Fast thermometer temperature measurement algorithm
阅读说明：本技术 一种体温计快速测温算法 (Fast thermometer temperature measurement algorithm ) 是由 戴昊霖 于 2020-12-18 设计创作，主要内容包括：本发明涉及一种体温计快速测温算法,包括,将体温计温度显示范围划分为n-1段,将体温计使用环境温度范围划分为n-2段,应用所述接触式电子体温计进行测温,并绘制出测量温度与所用时间的曲线,在测量温度与所用时间的曲线中,标记出测量时间点对应的斜率,测量结束时间和最终测量温度值,应用所述斜率与所述测量结束时间做乘积得到第一预估值,将最终测量温度值与第一预估值的差值得到补偿值训练值,重复上述步骤,得到补偿值训练数据集,以所述斜率和环境温度为变量,通过补偿值训练数据集,应用拟合算法得到补偿值预估模型,对人体进行测温,应用第一预估值和补偿值预估模型得到体温测量值。(The invention relates to a rapid thermometer temperature measurement algorithm, which comprises the step of dividing the temperature display range of a thermometer into n 1 A section for dividing the temperature range of the environment where the thermometer is used into n 2 And the step of measuring the temperature by using the contact type electronic thermometer, drawing a curve of the measured temperature and the used time, marking a slope corresponding to the measured time point in the curve of the measured temperature and the used time, measuring the end time and the final measured temperature value, multiplying the slope and the measured end time to obtain a first pre-estimated value, obtaining a compensation value training value by the difference value of the final measured temperature value and the first pre-estimated value, repeating the steps to obtain a compensation value training data set, obtaining a compensation value estimation model by using the slope and the ambient temperature as variables and using the compensation value training data set and a fitting algorithm, measuring the temperature of the human body, and obtaining a body temperature measured value by using the first pre-estimated value and the compensation value estimation model.)
1. A rapid temperature measurement algorithm for a thermometer is characterized by comprising the following steps,
s1: the temperature of the thermometer is displayed within the range of 35-41 ℃ by delta x1Is a unit of n1Segment and form n1+1 coordinate points;
s2: the temperature of the thermometer is 5-40 ℃ in the environment temperature range, and is delta y1Is a unit of n2Segment and form n2+1 coordinate points;
s3: in an off-line state, displaying n in the range by the temperature1+1 coordinate points as target temperature, with n in the ambient temperature range2+1 coordinate point is the environment temperature for measuring temperature, the contact type electronic thermometer is placed in the environment temperature for m minutes, then the temperature is measured by applying the contact type electronic thermometer, and a curve of the measured temperature and the used time is drawn;
s4: step S3 is repeated to obtain (n)1+1)*(n2+1) curves of measured temperature versus time used;
s5: the measurement time t is marked in the curve of the measured temperature versus the elapsed time1、t2And t3Corresponding slope k1、k2And k3Measuring the end time tendAnd a final measured temperature value T;
s6: applying said slope k3And the measurement end time tendThe product is made to obtain a first estimated value Te1Using T-Te1Obtaining a compensation value training value;
s7: step S6 is repeated to obtain (n)1+1)*(n2+1) compensation value training data;
s8: repeating the steps S1-S7 for n times to obtain a compensation value training data set;
s9: at the slope k1、k2、k3And the ambient temperature TamTraining a data set through the compensation value for a variable, and obtaining a compensation value pre-estimation model by applying a fitting algorithm, Ted＝a1*k1+a2*k2+a3*k3+a4*Tam；
S10: on-lineIn this state, the human body is measured, and the first estimated value T is usede1And compensation value estimation model TedObtaining a body temperature measurement value Tme＝Te1+Ted。
2. The thermometer thermometry algorithm of claim 1, wherein Δ χ is1Is 0.5 ℃.
3. The thermometer thermometry algorithm of claim 1, wherein Δ y1Is 1 ℃.
4. The thermometer thermometry algorithm of claim 1, wherein 30< m < 40.
5. The thermometer rapid thermometry algorithm of claim 1, wherein the measurement time point t1、t2And t310s, 20s and 30 s.
6. The rapid thermometer thermometry algorithm of claim 1 wherein the data collection strategy of repeating steps S1-S5 n times is collecting data at different target and ambient temperatures.
7. The thermometer rapid thermometry algorithm of claim 1 wherein the compensation training dataset is subjected to data preprocessing comprising normalization, outlier rejection, and data filtering.
8. The rapid thermometer thermometry algorithm of claim 7, wherein the outlier rejection algorithm is,
the target temperature and the environment temperature form a calculation area by adjacent coordinate points; and taking the mean value of the data points in the calculation area as a reference, and defining the data with the deviation of more than 0.05 ℃ as abnormal data.
9. The thermometer thermometry algorithm of claim 1, wherein the fitting algorithm uses partial least squares.
Technical Field
The invention relates to the field of medical instruments, in particular to a rapid thermometer temperature measurement algorithm.
Background
In the prior art, the temperature reaches the final stable value in the body temperature measuring process for 2-3 minutes, so poor customer experience is brought in the patient measuring process, and the following solution is provided for the problem.
The invention patent publication No. CN100520322C discloses a thermometer, an electronic device having the thermometer, and a body temperature measuring method, which can measure a temperature with high accuracy regardless of a difference in body type of a measurement object or a change in heat transfer characteristics due to contact with clothing, bedding, or the like. The deep temperature calculation means calculates a deep temperature based on the 1 st and 2 nd surface temperature from the surface sensor and the 1 st and 2 nd intermediate temperatures from the intermediate sensor. Since the deep temperature is obtained from the body surface temperatures of the 2 parts and the intermediate temperature, the deep temperature can be calculated regardless of the thermal resistance value of the thermometer without assuming the thermal resistance value from the deep part to the body surface of the human body. Thus, the deep temperature can be calculated regardless of the difference in body size of a living body or the contact of clothes, bedding, or the like, and the body temperature can be measured with high accuracy.
The invention of publication No. CN111473888A discloses a method for measuring the wrist body temperature by using a thermometer and obtaining the core body temperature in vivo after calculation. The invention has the following advantages and effects: the wrist is measured through fixation, and the body temperature of the core position of the human body can be obtained after calculation according to the second law of thermodynamics, so that the measurement result is more accurate.
Disclosure of Invention
The invention mainly aims to overcome the defects of the prior art and provides a rapid thermometer temperature measurement algorithm which comprises the following steps,
s1: the temperature of the thermometer is displayed within the range of 35-41 ℃ by delta x1Is a unit of n1Segment and form n1+1 coordinate points;
s2: the temperature of the thermometer is 5-40 ℃ in the environment temperature range, and is delta y1Is a unit of n2Segment and form n2+1 coordinate points;
s3: in an off-line state, displaying n in the range by the temperature1+1 coordinate points as target temperature, with n in the ambient temperature range2+1 coordinate point is the environment temperature for measuring temperature, the contact type electronic thermometer is placed in the environment temperature for m minutes, then the temperature is measured by applying the contact type electronic thermometer, and a curve of the measured temperature and the used time is drawn;
s4: step S3 is repeated to obtain (n)1+1)*(n2+1) curves of measured temperature versus time used;
s5: the measurement time t is marked in the curve of the measured temperature versus the elapsed time1、t2And t3Corresponding slope k1、k2And k3Measuring the end time tendAnd a final measured temperature value T;
s6: applying said slope k3And the measurement end time tendThe product is made to obtain a first estimated value Te1Using T-Te1Obtaining a compensation value training value;
s7: step S6 is repeated to obtain (n)1+1)*(n2+1) compensation value training data;
s8: repeating the steps S1-S7 for n times to obtain a compensation value training data set;
s9: at the slope k1、k2、k3And the ambient temperature TamTraining a data set through the compensation value for a variable, and obtaining a compensation value pre-estimation model by applying a fitting algorithm, Ted＝a1*k1+a2*k2+a3*k3+a4*Tam；
S10: on-line measuring the temperature of the human body, applying a first estimated value Te1And compensation value estimation model TedObtaining a body temperature measurement value Tme＝Te1+Ted。
Preferably, said Δ x1Is 0.5 ℃.
Preferably, the Δ y1Is 1 ℃.
Preferably, said 30< m < 40.
Preferably, the measuring time point t1、t2And t310s, 20s and 30s,.
Preferably, the data collection strategy of repeating the steps S1-S5 n times is to collect data at different target and ambient temperatures.
Preferably, the compensation value training data set is subjected to data preprocessing, wherein the data preprocessing comprises normalization, abnormal point rejection and data filtering.
Preferably, the outlier rejection algorithm is that adjacent coordinate points of the target temperature and the environment temperature form a calculation region; and taking the mean value of the data points in the calculation area as a reference, and defining the data with the deviation of more than 0.05 ℃ as abnormal data.
Preferably, the fitting algorithm employs a partial least squares method.
Has the advantages that: the rapid thermometer temperature measurement algorithm provided by the invention can be used for rapidly and accurately measuring the body temperature of a human body, and greatly improving the customer experience.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a rapid thermometer temperature measurement algorithm.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. 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.
As shown in fig. 1, a rapid thermometry algorithm for a thermometer includes the following steps,
s1: the temperature of the thermometer is displayed within the range of 35-41 ℃ by delta x1Is a unit of n1Segment and form n1+1 coordinate points;
s2: the temperature of the thermometer is 5-40 ℃ in the environment temperature range, and is delta y1Is a unit of n2Segment and form n2+1 coordinate points;
s3: in an off-line state, displaying n in the range by the temperature1+1 piecesThe coordinate point is taken as a target temperature, and n in the environment temperature range is taken as2+1 coordinate point is the environment temperature for measuring temperature, the contact type electronic thermometer is placed in the environment temperature for m minutes, then the temperature is measured by applying the contact type electronic thermometer, and a curve of the measured temperature and the used time is drawn;
s4: step S3 is repeated to obtain (n)1+1)*(n2+1) curves of measured temperature versus time used;
s5: the measurement time t is marked in the curve of the measured temperature versus the elapsed time1、t2And t3Corresponding slope k1、k2And k3Measuring the end time tendAnd a final measured temperature value T;
s6: applying said slope k3And the measurement end time tendThe product is made to obtain a first estimated value Te1Using T-Te1Obtaining a compensation value training value;
s7: step S6 is repeated to obtain (n)1+1)*(n2+1) compensation value training data;
s8: repeating the steps S1-S7 for n times to obtain a compensation value training data set;
s9: at the slope k1、k2、k3And the ambient temperature TamTraining a data set through the compensation value for a variable, and obtaining a compensation value pre-estimation model by applying a fitting algorithm, Ted＝a1*k1+a2*k2+a3*k3+a4*Tam；
S10: on-line measuring the temperature of the human body, applying a first estimated value Te1And compensation value estimation model TedObtaining a body temperature measurement value Tme＝Te1+Ted。
According to the above scheme, further, the Δ x1Is 0.5 ℃.
According to the above scheme, further, the Δ y1Is 1 ℃.
According to the above scheme, further, the 30< m < 40.
According to the above scheme, further, the measuring time point t1、t2And t310s, 20s and 30s,.
According to the above scheme, further, the data collection strategy of repeating the steps S1-S5 n times is to collect data at different target temperatures and ambient temperatures.
According to the scheme, further, the compensation value training data set is subjected to data preprocessing, wherein the data preprocessing comprises normalization, abnormal point elimination and data filtering.
According to the scheme, further, the abnormal point elimination algorithm is that adjacent coordinate points of the target temperature and the environment temperature form a calculation area; and taking the mean value of the data points in the calculation area as a reference, and defining the data with the deviation of more than 0.05 ℃ as abnormal data.
According to the scheme, further, the fitting algorithm adopts a partial least square method.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
- 上一篇：一种医用注射器针头装配设备
- 下一篇：一种温度场测试系统