CN113288088A - Real-time body temperature monitoring and early warning system based on vital sign detection - Google Patents

Real-time body temperature monitoring and early warning system based on vital sign detection Download PDF

Info

Publication number
CN113288088A
CN113288088A CN202110731605.8A CN202110731605A CN113288088A CN 113288088 A CN113288088 A CN 113288088A CN 202110731605 A CN202110731605 A CN 202110731605A CN 113288088 A CN113288088 A CN 113288088A
Authority
CN
China
Prior art keywords
data
body temperature
early warning
time
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.)
Granted
Application number
CN202110731605.8A
Other languages
Chinese (zh)
Other versions
CN113288088B (en
Inventor
王震坡
龙超华
祁春玉
李晓强
刘鹏
郭熙军
李阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute Of Technology New Source Information Technology Co ltd
Original Assignee
Beijing Institute Of Technology New Source Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute Of Technology New Source Information Technology Co ltd filed Critical Beijing Institute Of Technology New Source Information Technology Co ltd
Priority to CN202110731605.8A priority Critical patent/CN113288088B/en
Publication of CN113288088A publication Critical patent/CN113288088A/en
Application granted granted Critical
Publication of CN113288088B publication Critical patent/CN113288088B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—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
    • A61B5/01—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
    • A61B5/68—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
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms

Abstract

The invention provides a real-time body temperature monitoring and early warning system based on vital sign detection and a corresponding method, aiming at the defect that the existing instantaneous body temperature monitoring means is easily influenced by various factors such as the human body and the external environment, and by carrying out noise elimination, data filling and smoothing on a plurality of continuously acquired vital sign data, the adverse influence of the various factors on the body temperature detection precision is effectively overcome, the actual body temperature change of a monitored object in a specific time period can be accurately obtained, and the body temperature abnormity early warning efficiency is greatly improved, so that the system and the method are particularly suitable for epidemic prevention monitoring of a large number of people in public places at present.

