CN111714094A - Human body temperature change prediction method based on heart rate estimation and respiration estimation - Google Patents
Human body temperature change prediction method based on heart rate estimation and respiration estimation Download PDFInfo
- Publication number
- CN111714094A CN111714094A CN202010459898.4A CN202010459898A CN111714094A CN 111714094 A CN111714094 A CN 111714094A CN 202010459898 A CN202010459898 A CN 202010459898A CN 111714094 A CN111714094 A CN 111714094A
- Authority
- CN
- China
- Prior art keywords
- rate
- heart rate
- respiration
- body temperature
- estimation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000029058 respiratory gaseous exchange Effects 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 34
- 208000031636 Body Temperature Changes Diseases 0.000 title claims abstract description 8
- 230000036760 body temperature Effects 0.000 claims abstract description 69
- 238000013499 data model Methods 0.000 claims abstract description 4
- 230000036387 respiratory rate Effects 0.000 claims description 26
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013186 photoplethysmography Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 13
- 210000001061 forehead Anatomy 0.000 description 10
- 230000008859 change Effects 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 5
- 238000009529 body temperature measurement Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010011409 Cross infection Diseases 0.000 description 1
- 206010029803 Nosocomial infection Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- 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
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physiology (AREA)
- Surgery (AREA)
- Cardiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Pulmonology (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the technical field of human body temperature prediction, in particular to a human body temperature change prediction method based on heart rate estimation and respiration estimation, which is used for solving the problem that the human body temperature cannot be predicted more accurately. The invention comprises the following steps: step S1: calculating the heart rate h and the respiration rate b; step S2: pushing the heart rate h, the respiration rate b and the corresponding time t into a stack p; step S3: finding a data set S in the latest time from the stack P, calculating a heart rate value hb _ S in the most concentrated data set of the S center rate through a Meanshift algorithm to be used as a measured heart rate effective value, and calculating a respiration rate value hb _ l in the most concentrated data set of the S respiration rate through the Meanshift algorithm to be used as a measured respiration rate effective value; step S4: calculating a body temperature offset by the formula dT ═ f (hb _ s, hb _ l, age, t), where age is age and f is a data model created from a large amount of data; step S5: the body temperature offset dT is added TO the basal body temperature TO obtain the final body temperature T, i.e., T ═ TO + dT. Thereby more accurately predicting the body temperature.
Description
Technical Field
The invention relates to the technical field of human body temperature prediction, in particular to a human body temperature change prediction method based on heart rate estimation and respiration estimation.
Background
The accurate measurement of the physical temperature of the human body has positive guiding significance on the health of people, the thermometer is used for measuring the body temperature of the human body under the common condition, and the thermometer is successfully developed on the basis of the thermometer and is used for measuring the physical temperature of the human body. The temperature of the human body is measured, so that not only can the occurrence of diseases be diagnosed, but also positive prevention and warning effects can be played on certain serious diseases or hidden health hidden dangers inside the human body. Although the clinical thermometer is widely used for measuring the body temperature of a human body, the clinical thermometer needs to be in contact with the human body to measure the body temperature, namely, the contact type clinical thermometer, and the non-contact type clinical thermometer has strong requirements on large-range clinical temperature detection in public places, infant clinical temperature detection, special patients and other situations.
In the prior art, non-contact type body temperature detection mainly comprises a handheld forehead thermometer and a medical thermal imager. The handheld forehead thermometer is simple and convenient to use, the forehead temperature of a person can be measured only by aligning the handheld forehead thermometer with the forehead of the person and keeping a certain distance from the forehead, and the handheld forehead thermometer has the advantages of being non-contact and few in cross infection. The method has the obvious defect that the temperature estimated by the forehead temperature gun has a large error under the conditions of large environmental temperature change and large fall because the measurement is the measurement of the forehead surface problem of a human body, the environmental temperature needs to be corrected as the temperature, the blackbody is used as the temperature calibration without conditions, and the influence of the detection distance is large. Originally, handheld forehead thermometers were developed for home use, allowing a preliminary diagnosis of fever symptoms, but not as a clinical basis, nor prediction of changes in body temperature.
The thermal medical imager is used for taking a thermal image of the temperature distribution of a human body and is specially designed for the requirement of clinical diagnosis. Although it has higher temperature measurement precision, the temperature of any point on the surface of the human body can be accurately given. The instrument needs a special refrigerating device, and is mainly used for not measuring the core temperature of a human body, but representing the parts and the degrees of the unchangeable and changeable distribution of the body temperature through a thermal image of the temperature distribution of the human body, analyzing a thermal image and quantitatively measuring the temperature difference, and diagnosing the position, the nature and the degree of the disease or the illness according to the anatomical, pathological and clinical experiences. Therefore, the use cost is high, the operation needs related medical knowledge, the method is only suitable for professional medical institutions, and the change of the human body temperature cannot be predicted.
The patent with the application number of CN201710728557.0 and the name of a body temperature measuring device, a body temperature measuring method and a body temperature measuring device adopts active temperature measurement, needs manual operation equipment to carry out temperature measurement operation on a specific object temperature measuring area, and is not suitable for a scene of unattended and passive body temperature detection, such as non-contact sleep body temperature detection; the temperature measurement result needs to compensate the environmental temperature, and the problem of overlarge deviation of the result exists under the condition of large environmental temperature difference; the infrared heat radiation energy of the human body is greatly different in different detection distances, so that the result consistency can be ensured only by fixing the standard detection distance, the infrared heat radiation energy detection method is not suitable for the detection of the body temperature in a longer distance, and the change of the temperature of the human body cannot be predicted.
The above prior art can not predict the body temperature, and in order to better understand the change of the body temperature, the body temperature of the human body needs to be predicted.
A patent with application number CN 106991406 a, named as a visual perception identification system, is disclosed in the prior art. The patent establishes the relation between the visual image and the physiological signal of the tested user, and in the invention, the physiological signal extraction and analysis work including but not limited to RGB visible light, IR near infrared light and PPG monochromatic spectrum is completed through different data types of the input image, thereby laying a foundation for body temperature prediction.
The other application number is CN 110537900A, the patent name is a body temperature data processing device and a body temperature data processing method thereof, the whole process body temperature data of the temperature rise of the target body temperature is used as a fitting model, the short-time body temperature prediction of the patch type thermometer is timeliness, but the accuracy of the patch type thermometer is only optimized, the scheme is not a body temperature detection accuracy optimization scheme of a non-contact body temperature detection scheme, and the scheme cannot be used for the non-contact body temperature detection scheme. Because the temperature rise curves of all the tested individuals are different, the method can not predict the individual temperature change and can only predict the temperature rise of the patch type thermometer.
In summary, the body temperature cannot be well predicted in the prior art, and in order to more accurately predict the change of the body temperature, a body temperature change prediction method based on heart rate estimation and respiration estimation is provided.
Disclosure of Invention
Based on the above problems, the present invention aims to: the human body temperature change prediction method based on heart rate estimation and respiration estimation is provided and used for solving the problem that the human body temperature cannot be predicted more accurately in the prior art.
The invention specifically adopts the following technical scheme for realizing the purpose:
a human body temperature change prediction method based on heart rate estimation and respiration estimation comprises the following steps:
step S1: calculating the heart rate h and the respiration rate b;
step S2: pushing the heart rate h, the respiration rate b and the corresponding time t into a stack p;
step S3: finding a data set S in the latest time from the stack P, calculating a heart rate value hb _ S in the most concentrated data set of the S center rate through a Meanshift algorithm to be used as a measured heart rate effective value, and calculating a respiration rate value hb _ l in the most concentrated data set of the S respiration rate through the Meanshift algorithm to be used as a measured respiration rate effective value;
step S4: calculating a body temperature offset by the formula dT ═ f (hb _ s, hb _ l, age, t), where age is age and f is a data model created from a large amount of data;
the modeling of the model data f comprises the following steps:
step 1: visual pulse and respiration signals are extracted in a non-contact mode through a CMOS sensor, PPG signals are extracted through a photoplethysmography instrument, and the PPG signals are converted into pulse and respiration counts;
step 2: and constructing a body temperature prediction regression model according to the individual body temperature, heart rate, respiration and age correlation model.
Step S5: the body temperature offset dT is added to the basal body temperature T0 to obtain the final body temperature T, i.e., T0+ dT.
The heart rate H and the respiration rate b are further calculated in the data set S, that is, the heart rate H and the respiration rate b in the data set S are calculated in step S3 with the time of the window Wn being 5 frames as the sliding window, and the obtained heart rate set is H ═ hr1，hr2，...，hrn]The set of respiratory rates is B ═ br1，br2，...，brn](ii) a Wherein, hr1Is the first calculated heart rate, hr2Is the second calculated heart rate, hrnIs the nth calculated heart rate; br1Is the first calculated breathing rate, br2Is the second calculated breathing rate, brnIs the nth calculated respiration rate.
And further processing the heart rate set H and the respiratory rate set B, namely defining the heart rate set H as follows through time sequencing: h '═ hr'1，hr′2，hr′3，...，hr′n]The set of breathing rates, B, is defined by the time ordering as: b '═ br'1，br′2，br′3，...，br′n](ii) a Clustering the heart rate h and the respiration rate b by using a Meanshift clustering algorithm, wherein the defined formula is as follows:
hb_s＝F(H′)
hb_l＝F(B′)
wherein H ' is a heart rate set hr ' ordered by time '1Is the first heart rate, hr 'ordered by time'nIs the n-th heart rate after time sequencing, and B 'is the respiratory rate set after time sequencing, br'1Is the first respiratory rate, br ', ordered by time'nThe function F is defined as mean shift cluster for the nth breath rate sorted by time.
Method for obtaining F (H') by using Meanshift clusteringThe method comprises the following steps: definition Mh(hr′1) F (H'), the heart rate drift vector is:
the heart rate in the circular domain with radius d is defined as: sd(hr′1)＝{hr′i|(hr′i-hr′1)2＜d2Searching the heart rate in the circular area through iterative calculation of the mean value drift vector of the heart rate, stopping iteration when the distance between two heart rates after two continuous drifts is smaller than a threshold value, and outputting the heart rate value calculated at the moment as an effective heart rate value; wherein, S in the formuladIs the set of heart rates in the circular domain with radius d, and k is the number of heart rates in the circular domain.
The method for obtaining F (B') by using Meanshift clustering specifically comprises the following steps: definition Mb(br′1) F (B'), the mean shift vector of the breathing rate is:
the respiration rate in the circular domain with radius d is defined as: sd(br′1)＝{br′i|(br′i-br′1)2＜d2Searching for the respiratory rate in the circular area by iteratively calculating the mean shift vector of the respiratory rate, stopping iteration when the distance between two respiratory rates after two continuous drifts is less than a threshold value', and outputting the calculated respiratory rate value as an effective respiratory rate value; wherein, S in the formuladIs the respiration rate in the circular domain with radius d and k is the number of respiration rates in the circular domain.
The invention has the following beneficial effects:
(1) according to the method, the data set S in the latest time is found from the stack P, the heart rate effective value and the respiration rate effective value in the S are calculated through the Meanshift algorithm, the body temperature offset is calculated through the formula dT (hb _ S, hb _ l, age, t), and the body temperature offset and the basic body temperature can be used for obtaining the final body temperature, so that the body temperature can be predicted more accurately.
(2) The method does not depend on temperature acquisition of infrared thermal radiation measurement, does not need calibration of temperature blackbody equipment, and has the running possibility of low power consumption and multiple platforms.
(3) Compared with a body surface temperature and ring tight temperature compensation algorithm, the method has good environmental adaptability and is simpler than the body surface temperature and ring tight temperature compensation algorithm.
Drawings
FIG. 1 is an exemplary diagram of the calculation of hb _ s or hb _ l by the Meanshift algorithm of the present invention;
FIG. 2 is a schematic diagram of the modeling of model data f according to the present invention;
FIG. 3 is a statistical chart of body temperature prediction results according to the present invention;
Detailed Description
For a better understanding of the present invention by those skilled in the art, the present invention will be described in further detail below with reference to the accompanying drawings and the following examples.
Example (b):
as shown in fig. 1-3, the method for predicting body temperature variation based on heart rate estimation and respiration estimation comprises the following steps:
step S1: calculating a heart rate h and a respiration rate b through data collected by a camera;
step S2: pushing the heart rate h and the breathing rate b into a stack p with corresponding time t, namely p { [ h1, b1, t1], [ h2, b2, t2], [ hn, bn, tn ] }, wherein h1 and b1 respectively represent the heart rate and the breathing rate corresponding to the time t1, and hn and bn respectively represent the heart rate and the breathing rate corresponding to the time tn;
step S3: finding a data set S in the latest time from a stack P, namely the data set S is a subset of the stack P, calculating a heart rate value hb _ S in the maximum set of the S center rate data set through a Meanshift algorithm to be used as a measured heart rate effective value, and calculating a respiration rate value hb _ l in the maximum set of the S respiration rate data set through the Meanshift algorithm to be used as a measured respiration rate effective value;
in step S3, the heart rate h and the respiration rate b in the data set S are calculated using the time of 5 frames in the window Wn as a sliding window, and the obtained heart rate set isH＝[hr1，hr2，...，hrn]The set of respiratory rates is B ═ br1，br2，...，brn](ii) a Wherein, hr1Is the first calculated heart rate, hr2Is the second calculated heart rate, hrnIs the nth calculated heart rate; br1Is the first calculated breathing rate, br2Is the second calculated breathing rate, brnIs the nth calculated respiration rate.
And further processing the heart rate set H and the respiratory rate set B, namely defining the heart rate set H as follows through time sequencing: h '═ hr'1，hr′2，hr′3，...，hr′n]The set of breathing rates, B, is defined by the time ordering as: b '═ br'1，br′2，br′3，...，br′n](ii) a Clustering the heart rate h and the respiration rate b by using a Meanshift clustering algorithm, wherein the defined formula is as follows:
hb_s＝F(H′)
hb_l＝F(B′)
wherein H ' is a heart rate set hr ' ordered by time '1Is the first heart rate, hr 'ordered by time'nIs the n-th heart rate after time sequencing, and B 'is the respiratory rate set after time sequencing, br'1Is the first respiratory rate, br ', ordered by time'nThe function F is defined as mean shift cluster for the nth breath rate sorted by time.
As shown in FIG. 1, the method for obtaining F (H') by using Meanshift clustering specifically is as follows: definition Mh(hr′1) F (H'), the heart rate drift vector is:
the heart rate in the circular area with the radius d is visually represented in fig. 1 by the points in the circular area with the radius d, which are defined as: sd(hr′1)＝{hr′i|(hr′i-hr′1)2< d2}, finding the heart in the circular area by iteratively calculating the mean shift vector of the heart rateThe rate, that is, finding a point in the circular area, stopping iteration when the distance between two heart rates after two consecutive drifts is smaller than the threshold, that is, when the distance between two points after two consecutive drifts is smaller than the threshold, outputting the heart rate value calculated at this time as a heart rate effective value, so as to obtain F (H'), and obtaining F (H) to obtain hb _ s; wherein, S in the formuladIs the set of heart rates in the circular domain with radius d, k is the number of heart rates in the circular domain, and the arrow in the figure indicates the heart rate drift vector Mh(hr′1) Formula S indicated by the tail of the arrowd(hr′1)＝{hr′i|(hr′i-hr′1)2＜d2Hr in }'1The head indicates the next circular region center (i.e., formula)
Hr of'1The threshold value is a value that is considered to be set according to the time situation.
The method for obtaining F (B') by using Meanshift clustering specifically comprises the following steps: definition Mb(br′1) F (B'), the mean shift vector of the breathing rate is:
the respiration rate in the circular domain with radius d is defined as: sd(br′1)＝{br′i|(br′i-br′1)2＜d2And finding the respiratory rate in the circular area by iteratively calculating the mean shift vector of the respiratory rate, stopping iteration when the distance between two respiratory rates after two continuous drifts is less than a threshold value ', outputting the calculated respiratory rate value as an effective respiratory rate value to obtain F (B '), and obtaining the hb _ l by obtaining the F (B '). Wherein, S in the formuladThe respiration rate in the circular region with the radius d and k are the number of respiration rates in the circular region, and the specific manner of using fig. 1 is the same as the calculation of f (h).
Step S4: calculating a body temperature offset by using hb _ S and hb _ l obtained in step S3 through the formula dT ═ f (hb _ S, hb _ l, age, t), where age is age and f is a data model created from a large amount of data;
the modeling of the model data f comprises the following steps:
step 1: visual pulse and respiration signals are extracted in a non-contact mode through a CMOS sensor, PPG signals are extracted through a photoplethysmography instrument, the PPG signals are converted into pulse and respiration counts, and the photoplethysmography instrument is an instrument existing in the market;
step 2: and constructing a body temperature prediction regression model according to the individual body temperature, heart rate, respiration and age correlation model.
Step S5: the body temperature offset dT is added to the basal body temperature T0 to obtain the final body temperature T, i.e., T0+ dT, where the basal body temperature T0 is the known body temperature.
The human body temperature T can be more accurately predicted through the steps.
The above is an embodiment of the present invention. The embodiments and specific parameters in the embodiments are only for the purpose of clearly illustrating the verification process of the invention and are not intended to limit the scope of the invention, which is defined by the claims, and all equivalent structural changes made by using the contents of the specification and the drawings of the present invention should be covered by the scope of the present invention.
Claims (6)
1. A human body temperature change prediction method based on heart rate estimation and respiration estimation is characterized in that: the method comprises the following steps:
step S1: calculating the heart rate h and the respiration rate b;
step S2: pushing the heart rate h, the respiration rate b and the corresponding time t into a stack p;
step S3: finding a data set S in the latest time from the stack P, calculating a heart rate value hb _ S in the most concentrated data set of the S center rate through a Meanshift algorithm to be used as a measured heart rate effective value, and calculating a respiration rate value hb _ I in the most concentrated data set of the S respiration rate through the Meanshift algorithm to be used as a measured respiration rate effective value;
step S4: calculating a body temperature offset by the formula dT ═ f (hb _ s, hb _ l, age, t), where age is age and f is a data model created from a large amount of data;
step S5: the body temperature offset dT is added to the basal body temperature T0 to obtain the final body temperature T, i.e., T0+ dT.
2. The method of claim 1, wherein the heart rate estimation and respiration estimation based body temperature variation prediction method comprises: in step S3, the heart rate H and the respiration rate b in the data set S are calculated using the time of the window Wn-5 frames as a sliding window, and the obtained heart rate set is H ═ hr1，hr2，...，hrn]The set of respiratory rates is B ═ br1，br2，...，brn](ii) a Wherein, hr1Is the first calculated heart rate, hr2Is the second calculated heart rate, hrnIs the nth calculated heart rate; br1Is the first calculated breathing rate, br2Is the second calculated breathing rate, brnIs the nth calculated respiration rate.
3. The method of claim 2, wherein the heart rate estimation and respiration estimation based body temperature variation prediction method comprises: the heart rate set H is defined by a temporal ordering as: h '═ hr'1，hr′2，hr′3，...，hr′n]The set of breathing rates, B, is defined by the time ordering as: b '═ br'1，br′2，br′3，...，br′n](ii) a Clustering the heart rate h and the respiration rate b by using a Meanshift clustering algorithm, wherein the defined formula is as follows:
hb_s＝F(H′)
hb_I＝F(B′)
wherein H ' is a heart rate set hr ' ordered by time '1Is the first heart rate, hr 'ordered by time'nIs the n-th heart rate after time sequencing, and B 'is the respiratory rate set after time sequencing, br'1Is the first respiratory rate, br ', ordered by time'nFor the nth breathing rate, ordered by time, the function F is defined as MeansAnd (5) performing high clustering.
4. The method of claim 3, wherein the heart rate estimation and respiration estimation based body temperature variation prediction method comprises: definition Mh(hr′1) F (H'), the heart rate drift vector is:
the heart rate in the circular domain with radius d is defined as: sd(hr′1)＝{hr′i|(hr′i-hr′1)2＜d2Searching the heart rate in the circular area through iterative calculation of the mean value drift vector of the heart rate, stopping iteration when the distance between two heart rates after two continuous drifts is smaller than a threshold value, and outputting the heart rate value calculated at the moment as an effective heart rate value; wherein, S in the formuladIs the set of heart rates in the circular domain with radius d, and k is the number of heart rates in the circular domain.
5. The method of claim 3, wherein the heart rate estimation and respiration estimation based body temperature variation prediction method comprises: definition Mb(br′1) F (B'), the mean shift vector of the breathing rate is:
the respiration rate in the circular domain with radius d is defined as: sd(br′1)＝{br′i|(br′i-br′1)2＜d2Searching for the respiratory rate in the circular area by iteratively calculating the mean shift vector of the respiratory rate, stopping iteration when the distance between two respiratory rates after two continuous drifts is less than a threshold value', and outputting the calculated respiratory rate value as an effective respiratory rate value; wherein, S in the formuladIs the respiration rate in the circular domain with radius d and k is the number of respiration rates in the circular domain.
6. The method of claim 1, wherein the heart rate estimation and respiration estimation based body temperature variation prediction method comprises: the modeling of the model data f comprises the following steps:
step 1: visual pulse and respiration signals are extracted in a non-contact mode through a CMOS sensor, PPG signals are extracted through a photoplethysmography instrument, and the PPG signals are converted into pulse and respiration counts;
step 2: and constructing a body temperature prediction regression model according to the individual body temperature, heart rate, respiration and age correlation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010459898.4A CN111714094A (en) | 2020-05-28 | 2020-05-28 | Human body temperature change prediction method based on heart rate estimation and respiration estimation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010459898.4A CN111714094A (en) | 2020-05-28 | 2020-05-28 | Human body temperature change prediction method based on heart rate estimation and respiration estimation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111714094A true CN111714094A (en) | 2020-09-29 |
Family
ID=72566184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010459898.4A Pending CN111714094A (en) | 2020-05-28 | 2020-05-28 | Human body temperature change prediction method based on heart rate estimation and respiration estimation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111714094A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019211575A1 (en) * | 2018-05-03 | 2019-11-07 | Oxford University Innovation Limited | Method and apparatus for classifying subjects based on time series phenotypic data |
| CN110537900A (en) * | 2018-05-29 | 2019-12-06 | 浙江清华柔性电子技术研究院 | Body temperature data processing device and body temperature data processing method thereof |
-
2020
- 2020-05-28 CN CN202010459898.4A patent/CN111714094A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019211575A1 (en) * | 2018-05-03 | 2019-11-07 | Oxford University Innovation Limited | Method and apparatus for classifying subjects based on time series phenotypic data |
| CN110537900A (en) * | 2018-05-29 | 2019-12-06 | 浙江清华柔性电子技术研究院 | Body temperature data processing device and body temperature data processing method thereof |
Non-Patent Citations (3)
| Title |
|---|
| 俞谢益: "《基于典型相关分析的非接触式心率检测方法研究》", 《华侨大学硕士学位论文》 * |
| 李诗语: "《基于超声图像的桡动脉检测与跟踪算法研究》", 《广东工业大学硕士学位论文》 * |
| 皮慧: "《基于人脸图像的非接触式心率测量方法研究》", 《东南大学工程硕士学位论文》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Detection of respiratory infections using RGB-infrared sensors on portable device | |
| Murthy et al. | Touchless monitoring of breathing function | |
| CN106798545B (en) | Thermometer System | |
| Eastwood et al. | Predicting sleep apnea from three-dimensional face photography | |
| Basu et al. | Infrared imaging based hyperventilation monitoring through respiration rate estimation | |
| Luo et al. | Detection and prediction of ovulation from body temperature measured by an in-ear wearable thermometer | |
| RU2691006C2 (en) | Device and method for determining chest and abdominal breathing signals from image data | |
| Procházka et al. | Machine learning in rehabilitation assessment for thermal and heart rate data processing | |
| CN114999646B (en) | Newborn exercise development assessment system, method, device and storage medium | |
| US9498166B2 (en) | Method for displaying the temperature field of a biological subject | |
| Silsupadol et al. | Smartphone-based assessment of gait during straight walking, turning, and walking speed modulation in laboratory and free-living environments | |
| CN111588353A (en) | Body temperature measuring method | |
| Tracy et al. | Separating bedtime rest from activity using waist or wrist-worn accelerometers in youth | |
| Bouarfa et al. | Predicting free-living energy expenditure using a miniaturized ear-worn sensor: An evaluation against doubly labeled water | |
| CN111854964A (en) | Method and device for measuring body temperature, temperature measuring tool and storage medium | |
| CN112363139A (en) | Human body breathing time length detection method and device based on amplitude characteristics and storage medium | |
| Mateu-Mateus et al. | Camera-based method for respiratory rhythm extraction from a lateral perspective | |
| CN111714094A (en) | Human body temperature change prediction method based on heart rate estimation and respiration estimation | |
| Rinanto et al. | PCA-ANN Contactless Multimodality Sensors for Body Temperature Estimation | |
| Fry et al. | Detection of infant motor activity during spontaneous kicking movements for term and preterm infants using inertial sensors | |
| Farah et al. | Respiratory rate measurement in children using a thermal imaging camera | |
| Al-Kalidi et al. | Respiratory rate measurement in children using a thermal camera | |
| Lin et al. | Research on feature mining algorithm and disease diagnosis of pulse signal based on piezoelectric sensor | |
| JP2023535379A (en) | Methods and systems for body temperature estimation using wearable biosensors | |
| Mohammadzadeh et al. | Prediction of physiological response over varying forecast lengths with a wearable health monitoring platform |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200929 |