CN117807531B - Accurate blood oxygen data collection system based on intelligent ring - Google Patents
Accurate blood oxygen data collection system based on intelligent ring Download PDFInfo
- Publication number
- CN117807531B CN117807531B CN202410230265.4A CN202410230265A CN117807531B CN 117807531 B CN117807531 B CN 117807531B CN 202410230265 A CN202410230265 A CN 202410230265A CN 117807531 B CN117807531 B CN 117807531B
- Authority
- CN
- China
- Prior art keywords
- data
- blood oxygen
- value
- ambient light
- heart rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 title claims abstract description 153
- 229910052760 oxygen Inorganic materials 0.000 title claims abstract description 153
- 239000001301 oxygen Substances 0.000 title claims abstract description 153
- 239000008280 blood Substances 0.000 title claims abstract description 152
- 210000004369 blood Anatomy 0.000 title claims abstract description 152
- 238000013480 data collection Methods 0.000 title claims description 9
- 230000002159 abnormal effect Effects 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 238000010276 construction Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000033001 locomotion Effects 0.000 claims description 49
- 230000011218 segmentation Effects 0.000 claims description 44
- 230000008859 change Effects 0.000 claims description 26
- 238000000034 method Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 15
- 230000000694 effects Effects 0.000 description 9
- 238000005192 partition Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 239000000725 suspension Substances 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
-
- 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
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14552—Details of sensors specially adapted therefor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/02—Operational features
- A61B2560/0242—Operational features adapted to measure environmental factors, e.g. temperature, pollution
- A61B2560/0247—Operational features adapted to measure environmental factors, e.g. temperature, pollution for compensation or correction of the measured physiological value
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Physiology (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Optics & Photonics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Cardiology (AREA)
- Computing Systems (AREA)
- Pulmonology (AREA)
- Mathematical Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of blood oxygen data anomaly monitoring, in particular to an intelligent ring-based accurate blood oxygen data acquisition system, which comprises: the intelligent ring related data acquisition module: collecting blood oxygen data and related data of the intelligent ring; abnormal blood oxygen data detection and rejection module: for sample data extracted at any time in blood oxygen data, respectively constructing blood oxygen, ambient light and heart rate variation amplitude of characteristic data points according to numerical value variation of each data point in heart rate, blood oxygen and ambient light intensity data; completing the construction of an isolated tree based on the variation amplitude and the data point numerical value difference; constructing an isolated forest according to the preset extraction times; and screening abnormal data according to the abnormal scores of the data points in the isolated forest, and finishing accurate collection of blood oxygen data. The invention aims to adaptively complete abnormal detection of blood oxygen data through an isolated forest algorithm, eliminate abnormal data under interference and improve data detection precision.
Description
Technical Field
The application relates to the technical field of blood oxygen data anomaly monitoring, in particular to an intelligent ring-based accurate blood oxygen data acquisition system.
Background
The accurate blood oxygen data collection system based on the intelligent ring can help people to know the blood oxygen level of the people in real time, and has important significance for specific groups needing to monitor blood oxygen for a long time, such as athletes, people suffering from respiratory diseases and the like. However, smart rings are often subject to movement disturbances and ambient light disturbances when collecting blood oxygen concentrations. Therefore, abnormality detection is required for the acquired data.
The isolated forest algorithm is a common data anomaly detection algorithm, when the isolated forest algorithm is used for detecting abnormal blood oxygen data, the isolated tree partition points are generally selected randomly, so that the construction efficiency and precision of the isolated tree are reduced, meanwhile, the depth of each isolated tree in the default isolated forest in the algorithm is the same, however, the too deep depth of some isolated trees is not necessary at all, and the calculated amount is increased and the detection precision is reduced.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an intelligent ring-based accurate blood oxygen data acquisition system, which adopts the following technical scheme:
the invention provides an intelligent ring-based accurate blood oxygen data acquisition system, which comprises:
The intelligent ring related data acquisition module: collecting blood oxygen data, ambient light intensity data and heart rate data of the intelligent ring;
Abnormal blood oxygen data detection and rejection module: taking blood oxygen data as a data set, and respectively acquiring a normal heart rate value, a normal blood oxygen value and a normal ambient light intensity value according to the numerical change condition of each data point in heart rate, blood oxygen and ambient light intensity data for sample data extracted at any time in the data set; respectively acquiring an ambient light characteristic data point and a motion characteristic data point based on the normal state heart rate value and the normal state ambient light intensity value; according to the difference between the blood oxygen data, the ambient light intensity data and the heart rate data of the ambient light characteristic data points and the corresponding normal values, constructing the blood oxygen change amplitude, the ambient light change amplitude and the heart rate change amplitude of the ambient light characteristic data points;
Constructing an ambient light interference factor and a motion interference factor according to the blood oxygen, the heart rate and the ambient light variation amplitude of the ambient light characteristic data points and the motion characteristic data points; combining the motion interference factor, the ambient light interference factor and the data difference between the data points to construct an interference distance value between any two data points; forming all data points in the sample data into one node of an isolated tree, and constructing the segmentality of each data point according to the interference distance value between the data points in the node; taking the data point with the maximum intra-node segmentability as a segmentation point, and completing the construction of an isolated tree based on the segmentability of each data point in the nodes of the segmentation point;
Extracting sample data from the data set according to preset extraction times to construct an isolated forest; and screening abnormal data according to the abnormal scores of the data points in the isolated forest, and finishing accurate collection of blood oxygen data.
Preferably, the obtaining the normal heart rate value, the normal blood oxygen value and the normal ambient light intensity value according to the numerical variation condition of each data point in the heart rate, the blood oxygen and the ambient light intensity data respectively includes:
for each data point of the heart rate data, calculating the sum of absolute values of differences between the data point and heart rate values of all other data points in the heart rate data; calculating a summation result of the summation value and the minimum positive number;
Acquiring occurrence frequency of heart rate values of data points in heart rate data; taking the ratio of the occurrence frequency to the summation result as the possibility that each data point in heart rate data is a normal heart rate value; taking the data point with the highest normal state heart rate value possibility in the heart rate data as the normal state heart rate value;
and acquiring a normal blood oxygen value and a normal ambient light intensity value of the blood oxygen data and the ambient light intensity data by adopting a calculation method which is the same as the normal heart rate value.
Preferably, the acquiring the ambient light characteristic data point and the motion characteristic data point based on the normal state heart rate value and the normal state ambient light intensity value respectively includes:
recording all data points with the same normal state heart rate value as ambient light characteristic data points; all data points with the same normal ambient light intensity value are noted as motion feature data points.
Preferably, the constructing the blood oxygen variation amplitude, the environment light variation amplitude and the heart rate variation amplitude of the environment light characteristic data point according to the difference between the blood oxygen data, the environment light intensity data and the heart rate data of the environment light characteristic data point and the corresponding normal value includes:
Calculating the absolute value of the difference between the blood oxygen value of the ambient light characteristic data point and the normal blood oxygen value; taking the ratio between the absolute value of the difference and the normal blood oxygen value as the blood oxygen change amplitude of the ambient light characteristic data point;
And acquiring the ambient light variation amplitude and the heart rate variation amplitude by adopting a calculation method which is the same as the blood oxygen variation amplitude.
Preferably, the construction of the ambient light interference factor and the motion interference factor according to the blood oxygen, the heart rate and the ambient light variation amplitude of the ambient light characteristic data points and the motion characteristic data points comprises the following steps:
taking the average value of the ratio of the ambient light variation amplitude to the blood oxygen variation amplitude of all the ambient light characteristic data points as an ambient light interference factor;
obtaining the blood oxygen, heart rate and ambient light variation amplitude of the motion characteristic data points by adopting a calculation method which is the same as the blood oxygen, heart rate and ambient light variation amplitude of the ambient light characteristic data points; and taking the average value of the ratio of the heart rate variation amplitude to the blood oxygen variation amplitude of all the motion characteristic data points as a motion interference factor.
Preferably, the combining the motion interference factor, the ambient light interference factor and the data difference between the data points constructs an interference distance value between any two data points, including:
the expression for the interference distance value between data point a and data point b is:
where D represents the interference distance value between data points a and b, 、/>Represents the blood oxygen values of data points a and b, respectively,/>、/>Heart rate values representing data points a and b, respectively,/>、/>Ambient light intensity values representing data points a and b, respectively; /(I)、/>、/>Respectively representing a normal blood oxygen value, a normal heart rate value and a normal environment light intensity value; /(I)、/>Respectively representing the motion disturbance factor and the ambient light disturbance factor.
Preferably, the constructing the segmentality of each data point according to the interference distance value between the data points in the node includes:
For any one data point in the nodes, forming a left node of the any one data point by all data points with interference distance values larger than 0 with the any one data point; forming a right node of any one data point by all data points with interference distance values smaller than or equal to 0 with the any one data point; the left node and the right node are collectively called as a node of any data point;
Acquiring a distance distribution characteristic value in the node based on the numerical distribution of the interference distance value in the node; the data points with the values of normal blood oxygen value, normal heart rate value and normal environment light intensity value in all the data points in the node are recorded as normal data points;
wherein the partitional expression of data point a is:
Representing the segmentality of data point A,/> Representing the minimum interference distance value of data point A and data point in node P,/>Representing the minimum interference distance value of data point A and data point in node U,/>、/>Representing distance distribution eigenvalues within node P, U,/>Representing the absolute value of the interference distance value between data point a and all normal data points of the user.
Preferably, the obtaining the distance distribution characteristic value in the node based on the numerical distribution of the interference distance value in the node includes:
The expression of the distance distribution characteristic value in the node P is:
In the method, in the process of the invention, Representing distance distribution eigenvalues within node P,/>Representing an exponential function based on natural constants,/>、/>Respectively represent the maximum interference distance value and the minimum interference distance value between the data points in the node P and the preselected segmentation point A,/>, respectivelyRepresenting the number of data points within node p,/>Representing the interference distance value between the P-th data point and the preselected segmentation point A in the node P,/>Is the average interference distance value between all data points within the node P and the preselected segmentation point a.
Preferably, the constructing of the isolated tree is completed based on the segmentability of each data point in the node of the segmentation point, including:
calculating the sum of the segmentabilities of all the data points in the nodes for the left node and the right node of the segmentation point; obtaining the maximum segmentability in the node;
Taking the inverse of the product of the sum and the maximum segmentality as an exponent of an exponential function based on a natural constant; taking the calculation result of the exponential function as the growth stopping property of the node;
stopping growing when the growth stopping property of the node is larger than or equal to a preset growth stopping property threshold value;
Otherwise, selecting the data point with the largest segmentation from the nodes as a new segmentation point, and judging the growth stopping property of the left and right nodes of the new segmentation point again until reaching the preset depth of the isolated tree, and stopping growing.
Preferably, the screening the abnormal data according to the abnormal score of the data points in the isolated forest includes:
Taking the mean value of the abnormal scores of all the data points in the isolated forest as a threshold value; and recording the data points with the abnormality scores larger than the threshold value as abnormal data, and eliminating the abnormal data from blood oxygen data.
The invention has at least the following beneficial effects:
According to the intelligent ring sensor and related data acquisition method, the sensor and related data are arranged in the intelligent ring, the influence analysis is carried out according to the multidimensional data, and the interference condition that blood oxygen data receive movement and ambient light is excavated, so that the accuracy of blood oxygen data acquisition is improved; acquiring a normal heart rate value, a normal blood oxygen value and a normal environment light intensity value of a user through the heart rate data, the environment light intensity data and the distribution characteristics of all data in blood oxygen data relative to the whole data, and constructing reference state data for representing the user, so that the follow-up abnormal situation can be accurately analyzed; considering the change influence condition among related data, screening out all motion characteristic data points under the same normal state environment light intensity value and all environment light characteristic data points under the same normal state heart rate value, avoiding the influence condition of other data when analyzing the same data, improving the accuracy of analysis of various related data and avoiding confusion;
Meanwhile, the invention respectively reflects the change condition of blood oxygen relative to normal blood oxygen based on the environmental light characteristic data point and the motion characteristic data point through the change amplitude condition among the characteristic data points, constructs an environmental light interference factor and a motion interference factor, and digs the interference condition of environment and motion on blood oxygen data; the interference distance value between any two data points in the data acquired by the user is adaptively constructed by combining the interference factors and normal data of the user, the interference factors are taken as weights to reconstruct the distance index between the data points, and the accuracy of the selection of the segmentation points is improved by combining the actual blood oxygen data analysis scene; according to the method, the distribution condition of data in the left node and the right node of the tree is judged based on the interference distance value index, so that the segmentation performance of each data point is judged according to the segmentation effect, the segmentation performance of the segmentation points is measured more accurately through the segmentation effect, and the self-adaptive selection of the segmentation points of the isolated tree is completed; then, the method analyzes the segmentality of each data point in the left and right nodes of the segmentation point, digs the necessity of the node growth of the isolated tree, and timely discovers the growth suspension property of the node by constructing an index for distinguishing normal data from abnormal data, thereby saving the calculation resource, improving the precision and efficiency of the isolated forest algorithm, further improving the abnormal detection precision of the data point and further completing the accurate acquisition of the blood oxygen data of the intelligent ring.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent ring-based accurate blood oxygen data collection system according to one embodiment of the present invention;
FIG. 2 is a flow chart of index construction for detecting abnormal blood oxygen data.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of an intelligent finger ring-based blood oxygen data accurate acquisition system according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an intelligent ring-based accurate blood oxygen data acquisition system, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an intelligent ring-based accurate blood oxygen data collection system according to an embodiment of the present invention is shown, where the system includes: the intelligent ring related data acquisition module 101 and the abnormal blood oxygen data detection and rejection module 102.
The relevant data acquisition module 101 of intelligent ring, when the user is using intelligent ring to gather blood oxygen data, the emitting diode in the intelligent ring can transmit infrared light wave, acquires the wavelength and the power data of infrared light wave of transmission, acquires the intensity parameter of outside ambient light through the inside ambient light detection module of intelligent ring device simultaneously. The heart rate data of the user are collected through an optical heart rate sensor in the intelligent ring device. The blood oxygen data collected by each intelligent ring is multidimensional data, and not only comprises blood oxygen saturation, but also comprises related ambient light data, heart rate data and the like.
According to the embodiment, blood oxygen data, ambient light intensity data and heart rate data are used as analysis objects, so that preliminary collection of blood oxygen data and related data of a user can be completed based on the intelligent ring.
The abnormal blood oxygen data detecting and eliminating module 102 completes the acquisition of blood oxygen data, which is usually the percentage of oxygen carried in blood to the total volume, and related data such as user movement according to the above steps. Because the intelligent ring can be interfered by movement and ambient light when blood oxygen data are collected, the collected data are inaccurate data. The blood oxygen saturation of the body can change along with the movement of the body, and the consumption of oxygen in the body after running is high, so that the blood oxygen content is low. Since the peripheral light contains a large amount of red light, when strong light irradiates on the blood oxygen probe, the light receiver can deviate from a normal range, and measurement inaccuracy is caused. Therefore, abnormal data detection and elimination are required to be completed on the blood oxygen data collected by the intelligent ring by using an abnormal detection algorithm, and the accuracy of blood oxygen data collection of the intelligent ring is improved.
The isolated forest is a common abnormal data detection algorithm, when the isolated forest algorithm is used for detecting abnormal blood oxygen data, the depth of each isolated tree in the default isolated forest in the algorithm is the same, however, the too deep depth of some isolated trees is not necessary, and on the contrary, the calculation amount is increased, and the detection accuracy is reduced.
