CN114259210B - Sleep staging method and control system based on dynamic skin temperature - Google Patents
Sleep staging method and control system based on dynamic skin temperature Download PDFInfo
- Publication number
- CN114259210B CN114259210B CN202111616663.2A CN202111616663A CN114259210B CN 114259210 B CN114259210 B CN 114259210B CN 202111616663 A CN202111616663 A CN 202111616663A CN 114259210 B CN114259210 B CN 114259210B
- Authority
- CN
- China
- Prior art keywords
- skin temperature
- sleep
- monitoring
- sleeping
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 claims abstract description 102
- 230000008667 sleep stage Effects 0.000 claims abstract description 63
- 238000010801 machine learning Methods 0.000 claims abstract description 38
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 25
- 230000007613 environmental effect Effects 0.000 claims abstract description 20
- 230000001276 controlling effect Effects 0.000 claims abstract description 8
- 238000007689 inspection Methods 0.000 claims abstract description 7
- 230000001105 regulatory effect Effects 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims description 20
- 230000037053 non-rapid eye movement Effects 0.000 claims description 20
- 230000003860 sleep quality Effects 0.000 claims description 15
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 9
- 230000004461 rapid eye movement Effects 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 7
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 6
- 239000001569 carbon dioxide Substances 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 5
- 230000037007 arousal Effects 0.000 claims description 4
- 239000000758 substrate Substances 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 7
- 230000036760 body temperature Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008338 local blood flow Effects 0.000 description 3
- 230000004622 sleep time Effects 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004060 metabolic process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 210000000709 aorta Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000027288 circadian rhythm Effects 0.000 description 1
- 230000036757 core body temperature Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application provides a sleep stage method and a control system based on dynamic skin temperature, wherein the sleep stage method comprises the following steps: and a skin temperature monitoring step: monitoring skin temperature of different parts of the human body; sleep monitoring: monitoring the sleeping process to be tested in real time; a machine learning step: the skin temperature monitoring method comprises a training model and a test model, wherein the training model receives training set data transmitted by a skin temperature monitoring step and a sleep monitoring step, and continuously adjusts an initial skin temperature threshold; the training model outputs the trained skin temperature threshold value and forms a test model, and the skin temperature monitoring step and the sleep monitoring step input test set data into the test model for inspection; sleep staging step: stage the sleeping process and judge the sleeping period where the current tested is located; environmental monitoring control step: and judging the accurate sleep stage result output by the sleep stage step, and regulating and controlling the bedroom environment. The sleeping stage control method can accurately control the bedroom environment parameters according to the accurate sleeping stage of the dynamic skin temperature, and further ensure that the sleeping quality reaches the standard.
Description
Technical Field
The application relates to the technical field of human sleep monitoring, in particular to a non-contact sleep staging method and an accurate control system based on dynamic skin temperature, and especially relates to a sleep staging method and a control system based on dynamic skin temperature.
Background
In view of the very hot research of sleep stages, the method has wide market demands. Skin temperature or body temperature is an important physiological index for assessing human health and thermal comfort, has a close relationship with local blood flow, and a number of sleep state judging methods related to skin temperature are already developed at present.
The application patent publication No. CN109788913A discloses a method and system for determining a time window of sleep of a person, comprising receiving a sample of the temperature of the person's distal skin and detecting a pattern of temperature change in the sample of the temperature of the distal skin. The temperature change pattern indicates a reference point within the circadian rhythm. An optimal time window for sleep is determined based on the indicated reference point. The pattern of temperature change is a form of a decrease in the temperature of the distal skin followed by an increase in the temperature of the distal skin, wherein the decrease and increase occur within a time window of ten minutes or less. This patent determines sleep status by measuring the skin temperature at the distal end, which does not reflect the blood flow value of the population, particularly the brain, but does not distribute the aorta of the human body at the distal end (hands and feet).
The application patent with publication number of CN104095615B discloses a human sleep monitoring method and a monitoring system, sleep monitoring and awakening are realized by measuring capacitance, human gravity acceleration, body temperature information and heart rate information, firstly, the technology can only judge total sleep time, shallow sleep time and deep sleep time, and sleep stages cannot be divided in detail (namely, one to three stages of non-rapid eye movement periods); secondly, skin temperature plays an assisting role in the technology, and sleep stage is not dominant; finally, the technology measures the skin temperature at a local point, and cannot reflect the whole human blood flow value.
The application patent with publication number of CN113468147A discloses a method for establishing and using a body temperature database in a stable sleep state, and the technology establishes a database among skin temperature, core body temperature and sleep quality. However, firstly, the technology is mainly applied to sleep stage judgment under a stable sleep state, and can not judge the sleep state which is unstable, changeable and temporarily appears, and secondly, the technology only builds the relation between skin temperature and rapid eye movement stage and deep sleep stage, and can not judge the relation between skin temperature and 1-3 stages of the non-rapid eye movement stage; moreover, this technique does not take into account the effect of reversible changes in phase 1 to 3 of the non-rapid eye movement phase on body temperature; finally, the technology only considers the influence of improving the thermal environment on the sleep quality, but the sleep is influenced by a plurality of factors such as temperature, humidity, wind speed, noise, illumination, air quality and the like, and the sleep quality can not be improved only by changing a single factor.
The skin temperature is used for evaluating the sleeping state of a plurality of patents including the three patents, most of the patents use contact measurement, a series of sensors are required to be worn by a tested in the sleeping state, and the measurement itself can interfere with the sleeping quality; moreover, the physiological indexes adopted in the patents are static skin Wen Shuzhi, namely when the skin temperature reaches a certain value, the skin temperature is judged to enter a certain sleep stage, but the skin temperature is influenced by external environment and internal physiological metabolism, so that the skin temperature is directly influenced by different varieties of people, ages, sexes, regions and living habits, the internal physiological metabolism is different, and the external environment, especially the air temperature, directly influences the skin temperature through convective heat exchange, so that the static skin Wen Shuzhi is not reasonable to judge the sleep stage. Furthermore, sleep stages should be distinguished from each other by considering the influence of sleep rhythms, and even the same sleep period occurring at the same night, for example, non-rapid eye movement stage 2, whether it is converted from non-rapid eye movement stage 1 or non-rapid eye movement stage 3, and the corresponding decision rule is reproduced.
Disclosure of Invention
Aiming at the defects in the prior art, the application provides a sleep stage method and a control system based on dynamic skin temperature.
According to the sleep stage method and the control system based on the dynamic skin temperature, the scheme is as follows:
in a first aspect, there is provided a sleep staging method based on dynamic skin temperature, the method comprising:
and a skin temperature monitoring step: monitoring skin temperature of different parts of the human body, and transmitting skin temperature data to a machine learning step and a sleep stage step;
sleep monitoring: monitoring the sleeping process to be detected in real time, and transmitting sleeping data to the machine learning step;
a machine learning step: the skin temperature monitoring method comprises a training model and a testing model, wherein the training model continuously adjusts an initial skin temperature threshold after receiving training set data transmitted by a skin temperature monitoring step and a sleep monitoring step;
the training model outputs the trained skin temperature threshold value and forms a test model, and the skin temperature monitoring step and the sleep monitoring step input test set data into the test model for inspection; if the accuracy does not reach the standard, repeating the machine learning step, and if the accuracy reaches the standard, inputting the personalized skin temperature threshold value into a database of the sleep stage step;
sleep staging step: stage the sleeping process, and judge the data input in the skin temperature monitoring step in real time according to the skin temperature threshold value output in the machine learning step, so as to judge the sleeping period in which the current detected is positioned;
environmental monitoring control step: judging the accurate sleep stage result output by the sleep stage step, and ending the flow if the sleep quality reaches the standard;
if the sleeping quality does not reach the standard, the environmental monitoring control step compares the monitored bedroom environmental parameters with the proper parameter ranges in the built-in database, and the sleeping quality is ensured to reach the standard by preferentially regulating and controlling the maximum environmental parameters deviated from the preset range.
Preferably, the skin temperature monitoring step includes: using a non-contact measuring instrument to monitor the dynamic change value of the skin temperature of a human body in real time during sleeping, and defining the change delta T of the skin temperature at the nth minute n The method comprises the following steps:
wherein ,for the average skin temperature at the nth minute, +.>The average skin temperature was n-1 min.
Preferably, the continuously adjusting the initial skin temperature threshold value in the machine learning step specifically includes:
the skin temperature threshold is the minimum skin temperature change when the sleep stage conversion is judged, namely the skin temperature threshold is continuously close to the actual measurement condition, delta T m The skin temperature threshold after the mth adjustment is:
wherein ,ΔT0 For the initial skin temperature threshold, deltaT i The skin temperature threshold measured value of the ith time.
Preferably, in the sleep stage step: the sleeping process is divided into a wake phase, a rapid eye movement phase and a non-rapid eye movement phase, wherein the non-rapid eye movement phase is divided into 1 to 3 phases from shallow to deep according to sleeping depth, a skin temperature threshold database is arranged in a sleeping stage module, and 15 skin temperature thresholds exist for the same type of detected.
Preferably, the environmental monitoring control step includes: the bedroom environment mainly comprises a thermal environment, an acoustic environment, a light environment and air quality; the environmental monitoring control step monitors relevant environmental parameters including bedroom temperature, humidity, noise, illumination intensity and carbon dioxide concentration. :
in a second aspect, there is provided a sleep stage control system based on dynamic skin temperature, the system comprising:
skin temperature monitoring module: monitoring skin temperature of different parts of the human body, and transmitting skin temperature data to a machine learning module and a sleep stage module;
sleep monitoring module: monitoring the sleeping process to be detected in real time, and transmitting sleeping data to a machine learning module;
a machine learning module: the skin temperature monitoring system comprises a training model and a testing model, wherein the training model continuously adjusts an initial skin temperature threshold after receiving training set data transmitted by a skin temperature monitoring module and a sleep monitoring module;
the training model outputs the trained skin temperature threshold value and forms a test model, and the skin temperature monitoring module and the sleep monitoring module input test set data into the test model for inspection; repeating the machine learning module if the accuracy does not reach the standard, and inputting the personalized skin temperature threshold value into a database of the sleep stage module if the accuracy reaches the standard;
sleep stage module: the sleeping process is staged, and the data input by the skin temperature monitoring module are judged in real time according to the skin temperature threshold value output by the machine learning module, so that the sleeping period in which the current detected sleeping period is positioned is judged;
the environment monitoring control module: judging the accurate sleep stage result output by the sleep stage module, and ending the flow if the sleep quality reaches the standard;
if the sleeping quality does not reach the standard, the environment monitoring control module compares the monitored bedroom environment parameters with the proper parameter ranges in the built-in database, and the sleeping quality is ensured to reach the standard by preferentially regulating and controlling the maximum environment parameters deviated from the preset range.
Preferably, the skin temperature monitoring module comprises: using a non-contact measuring instrument to monitor the dynamic change value of the skin temperature of a human body in real time during sleeping, and defining the change delta T of the skin temperature at the nth minute n The method comprises the following steps:
wherein ,for the average skin temperature at the nth minute, +.>The average skin temperature was n-1 min.
Preferably, the continuous adjustment of the initial skin temperature threshold in the machine learning module specifically includes:
the skin temperature threshold is the minimum skin temperature change when the sleep stage conversion is judged, namely the skin temperature threshold is continuously close to the actual measurement condition, delta T m The skin temperature threshold after the mth adjustment is:
wherein ,ΔT0 For the initial skin temperature threshold, deltaT i Is the actual measurement value of the skin temperature threshold value of the ith time。
Preferably, in the sleep stage module: the sleeping process is divided into a wake phase, a rapid eye movement phase and a non-rapid eye movement phase, wherein the non-rapid eye movement phase is divided into 1 to 3 phases from shallow to deep according to sleeping depth, a skin temperature threshold database is arranged in a sleeping stage module, and 15 skin temperature thresholds exist for the same type of detected.
Preferably, the environment monitoring control module includes: the bedroom environment mainly comprises a thermal environment, an acoustic environment, a light environment and air quality; the environment monitoring control module monitors relevant environment parameters including bedroom temperature, humidity, noise, illumination intensity and carbon dioxide concentration.
Compared with the prior art, the application has the following beneficial effects:
1. according to the application, the dynamic skin temperature data are acquired in a non-contact mode, so that the effect of not interfering the sleep state to be tested is achieved;
2. according to the application, the magnitude of the skin temperature threshold is continuously corrected by adopting a machine learning mode, so that the influence of sleeping environment and sample individual difference is reduced to the greatest extent, and the aim of personalized accurate sleeping stage is fulfilled;
3. according to the sleeping room environment intelligent control system, a real-time environment monitoring and control mode is adopted, intelligent and accurate control is conducted on the sleeping room environment during sleeping, and therefore the sleeping quality of a user is guaranteed to reach the standard.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
fig. 1 is an overall block diagram of the present application.
Detailed Description
The present application will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present application, but are not intended to limit the application in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present application.
The embodiment of the application provides a sleep stage method based on dynamic skin temperature, which is shown by referring to fig. 1, and specifically comprises the following steps:
and a skin temperature monitoring step: the skin temperature of the human body has close relation with the local blood flow, and the skin temperatures of different parts of the human body are different; skin temperature of different parts of the human body is monitored, and skin temperature data are transmitted to a machine learning step and a sleep stage step.
Specifically, a non-contact measuring instrument (the precision can reach +/-0.1 ℃) is used for monitoring the dynamic change value of the skin temperature of a human body in a sleeping period in real time, and multi-point dynamic skin temperature data are transmitted to a machine learning step and a sleeping stage step in real time.
Define the variation DeltaT of skin temperature at the nth minute n The method comprises the following steps:
wherein ,for the average skin temperature at the nth minute, +.>The average skin temperature was n-1 min.
Sleep monitoring: when the system checks that the detected type is not in the database (according to the physiological information such as gender, age, BMI and the like), the sleep monitoring step monitors the detected sleep process in real time and transmits sleep data to the machine learning step.
A machine learning step: the skin temperature monitoring method comprises a training model and a test model, wherein the training model continuously adjusts an initial skin temperature threshold after receiving training set data transmitted by a skin temperature monitoring step and a sleep monitoring step; (definition of skin temperature threshold is defined as the minimum skin temperature change amount when sleep stage transition is determined), i.e. the skin temperature threshold is made to be continuously close to the actual measurement condition, as shown in the following, deltaT m The skin temperature threshold after the mth adjustment is:
wherein ,ΔT0 For the initial skin temperature threshold, deltaT i The skin temperature threshold measured value of the ith time.
The training model outputs the trained skin temperature threshold value and forms a test model, and the skin temperature monitoring step and the sleep monitoring step input test set data into the test model for inspection; if the accuracy does not reach the standard, repeating the machine learning step, and if the accuracy reaches the standard, inputting the personalized skin temperature threshold value into a database of the sleep stage step.
Sleep staging step: and (3) staging the sleeping process, judging the data input in the skin temperature monitoring step in real time according to the skin temperature threshold value output in the machine learning step, and further judging the sleeping period in which the current detected sleeping process is positioned.
Specifically, the sleep staging step divides the sleep process into an arousal (W), a rapid eye movement period (R), and a non-rapid eye movement period (N), wherein the non-rapid eye movement period is divided into 1 to 3 stages (N1 to N3) from shallow to deep depending on the sleeping depth. The skin temperature threshold value database is arranged in the sleep stage step, and 15 skin temperature threshold values (W-N1, N1-N2, N2-N3, N3-N2, N2-N1, N1-R, N2-R, N3-R, R-N1, R-N2, R-N3, N1-W, N2-W, N3-W, R-W, for example, W-N1 represents the skin temperature threshold value of the transition from W phase to N1 phase) exist for the same type of detected. And judging the data input in the skin temperature monitoring step in real time according to the skin temperature threshold value output in the machine learning step, so as to judge the sleeping period of the current detected person.
Environmental monitoring control step: judging the accurate sleep stage result output by the sleep stage step, and ending the flow if the sleep quality reaches the standard; if the sleeping quality does not reach the standard, the environmental monitoring control step compares the monitored bedroom environmental parameters with the proper parameter ranges in the built-in database, and the sleeping quality is ensured to reach the standard by preferentially regulating and controlling the maximum environmental parameters deviated from the preset range.
Specifically, in this step: the sleeping quality is affected by the bedroom environment, which mainly comprises four parts, namely a thermal environment, an acoustic environment, a light environment and air quality. And judging the accurate sleep stage result output by the sleep stage module, if the sleep quality reaches the standard, ending the process, if the sleep quality does not reach the standard, comparing the monitored environment parameters such as the bedroom temperature, the humidity, the noise, the illumination intensity, the carbon dioxide concentration and the like with the proper parameter range in the built-in database by the environment monitoring control module, and preferentially accurately regulating and controlling the environment parameter deviating from the maximum environment parameter from the preset range to ensure that the sleep quality reaches the standard.
The application also provides a sleep stage control system based on dynamic skin temperature, which is shown by referring to fig. 1, and specifically comprises:
skin temperature monitoring module: the temperature of the skin of the human body is closely related to the local blood flow, and the temperature of the skin of different parts of the human body is different. And a non-contact measuring instrument (the precision can reach +/-0.1 ℃) is used for monitoring the dynamic change value of the skin temperature of a human body in the sleeping period in real time, and multi-point dynamic skin temperature data are transmitted to a machine learning module and a sleeping stage module in real time.
Define the variation DeltaT of skin temperature at the nth minute n The method comprises the following steps:
wherein ,for the average skin temperature at the nth minute, +.>The average skin temperature was n-1 min.
Sleep monitoring module: when the system checks that the detected type is not in the database (according to the physiological information such as gender, age, BMI and the like), the sleep monitoring module monitors the detected sleep process in real time and transmits sleep data to the machine learning module.
A machine learning module: comprising training modelsAnd a test model. After the training model receives the training set data transmitted by the skin temperature monitoring module and the sleep monitoring module, the initial skin temperature threshold value is continuously adjusted (the definition of the skin temperature threshold value is the minimum skin temperature change quantity when the sleep stage conversion is judged), namely the skin temperature threshold value is continuously close to the actual measurement condition, as shown in the following, delta T m The skin temperature threshold after the mth adjustment is:
wherein ,ΔT0 For the initial skin temperature threshold, deltaT i The skin temperature threshold measured value of the ith time.
The training model outputs the trained skin temperature threshold value and forms a test model, the skin temperature monitoring module and the sleep monitoring module input test set data into the test model for inspection, if the accuracy does not reach the standard, the machine learning module is repeated, if the accuracy reaches the standard, the personalized skin temperature threshold value is input into a database of the sleep stage module.
Sleep stage module: and (3) staging the sleeping process, judging the data input by the skin temperature monitoring module in real time according to the skin temperature threshold value output by the machine learning module, and further judging the sleeping period in which the current detected sleeping process is positioned.
Specifically, in this module, the sleep process may be divided into arousal (W), rapid eye movement (R), and non-rapid eye movement (N), wherein the non-rapid eye movement is divided into phases 1 to 3 (N1 to N3) from shallow to deep depending on the sleeping depth. The sleep stage module is provided with a skin temperature threshold database, and for the same type of detected, 15 skin temperature thresholds (W-N1, N1-N2, N2-N3, N3-N2, N2-N1, N1-R, N2-R, N3-R, R-N1, R-N2, R-N3, N1-W, N2-W, N3-W, R-W, for example, W-N1 represents the skin temperature threshold for converting from W stage to N1 stage) exist. And judging the data input by the skin temperature monitoring module in real time according to the skin temperature threshold value output by the machine learning module, so as to judge the sleeping period of the current detected person.
The environment monitoring control module: the sleeping quality is affected by the bedroom environment, which mainly comprises four parts, namely a thermal environment, an acoustic environment, a light environment and air quality. And judging the accurate sleep stage result output by the sleep stage module, if the sleep quality reaches the standard, ending the process, if the sleep quality does not reach the standard, comparing the monitored environment parameters such as the bedroom temperature, the humidity, the noise, the illumination intensity, the carbon dioxide concentration and the like with the proper parameter range in the built-in database by the environment monitoring control module, and preferentially accurately regulating and controlling the environment parameter deviating from the maximum environment parameter from the preset range to ensure that the sleep quality reaches the standard.
The embodiment of the application provides a sleep stage method and a control system based on dynamic skin temperature, which are used for monitoring the dynamic change of skin temperature of multiple parts in the sleep process, performing machine learning on skin temperature and sleep data, determining skin temperature threshold values during the transition of each sleep stage, further realizing accurate sleep stage according to the dynamic skin temperature, and further accurately controlling bedroom environment parameters to ensure that the sleep quality reaches the standard.
Those skilled in the art will appreciate that the application provides a system and its individual devices, modules, units, etc. that can be implemented entirely by logic programming of method steps, in addition to being implemented as pure computer readable program code, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, the system and various devices, modules and units thereof provided by the application can be regarded as a hardware component, and the devices, modules and units for realizing various functions included in the system can also be regarded as structures in the hardware component; means, modules, and units for implementing the various functions may also be considered as either software modules for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present application. It is to be understood that the application is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the application. The embodiments of the application and the features of the embodiments may be combined with each other arbitrarily without conflict.
Claims (6)
1. A sleep staging method based on dynamic skin temperature, comprising:
and a skin temperature monitoring step: monitoring skin temperature of different parts of the human body, and transmitting skin temperature data to a machine learning step and a sleep stage step;
sleep monitoring: monitoring the sleeping process to be detected in real time, and transmitting sleeping data to the machine learning step;
a machine learning step: the skin temperature monitoring method comprises a training model and a testing model, wherein the training model continuously adjusts an initial skin temperature threshold after receiving training set data transmitted by a skin temperature monitoring step and a sleep monitoring step;
the training model outputs the trained skin temperature threshold value and forms a test model, and the skin temperature monitoring step and the sleep monitoring step input test set data into the test model for inspection; if the accuracy does not reach the standard, repeating the machine learning step, and if the accuracy reaches the standard, inputting the personalized skin temperature threshold value into a database of the sleep stage step;
sleep staging step: stage the sleeping process, and judge the data input in the skin temperature monitoring step in real time according to the skin temperature threshold value output in the machine learning step, so as to judge the sleeping period in which the current detected is positioned;
environmental monitoring control step: judging the accurate sleep stage result output by the sleep stage step, and ending the flow if the sleep quality reaches the standard;
if the sleeping quality does not reach the standard, the environmental monitoring control step compares the monitored bedroom environmental parameters with the proper parameter ranges in the built-in database, and the sleeping quality is ensured to reach the standard by preferentially regulating and controlling the maximum environmental parameters deviated from the preset range;
the sleep stage step comprises the following steps: the sleeping process is divided into a wake phase, a rapid eye movement phase and a non-rapid eye movement phase, wherein the non-rapid eye movement phase is divided into 1 to 3 phases from shallow to deep according to sleeping depth, and a skin temperature threshold database arranged in a sleeping stage module is used for detecting 15 skin temperature thresholds in the same type of detected;
the 15 skin temperature thresholds specifically include: W-N1, N1-N2, N2-N3, N3-N2, N2-N1, N1-R, N2-R, N-R, R-N1, R-N2, R-N3, N1-W, N2-W, N3-W, R-W, respectively characterize skin temperature thresholds transitioning from a previous stage to a subsequent stage; wherein W represents arousal; r represents the rapid eye movement period; the non-rapid eye movement period is divided into 1 to 3 periods from shallow to deep according to the sleeping depth, and N1, N2 and N3 are respectively adopted;
the definition of the skin temperature threshold is the minimum skin temperature change amount when the sleep stage transition is judged, namely the skin temperature threshold is continuously close to the actual measurement condition, as shown in the following,the skin temperature threshold after the mth adjustment is:
wherein ,for the initially set skin temperature threshold, +.>The skin temperature threshold measured value of the ith time.
2. The method of sleep staging based on dynamic skin temperature according to claim 1, characterized in that the skin temperature monitoring step comprises: using a non-contact measuring instrument to monitor the dynamic change value of the skin temperature of a human body in real time during sleeping, and defining the change delta T of the skin temperature at the nth minute n The method comprises the following steps:
wherein ,for the average skin temperature at the nth minute, +.>The average skin temperature was n-1 min.
3. The method of sleep staging based on dynamic skin temperature according to claim 1, characterized in that the environmental monitoring control step includes: the bedroom environment mainly comprises a thermal environment, an acoustic environment, a light environment and air quality; the environmental monitoring control step monitors relevant environmental parameters including bedroom temperature, humidity, noise, illumination intensity and carbon dioxide concentration.
4. A sleep stage control system based on dynamic skin temperature, comprising:
skin temperature monitoring module: monitoring skin temperature of different parts of the human body, and transmitting skin temperature data to a machine learning module and a sleep stage module;
sleep monitoring module: monitoring the sleeping process to be detected in real time, and transmitting sleeping data to a machine learning module;
a machine learning module: the skin temperature monitoring system comprises a training model and a testing model, wherein the training model continuously adjusts an initial skin temperature threshold after receiving training set data transmitted by a skin temperature monitoring module and a sleep monitoring module;
the training model outputs the trained skin temperature threshold value and forms a test model, and the skin temperature monitoring module and the sleep monitoring module input test set data into the test model for inspection; repeating the machine learning module if the accuracy does not reach the standard, and inputting the personalized skin temperature threshold value into a database of the sleep stage module if the accuracy reaches the standard;
sleep stage module: the sleeping process is staged, and the data input by the skin temperature monitoring module are judged in real time according to the skin temperature threshold value output by the machine learning module, so that the sleeping period in which the current detected sleeping period is positioned is judged;
the environment monitoring control module: judging the accurate sleep stage result output by the sleep stage module, and ending the flow if the sleep quality reaches the standard;
if the sleeping quality does not reach the standard, the environment monitoring control module compares the monitored bedroom environment parameters with the proper parameter range in the built-in database, and preferentially regulates and controls the maximum environment parameters deviating from the preset range, so that the sleeping quality is ensured to reach the standard;
the sleep stage module is characterized in that: the sleeping process is divided into a wake phase, a rapid eye movement phase and a non-rapid eye movement phase, wherein the non-rapid eye movement phase is divided into 1 to 3 phases from shallow to deep according to sleeping depth, and a skin temperature threshold database arranged in a sleeping stage module is used for detecting 15 skin temperature thresholds in the same type of detected;
the 15 skin temperature thresholds specifically include: W-N1, N1-N2, N2-N3, N3-N2, N2-N1, N1-R, N2-R, N-R, R-N1, R-N2, R-N3, N1-W, N2-W, N3-W, R-W, respectively characterize skin temperature thresholds transitioning from a previous stage to a subsequent stage; wherein W represents arousal; r represents the rapid eye movement period; the non-rapid eye movement period is divided into 1 to 3 periods from shallow to deep according to the sleeping depth, and N1, N2 and N3 are respectively adopted;
the definition of the skin temperature threshold is the minimum skin temperature change amount when the sleep stage transition is judged, namely the skin temperature threshold is continuously close to the actual measurement condition, as shown in the following,the skin temperature threshold after the mth adjustment is:
wherein ,for the initially set skin temperature threshold, +.>The skin temperature threshold measured value of the ith time.
5. The substrate according to claim 4The sleep stage control system for dynamic skin temperature is characterized in that the skin temperature monitoring module comprises: using a non-contact measuring instrument to monitor the dynamic change value of the skin temperature of a human body in real time during sleeping, and defining the change delta T of the skin temperature at the nth minute n The method comprises the following steps:
wherein ,for the average skin temperature at the nth minute, +.>The average skin temperature was n-1 min.
6. The dynamic skin temperature based sleep stage control system according to claim 4, wherein the environmental monitoring control module comprises: the bedroom environment mainly comprises a thermal environment, an acoustic environment, a light environment and air quality; the environment monitoring control module monitors relevant environment parameters including bedroom temperature, humidity, noise, illumination intensity and carbon dioxide concentration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111616663.2A CN114259210B (en) | 2021-12-27 | 2021-12-27 | Sleep staging method and control system based on dynamic skin temperature |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111616663.2A CN114259210B (en) | 2021-12-27 | 2021-12-27 | Sleep staging method and control system based on dynamic skin temperature |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114259210A CN114259210A (en) | 2022-04-01 |
CN114259210B true CN114259210B (en) | 2023-10-13 |
Family
ID=80830630
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111616663.2A Active CN114259210B (en) | 2021-12-27 | 2021-12-27 | Sleep staging method and control system based on dynamic skin temperature |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114259210B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016028662A (en) * | 2014-07-25 | 2016-03-03 | 船井電機株式会社 | Sleep evaluation device and sleep evaluation method |
CN107976901A (en) * | 2016-10-21 | 2018-05-01 | 财团法人工业技术研究院 | Sleep environment control system and control method thereof |
JP2019024628A (en) * | 2017-07-26 | 2019-02-21 | 株式会社スリープシステム研究所 | Sleep environment temperature control device and sleep environment temperature control method |
JP2020022732A (en) * | 2018-08-06 | 2020-02-13 | ライオン株式会社 | Sleep state determination device, sleep state determination system, and sleep state determination program |
CN111238005A (en) * | 2020-01-15 | 2020-06-05 | 上海交通大学 | Automatic control system and method of air conditioner sleep mode based on sleep staging |
WO2020133536A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Sleep state determining method and apparatus |
CN112451834A (en) * | 2020-11-24 | 2021-03-09 | 珠海格力电器股份有限公司 | Sleep quality management method, device, system and storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050209512A1 (en) * | 2004-03-16 | 2005-09-22 | Heruth Kenneth T | Detecting sleep |
US20150170053A1 (en) * | 2013-12-13 | 2015-06-18 | Microsoft Corporation | Personalized machine learning models |
US20210251568A1 (en) * | 2020-02-14 | 2021-08-19 | Objectvideo Labs, Llc | Infrared sleep monitoring |
-
2021
- 2021-12-27 CN CN202111616663.2A patent/CN114259210B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016028662A (en) * | 2014-07-25 | 2016-03-03 | 船井電機株式会社 | Sleep evaluation device and sleep evaluation method |
CN107976901A (en) * | 2016-10-21 | 2018-05-01 | 财团法人工业技术研究院 | Sleep environment control system and control method thereof |
JP2019024628A (en) * | 2017-07-26 | 2019-02-21 | 株式会社スリープシステム研究所 | Sleep environment temperature control device and sleep environment temperature control method |
JP2020022732A (en) * | 2018-08-06 | 2020-02-13 | ライオン株式会社 | Sleep state determination device, sleep state determination system, and sleep state determination program |
WO2020133536A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Sleep state determining method and apparatus |
CN111238005A (en) * | 2020-01-15 | 2020-06-05 | 上海交通大学 | Automatic control system and method of air conditioner sleep mode based on sleep staging |
CN112451834A (en) * | 2020-11-24 | 2021-03-09 | 珠海格力电器股份有限公司 | Sleep quality management method, device, system and storage medium |
Non-Patent Citations (2)
Title |
---|
DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG;Akara Supratak, Hao Dong, Chao Wu, and Yike Guo;IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING;第25卷(第11期);全文 * |
董腾飞.基于心率变异性的睡眠分期方法研究及睡眠监测系统研发.中国优秀硕士学位论文全文数据库工程科技Ⅱ辑.2021,全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN114259210A (en) | 2022-04-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114845630A (en) | Optimizing sleep time to adjust circadian rhythm based on personalized exercise timing | |
KR100791371B1 (en) | Apparatus and method for inducing sound sleep and wake-up | |
US9466200B2 (en) | Wake-up device | |
US10568565B1 (en) | Utilizing an area sensor for sleep analysis | |
CN105231997A (en) | Sleep quality judging method and sleep instrument | |
JP2017106716A (en) | Environmental adjustment program, environmental adjustment device, and environmental adjustment method | |
JP2022515374A (en) | System and method for determining arousal level | |
CN110706816B (en) | Method and equipment for sleep environment regulation and control based on artificial intelligence | |
CN108671359A (en) | Sleep householder method | |
KR20170087834A (en) | Computer system for determining a state of mind and providing a sensory-type antidote to a subject | |
CN113710967A (en) | Environment control system and environment control method | |
KR20180017854A (en) | A Appartus and Method for Anomaly Detection of the Circadian Rhythm Monitored with Wearable Sensors | |
CN111594999A (en) | Air conditioner, control method and device thereof and air conditioning system | |
JP6040874B2 (en) | Sleep stage estimation device | |
JP2017530849A (en) | Method and system for predicting continuous cardiac output (CCO) of a patient based on physiological data | |
CN116339509A (en) | Control method and control device of intelligent terminal equipment | |
CN114259210B (en) | Sleep staging method and control system based on dynamic skin temperature | |
JP2505077B2 (en) | Biorhythm adjustment device | |
CN112006652B (en) | Sleep state detection method and system | |
JP2021135000A (en) | Pleasant sleep dwelling environment support system | |
TW202108077A (en) | Focus automatic detection method and system | |
JP7233032B2 (en) | Environment control system and environment control method | |
Patrialova et al. | A novel feature of smart mask: Monitoring and control system of respiratory conditions using iot for high-activity-person during new normal era | |
JP2010104508A (en) | Method for analogizing personality, method for estimating external environmental effect and environment control system | |
CN117476181B (en) | Personalized static therapy plan generation method and system |
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 |