Description

Real-time body temperature monitoring and early warning system based on vital sign detection
Technical Field
The invention belongs to the technical field of human body physiological index monitoring, and particularly relates to a body temperature monitoring and early warning system based on multiple vital sign detection.
Background
At present, how to accurately monitor and early warn epidemic situations of infectious diseases caused by novel coronavirus under the background of global large-area transmission has very important significance for epidemic situation prevention and control work. The body temperature of a human body is an important physiological index, and is widely used for large-scale primary screening of various infectious diseases including new coronary pneumonia, and the quality of a detection result also determines whether epidemic situations can be found in time. The existing commonly used body temperature monitoring mode depends on the instantaneous measurement process executed by the body temperature test instrument, the result of the instantaneous measurement process is influenced by various factors such as other vital signs and external environment, large errors exist inevitably, for example, the body temperature changes in real time along with the changes of physiological factors such as heart rate, blood pressure and emotion of people and the changes of environmental temperature and humidity, and the single measurement result is not enough to correctly reflect the real body condition. Especially, for body temperature monitoring facilities arranged in public places, complex field environments and intensive people flows, conditions for repeatedly performing multiple detections on individuals to ensure precision are lacked, the abnormal body temperature condition is frequently missed or mistakenly reported, and the efficiency of epidemic prevention work is influenced. Therefore, how to overcome the defect of single instantaneous body temperature monitoring and provide an accurate body temperature monitoring and early warning system comprehensively considering the influence of other multiple factors is a technical problem to be solved in the field.
Disclosure of Invention
In view of the above, the present invention provides a real-time body temperature monitoring and early warning system based on vital sign detection, which includes:
the system comprises wearable equipment, terminal equipment, a data transmission part and a body temperature monitoring and early warning platform;
the wearable device is worn by a monitored object and is used for acquiring human body vital sign data of the monitored object in real time;
the data transmission part is used for transmitting data among the wearable equipment, the terminal equipment and the body temperature monitoring and early warning platform;
the body temperature monitoring and early warning platform is used for sequentially executing the following processing on vital sign data transmitted by the wearable equipment through the data transmission part:
a. according to a data set formed by continuously collecting data for a plurality of times of the body temperature, the heart rate, the diastolic pressure and the systolic pressure, noise data caused by accidental factors in the data set are removed through amplitude limiting filtering;
b. performing data filling to supplement missing values in the data set for a certain time of acquisition corresponding to the eliminated noise data;
c. executing a five-point three-time smoothing algorithm on the data filled data set to eliminate random errors caused by age, gender, season and day-night difference;
d. extracting the extreme value of the body temperature data in the data set after the random error is eliminated, and judging whether to provide early warning information or not;
and the terminal equipment is used for providing the display of the vital sign data and the early warning information.
Further, the body temperature monitoring and early warning platform acquires and uploads the following data aiming at the wearable device: body temperature value T of monitored objectkHeart rate value HkDiastolic blood pressure DkSystolic pressure value SkWhere k denotes the number of acquisitions k e [1,2,3, … performed within a certain time period]The following thresholds are defined, respectively:
Tmax: presetting an upper limit of a normal body temperature threshold;
Tmin: presetting a lower limit of a normal body temperature threshold;
and N is the minimum time interval for sending the body temperature early warning information.
Further, the body temperature monitoring and early warning platform executes amplitude limiting filtering to remove noise data caused by accidental factors, and the method specifically comprises the following steps:
a1, filtering the body temperature data T by using an amplitude limiting filtering method, removing noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000021
in formula (1), Tk、Tk-1Respectively representing the body temperature data of two continuous times, wherein delta T represents the possible maximum body temperature deviation, and comparing the difference value of the body temperature data of two continuous times with the delta T;
a2, filtering the heart rate data H by using an amplitude limiting filtering method, removing noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000022
in the formula (2), Hk、Hk-1Respectively representing heart rate data of two continuous times, wherein delta H represents the possible maximum heart rate deviation, and comparing the difference value of the heart rate values of the two continuous times with the delta H;
a3, filtering diastolic pressure data D by using an amplitude limiting filtering method, eliminating noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000023
in formula (3), Dk、Dk-1Respectively representing the diastolic blood pressure values of two consecutive times, wherein delta D represents the maximum deviation of possible diastolic blood pressure, and comparing the difference value of the diastolic blood pressure values of two consecutive times with delta D;
a4, filtering the systolic pressure data S by using an amplitude limiting filtering method, eliminating noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000024
in formula (4), Sk、Sk-1Respectively representing the systolic pressure values of two continuous times, and comparing the absolute value of the difference value of the systolic pressures of the two continuous times with the delta S, wherein the delta S represents the maximum deviation of the possible systolic pressures.
Further, the specific process of executing data to fill missing values in the supplementary data set includes:
and acquiring the rejected noise data at a time, and filling the missing values with the effective body temperature, heart rate and blood pressure data acquired at the previous time as follows to improve the effectiveness of the body temperature data:
Figure BDA0003139400340000025
Figure BDA0003139400340000031
Figure BDA0003139400340000032
Figure BDA0003139400340000033
in the formula, NaN represents null values after noise removal.
Further, the five-point three-time smoothing algorithm is specifically implemented on the data set filled with the data by performing the following smoothing process on the body temperature data:
let 2n +1 equidistant nodes X-n,X-n+1,……X-1,X0,X1,……Xn-1,XnThe above sign data are Y-n,Y-n+1,……Y-1,Y0,Y1,……Yn-1,Yn；
Let the equidistant distance between two adjacent nodes be h for exchange
Figure BDA0003139400340000034
The original node becomes t-n＝-n,t-n+1＝-n+1,……t-1＝-1,t0＝0,t1＝1,……tn-1＝n-1,tn＝n,
Fitting the obtained physical sign data by using an m-th-order polynomial to obtain a normal equation set;
Figure BDA0003139400340000035
when n is 2 and m is 3, a specific normal system of equations is obtained, from which a is solved0,a1,a2,a3And substituting the formula into the formula, and enabling t to be 0, +1, -1, +2, -2 to obtain a five-point cubic smoothing formula:
Figure BDA0003139400340000036
Figure BDA0003139400340000037
Figure BDA0003139400340000038
Figure BDA0003139400340000039
Figure BDA00031394003400000310
wherein the content of the first and second substances,
Figure BDA00031394003400000311
is YiImproved value.
According to each group of body temperature values, curve fitting is carried out, and through comparison, the following formula is adopted in design to smooth the body temperature curve, so that the smoothness is good, the speed is high, and the precision is high:
T＝(-3Tk-2+12Tk-1+17Tk+12Tk+1-3Tk+2)/35 (9)
further, the process of determining whether to provide the warning information specifically includes:
maximum value t of body temperature data extracted aiming at m times of acquisition in certain specific time periodmaxAnd a minimum value tmin：
tmax＝max(T1,T2,…,Tm) (10)
tmin＝min(T1,T2,…,Tm) (11)
The maximum value tmaxAnd a minimum value tminThe comparison with the corresponding threshold determines whether the following pre-warning trigger conditions are met:
tmax≤Tmin (12)
or
tmin≥Tmax (13)
If the trigger condition is met, providing the body temperature early warning should also meet the following 2-point constraint:
constraint 1: if the abnormal body temperature value simultaneously satisfies the conditions of heart rate acceleration, systolic pressure rise and diastolic pressure drop, the temperature data T is judgedkAnd (4) invalidation:
Figure BDA0003139400340000041
in the formula (14), the reaction mixture is,
Figure BDA0003139400340000042
representing the mean value of the heart rate over the first half of the particular time period,
Figure BDA0003139400340000043
representing the mean value of the heart rate in the latter half of the time;
Figure BDA0003139400340000044
in the formula (15), the reaction mixture is,
Figure BDA0003139400340000045
representing the mean diastolic blood pressure during the first half of the particular time period,
Figure BDA0003139400340000046
means of diastolic pressure in the latter half of the time;
Figure BDA0003139400340000047
in the formula (16), the reaction mixture is,
Figure BDA0003139400340000048
indicating the mean systolic pressure during the first half of the particular time period,
Figure BDA0003139400340000049
means of systolic blood pressure in the latter half of the time;
judging whether f (H, D, S) is 4f (H)) +2f (D)) + f (S) (17)
If and only if f (H) is 1, f (D) is 1, f (S) is 0, namely f (H, D, S) is 6, it indicates that the body temperature rise is caused by strenuous exercise at the moment, and the time body temperature data T is judgedkInvalid;
constraint 2: and sending the body temperature early warning information needs to meet the minimum time interval N, otherwise, the body temperature early warning information is not sent.
Nk≥N,k∈[1,2,3,…] (18)
In formula (18), NkAnd when the temperature extreme value meets the triggering early warning condition, the time interval from the last time of sending the warning information is obtained.
Correspondingly, the invention also provides a real-time body temperature monitoring and early warning method using the system, which specifically comprises the following steps:
step 1, wearable equipment collects human body vital sign data of a monitored object wearing the equipment in real time and uploads the data to a body temperature monitoring and early warning platform through a data transmission part;
step 2, the body temperature monitoring and early warning platform sequentially executes the following processing on the vital sign data transmitted by the wearable device through the data transmission part:
a. according to a data set formed by continuously collecting data for a plurality of times of the body temperature, the heart rate, the diastolic pressure and the systolic pressure, noise data caused by accidental factors in the data set are removed through amplitude limiting filtering;
b. performing data filling to supplement missing values in the data set for a certain time of acquisition corresponding to the eliminated noise data;
c. executing a five-point three-time smoothing algorithm on the data filled data set to eliminate random errors caused by age, gender, season and day-night difference;
d. extracting the extreme value of the body temperature data in the data set after the random error is eliminated, judging whether to provide early warning information or not, and if so, sending the early warning information to the terminal equipment through the data transmission part;
and 3, the terminal equipment receives the information sent by the body temperature monitoring and early warning platform and provides the vital sign data and the display of the early warning information.
The real-time body temperature monitoring and early warning system and the corresponding method based on vital sign detection provided by the invention aim at the defect that the existing instantaneous body temperature monitoring means is easily influenced by various factors such as the human body and the external environment, effectively overcomes the adverse influence of various factors on the body temperature detection precision by carrying out noise elimination, data filling and smoothing on a plurality of continuously acquired vital sign data, and can accurately obtain the actual body temperature change of a monitored object in a specific time period, thereby greatly improving the efficiency of body temperature abnormity early warning, and being particularly suitable for epidemic prevention monitoring of a large number of people in public places at present.
Drawings
FIG. 1 is a schematic diagram of the structure of the system of the present invention;
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The real-time body temperature monitoring and early warning system based on vital sign detection, as shown in fig. 1, includes:
the system comprises wearable equipment, terminal equipment, a data transmission part and a body temperature monitoring and early warning platform;
the wearable device is worn by a monitored object and is used for acquiring human body vital sign data of the monitored object in real time;
the data transmission part is used for transmitting data among the wearable equipment, the terminal equipment and the body temperature monitoring and early warning platform;
the body temperature monitoring and early warning platform is used for sequentially executing the following processing on vital sign data transmitted by the wearable equipment through the data transmission part:
a. according to a data set formed by continuously collecting data for a plurality of times of the body temperature, the heart rate, the diastolic pressure and the systolic pressure, noise data caused by accidental factors in the data set are removed through amplitude limiting filtering;
b. performing data filling to supplement missing values in the data set for a certain time of acquisition corresponding to the eliminated noise data;
c. executing a five-point three-time smoothing algorithm on the data filled data set to eliminate random errors caused by age, gender, season and day-night difference;
d. extracting the extreme value of the body temperature data in the data set after the random error is eliminated, and judging whether to provide early warning information or not;
and the terminal equipment is used for providing the display of the vital sign data and the early warning information.
In a preferred embodiment of the present invention, the body temperature monitoring and early warning platform collects and uploads the following data for the wearable device: body temperature value T of monitored objectkHeart rate value HkDiastolic blood pressure DkSystolic pressure value SkWhere k denotes the number of acquisitions k e [1,2,3, … performed within a certain time period]The following thresholds are defined, respectively:
Tmax: presetting an upper limit of a normal body temperature threshold;
Tmin: presetting a lower limit of a normal body temperature threshold;
and N is the minimum time interval for sending the body temperature early warning information.
In a preferred embodiment of the present invention, the body temperature monitoring and early warning platform performs amplitude limiting filtering to remove noise data caused by accidental factors, and specifically includes:
a1, filtering the body temperature data T by using an amplitude limiting filtering method, removing noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000061
in formula (1), Tk、Tk-1Respectively representing the body temperature data of two continuous times, wherein delta T represents the possible maximum body temperature deviation, and comparing the difference value of the body temperature data of two continuous times with the delta T;
a2, filtering the heart rate data H by using an amplitude limiting filtering method, removing noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000062
in the formula (2), Hk、Hk-1Respectively representing heart rate data of two consecutive timesΔ H represents the maximum possible heart rate deviation, the difference between two successive heart rate values being compared with Δ H;
a3, filtering diastolic pressure data D by using an amplitude limiting filtering method, eliminating noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000063
in formula (3), Dk、Dk-1Respectively representing the diastolic blood pressure values of two consecutive times, wherein delta D represents the maximum deviation of possible diastolic blood pressure, and comparing the difference value of the diastolic blood pressure values of two consecutive times with delta D;
a4, filtering the systolic pressure data S by using an amplitude limiting filtering method, eliminating noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000064
in formula (4), Sk、Sk-1Respectively representing the systolic pressure values of two continuous times, and comparing the absolute value of the difference value of the systolic pressures of the two continuous times with the delta S, wherein the delta S represents the maximum deviation of the possible systolic pressures.
In a preferred embodiment of the present invention, the specific process of executing data to fill missing values in the supplementary data set includes:
and acquiring the rejected noise data at a time, and filling the missing values with the effective body temperature, heart rate and blood pressure data acquired at the previous time as follows to improve the effectiveness of the body temperature data:
Figure BDA0003139400340000065
Figure BDA0003139400340000066
Figure BDA0003139400340000067
Figure BDA0003139400340000068
in the formula, NaN represents null values after noise removal.
In a preferred embodiment of the present invention, the five-point three-time smoothing algorithm is specifically performed on the data-filled data set by performing the following smoothing process on the body temperature data:
T＝(-3Tk-2+12Tk-1+17Tk+12Tk+1-3Tk+2)/35 (9)
in a preferred embodiment of the present invention, the process of determining whether to provide the warning information specifically includes:
extraction of maximum t of body temperature data for m acquisitions of a 5 minute time periodmaxAnd a minimum value tmin：
tmax＝max(T1,T2,…,Tm) (10)
tmin＝min(T1,T2,…,Tm) (11)
The maximum value tmaxAnd a minimum value tminThe comparison with the corresponding threshold determines whether the following pre-warning trigger conditions are met:
tmax≤Tmin (12)
or
tmin≥Tmax (13)
If the trigger condition is met, providing the body temperature early warning should also meet the following 2-point constraint:
constraint 1: if the abnormal body temperature value simultaneously satisfies the conditions of heart rate acceleration, systolic pressure rise and diastolic pressure drop, the temperature data T is judgedkAnd (4) invalidation:
Figure BDA0003139400340000071
in the formula (14), the reaction mixture is,
Figure BDA0003139400340000072
representing the mean heart rate over the first half of the 5 minute period,
Figure BDA0003139400340000073
representing the mean value of the heart rate in the latter half of the time;
Figure BDA0003139400340000074
in the formula (15), the reaction mixture is,
Figure BDA0003139400340000075
representing the mean diastolic blood pressure during the first half of the 5 minute time period,
Figure BDA0003139400340000076
means of diastolic pressure in the latter half of the time;
Figure BDA0003139400340000077
in the formula (16), the reaction mixture is,
Figure BDA0003139400340000078
means systolic mean values over the first half of the 5 minute period,
Figure BDA0003139400340000079
means of systolic blood pressure in the latter half of the time;
judging whether f (H, D, S) is 4f (H)) +2f (D)) + f (S) (17)
If and only if f (H) is 1, f (D) is 1, f (S) is 0, namely f (H, D, S) is 6, it indicates that the body temperature rise is caused by strenuous exercise at the moment, and the time body temperature data T is judgedkInvalid;
constraint 2: the minimum time interval N, such as 15 minutes, needs to be met for sending the body temperature early warning information, otherwise the body temperature warning information is not sent.
Nk≥N,k∈[1,2,3,…] (18)
In formula (18), NkAnd when the temperature extreme value meets the triggering early warning condition, the time interval from the last time of sending the warning information is obtained.
Correspondingly, the invention also provides a real-time body temperature monitoring and early warning method using the system, as shown in fig. 2, the following steps are specifically executed:
step 1, wearable equipment collects human body vital sign data of a monitored object wearing the equipment in real time and uploads the data to a body temperature monitoring and early warning platform through a data transmission part;
step 2, the body temperature monitoring and early warning platform sequentially executes the following processing on the vital sign data transmitted by the wearable device through the data transmission part:
a. according to a data set formed by continuously collecting data for a plurality of times of the body temperature, the heart rate, the diastolic pressure and the systolic pressure, noise data caused by accidental factors in the data set are removed through amplitude limiting filtering;
b. performing data filling to supplement missing values in the data set for a certain time of acquisition corresponding to the eliminated noise data;
c. executing a five-point three-time smoothing algorithm on the data filled data set to eliminate random errors caused by age, gender, season and day-night difference;
d. extracting the extreme value of the body temperature data in the data set after the random error is eliminated, judging whether to provide early warning information or not, and if so, sending the early warning information to the terminal equipment through the data transmission part;
and 3, the terminal equipment receives the information sent by the body temperature monitoring and early warning platform and provides the vital sign data and the display of the early warning information.
Specifically, the detailed process of the method comprises the following steps of sequentially performing:
the body temperature monitoring and early warning platform is used for collecting and uploading the following data aiming at wearable equipment: body temperature value T of monitored objectkHeart rate value HkDiastolic blood pressure DkSystolic pressure value SkWhere k denotes the number of acquisitions k e [1,2,3, … performed within a certain time period]The following thresholds are defined, respectively:
Tmax: presetting an upper limit of a normal body temperature threshold;
Tmin: presetting a lower limit of a normal body temperature threshold;
and N is the minimum time interval for sending the body temperature early warning information.
The body temperature monitoring early warning platform executes amplitude limiting filtering to remove noise data caused by accidental factors:
a1, filtering the body temperature data T by using an amplitude limiting filtering method, removing noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000081
in formula (1), Tk、Tk-1Respectively representing the body temperature data of two continuous times, wherein delta T represents the possible maximum body temperature deviation, and comparing the difference value of the body temperature data of two continuous times with the delta T;
a2, filtering the heart rate data H by using an amplitude limiting filtering method, removing noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000082
in the formula (2), Hk、Hk-1Respectively representing heart rate data of two continuous times, wherein delta H represents the possible maximum heart rate deviation, and comparing the difference value of the heart rate values of the two continuous times with the delta H;
a3, filtering diastolic pressure data D by using an amplitude limiting filtering method, eliminating noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000091
in formula (3), Dk、Dk-1Respectively representing the diastolic blood pressure values of two consecutive times, wherein delta D represents the maximum deviation of possible diastolic blood pressure, and comparing the difference value of the diastolic blood pressure values of two consecutive times with delta D;
a4, filtering the systolic pressure data S by using an amplitude limiting filtering method, eliminating noise data caused by accidental factors, and improving the representativeness of the data:
Figure BDA0003139400340000092
in formula (4), Sk、Sk-1Respectively representing the systolic pressure values of two continuous times, and comparing the absolute value of the difference value of the systolic pressures of the two continuous times with the delta S, wherein the delta S represents the maximum deviation of the possible systolic pressures.
The specific process of executing data to fill missing values in the supplemental data set includes:
and acquiring the rejected noise data at a time, and filling the missing values with the effective body temperature, heart rate and blood pressure data acquired at the previous time as follows to improve the effectiveness of the body temperature data:
Figure BDA0003139400340000093
Figure BDA0003139400340000094
Figure BDA0003139400340000095
Figure BDA0003139400340000096
in the formula, NaN represents null values after noise removal.
And performing a five-point cubic smoothing algorithm on the data-filled data set:
T＝(-3Tk-2+12Tk-1+17Tk+12Tk+1-3Tk+2)/35 (9)
further, the process of determining whether to provide the warning information specifically includes:
maximum value t of body temperature data extracted aiming at m times of acquisition in certain specific time periodmaxAnd a minimum value tmin：
tmax＝max(T1,T2,…,Tm) (10)
tmin＝min(T1,T2,…,Tm) (11)
The maximum value tmaxAnd a minimum value tminThe comparison with the corresponding threshold determines whether the following pre-warning trigger conditions are met:
tmax≤Tmin (12)
or
tmin≥Tmax (13)。
If the trigger condition is met, providing a body temperature warning should also meet the 2-point constraint described above.
It should be understood that, the sequence numbers of the steps in the embodiments of the present invention do not mean the execution sequence, and the execution sequence of each process should be determined by the function and the inherent logic of the process, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (7)

1. The utility model provides a real-time body temperature monitoring early warning system based on vital sign detects which characterized in that: the method comprises the following steps:
the system comprises wearable equipment, terminal equipment, a data transmission part and a body temperature monitoring and early warning platform;
the wearable device is worn by a monitored object and is used for acquiring human body vital sign data of the monitored object in real time;
the data transmission part is used for transmitting data among the wearable equipment, the terminal equipment and the body temperature monitoring and early warning platform;
the body temperature monitoring and early warning platform is used for sequentially executing the following processing on vital sign data transmitted by the wearable equipment through the data transmission part:
a. according to a data set formed by continuously collecting data for a plurality of times of the body temperature, the heart rate, the diastolic pressure and the systolic pressure, noise data caused by accidental factors in the data set are removed through amplitude limiting filtering;
b. performing data filling to supplement missing values in the data set for a certain time of acquisition corresponding to the eliminated noise data;
c. executing a five-point three-time smoothing algorithm on the data filled data set to eliminate random errors caused by age, gender, season and day-night difference;
d. extracting the extreme value of the body temperature data in the data set after the random error is eliminated, and judging whether to provide early warning information or not;
and the terminal equipment is used for providing the display of the vital sign data and the early warning information.
2. The system of claim 1, wherein: the body temperature monitoring and early warning platform is used for collecting and uploading the following data aiming at wearable equipment: body temperature value T of monitored objectkHeart rate value HkDiastolic blood pressure Dk and systolic blood pressure SkWhere k denotes the number of acquisitions k e [1,2,3, … performed within a certain time period]The following thresholds are defined, respectively:
Tmax: presetting an upper limit of a normal body temperature threshold;
Tmin: presetting a lower limit of a normal body temperature threshold;
and N is the minimum time interval for sending the body temperature early warning information.
3. The system of claim 2, wherein: the body temperature monitoring early warning platform carries out amplitude limiting filtering to remove noise data caused by accidental factors, and the method specifically comprises the following steps:
a1, filtering the body temperature data T by using a limiting filtering method:
Figure FDA0003139400330000011
in the formula, Tk、Tk-1Respectively representing the body temperature data of two consecutive times, and delta T represents the possible maximum body temperature deviation;
a2, filtering the heart rate data H by using a limiting filtering method:
Figure FDA0003139400330000012
in the formula, Hk、Hk-1Respectively representing heart rate data of two consecutive times, and deltaH represents the possible maximum heart rate deviation;
a3, filtering the diastolic pressure data D by using a limiting filtering method:
Figure FDA0003139400330000021
in the formula, Dk、Dk-1Respectively representing the diastolic blood pressure value of two consecutive times, and delta D represents the maximum possible diastolic blood pressure deviation;
a4, filtering the systolic blood pressure data S by using a limiting filtering method:
Figure FDA0003139400330000022
in the formula, Sk、Sk-1Respectively, represent the systolic pressure values of two consecutive times, and deltas represents the maximum possible systolic pressure deviation.
4. The system of claim 2, wherein: the specific process of executing data to fill missing values in the supplementary data set includes:
and acquiring the rejected noise data at a time, and filling the missing values with the effective body temperature, heart rate and blood pressure data acquired at the previous time as follows to improve the effectiveness of the body temperature data:
Figure FDA0003139400330000023
Figure FDA0003139400330000024
Figure FDA0003139400330000025
Figure FDA0003139400330000026
in the formula, NaN represents null values after noise removal.
5. The system of claim 2, wherein: executing a five-point cubic smoothing algorithm on the data-filled data set specifically includes executing the following smoothing process on the body temperature data:
T＝(-3Tk-2+12Tk-1+17Tk+12Tk+1-3Tk+2)/35。
6. the system of claim 2, wherein: the process of judging whether to provide the early warning information specifically comprises the following steps:
maximum value t of body temperature data extracted aiming at m times of acquisition in certain specific time periodmaxAnd a minimum value tmin：
tmax＝max(T1,T2,…,Tm)
tmin＝min(T1,T2,…,Tm)
The maximum value tmaxAnd a minimum value tminThe comparison with the corresponding threshold determines whether the following pre-warning trigger conditions are met:
tmax≤Tmin
or
tmin≥Tmax；
If the trigger condition is met, providing the body temperature early warning should also meet the following 2-point constraint:
constraint 1: if the abnormal body temperature value simultaneously satisfies the conditions of heart rate acceleration, systolic pressure rise and diastolic pressure drop, the temperature data T is judgedkAnd (4) invalidation:
Figure FDA0003139400330000031
in the formula (I), the compound is shown in the specification,
Figure FDA0003139400330000032
representing the mean value of the heart rate over the first half of the particular time period,
Figure FDA0003139400330000033
representing the mean value of the heart rate in the latter half of the time;
Figure FDA0003139400330000034
in the formula (I), the compound is shown in the specification,
Figure FDA0003139400330000035
representing the mean diastolic blood pressure during the first half of the particular time period,
Figure FDA0003139400330000036
means of diastolic pressure in the latter half of the time;
Figure FDA0003139400330000037
in the formula (I), the compound is shown in the specification,
Figure FDA0003139400330000038
indicating the mean systolic pressure during the first half of the particular time period,
Figure FDA0003139400330000039
means of systolic blood pressure in the latter half of the time;
judging that f (H, D, S) is 4f (H)) +2f (D)) + f (S),
if and only if f (H) is 1, f (D) is 1, f (S) is 0, namely f (H, D, S) is 6, it indicates that the body temperature rise is caused by strenuous exercise at the moment, and the time body temperature data T is judgedkInvalid;
constraint 2: sending the body temperature early warning information needs to meet the minimum time interval N, otherwise, the body temperature early warning information is not sent:
Nk≥N,k∈[1,2,3,…]
in the formula, NkAnd when the temperature extreme value meets the triggering early warning condition, the time interval from the last time of sending the warning information is obtained.
7. A real-time body temperature monitoring and early warning method using the system as claimed in any one of claims 1 to 6, which is characterized by specifically performing the following steps:
step 1, wearable equipment collects human body vital sign data of a monitored object wearing the equipment in real time and uploads the data to a body temperature monitoring and early warning platform through a data transmission part;
step 2, the body temperature monitoring and early warning platform sequentially executes the following processing on the vital sign data transmitted by the wearable device through the data transmission part:
a. according to a data set formed by continuously collecting data for a plurality of times of the body temperature, the heart rate, the diastolic pressure and the systolic pressure, noise data caused by accidental factors in the data set are removed through amplitude limiting filtering;
b. performing data filling to supplement missing values in the data set for a certain time of acquisition corresponding to the eliminated noise data;
c. executing a five-point three-time smoothing algorithm on the data filled data set to eliminate random errors caused by age, gender, season and day-night difference;
d. extracting the extreme value of the body temperature data in the data set after the random error is eliminated, judging whether to provide early warning information or not, and if so, sending the early warning information to the terminal equipment through the data transmission part;
and 3, the terminal equipment receives the information sent by the body temperature monitoring and early warning platform and provides the vital sign data and the display of the early warning information.
CN202110731605.8A 2021-06-29 2021-06-29 Real-time body temperature monitoring and early warning system based on vital sign detection Active CN113288088B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110731605.8A CN113288088B (en) 2021-06-29 2021-06-29 Real-time body temperature monitoring and early warning system based on vital sign detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110731605.8A CN113288088B (en) 2021-06-29 2021-06-29 Real-time body temperature monitoring and early warning system based on vital sign detection

Publications (2)

Publication Number Publication Date
CN113288088A true CN113288088A (en) 2021-08-24
CN113288088B CN113288088B (en) 2023-09-15

Family

ID=77329946

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110731605.8A Active CN113288088B (en) 2021-06-29 2021-06-29 Real-time body temperature monitoring and early warning system based on vital sign detection

Country Status (1)

Country Link
CN (1) CN113288088B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114159222A (en) * 2022-02-14 2022-03-11 江苏省人民医院（南京医科大学第一附属医院） Brain temperature data processing system based on brain temperature monitoring

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106264485A (en) * 2015-05-29 2017-01-04 上海温尔信息科技有限公司 Monitor system, temperature monitor and body temperature data processing equipment thereof
CN106725355A (en) * 2016-12-13 2017-05-31 电子科技大学 A kind of Worn type measurement of bldy temperature wrist strap and body temperature measurement method
CN106798545A (en) * 2017-03-03 2017-06-06 董云鹏 Thermometer System
CN108458808A (en) * 2018-01-25 2018-08-28 芜湖应天光电科技有限责任公司 A kind of children thermometer based on Intelligent bracelet
CN109621086A (en) * 2019-01-11 2019-04-16 防灾科技学院 A kind of portable medical space patient's intelligent monitor system
US20200060553A1 (en) * 2017-04-27 2020-02-27 Murata Manufacturing Co., Ltd. Body temperature measuring device
CN111588353A (en) * 2020-04-09 2020-08-28 北京雪扬科技有限公司 Body temperature measuring method
CN111802273A (en) * 2020-06-23 2020-10-23 昭苏县西域马业有限责任公司 Intelligent collar for horse health monitoring and monitoring method

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106264485A (en) * 2015-05-29 2017-01-04 上海温尔信息科技有限公司 Monitor system, temperature monitor and body temperature data processing equipment thereof
CN106725355A (en) * 2016-12-13 2017-05-31 电子科技大学 A kind of Worn type measurement of bldy temperature wrist strap and body temperature measurement method
CN106798545A (en) * 2017-03-03 2017-06-06 董云鹏 Thermometer System
US20200060553A1 (en) * 2017-04-27 2020-02-27 Murata Manufacturing Co., Ltd. Body temperature measuring device
CN108458808A (en) * 2018-01-25 2018-08-28 芜湖应天光电科技有限责任公司 A kind of children thermometer based on Intelligent bracelet
CN109621086A (en) * 2019-01-11 2019-04-16 防灾科技学院 A kind of portable medical space patient's intelligent monitor system
CN111588353A (en) * 2020-04-09 2020-08-28 北京雪扬科技有限公司 Body temperature measuring method
CN111802273A (en) * 2020-06-23 2020-10-23 昭苏县西域马业有限责任公司 Intelligent collar for horse health monitoring and monitoring method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114159222A (en) * 2022-02-14 2022-03-11 江苏省人民医院（南京医科大学第一附属医院） Brain temperature data processing system based on brain temperature monitoring

Also Published As

Publication number Publication date
CN113288088B (en) 2023-09-15

Similar Documents

Publication Publication Date Title
CN111261282A (en) Sepsis early prediction method based on machine learning
CN113095302B (en) Depth model for arrhythmia classification, method and device using same
Tsien et al. Multiple signal integration by decision tree induction to detect artifacts in the neonatal intensive care unit
Guo et al. Epileptic seizure detection by cascading isolation forest-based anomaly screening and EasyEnsemble
CN109166630B (en) Infectious disease data monitoring and processing method and system
CN107252313A (en) The monitoring method and system of a kind of safe driving, automobile, readable storage medium storing program for executing
CN113995419B (en) Atrial fibrillation risk prediction system based on heartbeat rhythm signal and application thereof
JP5544365B2 (en) Improvements in multi-parameter monitoring or improvements related to multi-parameter monitoring
CN111557659B (en) Arrhythmia classification method based on multi-feature fusion and Stacking-DWKNN algorithm
CN112971795B (en) Electrocardiosignal quality evaluation method
KR20170053693A (en) Method and apparatus for disease detection
Roy et al. Photoplethysmogram signal quality evaluation by unsupervised learning approach
CN113499035B (en) Pain identification system based on confidence interval fusion threshold criterion
CN113288088A (en) Real-time body temperature monitoring and early warning system based on vital sign detection
Ngo et al. Design of a real-time morphology-based anomaly detection method from ecg streams
WO2013086615A1 (en) Device and method for detecting congenital dysphagia
CN111110208A (en) LSTM-based oxygen reduction state prediction method for chronic obstructive pulmonary disease
KR102169637B1 (en) Method for predicting of mortality risk and device for predicting of mortality risk using the same
Krivenko et al. Using mel-frequency cepstrum and amplitude-time heart variability as XGBoost handcrafted features for heart disease detection
CN113440122A (en) Emotion fluctuation monitoring and identification big data early warning system based on vital signs
Nath et al. Towards photoplethysmogram based non-invasive blood pressure classification
CN111631683B (en) Electrocardiogram data or electroencephalogram data processing and detecting method and storage medium
de Medeiros et al. Heart arrhythmia classification using the PPM algorithm
CN111383764B (en) Correlation detection system for mechanical ventilation driving pressure and ventilator related event
Wong et al. Probabilistic detection of vital sign abnormality with Gaussian process regression

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant