CN117338270A - Household multi-parameter monitor - Google Patents
Household multi-parameter monitor Download PDFInfo
- Publication number
- CN117338270A CN117338270A CN202311657719.8A CN202311657719A CN117338270A CN 117338270 A CN117338270 A CN 117338270A CN 202311657719 A CN202311657719 A CN 202311657719A CN 117338270 A CN117338270 A CN 117338270A
- Authority
- CN
- China
- Prior art keywords
- image
- detection model
- test paper
- arm
- height
- 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.)
- Granted
Links
- 238000010876 biochemical test Methods 0.000 claims abstract description 69
- 210000000707 wrist Anatomy 0.000 claims abstract description 53
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 35
- 238000003780 insertion Methods 0.000 claims abstract description 30
- 230000037431 insertion Effects 0.000 claims abstract description 30
- 239000008280 blood Substances 0.000 claims abstract description 29
- 210000004369 blood Anatomy 0.000 claims abstract description 29
- 239000007788 liquid Substances 0.000 claims abstract description 24
- 230000036772 blood pressure Effects 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims abstract description 18
- 238000009530 blood pressure measurement Methods 0.000 claims abstract description 16
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims abstract description 12
- 239000008103 glucose Substances 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 75
- 239000013598 vector Substances 0.000 claims description 57
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 19
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000008020 evaporation Effects 0.000 claims 2
- 238000001704 evaporation Methods 0.000 claims 2
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 210000003811 finger Anatomy 0.000 description 14
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 238000010241 blood sampling Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 231100000037 inhalation toxicity test Toxicity 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005406 washing Methods 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
- A61B5/02—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
- A61B5/022—Measuring pressure in heart or blood vessels by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers
-
- 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
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/15—Devices for taking samples of blood
- A61B5/157—Devices characterised by integrated means for measuring characteristics of blood
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/66—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving blood sugars, e.g. galactose
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Theoretical Computer Science (AREA)
- Cardiology (AREA)
- Hematology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- Evolutionary Computation (AREA)
- Heart & Thoracic Surgery (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Immunology (AREA)
- Computing Systems (AREA)
- Urology & Nephrology (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Vascular Medicine (AREA)
- Pulmonology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Microbiology (AREA)
- Cell Biology (AREA)
- Biotechnology (AREA)
- Diabetes (AREA)
Abstract
The invention discloses a household multiparameter monitor, which comprises: the device comprises a main processor, a display, a camera device, a blood pressure measuring module and a blood sugar measuring module; the blood pressure measurement module includes: blood pressure gauges, armbands, and/or wrist bands; the main processor is used for detecting whether the tracheal plug of the armband is correctly inserted into the jack according to the first image, detecting the difference between the height of the armband and/or the wrist strap and the heart height of a patient, and detecting the arm movement degree of the patient wearing the armband or the wrist strap; the blood glucose measurement module includes: biochemical measuring instrument and test paper; the main processor is used for detecting the positive and negative directions of the insertion of the biochemical test paper, the alcohol volatilization time on the fingers of the user and the fullness degree of the biochemical test paper sucked into the test liquid according to the second image. The use mode of the household multi-parameter monitor can be observed through the camera, the user is guided to operate according to normal steps, and the experience of the user and the efficiency of health monitoring are improved.
Description
Technical Field
The invention discloses the technical field of health monitoring, in particular to a household multi-parameter monitor.
Background
The household multiparameter monitor is one integrated with blood pressure measurement and blood sugar measurement and is used widely in the household health monitoring of patient. However, the steps of blood pressure measurement and blood glucose measurement are relatively complex, and the specific steps are usually explained by the specification, which is quite different for many elderly people. In addition, there is a way to explain the operation steps through the teaching video, but, the acquisition of the teaching video generally needs to scan the two-dimensional code on the home multi-parameter monitor, or acquire through the background customer service. This approach is still difficult for elderly people who are not good at using the intelligent electronic products, and often causes errors or deviations in use due to reduced learning or understanding capabilities, even memory, etc.
Therefore, those skilled in the art are required to develop a new technical solution to solve the above problems.
Disclosure of Invention
To overcome the problems in the related art, the present disclosure provides a home multi-parameter monitor, the monitor comprising: the device comprises a main processor, a display, a camera device, a blood pressure measuring module and a blood sugar measuring module, wherein the display, the camera device, the blood pressure measuring module and the blood sugar measuring module are respectively and electrically connected with the main processor;
the blood pressure measurement module includes: the blood pressure measuring device comprises a blood pressure meter, an armband and/or a wrist band, wherein the camera device is used for acquiring a first image of a user in the blood pressure measuring process;
the main processor is used for detecting whether the tracheal plug of the armband is correctly inserted into the jack according to the first image, detecting the difference value between the height of the armband and/or the wrist strap and the heart height of a patient, and detecting the arm movement degree of the armband or the wrist strap worn by the patient;
the blood glucose measurement module includes: the image pick-up device is used for collecting a second image of the user in the measuring process of the biochemical test paper;
the main processor is used for detecting the positive and negative directions of the insertion of the biochemical test paper, the volatilization time of the alcohol on the fingers of the user and the fullness degree of the biochemical test paper sucked into the test liquid according to the second image.
Optionally, the home multi-parameter monitor further comprises: the prompting device is electrically connected with the main processor;
the prompting device is used for sending an alarm prompt according to the instruction of the main processor when the tracheal plug of the armband is not inserted into the jack, or when the difference between the depth value of the tracheal plug of the armband inserted into the jack and the standard depth value is larger than a first preset threshold, or when the difference between the height of the armband and/or the wrist strap and the heart height of a patient is larger than a second preset threshold, or when the arm moving degree of the armband or the wrist strap worn by the patient is larger than a preset third preset threshold, or when the back surface of the biochemical test paper is inserted into the biochemical measuring instrument, or when the difference between the alcohol volatilization time and the standard volatilization time on the fingers of a user is larger than a fourth preset threshold, or when the difference between the plumpness of the biochemical test paper sucked into the test liquid and the standard plumpness is larger than a fifth preset threshold.
Optionally, the main processor is configured to detect whether the tracheal plug of the cuff is correctly inserted into the insertion hole according to the first image, detect a difference between the height of the cuff and/or the wristband and the height of the heart of the patient, and wear the arm of the cuff or the wristband, and detect the forward and reverse directions of the insertion of the biochemical test paper according to the second image, and the fullness of the biochemical test paper in the test liquid, including:
respectively preprocessing data of a first image and a second image acquired by the camera device;
extracting a first feature vector of the preprocessed first image through an S-ViT model, and extracting a second feature vector of the preprocessed second image;
according to the first characteristic vector, the second characteristic vector, the pre-trained arm belt tracheal plug detection model, the arm belt and/or wrist belt height detection model, the arm movement detection model, the biochemical test paper insertion positive and negative detection model, the alcohol volatilization detection model and the siphon plumpness detection model, detecting the depth value of the tracheal plug inserted into the jack, the difference value between the height of the arm belt and/or wrist belt and the heart height of a patient, the arm movement of the arm belt or wrist belt worn by the patient, the positive and negative directions of the biochemical test paper insertion, the alcohol volatilization time and the plumpness of the biochemical test paper sucked into the test liquid.
Optionally, the detecting the depth value of the tracheal plug inserted into the jack, the difference between the height of the armband and/or the wrist strap and the heart height of the patient, the arm mobility of the armband or the wrist strap worn by the patient, the forward and reverse directions of the insertion of the biochemical test paper, the alcohol volatilization time and the fullness degree of the biochemical test paper sucked into the test liquid according to the first feature vector, the second feature vector, the pre-trained armband tracheal plug detection model, the arm band and/or the wrist strap height detection model, the arm mobility detection model, the forward and reverse directions of the insertion of the biochemical test paper, the alcohol volatilization time and the siphon fullness degree detection model comprises:
taking the first characteristic vector as the input of a pre-trained arm-band air pipe plug detection model, and judging whether the difference value between the depth value of the arm-band air pipe plug inserted into the jack and the standard depth value is larger than a first preset threshold value or not according to the output of the arm-band air pipe plug detection model;
taking the first characteristic vector as input of a pre-trained arm band and/or wrist band height detection model, and judging whether the difference between the height of the arm band and/or wrist band and the heart height of a patient is larger than a second preset threshold value or not according to the output of the arm band and/or wrist band height detection model;
taking the first feature vector as input of a pre-trained arm mobility detection model, and judging whether the arm mobility of the patient wearing the armband or the wrist strap is greater than a third preset threshold according to the output of the arm mobility detection model;
taking the second feature vector as input of a pre-trained forward and reverse detection model for inserting the biochemical test paper, and judging the forward and reverse of the insertion of the biochemical test paper according to the output of the forward and reverse detection model for inserting the biochemical test paper;
taking the second characteristic vector as input of a pre-trained alcohol volatilization detection model, and judging whether the difference between the alcohol volatilization time and the standard volatilization time is larger than a fourth preset threshold value according to the output of the alcohol volatilization detection model;
and taking the second characteristic vector as the input of a pre-trained siphon plumpness detection model, and judging whether the difference between the plumpness of the biochemical test paper sucked into the test liquid and the standard plumpness is larger than a fifth preset threshold according to the output of the siphon plumpness detection model.
Optionally, the extracting the first feature vector of the preprocessed first image through the S-ViT model includes:
dividing the first image into 14 x 14 small squares, wherein each small square comprises a plurality of pixel points;
dividing the first image into 14 x 14 tiles with a W having a dimension of 48 x 16 E Matrix, obtain the third eigenvector E with dimension 196 x 256 t ；
The third eigenvector is passed through CNN with dimension 196 x1 to obtain importance matrix E s ；
By an importance matrix E s The weights are sequenced, importance scores of each small square are obtained, the data ranked in the top 25 bits are selected to replace 196 data, and a first feature vector is obtained.
Optionally, the extracting the second feature vector of the preprocessed second image includes:
dividing the second image into 14 x 14 small squares, wherein each small square comprises a plurality of pixel points;
divide into 14 x 14 squaresTwo images and W with dimension 48 x 16 E Matrix, obtain fourth eigenvector E with dimension 196 x 256 t ；
The fourth eigenvector is passed through CNN with dimension 196 x1 to obtain importance matrix E s ；
By an importance matrix E s And sequencing the weights to obtain importance scores of each small square, and selecting the data ranked in the top 25 bits to replace 196 data to obtain a second feature vector.
Optionally, the camera device is used for gathering the second image of user in the biochemical test paper measuring process, includes:
when the camera device collects a second image, a rectangular area range W where the biochemical test paper is positioned is defined by a frame 1 The rectangle W 1 Is defined by the two diagonal points PA (x 1, y 1) and PB (x 2, y 2), the intermediate corner point x0 ((x1+x2)/2, y0= (y1+y2)/2).
Optionally, the home multi-parameter monitor further comprises: the camera device is arranged on the rotatable base;
the rotatable base is provided with x-y coordinate axes.
Optionally, the main processor is further configured to: detecting an included angle between x-y coordinate axes on the camera device and the rotatable base, and stopping acquiring the first image and/or the second image by using the camera device if the included angle is larger than a first angle threshold or smaller than a second angle threshold.
In summary, through the technical scheme in the disclosed embodiments of the present invention, the following beneficial effects can be brought:
1) The blood pressure and blood sugar of a patient can be monitored, and a user can select a single blood pressure measuring instrument, a single blood sugar measuring instrument, a blood pressure measuring instrument, a blood sugar measuring instrument and other different combination modes in the use process;
2) The user can be guided to measure the blood pressure and/or the blood sugar according to the correct operation steps by observing the using method of the user through the image pickup device;
3) The neural network model is used for identifying the image acquired by the camera device, so that the identification accuracy is improved;
4) The application method and the steps of the embedded product are proposed, in order to enable ViT to run smoothly on the embedded type, main calculation is subjected to weight sorting, a large number of unimportant weight items are omitted from calculation, and the power consumption and the processing time of a processor are greatly reduced;
5) The method for independently adjusting the angle of the camera is provided, so that other tasks can be accurately observed and judged.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the description serve to explain, but do not limit the disclosure. In the drawings:
FIG. 1 is a schematic diagram of a home multi-parameter monitor, according to an exemplary embodiment;
FIG. 2 is a schematic view of the structure of another home multi-parameter monitor according to FIG. 1;
FIG. 3 is a schematic flow chart of detecting an image according to one of the main processors shown in FIG. 1;
FIG. 4 is a flow chart of a first feature vector extraction according to the one shown in FIG. 3;
fig. 5 is a flow chart of a second feature vector extraction according to the one shown in fig. 3.
Detailed Description
The following describes in detail the embodiments of the present disclosure with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the disclosure, are not intended to limit the disclosure.
Fig. 1 is a schematic structural view of a home multi-parameter monitor according to an exemplary embodiment, as shown in fig. 1, the monitor comprising: the device comprises a main processor 110, a display 120, a camera 130, a blood pressure measurement module 140 and a blood sugar measurement module 150, wherein the display 120, the camera 130, the blood pressure measurement module 140 and the blood sugar measurement module 150 are respectively and electrically connected with the main processor 110; the blood pressure measurement module 140 includes: a blood pressure meter 141, an armband and/or a wrist band 142, the camera 130 is used for collecting a first image of a user during the blood pressure measurement process; the main processor 110 is configured to detect whether the tracheal plug of the cuff is properly inserted into the insertion hole according to the first image, detect a difference between the height of the cuff and/or the wrist strap and the heart height of the patient, and detect an arm movement degree of the patient wearing the cuff or the wrist strap; the blood glucose measurement module 150 includes: the image pickup device 130 is used for collecting a second image of the user in the process of measuring the biochemical test paper; the main processor 110 is used for detecting the forward and reverse directions of the insertion of the biochemical test paper, the volatilization time of the alcohol on the fingers of the user and the fullness of the biochemical test paper sucked into the test liquid according to the second image.
Illustratively, in the disclosed embodiments, a home multi-parameter monitor is provided, which can be used for blood pressure measurement and blood glucose measurement, specifically, blood pressure measurement is performed by the blood pressure measurement module 140, and blood glucose measurement is performed by the blood glucose measurement module 150. The blood pressure measurement module 140 includes a blood pressure meter 141 and an arm band and/or a wrist band 142, and when the patient is in the measurement process, the arm band 141 is bound to the arm, the tracheal plug is inserted into the arm band, or the wrist band 141 is bound to the wrist, and after the position of the arm band and/or the wrist band 141 is adjusted, the blood pressure meter is turned on to measure the blood pressure value. The blood glucose measuring module 150 includes a biochemical measuring instrument 151 and a test paper 152, and the test paper 152 is inserted into the biochemical measuring instrument 151 (the test paper is required to be checked for inserting forward and backward when the test paper is inserted) when the patient performs blood glucose measurement, and after the biochemical measuring instrument 151 indicates blood taking. After washing the hands, the abdomen of the finger is disinfected by 75% alcohol (middle finger and index finger are generally selected), the adjusted pen is vertically penetrated, and the thumb and index finger of the other hand are used for pinching the upper part of the finger to be measured. After bleeding from the pricked finger, the blood is dropped onto the test paper 152 at the blood sampling site, and then the appearance of the blood glucose value on the biochemical measuring instrument 151 is waited.
Further, the household multi-parameter monitor in the disclosed embodiment of the invention further comprises: the main processor 110 and the camera 130 are used for preventing the phenomena that when the household multiparameter monitor is used by a patient, the arm belt is inserted into the wrong hole, the arm belt or the wrist belt is not in the same height as the heart of the patient, the test paper is inserted reversely, the alcohol on the finger of the user is too much, the fullness of the biochemical test paper sucked into the test liquid is insufficient, and the like, so that in the process of blood pressure measurement/blood sugar measurement by the patient using the household multiparameter monitor, the camera 130 is used for collecting images of the user during the process of using the household multiparameter monitor, and the main processor 110 is used for detecting whether the air pipe plug of the arm belt is correctly inserted into the jack, detecting the difference between the height of the arm belt and/or the wrist belt and the heart of the patient, detecting the arm movement degree of the arm belt or the wrist belt worn by the patient, detecting the forward and backward direction of the insertion of the biochemical test paper, detecting the alcohol volatilization time on the finger of the user, and detecting the fullness of the biochemical test paper sucked into the test liquid.
In addition, the household multi-parameter monitor further includes a display 120, where the display 120 is configured to display a monitoring result of the main processor 110 on the image acquired by the camera 130. It will be appreciated that the display 120 may be integrated with the blood pressure meter 141 and the biochemical measuring device 151 or may be a separate display device.
Fig. 2 is a schematic structural view of another home multi-parameter monitor according to fig. 1, and as shown in fig. 2, the home multi-parameter monitor further includes: a reminder 160, the reminder 160 being electrically connected to the main processor 110; the prompting device 160 is configured to send an alarm according to an instruction of the main processor when the tracheal plug of the armband is not inserted into the jack, or when a difference between a depth value of the tracheal plug of the armband inserted into the jack and a standard depth value is greater than a first preset threshold, or when a difference between a height of the armband and/or the wrist strap and a heart height of a patient is greater than a second preset threshold, or when an arm movement of the armband or the wrist strap worn by the patient is greater than a third preset threshold, or when a reverse side of the biochemical test paper is inserted into the biochemical measuring instrument, or when a difference between an alcohol volatilization time and a standard volatilization time on a finger of a user is greater than a fourth preset threshold, or when a difference between a plumpness of the biochemical test paper sucked into the test liquid and a standard plumpness is greater than a fifth preset threshold.
For example, the prompting device 160 may be an audible and visual alarm device, when the tracheal plug of the armband is not inserted into the jack, or when the difference between the depth value of the tracheal plug of the armband inserted into the jack and the standard depth value is greater than a first preset threshold, or when the difference between the height of the armband and/or the wrist strap and the heart height of the patient is greater than a second preset threshold, or when the arm mobility of the armband or the wrist strap worn by the patient is greater than a preset third preset threshold, or when the back surface of the biochemical test paper is inserted into the biochemical measuring instrument, or when the difference between the alcohol volatilization time on the finger of the user and the standard volatilization time is greater than a fourth preset threshold, or when the difference between the fullness degree of the biochemical test paper sucked into the test liquid and the standard fullness degree is greater than a fifth preset threshold, an alarm is sent to indicate that some misoperation exists in the process of blood pressure measurement and/or blood sugar measurement by the user, and prompt the user to perform normal operation.
Further, the correct operating steps and normative methods of use may also be displayed via the display 120.
FIG. 3 is a schematic flow chart of detecting an image according to a main processor shown in FIG. 1, and as shown in FIG. 3, the main processor is configured to: detecting whether a tracheal plug of the armband is correctly inserted into the jack according to the first image, detecting a difference between the height of the armband and/or the wrist band and the heart height of a patient, and the arm moving degree of the armband or the wrist band worn by the patient, wherein the main processor is used for detecting the positive and negative directions of the insertion of the biochemical test paper according to the second image, and the plumpness of the biochemical test paper sucked into the test liquid, and the specific steps comprise:
in step 301, data preprocessing is performed on a first image and a second image acquired by an imaging device, respectively.
Illustratively, the first image and the second image are subjected to data preprocessing, the data preprocessing including: label making, data enhancement and the like.
In the embodiment of the invention, the video data of the user in the process of using the household multi-parameter monitor is acquired through the camera device, at least 3000 images are acquired according to the photographing frequency of 30Hz, and the images are preprocessed.
In step 302, a first feature vector of a preprocessed first image is extracted by the S-ViT model, and a second feature vector of a preprocessed second image is extracted.
For example, in the embodiment of the present disclosure, when feature vectors are extracted from the preprocessed first image and the preprocessed second image, a general ViT model is not adopted, but a modified version S-ViT model of the ViT model is adopted, and because the neural network is to be entered in the embedded system, weight pre-selection is performed on the basis of the prior art to reduce the pressure of the operation of the embedded system.
It can be understood that in the general ViT model, the basic size of the image is 224×224×3, where 224×224 is the length and width pixels and 3 is the 3 RGB color channels. The picture is divided into 14 x 14 (=196) tiles, each of which is 16 x 16 pixels. The general model ViT performs at least 197 x 2*n (where 197 x 197 represents the correlation of 197 sets (=196+1 eigenvectors for global components) with all sets, 2*n is the input and W, respectively, when calculating Q and K for one autocorrelation q /W k The number of times of calculation) of the multiplication. The S-ViT model in the embodiment of the invention is shown in W Q 、W K 、W V Is added with a group of W E The vector is used to learn and predict its importance, rather than mechanically calculating the relationship before all the tiles at a time.
In step 303, the depth value of the tracheal plug inserted into the insertion hole, the difference between the height of the cuff and/or wristband and the heart height of the patient, the arm movement of the patient wearing the cuff or wristband, the forward and reverse direction of the insertion of the biochemical test paper, the alcohol volatilization time and the fullness of the biochemical test paper in the test liquid are detected according to the first feature vector, the second feature vector, the pre-trained cuff tracheal plug detection model, the cuff and/or wristband height detection model, the arm movement detection model, the forward and reverse direction of the insertion of the biochemical test paper, the alcohol volatilization detection model and the siphon fullness detection model.
For example, after the first feature vector and the second feature vector are obtained, according to a pre-trained arm tracheal plug detection model, an arm and/or wristband height detection model, an arm mobility detection model, a biochemical test paper insertion positive and negative detection model, an alcohol volatilization detection model and a siphon plumpness detection model, a depth value of the tracheal plug inserted into the jack, a difference between the height of the arm and/or wristband and the heart height of the patient, the arm mobility of the arm or wristband worn by the patient, the positive and negative directions of the biochemical test paper insertion, the alcohol volatilization time and the plumpness of the biochemical test paper sucked into the test liquid are detected.
Specifically, according to the first feature vector, the second feature vector, the pre-trained arm-band tracheal plug detection model, the arm-band and/or wristband height detection model, the arm mobility detection model, the biochemical test paper insertion positive and negative detection model, the alcohol volatilization detection model and the siphon plumpness detection model, the depth value of the tracheal plug inserted into the jack, the difference between the height of the arm-band and/or wristband and the heart height of the patient, the arm mobility of the arm-band or wristband worn by the patient, the positive and negative of the biochemical test paper insertion, the alcohol volatilization time and the plumpness of the biochemical test paper inhalation test liquid are detected, the method comprises the following steps: taking the first feature vector as input of a pre-trained arm belt air pipe plug detection model, and judging whether the difference value between the depth value of the arm belt air pipe plug inserted into the jack and the standard depth value is larger than a first preset threshold value or not according to the output of the arm belt air pipe plug detection model; taking the first characteristic vector as input of a pre-trained arm band and/or wrist band height detection model, and judging whether the difference between the height of the arm band and/or wrist band and the heart height of a patient is larger than a second preset threshold value or not according to the output of the arm band and/or wrist band height detection model; taking the first feature vector as input of a pre-trained arm mobility detection model, and judging whether the arm mobility of the patient wearing the arm belt or the wrist belt is greater than a third preset threshold according to the output of the arm mobility detection model; taking the second feature vector as input of a pre-trained forward and reverse detection model for inserting the biochemical test paper, and judging the forward and reverse of the insertion of the biochemical test paper according to the output of the forward and reverse detection model for inserting the biochemical test paper; taking the second characteristic vector as input of a pre-trained alcohol volatilization detection model, and judging whether the difference between the alcohol volatilization time and the standard volatilization time is larger than a fourth preset threshold value according to the output of the alcohol volatilization detection model; and taking the second characteristic vector as the input of a pre-trained siphon plumpness detection model, and judging whether the difference between the plumpness of the biochemical test paper sucked into the test liquid and the standard plumpness is larger than a fifth preset threshold value according to the output of the siphon plumpness detection model.
It should be noted that, in the embodiment of the present invention, when the model is trained, sample images are collected under environments with different brightness and different color temperatures, and feature vectors are extracted through the sample images with different brightness and different color temperatures, and a neural network model is trained, so that the trained neural network model can identify images under different ambient light, and whether the steps of using the household multi-parameter instrument by a patient are correct or not is accurately detected.
Fig. 4 is a flowchart of a first feature vector extraction according to the embodiment shown in fig. 3, and as shown in fig. 4, the first feature vector of the first image after the preprocessing is extracted by the S-ViT model includes:
in step 401, the first image is divided into 14×14 tiles, and each tile includes a number of pixels.
In step 402, a first image divided into 14×14 tiles is combined with W having a dimension of 48×16 E Matrix, obtain the third eigenvector E with dimension 196 x 256 t 。
In step 403, the third feature vector is passed through a CNN with dimension 196×1×1 to obtain an importance matrix E s 。
In step 404, the importance matrix E is passed through s The weights are sequenced, importance scores of each small square are obtained, the data ranked in the top 25 bits are selected to replace 196 data, and a first feature vector is obtained.
Fig. 5 is a flow chart of a second feature vector extraction according to the one shown in fig. 3, as shown in fig. 5, the extracting of the second feature vector of the preprocessed second image, comprising:
in step 501, the second image is divided into 14×14 tiles, and each tile includes a number of pixels.
In step 502, a second image divided into 14×14 tiles is combined with W having a dimension of 48×16 E Matrix, obtain fourth eigenvector E with dimension 196 x 256 t 。
In step 503, the importance matrix E is obtained by passing the fourth eigenvector through a CNN with dimension 196×1×1 s 。
In step 504, the importance matrix E is passed s And sequencing the weights to obtain importance scores of each small square, and selecting the data ranked in the top 25 bits to replace 196 data to obtain a second feature vector.
The S-ViT model in the disclosed embodiment of the invention is exemplified by Q 、W K 、W V Is added with a group of W E The vector is used to learn and predict its importance, rather than mechanically calculating the relationship before all the tiles at a time. The original data is then set to 12 heads, with dimensions 197×768 (12×64=16×16×3). Raw data 196 x 768 (Cls are not considered here) passes through W E After multiplication (matrix dimension 48×16), the characteristic Et (dimension 196×256) is obtained, and then the importance matrix Es (dimension 196×196) is obtained through a CNN of 196×1×1. The importance of each grid and other grids is obtained by sorting by weight, and the self-attribute is performed by replacing 196 with the first 25 data, and all global components are still calculated. The final calculation of the self-attitudes is changed from 197 to 2*n to 1 to 197+196 to 25 to 2*n, and the requirement on the processor is greatly reduced.
Optionally, the image capturing device is configured to collect a second image of a user during a biochemical test paper measurement process, and includes: when the camera device collects a second image, a rectangular area range W where the biochemical test paper is located is defined 1 The rectangle W 1 Is defined by the two diagonal points PA (x 1, y 1) and PB (x 2, y 2), the intermediate corner point x0 ((x1+x2)/2, y0= (y1+y2)/2).
For example, assuming task a is to be done, it is necessary to acquire the position where the test strip has been inserted into the test strip port. At this time, task S will first start to find the best viewing angle, frame the rectangular area W1 where the test paper is inserted into the test paper port, and use PA: (x 1, y 1), PB: (x 2, y 2) is represented as two diagonal points (where the middle point Oc (x 0, y 0), where x0= (x1+x2)/2; y0= (y1+y2)/2). In order to obtain the optimal angle picture, a plurality of experiments are performed to obtain a preset frame W0 and a diagonal coordinate PD: (m 1, n 1), PE: (m 2, n 2) (wherein the intermediate point Of (m 0, n 0), wherein m0= (m1+m2)/2; n0= (n1+n2)/2) is the best.
Optionally, the home multi-parameter monitor further comprises: a rotatable base on which the image pickup device is mounted; the rotatable base is provided with x-y coordinate axes.
Optionally, the main processor is further configured to: detecting an included angle between the X-Y coordinate axes on the camera device and the rotatable base, and stopping acquiring the first image and/or the second image by using the camera device if the included angle is larger than a first angle threshold or smaller than a second angle threshold.
For example, the image quality coefficient is used to represent the quality of the image captured by the image capturing device, and the image quality coefficient is related to the angle between the rotatable base and the plane. The image quality coefficient Q is proportional to the included angles α, β between the center points (it is understood that the center point of the rotatable base forms an included angle α with the x-axis direction and an included angle β with the y-axis direction). Taking the x-axis as an example: cos (kα), where k is the lens parameters, and a=x0/a×gx/2, is confirmed after the best effect is obtained by experiment. The image quality factor Q is also proportional to the size of the recognition object(the larger the area per se, the better the identification). Q=cos (kα) ×cos (kβ) ×ar. If the quality factor Q is higher than a certain preset value or SO (-)>) If the image quality coefficient Q is smaller than a certain threshold (the object is prevented from being too small and not optimal)Otherwise, if the value is lower than the preset value, the XY axis rotating base needs to be controlled to fall into the range.
In summary, the present disclosure relates to a household multi-parameter monitor, comprising: the device comprises a main processor, a display, a camera device, a blood pressure measuring module and a blood sugar measuring module; the blood pressure measurement module includes: blood pressure gauges, armbands, and/or wrist bands; the main processor is used for detecting whether the tracheal plug of the armband is correctly inserted into the jack according to the first image, detecting the difference between the height of the armband and/or the wrist strap and the heart height of a patient, and detecting the arm movement degree of the patient wearing the armband or the wrist strap; the blood glucose measurement module includes: biochemical measuring instrument and test paper; the main processor is used for detecting the positive and negative directions of the insertion of the biochemical test paper, the alcohol volatilization time on the fingers of the user and the fullness degree of the biochemical test paper sucked into the test liquid according to the second image. The use mode of the household multi-parameter monitor can be observed through the camera, the user is guided to operate according to normal steps, and the experience of the user and the efficiency of health monitoring are improved.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and all the simple modifications belong to the protection scope of the present disclosure.
In addition, the specific features described in the foregoing embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, the present disclosure does not further describe various possible combinations.
Moreover, any combination between the various embodiments of the present disclosure is possible as long as it does not depart from the spirit of the present disclosure, which should also be construed as the disclosure of the present disclosure.
Claims (9)
1. A household multi-parameter monitor, the monitor comprising: the device comprises a main processor, a display, a camera device, a blood pressure measuring module and a blood sugar measuring module, wherein the display, the camera device, the blood pressure measuring module and the blood sugar measuring module are respectively and electrically connected with the main processor;
the blood pressure measurement module includes: the blood pressure measuring device comprises a blood pressure meter, an armband and/or a wrist band, wherein the camera device is used for acquiring a first image of a user in the blood pressure measuring process;
the main processor is used for detecting whether the tracheal plug of the armband is correctly inserted into the jack according to the first image, detecting the difference value between the height of the armband and/or the wrist strap and the heart height of a patient, and detecting the arm movement degree of the armband or the wrist strap worn by the patient;
the blood glucose measurement module includes: the image pick-up device is used for collecting a second image of the user in the measuring process of the biochemical test paper;
the main processor is used for detecting the positive and negative directions of the insertion of the biochemical test paper, the volatilization time of the alcohol on the fingers of the user and the fullness degree of the biochemical test paper sucked into the test liquid according to the second image.
2. The home multiparameter of claim 1, further comprising: the prompting device is electrically connected with the main processor;
the prompting device is used for sending an alarm prompt according to the instruction of the main processor when the tracheal plug of the armband is not inserted into the jack, or when the difference between the depth value of the tracheal plug of the armband inserted into the jack and the standard depth value is larger than a first preset threshold, or when the difference between the height of the armband and/or the wrist strap and the heart height of a patient is larger than a second preset threshold, or when the arm moving degree of the armband or the wrist strap worn by the patient is larger than a preset third preset threshold, or when the back surface of the biochemical test paper is inserted into the biochemical measuring instrument, or when the difference between the alcohol volatilization time and the standard volatilization time on the fingers of a user is larger than a fourth preset threshold, or when the difference between the plumpness of the biochemical test paper sucked into the test liquid and the standard plumpness is larger than a fifth preset threshold.
3. The home multiparameter monitor of claim 2, wherein the main processor is configured to detect whether the tracheal plug of the cuff is properly inserted into the receptacle based on the first image, detect a difference between the height of the cuff and/or wristband and the height of the heart of the patient, and the degree of arm movement of the cuff or wristband worn by the patient, the main processor is configured to detect the forward and reverse of insertion of the biochemical test paper based on the second image, and the degree of fullness of the biochemical test paper in the test liquid, comprising:
respectively preprocessing data of a first image and a second image acquired by the camera device;
extracting a first feature vector of the preprocessed first image through an S-ViT model, and extracting a second feature vector of the preprocessed second image;
according to the first characteristic vector, the second characteristic vector, the pre-trained arm belt tracheal plug detection model, the arm belt and/or wrist belt height detection model, the arm movement detection model, the biochemical test paper insertion positive and negative detection model, the alcohol volatilization detection model and the siphon plumpness detection model, detecting the depth value of the tracheal plug inserted into the jack, the difference value between the height of the arm belt and/or wrist belt and the heart height of a patient, the arm movement of the arm belt or wrist belt worn by the patient, the positive and negative directions of the biochemical test paper insertion, the alcohol volatilization time and the plumpness of the biochemical test paper sucked into the test liquid.
4. A home multiparameter monitor according to claim 3, wherein the detecting of the depth value of the insertion of the tracheal plug into the receptacle, the difference between the height of the cuff and/or wristband and the heart height of the patient, the arm movement of the patient wearing the cuff or wristband, the forward and reverse of the insertion of the biochemical test paper, the alcohol evaporation time and the fullness of the biochemical test paper in the test liquid according to the first feature vector, the second feature vector, the pre-trained cuff tracheal plug detection model, the cuff and/or wristband height detection model, the arm movement detection model, the biochemical test paper insertion forward and reverse detection model, the alcohol evaporation detection model and the siphon fullness detection model comprises:
taking the first characteristic vector as the input of a pre-trained arm-band air pipe plug detection model, and judging whether the difference value between the depth value of the arm-band air pipe plug inserted into the jack and the standard depth value is larger than a first preset threshold value or not according to the output of the arm-band air pipe plug detection model;
taking the first characteristic vector as input of a pre-trained arm band and/or wrist band height detection model, and judging whether the difference between the height of the arm band and/or wrist band and the heart height of a patient is larger than a second preset threshold value or not according to the output of the arm band and/or wrist band height detection model;
taking the first feature vector as input of a pre-trained arm mobility detection model, and judging whether the arm mobility of the patient wearing the armband or the wrist strap is greater than a third preset threshold according to the output of the arm mobility detection model;
taking the second feature vector as input of a pre-trained forward and reverse detection model for inserting the biochemical test paper, and judging the forward and reverse of the insertion of the biochemical test paper according to the output of the forward and reverse detection model for inserting the biochemical test paper;
taking the second characteristic vector as input of a pre-trained alcohol volatilization detection model, and judging whether the difference between the alcohol volatilization time and the standard volatilization time is larger than a fourth preset threshold value according to the output of the alcohol volatilization detection model;
and taking the second characteristic vector as the input of a pre-trained siphon plumpness detection model, and judging whether the difference between the plumpness of the biochemical test paper sucked into the test liquid and the standard plumpness is larger than a fifth preset threshold according to the output of the siphon plumpness detection model.
5. A home multiparameter monitor according to claim 3, wherein the extracting the first eigenvector of the preprocessed first image by the S-ViT model comprises:
dividing the first image into 14 x 14 small squares, wherein each small square comprises a plurality of pixel points;
dividing the first image into 14 x 14 tiles with a W having a dimension of 48 x 16 E Matrix, obtain the third eigenvector E with dimension 196 x 256 t ；
The third eigenvector is passed through CNN with dimension 196 x1 to obtain importance matrix E s ；
By an importance matrix E s The weights are sequenced, importance scores of each small square are obtained, the data ranked in the top 25 bits are selected to replace 196 data, and a first feature vector is obtained.
6. A home multiparameter monitor according to claim 3, wherein the extracting the second eigenvector of the preprocessed second image comprises:
dividing the second image into 14 x 14 small squares, wherein each small square comprises a plurality of pixel points;
dividing the second image into 14 x 14 tiles with a W having a dimension of 48 x 16 E Matrix, obtain fourth eigenvector E with dimension 196 x 256 t ；
The fourth eigenvector is passed through CNN with dimension 196 x1 to obtain importance matrix E s ；
By an importance matrix E s And sequencing the weights to obtain importance scores of each small square, and selecting the data ranked in the top 25 bits to replace 196 data to obtain a second feature vector.
7. The home multiparameter of claim 4, wherein the camera device is configured to capture a second image of the user during measurement of the biochemical test paper, comprising:
when the camera device collects a second image, a rectangular area range W where the biochemical test paper is positioned is defined by a frame 1 The rectangle W 1 Is defined by the two diagonal points PA (x 1, y 1) and PB (x 2, y 2), the intermediate corner point x0 ((x1+x2)/2, y0= (y1+y2)/2).
8. The home multiparameter of claim 7, further comprising: the camera device is arranged on the rotatable base;
the rotatable base is provided with x-y coordinate axes.
9. The home multiparameter monitor of claim 8, wherein the main processor is further operable to: detecting an included angle between x-y coordinate axes on the camera device and the rotatable base, and stopping acquiring the first image and/or the second image by using the camera device if the included angle is larger than a first angle threshold or smaller than a second angle threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657719.8A CN117338270B (en) | 2023-12-06 | 2023-12-06 | Household multi-parameter monitor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657719.8A CN117338270B (en) | 2023-12-06 | 2023-12-06 | Household multi-parameter monitor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117338270A true CN117338270A (en) | 2024-01-05 |
| CN117338270B CN117338270B (en) | 2024-03-08 |
Family
ID=89371453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311657719.8A Active CN117338270B (en) | 2023-12-06 | 2023-12-06 | Household multi-parameter monitor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117338270B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090275805A1 (en) * | 2008-04-30 | 2009-11-05 | Welch Allyn, Inc. | On demand help/in-service for a medical device |
| CN106255878A (en) * | 2014-02-17 | 2016-12-21 | 安盛生科股份有限公司 | Mobile device is utilized to measure physics and biochemical parameters |
| CN108712881A (en) * | 2016-07-28 | 2018-10-26 | 松下电器（美国）知识产权公司 | Person to be measured determine method, person to be measured determine system, blood pressure the measurement state decision procedure for measuring state determining apparatus and blood pressure for measuring condition judgement method, blood pressure |
| CN109044303A (en) * | 2018-07-10 | 2018-12-21 | 青岛真时科技有限公司 | A kind of blood pressure measuring method based on wearable device, device and equipment |
| CN110462385A (en) * | 2017-03-17 | 2019-11-15 | 安盛生科股份有限公司 | For improving the availability of physiological measurements and the method for accuracy |
| CN115337044A (en) * | 2022-07-18 | 2022-11-15 | 深圳市安保数字感控科技有限公司 | Nucleic acid sampling monitoring method, device, system and computer readable storage medium |
-
2023
- 2023-12-06 CN CN202311657719.8A patent/CN117338270B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090275805A1 (en) * | 2008-04-30 | 2009-11-05 | Welch Allyn, Inc. | On demand help/in-service for a medical device |
| CN106255878A (en) * | 2014-02-17 | 2016-12-21 | 安盛生科股份有限公司 | Mobile device is utilized to measure physics and biochemical parameters |
| CN108712881A (en) * | 2016-07-28 | 2018-10-26 | 松下电器（美国）知识产权公司 | Person to be measured determine method, person to be measured determine system, blood pressure the measurement state decision procedure for measuring state determining apparatus and blood pressure for measuring condition judgement method, blood pressure |
| CN110462385A (en) * | 2017-03-17 | 2019-11-15 | 安盛生科股份有限公司 | For improving the availability of physiological measurements and the method for accuracy |
| CN109044303A (en) * | 2018-07-10 | 2018-12-21 | 青岛真时科技有限公司 | A kind of blood pressure measuring method based on wearable device, device and equipment |
| CN115337044A (en) * | 2022-07-18 | 2022-11-15 | 深圳市安保数字感控科技有限公司 | Nucleic acid sampling monitoring method, device, system and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| LUCAS BEYER ET AL: "Better plain ViT baselines for ImageNet-1k", ARXIV:2205.01580V1, pages 1 - 3 * |
| YUCHENG ZHAO ET AL: "Streaming Video Model", ARXIV:2303.17228V1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117338270B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111368810B (en) | Sit-up detection system and method based on human body and skeleton key point identification | |
| CN106621284B (en) | A kind of intelligent physical examinations platform | |
| WO2020103417A1 (en) | Bmi evaluation method and device, and computer readable storage medium | |
| CN107708555A (en) | Measurement apparatus and measuring method | |
| WO2017156834A1 (en) | Intelligent gloves for measuring calorie consumption and monitoring hand gesture recognition, and estimation method and system | |
| US20210059569A1 (en) | Fall risk evaluation method, fall risk evaluation device, and non-transitory computer-readable recording medium in which fall risk evaluation program is recorded | |
| Tao et al. | A comparative home activity monitoring study using visual and inertial sensors | |
| CN111466878A (en) | Real-time monitoring method and device for pain symptoms of bedridden patients based on expression recognition | |
| JP3575979B2 (en) | Cared person observation device and method | |
| CN113856186B (en) | Pull-up action judging and counting method, system and device | |
| CN113288452A (en) | Operation quality detection method and device | |
| CN108717872A (en) | Health analysis method and system based on face, hard recognition and big data | |
| CN110456050B (en) | Portable intelligent digital parasite in vitro diagnostic instrument | |
| CN109997199A (en) | Tuberculosis inspection method based on deep learning | |
| CN117338270B (en) | Household multi-parameter monitor | |
| CN110457981A (en) | The method, apparatus and electronic device of living body detecting | |
| US20210059596A1 (en) | Cognitive function evaluation method, cognitive function evaluation device, and non-transitory computer-readable recording medium in which cognitive function evaluation program is recorded | |
| CN106326672B (en) | Sleep detection method and system | |
| CN115568823B (en) | Human body balance capability assessment method, system and device | |
| KR20210118496A (en) | Image-based intelligent push-up discrimination method and system | |
| CN117333932A (en) | Method, equipment and medium for identifying sarcopenia based on machine vision | |
| CN110555394A (en) | Fall risk assessment method based on human body shape characteristics | |
| TWI759218B (en) | Non-contact heart rhythm category monitoring system and method | |
| CN115331304A (en) | Running identification method | |
| US11850090B2 (en) | Guided lung coverage and automated detection using ultrasound devices |
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 |