a database of a traditional Chinese medicine constitution monitoring system, a tested person is firstly recruited, and a self-measuring table of the traditional Chinese medicine constitution is filled in, wherein the measuring table is King qi, zhu Yanbo, xue Hesheng, and the like: 12-14, calculating the score of the body by a conversion score formula to obtain a corresponding physique; collecting pulse wave signals through a PPG (photo volume pulse wave sensor), processing the signals through a chip, removing noise, performing analog-digital conversion, storing data, and transmitting the data to a computer for pattern feature recognition to extract pulse wave signal features; and finally, grouping the pulse wave signal characteristics of the tested pulse wave signals through a cluster analysis correlation algorithm, and tracing by combining the self-measuring meter results of the physique to obtain the pulse wave characteristic center point corresponding to the corresponding physique. And in order to ensure the accuracy and reliability of classification, the classification result is subjected to optimization inspection.
After the work is completed, a system improvement recommendation system is manufactured, and personalized sports, diet and life work and rest habit prompts and recommendations are given for different physique. The user can monitor the pulse wave of the user in real time through the system and detect the physical fitness of the user in a staged mode. The system design flow chart is shown in fig. 6.
Compared with the traditional Chinese medicine physique identifier, the system opens up a new field for researching the relationship between human life phenomenon and diseases and health, provides a new visual angle and a new method for preventing and controlling chronic diseases and public health, forms a disease prediction system based on physique, establishes a corresponding chronic disease prediction standard and evaluation system, makes a chronic disease regulating body prevention and control scheme, develops a regulating body prescription medicine and the like, builds a disease intervention plan based on 'physique is adjustable', and makes various chronic disease prevention and control practice guidelines. The construction of the prevention and control system of 'early screening-early warning-early intervention' for chronic disease regulation provides a new path and method for the development of chronic disease prevention and control large-health industries such as cancer in China, promotes the quantitative and intelligent development of Chinese medicine science, and provides technical support for the mastering of the right of speaking of independent intellectual property rights of Chinese medicine physique in China.
The collection scale is seven hundred seventy-eight parts, three hundred sixteen single physique targets are screened according to physique conditions by calculating conversion fraction, but because sample data are smaller and tested population is basically 17-26 years old young population, the number of rare physique tested such as qi deficiency, phlegm dampness and the like is very small, subsequent data analysis is difficult to carry out, and three hundred zero five tested are finally screened to carry out subsequent pulse wave data acquisition. (one hundred and fifty-five kinds of mild and forty-eight kinds of yin deficiency and forty-seventeen kinds of yang deficiency and forty-five kinds of damp-heat)
Pulse wave signals are acquired using a reflective photo sensor PulseSensor according to the photoplethysmogram (PPG) principle. The photoelectric volume method for collecting pulse waves has the advantages of realizing noninvasive collection, being low in cost and accurate in measurement result, and being capable of well meeting the application requirements of wearable devices. The sensor can be worn on the finger, wrist, earlobe and other parts during measurement. When the light beam passes through the peripheral blood vessel, the transmittance of the light beam changes due to the change of arterial pulse congestion volume, and at the moment, the light reflected by human tissues is received by the photoelectric converter, converted into an electric signal, amplified and output. The hardware circuit connection diagram is shown in fig. 7.
The PulseSensor sensor selects green light with the peak wavelength of 515nm as a light source;
the method comprises the steps of collecting tested resting state pulse wave data through previous hardware equipment, enabling a tested end to sit, enabling a left hand arm to be horizontally placed on a table top in the collecting process, adjusting breathing for one minute, and then collecting three minutes of tested left arm index finger resting state pulse waves.
After the front end is used for collecting the light source and the light receiver of the pulse wave signals, the PulseSensor sensor also integrates an amplifying and filtering circuit in the sensor circuit board, so that the pulse wave signals subjected to noise amplification and filtering can be directly obtained from the analog output pins of the sensor.
The APDS-9008 module at the front end is used as a photoelectric converter and is used for receiving the light rays reflected by blood and converting the light intensity signals into electric signals to be transmitted to a following circuit. After that, the influence caused by the factors such as ambient light, slight disturbance of human body and the like is removed through a low-pass filtering module. The filtered signal is sent to the MCP6001 module for amplification. Because the pulse wave signal amplitude is in millivolt level, the signal is weak, the amplification factor is set to be 330 times, and the amplified pulse wave signal is output from an analog output pin of the sensor. The sensor workflow diagram is shown in fig. 8.
In the analog-to-digital conversion and transmission part, sampling and transmission communication is performed through an Arduino Uno board. According to the characteristics of pulse wave frequency bands and the limitation of the output speed of an Arduino serial port, setting the sampling frequency to 200Hz, and displaying the acquired signals in a serial port monitor in real time;
to better suit the requirements of the wearable device, bluetooth is used for data transmission. The HC-05 Bluetooth module can be used for transmitting pulse wave data acquired by the arduino to a PC or mobile phone end, and the working mode and Bluetooth transmission parameters of the Bluetooth module can be set in the arduino IDE, so that the signal transmission requirement is met, and the pulse wave data are transmitted to a cloud through the PC or mobile phone end.
Because the main wave is a pressure wave which rapidly shoots blood and suddenly increases the aortic internal pressure when the left ventricle contracts, the peak-to-peak value of the pressure wave represents the highest point of the aortic pressure, which indicates that the arterial systolic pressure reaches the maximum at the moment; the slope, amplitude and waveform area of ascending branch indirectly reflect the heart blood output, ejection speed, left ventricular function state and resistance effect of ejection, and these data are different depending on the age, constitution, physical quality and activity of the individual. Therefore, four indexes of the main peak value, the rising branch slope, the waveform area and the pulse rate of the pulse wave are selected as characteristic values.
Firstly, screening a better data segment through a tested integral waveform diagram, displaying three thousands of sampling points in the better data segment, and drawing the waveform diagram. For a healthy adult pulse, the present invention requires analysis of the following components in the pulse wave waveform (see fig. 1), (1) rising branches: the ventricular injection main artery has large blood volume and high flow velocity, is a rapid ventricular injection period, rapidly increases arterial blood pressure, expands a tube wall, forms an ascending curve OA from a base line to a main peak top in pulse waveform, has the ascending time of t1, and has the main wave with the highest peak top positioned in an ascending branch; (2) and (3) descending branches: in the later stage of ventricular ejection, the ejection speed is reduced, the blood volume entering the aorta is less than the blood volume flowing from the main artery to the periphery, the expanded aorta starts to retract, the arterial blood pressure is gradually reduced, and a descending branch in a pulse wave waveform, namely a descending curve from the main wave capping to the base line in the pulse wave waveform is formed; (3) tidal wave: peak B is generally lower than the main peak and higher than Yu Chongbo peak; (4) heavy wave: the aortic elastic recoil wave is generated when the aortic valve closes, the last ascending wave in the descending branch.
The troughs are the most easily determined periodic features in the pulse map, so the pulse period is segmented using the calibrated troughs as the segmentation points. And (3) by calling a peakdet function in MATLAB, programming, traversing each point of the acquired pulse wave curve, comparing the amplitudes of each point, and if the amplitude of a certain point is smaller than the amplitudes of the left and right points, marking the certain point as a pulse wave valley point and recording the point data. The pulse wave is divided, and the period of the corresponding pulse wave is obtained. The pulse rate is similar to the heart rate, and the calculation formula is sixty seconds divided by the period, so that the pulse rate is obtained. The sample results of the segmentation period are shown in fig. 2.
The peak is the most obvious characteristic point in the pulse wave waveform in the pulse period and the application range is the widest, and many characteristic values of the pulse wave are determined by the peak, so that each main wave peak needs to be recorded in the pulse wave waveform. Marking all wave peak points including heavy waves and tide waves by using a method for marking wave valley points, traversing and comparing the amplitude values of all points in a pulse wave curve, and marking a certain point as a wave peak point if the amplitude value of the certain point is larger than the amplitude values of the left point and the right point of the certain point. Although the main wave peak value of each pulse wave is different in size, in general, the height is in a certain range, the amplitude is maximum, the rising speed is fastest, and the difference value between the main wave peak value and the trough is maximum, so we consider to extract the main wave peak point by adopting a threshold method, set a value close to the conventional wave peak amplitude, compare all the wave peak point amplitudes marked before with the value, and the wave peak point is the main wave peak point larger than the value, thereby extracting the wave peak.
Because of the influence of individual physique, the peak values of the tide wave and the heavy wave are similar to the peak value of the main wave, and when the peak is screened by using a single fixed threshold value, the peak value point of the tide wave and the heavy wave is easy to obtain, but not the peak value point of the main wave; in order to avoid data loss caused by the fact that the amplitude of the pulse wave changes with time and the acquired main wave peak value is smaller than the conventional main wave peak value, a dynamic amplitude threshold method is adopted to extract peak values, and a flow chart is shown in fig. 4: firstly, taking a conventional main wave peak value as an initial threshold value of a first period to carry out first screening, if the number of peak points is 1, indicating that the threshold value is properly set, calibrating the threshold value as a main wave peak point, and entering a next period; if the number of peak points is greater than 1, the peak value of the peak point with the threshold value smaller than Yu Chongbo (and tide wave) is indicated, the occurrence time of the screened peak points is compared, and as the main wave occurs earliest in one period, the peak point which occurs earliest is the peak value of the main wave peak, calibration is carried out, and the next period is entered; if the number of the peak points is zero, the initial threshold value is firstly decreased by taking five as a gradient until the number of the peak points is greater than zero, and the two steps are repeated. According to the cycle, a main wave crest peak point of each cycle is obtained, and the rising time is calculated by utilizing the difference between the occurrence time of the main wave crest peak point and the occurrence time of the initial wave trough of the cycle; dividing each main wave crest peak value by the corresponding rising time to obtain the rising branch slope. And calculating the corresponding pulse wave area by combining the trough valley value obtained by marking through the divided pulse wave period and utilizing a trapz function in MATLAB.
Classifying the data by using an unsupervised cluster analysis method. Firstly, reducing the dimension by using PCA, and converting the four features extracted in the previous step into two-dimensional features. Compared with the effects of several clustering methods, the K-means algorithm is selected, so that the method has high convergence efficiency and high speed, and meets the requirements of the experimental design. Firstly, adopting a main component analysis method based on JavaScript to reduce the dimensions of the four extracted features to obtain two-dimensional features, and splicing the four two-dimensional features to obtain a target feature. Clustering the target features to obtain four clusters and four cluster centers. And tracing to obtain the actual physical constitution ratio of each cluster, wherein the physical constitution ratio with the largest ratio is the physical constitution type represented by the center of the cluster. The clustering result is shown in fig. 5.
In order to further meet the physical improvement requirement of users, the system is used for supplementing and designing physical improvement and recommending web pages. Three plates of formation cause and disease tendency, diet nursing and instrument health maintenance are designed for each physique, and a user can check the characteristics of the physique in the system by himself, obtain personalized physique improvement suggestions and further adjust living habits to improve the physique (the use description diagram of the user is shown in fig. 9). In addition, the website is also provided with a constitution science popularization plate which can update science popularization articles every day and popularize Chinese medicine constitution and health-preserving related knowledge for users.
Claims (2)
1. An intelligent wearable traditional Chinese medicine physique assessment system, the system comprising: the system comprises a wearing end and a cloud end, wherein the wearing end acquires photoelectric volume pulse wave signals in a target resting state and then sends the photoelectric volume pulse wave signals to the cloud end, and the cloud end classifies target physique by analyzing the acquired photoelectric volume pulse wave signals; the classification includes: mild, yin deficiency, yang deficiency, damp heat;
after the wearing end collects the photoelectric volume pulse wave signals in the target resting state, the signals are filtered and amplified firstly, and then the processed signals are transmitted to the cloud;
the cloud firstly establishes a clustering center, and a sample database is acquired through a wearing end, wherein the sample database comprises the following components: the goals of mild constitutions, yin deficiency constitutions, yang deficiency constitutions and damp heat constitutions, and each constitutions includes multiple goals; after the cloud receives the sample database acquired and processed by the wearing end, extracting the characteristics of each signal in the database, wherein the extracted characteristics comprise: pulse wave main peak value, rising branch slope, waveform area and pulse rate; reducing dimensions of the extracted four features by adopting a main component analysis method based on JavaScript to obtain two-dimensional features, and splicing the four two-dimensional features to obtain a target feature; the target features obtained by the sample database are gathered into 4 classes, 4 clustering centers are obtained, and the 4 classes are respectively: mild, yin deficiency, yang deficiency, damp heat;
setting a WebSocket at a wearing end to realize real-time two-way communication with a cloud; after each time new data arrives and clustering operation is carried out, euclidean distances between the target features of the new data points and four new clustering center points are calculated, and physique corresponding to the shortest distance center point is the physique type of the tester; therefore, the data of the user can be collected in real time, the data volume is increased, the database is expanded, and the accuracy of physique classification is improved;
and then returning the classification result of the cloud to the wearing end.
2. The intelligent wearable system for assessing the physical fitness of a traditional Chinese medicine of claim 1, wherein the method for extracting the characteristics comprises the following steps:
step 1: calculating a trough point;
traversing each point of the acquired pulse wave curve, comparing the amplitude values of each point, and if the amplitude value of a certain point is smaller than the amplitude values of the left and right points, marking the point as a pulse wave valley point and recording the point data; dividing the pulse wave to obtain the period of the corresponding pulse wave, and further obtaining the pulse rate;
step 2: calculating a peak point;
traversing and comparing the amplitude values of each point in the pulse wave curve, and marking the pulse wave curve as a peak point if the amplitude value of one point is larger than the amplitude values of the left and right points; extracting a main wave peak point by adopting a threshold method, setting a fixed threshold value, comparing the amplitude values of all wave peak points marked before with the main wave peak point, wherein the wave peak point is the main wave peak point which is larger than the fixed threshold value, and further extracting the wave peak;
step 3: screening wave peaks, and calculating rising branch slope and pulse wave area;
extracting peak points by adopting a dynamic amplitude threshold method, firstly taking a conventional main wave peak value as an initial threshold value of a first period to carry out first screening, if the number of the peak points is 1, indicating that the threshold value is properly set, calibrating the threshold value as the main wave peak point, and entering a next period;
if the number of peak points is greater than 1, the threshold value is smaller Yu Chongbo, and the occurrence time of the peak points screened out is compared with the peak value of the tide wave peak, and because the peak point which occurs earliest in one period is the peak point of the main wave peak, calibration is carried out, and the next period is entered; if the number of the peak points is zero, firstly decreasing the initial threshold value by taking five as a gradient until the number of the peak points is greater than zero, and repeating the two steps; according to the cycle, a main wave crest peak point of each cycle is obtained, and the rising time is calculated by utilizing the difference between the occurrence time of the main wave crest peak point and the occurrence time of the initial wave trough of the cycle; dividing each main wave crest peak value by the corresponding rising time to obtain rising branch slope; and calculating the corresponding pulse wave area by combining the trough valley values obtained by marking through the divided pulse wave periods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310366362.1A CN116458845A (en) | 2023-04-07 | 2023-04-07 | Wearable traditional chinese medical science physique evaluation system of intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310366362.1A CN116458845A (en) | 2023-04-07 | 2023-04-07 | Wearable traditional chinese medical science physique evaluation system of intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116458845A true CN116458845A (en) | 2023-07-21 |
Family
ID=87181727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310366362.1A Pending CN116458845A (en) | 2023-04-07 | 2023-04-07 | Wearable traditional chinese medical science physique evaluation system of intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116458845A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104305971A (en) * | 2014-11-07 | 2015-01-28 | 冯文强 | Pulse-taking detection method, pulse-taking instrument and system |
| CN104706337A (en) * | 2015-02-11 | 2015-06-17 | 华东师范大学 | Automatic pulse wave crest and trough detection method |
| CN107970027A (en) * | 2017-11-23 | 2018-05-01 | 安徽大学 | A kind of radial artery detection and human body constitution identifying system and method |
| CN108261190A (en) * | 2016-12-30 | 2018-07-10 | 深圳先进技术研究院 | Continuous BP measurement method, apparatus and equipment |
| KR20180080515A (en) * | 2017-01-04 | 2018-07-12 | 경상대학교산학협력단 | Sasang Constitution Discriminate Method and Sasang Constitution Discriminator |
| CN109709527A (en) * | 2019-01-14 | 2019-05-03 | 上海海洋大学 | The Gauss wave crest method of Gauss Decomposition in a kind of Full wave shape laser-measured height echo signal |
-
2023
- 2023-04-07 CN CN202310366362.1A patent/CN116458845A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104305971A (en) * | 2014-11-07 | 2015-01-28 | 冯文强 | Pulse-taking detection method, pulse-taking instrument and system |
| CN104706337A (en) * | 2015-02-11 | 2015-06-17 | 华东师范大学 | Automatic pulse wave crest and trough detection method |
| CN108261190A (en) * | 2016-12-30 | 2018-07-10 | 深圳先进技术研究院 | Continuous BP measurement method, apparatus and equipment |
| KR20180080515A (en) * | 2017-01-04 | 2018-07-12 | 경상대학교산학협력단 | Sasang Constitution Discriminate Method and Sasang Constitution Discriminator |
| CN107970027A (en) * | 2017-11-23 | 2018-05-01 | 安徽大学 | A kind of radial artery detection and human body constitution identifying system and method |
| CN109709527A (en) * | 2019-01-14 | 2019-05-03 | 上海海洋大学 | The Gauss wave crest method of Gauss Decomposition in a kind of Full wave shape laser-measured height echo signal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A noninvasive blood glucose monitoring system based on smartphone PPG signal processing and machine learning | |
| JP7261811B2 (en) | Systems and methods for non-invasive determination of blood pressure lowering based on trained predictive models | |
| Naeini et al. | A real-time PPG quality assessment approach for healthcare Internet-of-Things | |
| CN106971059B (en) | Wearable equipment based on neural network self-adaptation health monitoring | |
| CN107242857A (en) | The intelligent traditional Chinese medical science based on deep learning integrates diagnosis and therapy system | |
| Wang et al. | Photoplethysmography-based blood pressure estimation combining filter-wrapper collaborated feature selection with LASSO-LSTM model | |
| CN109065162A (en) | A kind of comprehensive intelligent diagnostic system | |
| Ma et al. | KD-informer: A cuff-less continuous blood pressure waveform estimation approach based on single photoplethysmography | |
| CN106618481A (en) | Traditional Chinese medicine intelligent diagnosis expert system | |
| CN113143230B (en) | Peripheral arterial blood pressure waveform reconstruction system | |
| Chen et al. | Machine learning method for continuous noninvasive blood pressure detection based on random forest | |
| KR20220013559A (en) | System for monitoring physiological parameters | |
| CN113729648B (en) | Wearable pulse-taking bracelet system based on multiple pulse sensors | |
| CN113040738B (en) | Blood pressure detecting device | |
| Priyadarshini et al. | Review of PPG signal using machine learning algorithms for blood pressure and glucose estimation | |
| Ma et al. | Automatic sleep-stage classification of heart rate and actigraphy data using deep and transfer learning approaches | |
| CN116458845A (en) | Wearable traditional chinese medical science physique evaluation system of intelligence | |
| CN114403866B (en) | Noninvasive blood sugar prediction device based on near-infrared light wavelength conversion | |
| CN109147945A (en) | Chinese Medicine Diagnoses System and bracelet | |
| CN109009005A (en) | A kind of wearable Chinese medicine pulse acquisition and analysis system | |
| CN108364690A (en) | A kind of Multifunction life sign detecting system and its working method | |
| CN114176532A (en) | Clinical verification method for determining cfPWV parameters and application system thereof | |
| Yan et al. | Uncertainty quantification of microcirculatory characteristic parameters for recognition of cardiovascular diseases | |
| CN113907733A (en) | Bonaxi AI | |
| Liu et al. | Symmetrical Photoplethysmogram Signal based Cuff-less Blood Pressure Estimation |
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 |