In the embodiment, historical blood oxygen data collected by the intelligent ring is used as a data set, a replaced extraction part sample is arranged in the data set, an isolated tree is constructed, the number of the extracted samples is set to 300, the preset extraction times are set to 100, and an implementer can adjust according to actual conditions.
And analyzing part of samples extracted at any time, adaptively selecting segmentation nodes from the extracted samples, and segmenting the samples into two types through the segmentation nodes. Any one data point A in the extracted sample is taken as a partition node, wherein the blood oxygen value corresponding to the data point A isThe corresponding ambient light intensity value is/>The corresponding heart rate value is/>。
The partition points selected from the isolated forest are used for distinguishing abnormal data from normal data in the samples, and usually, one sample point is randomly selected from the extracted samples to serve as the partition point, wherein the sample point with the data value larger than the partition point is one type and is placed in one node of the isolated tree, and the sample point with the data value smaller than the partition point is one type and is placed in the other node of the isolated tree. However, in this embodiment, the data points correspond to data in multiple dimensions, and there is a correlation between different dimensions, that is, the ambient light intensity and the heart rate data both interfere with the blood oxygen saturation, so when the data value of the blood oxygen saturation is directly used for node division, the correlation of the data is often ignored, and each dimension needs to generate a corresponding isolated tree, which has low efficiency and accuracy.
Therefore, in this embodiment, the collected data are analyzed to obtain the correlation factor between the data, and the data difference value is adaptively constructed based on the correlation factor, where the data are the whole data collected by the intelligent ring, and are not the data extracted once. For the historical data points collected by the intelligent ring, each historical data point has corresponding blood oxygen data, environment light intensity data and heart rate data.
Because the ambient light interference is that the ambient light passes through the skin and is detected by the optical sensor of the intelligent ring, the sensor can misunderstand that the oxygen content in the blood is more, and therefore the acquired blood oxygen concentration value is higher. While under the disturbance of movement, when the human body is in a movement state, the blood circulation is quickened, which can lead to the reduction of the blood oxygen concentration.
Analyzing the data of different dimensions of the acquired data points, wherein the data of each dimension can acquire a corresponding data change curve, and taking heart rate data as an example, the abscissa of the data points in the heart rate data curve is the acquisition time of the data points, and the ordinate is the heart rate value. Firstly, analyzing heart rate values of data points, and because heart rate values corresponding to most of the time of users fluctuate within a certain range, heart rate values of data point a can be obtainedLikelihood of being a normal heart rate value for a user：
In the method, in the process of the invention,Heart rate value/>, representing data point aIs the likelihood of the normal heart rate value of the user,/>Heart rate value/>, representing data point aFrequency of occurrence in heart rate data, N represents the number of data points in heart rate data. /(I)Representing the division/>, in heart rate dataHeart rate value of the i-th data point outside,/>Heart rate value representing data point a,/>To prevent the denominator from being 0, the present embodiment is set to 0.001.
Note that, when the heart rate value of data point a isThe greater the frequency of occurrence, i.e./>The larger the heart rate, the more stable the heart rate is around the heart rate value, the greater the likelihood that the heart rate will be a normal heart rate value. /(I)The smaller the difference between them, the more the heart rate value is in the central region of the heart rate fluctuation range, the greater the likelihood that the heart rate is normal.
The present embodiment selects the heart rate value with the highest probability K as the normal heart rate value of the user. The larger the difference between the actual heart rate value and the normal heart rate value of the user is, the stronger the interference of the heart rate on the blood oxygen concentration data acquisition of the user is indicated.
According to the method with the same normal state heart rate value, the normal state blood oxygen value and the normal state environment light intensity value of the user can be obtained.
In order to distinguish the change amplitude of heart rate data and ambient light intensity data under the condition that the heart rate data is not influenced by other factors, the historical data points are subjected to preliminary screening to obtain all data points under the same normal ambient light intensity value, the data points are marked as motion characteristic data points, and similarly, all data points under the same normal heart rate value are obtained and marked as ambient light characteristic data points.
Analyzing by using the characteristic data points of the ambient light, and constructing an ambient light interference factor:
In the method, in the process of the invention, Representing the blood oxygen change amplitude of the ambient light characteristic data point a,/>Represents the blood oxygen value of data point a,/>Represents a normalcy blood oxygen value;
Represents the ambient light disturbance factor, M represents the number of ambient light characteristic data points,/> Ambient light variation amplitude representing ambient light characteristic data point m,/>The blood oxygen variation amplitude of the ambient light characteristic data point m is represented.
The blood oxygen change amplitude of the user at the time corresponding to the ambient light characteristic data point a is calculatedReflecting the change condition of the blood oxygen relative to the normal blood oxygen through the difference between the ambient light characteristic data point a and the normal blood oxygen value; the interference of the ambient light change on the blood oxygen change is reflected by calculating the ratio of the change amplitude of the ambient light to the blood oxygen, and the larger the ratio is, the larger the ambient light interference factor is.
For the motion feature data points, the motion disturbance factors of the motion feature data points are obtained by adopting the same calculation method as the ambient light disturbance factors of the ambient light feature data points.
According to the above steps, the motion disturbance factor can be obtained. In this embodiment, based on the motion interference factor and the ambient light interference factor, the interference distance value between the data points is adaptively obtained, where taking the data point a and the data point b as an example, the interference distance value between the data point a and the data point b is calculated:
where D represents the interference distance value between data points a and b, 、/>Represents the blood oxygen values of data points a and b, respectively,/>、/>Heart rate values representing data points a and b, respectively,/>、/>Ambient light intensity values representing data points a and b, respectively; /(I)、/>、/>Respectively representing a normal blood oxygen value, a normal heart rate value and a normal environment light intensity value; /(I)、/>Respectively representing the motion disturbance factor and the ambient light disturbance factor.
The distance index of the data point is constructed by taking the interference factor as the weight. Wherein the difference is positive and negative, so the distance value is also positive and negative.
All data points in the randomly extracted sample data are formed into one node in an isolated tree, for any one data point in the node, taking the data point A as an example, for the interference distance value between each data point in the node and the data point A, when the interference distance value is larger than 0, the data point A is placed in the right node of the data point A, and when the interference distance value is smaller than or equal to 0, the data point A is placed in the left node of the data point A.
Dividing all data points in the nodes except the data point A to obtain a left node and a right node, and constructing the division of the data point A based on the interference distance value difference of the data points in all the two nodes：
In the method, in the process of the invention,Representing distance distribution eigenvalues within node P,/>Representing an exponential function based on natural constants,/>、/>Respectively represent the maximum interference distance value and the minimum interference distance value between the data points A and all the data points in the node P,/>Representing the number of data points within node p,/>Representing the interference distance value between the P-th data point and data point A in node P,/>Is the average interference distance value between all data points within node P and data point a.
Representing the segmentality of data point A,/>Representing the minimum interference distance value of data point A and data point in node P,/>Representing the minimum interference distance value of data point A and data point in node U,/>Representing distance distribution eigenvalues within node U,/>Representing the absolute value of the interference distance value between data point a and all normal data points of the user. The normal data points are all data points with the values of normal blood oxygen value, normal heart rate value and normal environment light intensity value. Wherein,Adopt AND/>The same calculation method is used for obtaining.
It should be noted that, in the formula V, a P node is taken as an example, and similarly, V corresponding to a U node may also be obtained. By calculating the distribution distance difference of the data in the nodes at the left side and the right side of the data point, the larger the difference between the data point and the mean value is, the larger the integral data difference in the nodes is, and the distance distribution characteristic value in the node P isThe larger the difference between the data in the nodes is indicated to be more obvious, and the worse the segmentability of the data point A as the segmentation point is indicated to be; by calculating the distance between the data point A and the normal data point of the user, the smaller the distance is, the larger the segmentation is, the larger the difference between the two types of data is, and the better the segmentation effect of the data point A as the segmentation point is. The smaller the segmentation, the smaller the difference between the two types of data, and the worse the segmentation effect of the data point A as the segmentation point.
In this embodiment, the data point with the highest partition property in the extracted sample data is selected as the partition point, the remaining sample points are partitioned into left and right nodes, and the judgment condition is required to be aborted when the data points in the left and right nodes are re-partitioned and the growth of the isolated tree is selected, so that the present embodiment constructs the growth judgment condition of the nodes by judging whether the nodes need to be continuously partitioned.
Since the isolated forest distinguishes normal data from abnormal data, if the nodes in the isolated tree growth do not have abnormal values, the subsequent isolated tree growth is unnecessary, not only is the calculation resource wasted, but also the normal values can be mistakenly divided into the abnormal values, so that the accuracy and the efficiency of an isolated forest algorithm are reduced. Therefore, in this embodiment, the growth stopping property of each node of the isolated tree is obtained by analyzing the partition property of the data in the node, and taking the growth stopping property of any node as an example:
In the method, in the process of the invention, Representing growth suspension of nodes,/>An exponential function based on a natural constant e is represented,Representing maximum segmentality in data points within a node,/>The partitionability of the p-th data point in the node is shown.
Note that, when the segmentality of each data point in the isolated tree node is larger, the maximum segmentality of the node as a wholeThe larger the node, the larger the possible existence of the divided data points, the bad the dividing effect in the node, and the normal data and the abnormal data cannot be divided, so the growth stopping performance of the node is smaller, and the growth needs to be continued.
According to the steps, the growth stopping performance Z corresponding to the node can be obtained, the preset growth stopping performance threshold value is set to be 0.75, and when the growth stopping performance corresponding to the node is larger than or equal to the set threshold value, the isolated tree node does not meet the growth condition, and growth is stopped; otherwise, acquiring new data points with maximum segmentality from the nodes, simultaneously acquiring left and right nodes of the new data points, and repeating the steps until the isolated tree nodes do not meet the growth conditions or the isolated tree depth reaches the preset depth. In this embodiment, the preset depth of the isolated tree is 100, and the operator can set the value according to the actual situation.
And (3) completing the construction of the isolated tree for extracting the sample according to the steps, putting the extracted sample data back into the original data set, extracting the sample again according to the preset extraction times, and repeating the steps to complete the construction of the isolated tree, so that the isolated forest can be obtained.
The anomaly score of the data point can be obtained by an isolated forest algorithm, and the obtaining process is a known technology and is not described herein. The closer the anomaly score is to 1, the greater the probability that the data point is an outlier. In the embodiment, the average value of the abnormal scores of the data points is used as a threshold value, the data points which are larger than or equal to the average value of the abnormal scores are used as abnormal data, the abnormal data are removed, and the accuracy and the efficiency of blood oxygen data acquisition are improved. An index construction flow chart for detecting abnormal blood oxygen data is shown in fig. 2.
Thus, the abnormal data detection of the blood oxygen data is completed, the abnormal data is removed, and the accuracy of blood oxygen data acquisition is improved.
In summary, according to the embodiment of the invention, the sensor and the related data are built in the intelligent ring are collected, the influence analysis is carried out according to the multidimensional data, and the interference condition that the blood oxygen data receives movement and ambient light is excavated, so that the accuracy of blood oxygen data collection is improved; acquiring a normal heart rate value, a normal blood oxygen value and a normal environment light intensity value of a user through the heart rate data, the environment light intensity data and the distribution characteristics of all data in blood oxygen data relative to the whole data, and constructing reference state data for representing the user, so that the follow-up abnormal situation can be accurately analyzed; considering the change influence condition among related data, screening out all motion characteristic data points under the same normal state environment light intensity value and all environment light characteristic data points under the same normal state heart rate value, avoiding the influence condition of other data when analyzing the same data, improving the accuracy of analysis of various related data and avoiding confusion;
Meanwhile, the embodiment of the invention respectively reflects the change condition of blood oxygen relative to normal blood oxygen based on the environmental light characteristic data point and the motion characteristic data point through the change amplitude condition among the characteristic data points, constructs an environmental light interference factor and a motion interference factor, and excavates the interference condition of environment and motion on blood oxygen data; the interference distance value between any two data points in the data acquired by the user is adaptively constructed by combining the interference factors and normal data of the user, the interference factors are taken as weights to reconstruct the distance index between the data points, and the accuracy of the selection of the segmentation points is improved by combining the actual blood oxygen data analysis scene; according to the embodiment of the invention, the distribution condition of the data in the left node and the right node of the data is judged based on the interference distance value index, so that the segmentation performance of each data point is judged according to the segmentation effect, the segmentation performance of the segmentation points is measured more accurately through the segmentation effect, and the self-adaptive selection of the segmentation points of the isolated tree is completed; then, the method analyzes the segmentality of each data point in the left and right nodes of the segmentation point, digs the necessity of the growth of the isolated tree node, timely discovers the growth suspension of the node by constructing an index for distinguishing normal data and abnormal data, saves calculation resources, improves the precision and efficiency of an isolated forest algorithm, further improves the abnormal detection precision of the data point, and further completes the accurate acquisition of blood oxygen data of the intelligent ring.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. Accurate collection system of blood oxygen data based on intelligent ring, its characterized in that, the system includes:
The intelligent ring related data acquisition module: collecting blood oxygen data, ambient light intensity data and heart rate data of the intelligent ring;
Abnormal blood oxygen data detection and rejection module: taking blood oxygen data as a data set, and respectively acquiring a normal heart rate value, a normal blood oxygen value and a normal ambient light intensity value according to the numerical change condition of each data point in heart rate, blood oxygen and ambient light intensity data for sample data extracted at any time in the data set; respectively acquiring an ambient light characteristic data point and a motion characteristic data point based on the normal state heart rate value and the normal state ambient light intensity value; according to the difference between the blood oxygen data, the ambient light intensity data and the heart rate data of the ambient light characteristic data points and the corresponding normal values, constructing the blood oxygen change amplitude, the ambient light change amplitude and the heart rate change amplitude of the ambient light characteristic data points;
Constructing an ambient light interference factor and a motion interference factor according to the blood oxygen, the heart rate and the ambient light variation amplitude of the ambient light characteristic data points and the motion characteristic data points; combining the motion interference factor, the ambient light interference factor and the data difference between the data points to construct an interference distance value between any two data points; forming all data points in the sample data into one node of an isolated tree, and constructing the segmentality of each data point according to the interference distance value between the data points in the node; taking the data point with the maximum intra-node segmentability as a segmentation point, and completing the construction of an isolated tree based on the segmentability of each data point in the nodes of the segmentation point;
Extracting sample data from the data set according to preset extraction times to construct an isolated forest; screening abnormal data according to abnormal scores of data points in the isolated forest to finish accurate collection of blood oxygen data;
the method for respectively obtaining the normal heart rate value, the normal blood oxygen value and the normal environment light intensity value according to the numerical change condition of each data point in the heart rate, the blood oxygen and the environment light intensity data comprises the following steps:
for each data point of the heart rate data, calculating the sum of absolute values of differences between the data point and heart rate values of all other data points in the heart rate data; calculating a summation result of the summation value and the minimum positive number;
Acquiring occurrence frequency of heart rate values of data points in heart rate data; taking the ratio of the occurrence frequency to the summation result as the possibility that each data point in heart rate data is a normal heart rate value; taking the data point with the highest normal state heart rate value possibility in the heart rate data as the normal state heart rate value;
Acquiring a normal blood oxygen value and a normal ambient light intensity value of blood oxygen data and ambient light intensity data by adopting a calculation method which is the same as a normal heart rate value;
The acquiring the ambient light characteristic data point and the motion characteristic data point based on the normal state heart rate value and the normal state ambient light intensity value respectively comprises the following steps:
recording all data points with the same normal state heart rate value as ambient light characteristic data points; all data points with the same normal ambient light intensity value are noted as motion feature data points.
2. The intelligent ring-based accurate blood oxygen data collection system according to claim 1, wherein the constructing the blood oxygen variation amplitude, the ambient light variation amplitude and the heart rate variation amplitude of the ambient light characteristic data points according to the differences between the blood oxygen data, the ambient light intensity data and the heart rate data of the ambient light characteristic data points and the corresponding normal values comprises:
Calculating the absolute value of the difference between the blood oxygen value of the ambient light characteristic data point and the normal blood oxygen value; taking the ratio between the absolute value of the difference and the normal blood oxygen value as the blood oxygen change amplitude of the ambient light characteristic data point;
And acquiring the ambient light variation amplitude and the heart rate variation amplitude by adopting a calculation method which is the same as the blood oxygen variation amplitude.
3. The intelligent ring-based blood oxygen data accurate acquisition system according to claim 1, wherein the construction of the ambient light interference factor and the motion interference factor according to the blood oxygen, the heart rate and the ambient light variation amplitude of the ambient light characteristic data points and the motion characteristic data points comprises the following steps:
taking the average value of the ratio of the ambient light variation amplitude to the blood oxygen variation amplitude of all the ambient light characteristic data points as an ambient light interference factor;
obtaining the blood oxygen, heart rate and ambient light variation amplitude of the motion characteristic data points by adopting a calculation method which is the same as the blood oxygen, heart rate and ambient light variation amplitude of the ambient light characteristic data points; and taking the average value of the ratio of the heart rate variation amplitude to the blood oxygen variation amplitude of all the motion characteristic data points as a motion interference factor.
4. The intelligent finger ring based blood oxygen data accurate acquisition system according to claim 1, wherein said combining the motion disturbance factor, the ambient light disturbance factor and the data difference between the data points to construct the disturbance distance value between any two data points comprises:
the expression for the interference distance value between data point a and data point b is:
where D represents the interference distance value between data points a and b,/> 、/>Represents the blood oxygen values of data points a and b, respectively,/>、/>Heart rate values representing data points a and b, respectively,/>、/>Ambient light intensity values representing data points a and b, respectively; /(I)、/>、Respectively representing a normal blood oxygen value, a normal heart rate value and a normal environment light intensity value; /(I)、/>Respectively representing the motion disturbance factor and the ambient light disturbance factor.
5. The intelligent finger ring based blood oxygen data accurate acquisition system according to claim 1, wherein said constructing the segmentality of each data point based on the interference distance value between data points in the node comprises:
For any one data point in the nodes, forming a left node of the any one data point by all data points with interference distance values larger than 0 with the any one data point; forming a right node of any one data point by all data points with interference distance values smaller than or equal to 0 with the any one data point; the left node and the right node are collectively called as a node of any data point;
Acquiring a distance distribution characteristic value in the node based on the numerical distribution of the interference distance value in the node; the data points with the values of normal blood oxygen value, normal heart rate value and normal environment light intensity value in all the data points in the node are recorded as normal data points;
wherein the partitional expression of data point a is:
Representing the segmentality of data point A,/> Representing the minimum interference distance value of data point A and data point in node P,/>Representing the minimum interference distance value of data point A and data point in node U,/>、/>Representing distance distribution eigenvalues within node P, U,/>Representing the absolute value of the interference distance value between data point a and all normal data points of the user.
6. The intelligent finger ring based blood oxygen data accurate acquisition system according to claim 5, wherein the acquiring the intra-node distance distribution characteristic value based on the intra-node interference distance value comprises:
The expression of the distance distribution characteristic value in the node P is:
In the/> Representing distance distribution eigenvalues within node P,/>Representing an exponential function based on natural constants,/>、/>Respectively represent the maximum interference distance value and the minimum interference distance value between the data points in the node P and the preselected segmentation point A,/>, respectivelyRepresenting the number of data points within node P,/>Representing the interference distance value between the P-th data point and the preselected segmentation point A in the node P,/>Is the average interference distance value between all data points within the node P and the preselected segmentation point a.
7. The intelligent finger ring based accurate blood oxygen data collection system according to claim 5, wherein the division of each data point in the nodes based on the division points completes the construction of an isolated tree, comprising:
calculating the sum of the segmentabilities of all the data points in the nodes for the left node and the right node of the segmentation point; obtaining the maximum segmentability in the node;
Taking the inverse of the product of the sum and the maximum segmentality as an exponent of an exponential function based on a natural constant; taking the calculation result of the exponential function as the growth stopping property of the node;
stopping growing when the growth stopping property of the node is larger than or equal to a preset growth stopping property threshold value;
Otherwise, selecting the data point with the largest segmentation from the nodes as a new segmentation point, and judging the growth stopping property of the left and right nodes of the new segmentation point again until reaching the preset depth of the isolated tree, and stopping growing.
8. The intelligent finger ring based blood oxygen data accurate acquisition system according to claim 1, wherein said screening of anomaly data based on anomaly scores of data points in isolated forests comprises:
Taking the mean value of the abnormal scores of all the data points in the isolated forest as a threshold value; and recording the data points with the abnormality scores larger than the threshold value as abnormal data, and eliminating the abnormal data from blood oxygen data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410230265.4A CN117807531B (en) | 2024-02-29 | 2024-02-29 | Accurate blood oxygen data collection system based on intelligent ring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410230265.4A CN117807531B (en) | 2024-02-29 | 2024-02-29 | Accurate blood oxygen data collection system based on intelligent ring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117807531A CN117807531A (en) | 2024-04-02 |
| CN117807531B true CN117807531B (en) | 2024-05-24 |
Family
ID=90430355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410230265.4A Active CN117807531B (en) | 2024-02-29 | 2024-02-29 | Accurate blood oxygen data collection system based on intelligent ring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117807531B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118101135B (en) * | 2024-04-15 | 2024-06-21 | 深圳市魔样科技股份有限公司 | Intelligent finger ring data safe transmission method and system |
| CN118282652B (en) * | 2024-05-31 | 2024-09-06 | 深圳市魔样科技股份有限公司 | User data security protection method for intelligent ring |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1985764A (en) * | 2005-12-23 | 2007-06-27 | 深圳迈瑞生物医疗电子股份有限公司 | Blood oxygen measuring method and device capable of eliminating moving inteference |
| CN107260139A (en) * | 2017-05-27 | 2017-10-20 | 中科光谱（北京）科技有限公司 | A kind of social tool sensing heart rate ring and social contact method |
| CN115670416A (en) * | 2021-07-26 | 2023-02-03 | 神煜电子股份有限公司 | Heart rate blood oxygen monitoring device |
| CN116982948A (en) * | 2023-08-29 | 2023-11-03 | 深圳市随芯电子有限公司 | Human cardiovascular condition detection method and system for intelligent finger ring |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10786201B2 (en) * | 2017-10-12 | 2020-09-29 | Purdue Research Foundation | Methods for detecting heart rate, respiration, and oxygen saturation and uses thereof |
-
2024
- 2024-02-29 CN CN202410230265.4A patent/CN117807531B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1985764A (en) * | 2005-12-23 | 2007-06-27 | 深圳迈瑞生物医疗电子股份有限公司 | Blood oxygen measuring method and device capable of eliminating moving inteference |
| CN107260139A (en) * | 2017-05-27 | 2017-10-20 | 中科光谱（北京）科技有限公司 | A kind of social tool sensing heart rate ring and social contact method |
| CN115670416A (en) * | 2021-07-26 | 2023-02-03 | 神煜电子股份有限公司 | Heart rate blood oxygen monitoring device |
| CN116982948A (en) * | 2023-08-29 | 2023-11-03 | 深圳市随芯电子有限公司 | Human cardiovascular condition detection method and system for intelligent finger ring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117807531A (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117807531B (en) | Accurate blood oxygen data collection system based on intelligent ring | |
| CN107822622B (en) | Electrocardiogram diagnosis method and system based on deep convolutional neural network | |
| CN114391846B (en) | Emotion recognition method and system based on filtering type feature selection | |
| CN109645990A (en) | A kind of CRT technology method of epileptic's EEG signals | |
| CN116237817B (en) | Five-axis linkage numerical control machine intelligent monitoring system based on Internet of things | |
| CN111597991A (en) | Rehabilitation detection method based on channel state information and BilSTM-Attention | |
| CN110033432B (en) | Urinary calculus component analysis method and system based on machine learning and energy spectrum CT | |
| CN111370124A (en) | Health analysis system and method based on facial recognition and big data | |
| CN116451110A (en) | Blood glucose prediction model construction method based on signal energy characteristics and pulse period | |
| CN113128585B (en) | Deep neural network based multi-size convolution kernel method for realizing electrocardiographic abnormality detection and classification | |
| CN117786429A (en) | Old man health monitoring data processing method based on wearable equipment | |
| CN115083604A (en) | Construction method, system and prediction device of postoperative adverse event prediction model | |
| CN113111918A (en) | Cerebral apoplexy risk screening method based on abnormal sample detection and multi-dimensional information output | |
| CN113069124A (en) | Electrocardio monitoring method based on CNN-ET model | |
| CN113539473A (en) | Method and system for diagnosing brucellosis only by using blood routine test data | |
| CN115670417A (en) | Health assessment method and system for running monitoring | |
| CN113066544B (en) | FVEP characteristic point detection method based on CAA-Net and LightGBM | |
| CN111345815B (en) | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal | |
| CN117877736B (en) | Intelligent ring abnormal health data early warning method based on machine learning | |
| CN118507033B (en) | Automatic interpretation and diagnosis support system for medical examination results | |
| CN118633939B (en) | Multi-mode emotion recognition method and system | |
| Sabatini et al. | Photoplethysmographic Signal Quality Assessment: a Comparative Study of Unsupervised and Supervised Neural Networks | |
| CN116712035B (en) | Sleep stage method and system based on CNN-PSO-BiLSTM | |
| CN117883076B (en) | Human movement energy consumption monitoring system and method based on big data | |
| Zhou et al. | Research on intelligent diagnosis algorithm of diseases based on machine learning |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: 518000 1st, 2nd, 4th, 5th and 6th floors of Qiufen (10A) Building, Taihua wutong Industrial Park, Sanwei Community, Hangcheng Street, Bao'an District, Shenzhen, Guangdong Applicant after: Shenzhen Moyang Technology Co.,Ltd. Address before: 518000 1st, 2nd, 4th, 5th and 6th floors of Qiufen (10A) Building, Taihua wutong Industrial Park, Sanwei Community, Hangcheng Street, Bao'an District, Shenzhen, Guangdong Applicant before: SHENZHEN MOYOUNG TECHNOLOGY CO.,LTD. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |