CN109009139A - Sleep monitor method and device - Google Patents
Sleep monitor method and device Download PDFInfo
- Publication number
- CN109009139A CN109009139A CN201810582893.3A CN201810582893A CN109009139A CN 109009139 A CN109009139 A CN 109009139A CN 201810582893 A CN201810582893 A CN 201810582893A CN 109009139 A CN109009139 A CN 109009139A
- Authority
- CN
- China
- Prior art keywords
- sleep
- information
- standard
- activity
- classifier
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- Veterinary Medicine (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physiology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Anesthesiology (AREA)
- Fuzzy Systems (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
This application discloses a kind of sleep monitor method and devices.This method includes the standard sleep information of collecting sample；Classifier is obtained using the standard sleep information as training set training；Monitor information of the user to be measured in sleep state；The information is classified according to the classifier；The sleep state of the user to be measured is obtained according to classification results.The application based on contactless acceleration value acquisition technique to sleep quality when biological information be monitored, avoid invade subject's privacy, do not influence the ortho of user, application method is easy to learn and cheap, is suitble to long-term household monitoring sleep quality.
Description
Technical field
This application involves sleep monitor fields, in particular to a kind of sleep monitor method and device.
Background technique
Sleep monitor is extremely important for the elderly because the serious diseases such as depression and diabetes usually with sleep
It is insufficient and irregular related.Due to body position and movement and some specified diseases (such as sleep apnea and not during sleep
Pacify leg syndrome etc.) it is in close relations, in many cases, it is necessary to monitor body gesture and movement during sleep.
Sleep monitor is diagnosed for identifying sleep disturbance as early as possible and treatment disease is extremely important in time.Sleep monitor is not
It can only be provided to medical services person about the irregular sleep of patient and its quantitative data of duration, and can be in detail
Patient sleeps' situation is described, such as occurs the big-movement to get in and out of bed because getting up in the night to urinate.These information facilitate discovery and certain diseases
Relevant body variation tendency.In addition, sleep monitor can be with the therapeutic effect of monitoring sleep related disease.Many medical researches
Focus on find correlation between body gesture and various breathing problems (such as sleep apnea) during sleep.Institute
With, if there is a sleep monitor system can provide sleep during body gesture details, it will help such research.
In relevant sleep monitoring technology it is relatively accurate and be reliably polysomnography (record sleep period diencephalon electricity
Figure, electroculogram, electromyogram etc.).These systems using when have inconvenience because they need subject to wear, and
Expense is high when needing professional to be monitored, therefore using.A kind of more relatively easy sleep monitor instrument is movable note
Instrument is recorded, this is that one kind may be coupled to four limbs (such as wrist) to provide the equipment of exercise data；But this instrument still needs
It is worn over subject.Some systems are based on audio and video frequency signal and carry out Sleep-Monitoring, but they have caused people to hidden
The worry of private problem.Some to be had been developed by sensing body pressure or vibration come work sleep monitoring system, these are
Structure of uniting is relatively easy, but subject can not feel well during sleep.
For polysomnography needs are contacted with subject's body in relevant sleep monitoring technology and expense is high,
Activity recorder needs are contacted with subject's body, the invasion of privacy of the sleep monitoring system based on audio and video frequency signal, pressure
Power and/or vibration sensing instrument cause the problems such as subject is uncomfortable, and currently no effective solution has been proposed.
Summary of the invention
The main purpose of the application is to provide a kind of sleep monitor method and device, at least to solve above-mentioned technical problem
One of.
To achieve the goals above, according to the one aspect of the application, a kind of sleep monitor method is provided, comprising: adopt
Collect the standard sleep information of sample；Classifier is obtained using the standard sleep information as training set training；Monitor user to be measured
Information in sleep state；The information is classified according to the classifier；The user to be measured is obtained according to classification results
Sleep state.
Further, sleep monitor method as the aforementioned, the standard sleep information of the collecting sample, comprising: acquisition sample
This standard static sleep info, the standard Active sleep information of collecting sample；The standard static of the collecting sample, which is slept, to be believed
Breath, the standard physical information including collecting sample in sleep state；The standard Active sleep information of the collecting sample, including
Standard actions information of the collecting sample in sleep state；It is described to be divided the standard sleep information as training set training
Class device, comprising: obtain body gesture classifier for the standard physical information as training set training, the standard actions are believed
Breath obtains activity classifier as training set training；Information of the monitoring user to be measured in sleep state, comprising: monitoring to
Biological information of the user in sleep state is surveyed, action message of the user to be measured in sleep state is monitored；It is described according to
Classifier classifies the information, comprising: the biological information is classified according to the body gesture classifier, according to the work
Dynamic classifier classifies the action message；It is described to obtain the sleep state of the user to be measured according to classification results, comprising: root
Body gesture of the user to be measured in sleep state is obtained according to classification results, obtains the user to be measured according to classification results
Activity in sleep state.
Further, sleep monitor method as the aforementioned, the standard sleep information of the collecting sample, comprising: setting
In time, the multiaxis acceleration of one or many samples one or more sampled point in sleep state is acquired per unit time
Value.
Further, sleep monitor method as the aforementioned, it is described the standard physical information is trained as training set
To body gesture classifier, wherein the body gesture classification includes: empty bed and lying posture.
Further, sleep monitor method as the aforementioned, it is described the standard physical information is trained as training set
To body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture and lying posture.
Further, sleep monitor method as the aforementioned, it is described the standard physical information is trained as training set
To body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture, lies on the back, prostrate, lies on the left side and right side is sleeping.
Further, sleep monitor method as the aforementioned, it is described the standard actions information is trained as training set
To activity classifier, wherein the class of activity includes non-activity and has activity；The non-activity, including keep the body appearance
Gesture；It is described to have activity, converting mutually, keeping carry out activity in the case of the body gesture including the body gesture.
Further, sleep monitor method as the aforementioned, it is described the standard actions information is trained as training set
To activity classifier, comprising: determine the upper-level threshold and/or lower threshold of non-activity signal value according to the non-activity information.
Further, sleep monitor method as the aforementioned, information of the monitoring user to be measured in sleep state, packet
It includes: within the set time, acquiring the one or many user to be measured one or more in sleep state per unit time and adopt
The multiaxis acceleration value of sampling point；Wherein the user to be measured is the sample.
Further, sleep monitor method as the aforementioned, it is described to be divided the action message according to the activity classifier
Class, comprising: judge whether the action message is greater than or equal to upper-level threshold and is less than or equal to lower threshold.
Further, sleep monitor method as the aforementioned, it is described to obtain the user to be measured according to classification results and sleeping
Activity when state, comprising: if the result judged is yes, it is determined that the action message is non-activity；If described
The result judged is is not, it is determined that the action message is to have activity.
To achieve the goals above, according to the another aspect of the application, a kind of sleep monitoring device is provided, comprising: adopt
Collect module, training module, detection module, categorization module, determining module；The acquisition module, the standard for collecting sample are slept
Dormancy information；The training module, for obtaining classifier for the standard sleep information as training set training；The detection mould
Block, for monitoring information of the user to be measured in sleep state；The categorization module, for according to the classifier by the letter
Breath classification；The determining module, for obtaining the sleep state of the user to be measured according to classification results.
Further, sleep monitoring device as the aforementioned, the standard sleep information of the collecting sample, comprising: acquisition sample
This standard static sleep info, the standard Active sleep information of collecting sample；The standard static of the collecting sample, which is slept, to be believed
Breath, the standard physical information including collecting sample in sleep state；The standard Active sleep information of the collecting sample, including
Standard actions information of the collecting sample in sleep state；It is described to be divided the standard sleep information as training set training
Class device, comprising: obtain body gesture classifier for the standard physical information as training set training, the standard actions are believed
Breath obtains activity classifier as training set training；Information of the monitoring user to be measured in sleep state, comprising: monitoring to
Biological information of the user in sleep state is surveyed, action message of the user to be measured in sleep state is monitored；It is described according to
Classifier classifies the information, comprising: the biological information is classified according to the body gesture classifier, according to the work
Dynamic classifier classifies the action message；It is described to obtain the sleep state of the user to be measured according to classification results, comprising: root
Body gesture of the user to be measured in sleep state is obtained according to classification results, obtains the user to be measured according to classification results
Activity in sleep state.
Further, sleep monitoring device as the aforementioned, the standard sleep information of the collecting sample, comprising: setting
In time, the multiaxis acceleration of one or many samples one or more sampled point in sleep state is acquired per unit time
Value.
Further, sleep monitoring device as the aforementioned, it is described the standard physical information is trained as training set
To body gesture classifier, wherein the body gesture classification includes: empty bed and lying posture.
Further, sleep monitoring device as the aforementioned, it is described the standard physical information is trained as training set
To body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture and lying posture.
Further, sleep monitoring device as the aforementioned, it is described the standard physical information is trained as training set
To body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture, lies on the back, prostrate, lies on the left side and right side is sleeping.
Further, sleep monitoring device as the aforementioned, it is described the standard actions information is trained as training set
To activity classifier, wherein the class of activity includes non-activity and has activity；The non-activity, including keep the body appearance
Gesture；It is described to have activity, converting mutually, keeping carry out activity in the case of the body gesture including the body gesture.
Further, sleep monitoring device as the aforementioned, it is described the standard actions information is trained as training set
To activity classifier, comprising: determine the upper-level threshold and/or lower threshold of non-activity signal value according to the non-activity information.
Further, sleep monitoring device as the aforementioned, information of the monitoring user to be measured in sleep state, packet
It includes: within the set time, acquiring the one or many user to be measured one or more in sleep state per unit time and adopt
The multiaxis acceleration value of sampling point；Wherein the user to be measured is the sample.
Further, sleep monitoring device as the aforementioned, it is described to be divided the action message according to the activity classifier
Class, comprising: judge whether the action message is greater than or equal to upper-level threshold and is less than or equal to lower threshold.
Further, sleep monitoring device as the aforementioned, it is described to obtain the user to be measured according to classification results and sleeping
Activity when state, comprising: if the result judged is yes, it is determined that the action message is non-activity；If described
The result judged is is not, it is determined that the action message is to have activity.
In the embodiment of the present application, the body by the way of contactless acquisition acceleration value, when by sleep quality
Body information is monitored, and has achieved the purpose that detection body gesture and movable when sleep.The additional aspect of the present invention and advantage
It will be set forth in part in the description, partially will become apparent from the description below, or practice understanding through the invention
It arrives.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present application, so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is for explaining the application, not
Constitute the improper restriction to the application.In the accompanying drawings:
Fig. 1 is the flow chart of sleep monitor method provided by the embodiments of the present application；
Fig. 2 is the sampled point layout drawing of the embodiment of the present application；
Fig. 3 is four kinds of lying posture schematic diagrames of the embodiment of the present application；
Fig. 4 is the structure chart of sleep monitoring device provided by the embodiments of the present application；
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
In this application, term " on ", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outside",
" in ", "vertical", "horizontal", " transverse direction ", the orientation or positional relationship of the instructions such as " longitudinal direction " be orientation based on the figure or
Positional relationship.These terms are not intended to limit indicated dress primarily to better describe the present invention and embodiment
Set, element or component must have particular orientation, or constructed and operated with particular orientation.
Also, above-mentioned part term is other than it can be used to indicate that orientation or positional relationship, it is also possible to for indicating it
His meaning, such as term " on " also are likely used for indicating certain relations of dependence or connection relationship in some cases.For ability
For the those of ordinary skill of domain, the concrete meaning of these terms in the present invention can be understood as the case may be.
In addition, term " installation ", " setting ", " being equipped with ", " connection ", " connected ", " socket " shall be understood in a broad sense.For example,
It may be a fixed connection, be detachably connected or monolithic construction；It can be mechanical connection, or electrical connection；It can be direct phase
It even, or indirectly connected through an intermediary, or is two connections internal between device, element or component.
For those of ordinary skills, the specific meanings of the above terms in the present invention can be understood according to specific conditions.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
According to embodiments of the present invention, a kind of sleep monitor method is provided, as shown in Figure 1, this method includes following step
Rapid S1 to step S5:
Step S1, the standard sleep information of collecting sample；
The standard sleep information is obtained classifier by step S2；
Step S3 monitors information of the user to be measured in sleep state；
Step S4 classifies the information according to the classifier；
Step S5 obtains the sleep state of the user to be measured according to classification results.
In some embodiments, sleep monitor method as the aforementioned, the standard sleep information of the collecting sample, comprising:
The standard static sleep info of collecting sample, the standard Active sleep information of collecting sample；The standard static of the collecting sample
Sleep info, the standard physical information including collecting sample in sleep state；The standard Active sleep of the collecting sample is believed
Breath, the standard actions information including collecting sample in sleep state；
It is described to obtain classifier for the standard sleep information as training set training, comprising: to believe the standard physical
Breath obtains body gesture classifier as training set training, obtains activity point for the standard actions information as training set training
Class device；
Information of the monitoring user to be measured in sleep state, comprising: monitor body of the user to be measured in sleep state
Body information monitors action message of the user to be measured in sleep state；
It is described that the information is classified according to the classifier, comprising: according to the body gesture classifier by the body
The classification of body information, classifies the action message according to the activity classifier；
It is described to obtain the sleep state of the user to be measured according to classification results, comprising: to be obtained according to classification results described
Body gesture of the user to be measured in sleep state obtains work of the user to be measured in sleep state according to classification results
It is dynamic.
In some embodiments, sleep monitor method as the aforementioned, the standard sleep information of the collecting sample, comprising:
Within the set time, one or many samples multiaxis of one or more sampled point in sleep state is acquired per unit time to add
Velocity amplitude.Specifically, three sampled points are set, the arrangement of three sampled points is as shown in Fig. 2, two of them sampled point is arranged
In the two sides of people's sleep area, the lower section of people's sleep area bed surface is arranged in another sampled point；Acquire each sampled point
The acceleration of three mutually perpendicular axis, as shown in Fig. 2, the z-axis of three points is parallel with gravity direction, wherein the two sides
The x-axis of sampled point be parallel to the side of bed, the side of the x-axis of another sampled point perpendicular to bed.When with identical setting
Between empty bed, sample are sampled respectively with four kinds of lying postures and a kind of sitting posture, four kinds of lying postures include: lie on the back, prostrate, left side
Sleeping and right side is sleeping, for prostrate and lies on the back as shown in figure 3, wherein sleeping and lie on the left side for right side in Fig. 3 (a), in Fig. 3 (b)；The seat
Appearance is that sample is sat in bed, and back is against on the wall of the head of a bed, to simulate the posture that people sees TV or reading.
In some embodiments, sleep monitor method as the aforementioned, it is described using the standard physical information as training set
Training obtains body gesture classifier, wherein the body gesture classification includes: empty bed and lying posture.Specifically, the training set
The information of sampled point including the empty bed and four kinds of lying postures that are acquired in the setting time；Support can be used in the training and classification
The open source software OrangeCanvas platform of Various Classifiers on Regional carries out；The body gesture classifier is Naive Bayes Classification
Device；The lying posture class of the body gesture classifier is one kind.
In some embodiments, sleep monitor method as the aforementioned, it is described using the standard physical information as training set
Training obtains body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture and lying posture.Specifically, the instruction
Practice the information that collection includes the sampled point of the empty bed acquired in the setting time, sitting posture and four kinds of lying postures；The training and classification
It can be used and the open source software OrangeCanvas platform of Various Classifiers on Regional is supported to carry out；The body gesture classifier is simplicity
Bayes classifier；The lying posture class of the body gesture classifier is one kind.
In some embodiments, sleep monitor method as the aforementioned, it is described using the standard physical information as training set
Training obtain body gesture classifier, wherein the body gesture classification include: empty bed, sitting posture, lie on the back, prostrate, lie on the left side and
Right side is sleeping.Specifically, the training set includes the empty bed acquired in the setting time, the sampled point of sitting posture and four kinds of lying postures
Information；The training and classification, which can be used, supports the open source software OrangeCanvas platform of Various Classifiers on Regional to carry out；The body
Body posture Posture classifier is Naive Bayes Classifier.
In some embodiments, sleep monitor method as the aforementioned, it is described using the standard actions information as training set
Training obtains activity classifier, wherein the class of activity includes non-activity and has activity；The non-activity, including described in holding
Body gesture；It is described to have activity, converting mutually, keeping living in the case of the body gesture including the body gesture
It is dynamic.Specifically, the training set includes sampled point when sample keeps any one lying posture to lie on a bed within the set time
Multiaxis acceleration value set.
In some embodiments, sleep monitor method as the aforementioned, it is described using the standard actions information as training set
Training obtains activity classifier, comprising: the upper-level threshold and/or lower threshold of non-activity signal value are determined according to the non-activity information.Tool
Body, the multiaxis acceleration value distribution in the training set in a certain range, determine two boundary values of this range, i.e., on
Threshold and lower threshold.
In some embodiments, sleep monitor method as the aforementioned, the monitoring user to be measured is in sleep state
Information, comprising: within the set time, acquire one or many users to be measured per unit time in sleep state one
Or the multiaxis acceleration value of multiple sampled points；Wherein the user to be measured is the sample.Specifically, adopting for user to be measured is monitored
The setting position of sampling point and quantity are identical as the setting position of the sampled point of collecting sample above-mentioned and quantity, and each monitoring is to be measured
The sampled point of user and the direction of the axis of the acceleration of the sampled point of collecting sample above-mentioned and quantity are also identical.
In some embodiments, sleep monitor method as the aforementioned, it is described according to the activity classifier by the activity
Information classification, comprising: judge whether the action message is greater than or equal to upper-level threshold and is less than or equal to lower threshold.Specifically, sentence
The y axis of each collection point of the collected user to be measured and acceleration value of z-axis is no is greater than or equal to every time in the disconnected unit time
Upper-level threshold and be less than or equal to lower threshold.
In some embodiments, sleep monitor method as the aforementioned, it is described to obtain the user to be measured according to classification results
Activity in sleep state, comprising: if the result judged is yes, it is determined that the action message is non-activity；Such as
The result judged described in fruit is is not, it is determined that the action message is to have activity.Specifically, if the result of the judgement is
It is then to abandon the acceleration value；If the result judged is is not, the acceleration value is denoted as once may be living
It is dynamic.Then counting the possible movable number in setting time can described in judgement if the number is lower than a preset value
Movable it can not influence sleep quality；If the number is higher than the preset value, calculated wherein not using DB-SCAN clustering algorithm
Be concerned with movable quantity.All irrelevant activities occurred in a short time can be classified as the seat in a stage by the clustering algorithm
Vertical uneasiness.
It can be seen from the above description that the present invention realizes following technical effect: being based on contactless acceleration value
Acquisition technique is monitored the static information and multidate information of sleep quality, i.e., to sleep when human body posture and activity into
Row detection can avoid invading subject's privacy, not influence the ortho of user, and application method is easy to learn and cheap, is suitble to
Body gesture is when long-term household monitoring sleep to prevent or treat related disease.
According to embodiments of the present invention, a kind of sleep monitoring device is provided, as shown in figure 4, the device includes: acquisition module
101, training module 102, detection module 103, categorization module 104, determining module 105；
The acquisition module 101, the standard sleep information for collecting sample；
The training module 102, for obtaining classifier for the standard sleep information as training set training；
The detection module 103, for monitoring information of the user to be measured in sleep state；
The categorization module 104, for the information to be classified according to the classifier；
The determining module 105, for obtaining the sleep state of the user to be measured according to classification results.
In some embodiments, sleep monitoring device as the aforementioned, the acquisition module 101, specifically, the acquisition mould
RFID tag can be used as sensor in block 101；Standard physical information of the collecting sample in sleep state, can be by
Radio frequency identification reader transmits a signal to WISP, i.e. wireless identification incudes platform.
In some embodiments, sleep monitoring device as the aforementioned, the standard sleep information of the collecting sample, comprising:
The standard static sleep info of collecting sample, the standard Active sleep information of collecting sample；The standard static of the collecting sample
Sleep info, the standard physical information including collecting sample in sleep state；The standard Active sleep of the collecting sample is believed
Breath, the standard actions information including collecting sample in sleep state；
It is described to obtain classifier for the standard sleep information as training set training, comprising: to believe the standard physical
Breath obtains body gesture classifier as training set training, obtains activity point for the standard actions information as training set training
Class device；
Information of the monitoring user to be measured in sleep state, comprising: monitor body of the user to be measured in sleep state
Body information monitors action message of the user to be measured in sleep state；
It is described that the information is classified according to the classifier, comprising: according to the body gesture classifier by the body
The classification of body information, classifies the action message according to the activity classifier；
It is described to obtain the sleep state of the user to be measured according to classification results, comprising: to be obtained according to classification results described
Body gesture of the user to be measured in sleep state obtains work of the user to be measured in sleep state according to classification results
It is dynamic.
In some embodiments, sleep monitoring device as the aforementioned, the standard sleep information of the collecting sample, comprising:
Within the set time, one or many samples multiaxis of one or more sampled point in sleep state is acquired per unit time to add
Velocity amplitude.Specifically, three sampled points are set, the arrangement of three sampled points is as shown in Fig. 2, two of them sampled point is arranged
In the two sides of people's sleep area, the lower section of people's sleep area bed surface is arranged in another sampled point；Acquire each sampled point
The acceleration of three mutually perpendicular axis, as shown in Fig. 2, the z-axis of three points is parallel with gravity direction, wherein the two sides
The x-axis of sampled point be parallel to the side of bed, the side of the x-axis of another sampled point perpendicular to bed.When with identical setting
Between empty bed, sample are sampled respectively with four kinds of lying postures and a kind of sitting posture, four kinds of lying postures include: lie on the back, prostrate, left side
Sleeping and right side is sleeping, for prostrate and lies on the back as shown in figure 3, wherein sleeping and lie on the left side for right side in Fig. 3 (a), in Fig. 3 (b)；The seat
Appearance is that sample is sat in bed, and back is against on the wall of the head of a bed, to simulate the posture that people sees TV or reading.
In some embodiments, sleep monitoring device as the aforementioned, it is described using the standard physical information as training set
Training obtains body gesture classifier, wherein the body gesture classification includes: empty bed and lying posture.Specifically, the training set
The information of sampled point including the empty bed and four kinds of lying postures that are acquired in the setting time；Support can be used in the training and classification
The open source software OrangeCanvas platform of Various Classifiers on Regional carries out；The body gesture classifier is Naive Bayes Classification
Device；The lying posture class of the body gesture classifier is one kind.
In some embodiments, sleep monitoring device as the aforementioned, it is described using the standard physical information as training set
Training obtains body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture and lying posture.Specifically, the instruction
Practice the information that collection includes the sampled point of the empty bed acquired in the setting time, sitting posture and four kinds of lying postures；The training and classification
It can be used and the open source software OrangeCanvas platform of Various Classifiers on Regional is supported to carry out；The body gesture classifier is simplicity
Bayes classifier；The lying posture class of the body gesture classifier is one kind.
In some embodiments, sleep monitoring device as the aforementioned, it is described using the standard physical information as training set
Training obtain body gesture classifier, wherein the body gesture classification include: empty bed, sitting posture, lie on the back, prostrate, lie on the left side and
Right side is sleeping.Specifically, the training set includes the empty bed acquired in the setting time, the sampled point of sitting posture and four kinds of lying postures
Information；The training and classification, which can be used, supports the open source software OrangeCanvas platform of Various Classifiers on Regional to carry out；The body
Body posture Posture classifier is Naive Bayes Classifier.
In some embodiments, sleep monitoring device as the aforementioned, it is described using the standard actions information as training set
Training obtains activity classifier, wherein the class of activity includes non-activity and has activity；The non-activity, including described in holding
Body gesture；It is described to have activity, converting mutually, keeping living in the case of the body gesture including the body gesture
It is dynamic.Specifically, the training set includes sampled point when sample keeps any one lying posture to lie on a bed within the set time
Multiaxis acceleration value set.
In some embodiments, sleep monitoring device as the aforementioned, it is described using the standard actions information as training set
Training obtains activity classifier, comprising: the upper-level threshold and/or lower threshold of non-activity signal value are determined according to the non-activity information.Tool
Body, the multiaxis acceleration value distribution in the training set in a certain range, determine two boundary values of this range, i.e., on
Threshold and lower threshold.
In some embodiments, sleep monitoring device as the aforementioned, the monitoring user to be measured is in sleep state
Action message, comprising: within the set time, acquire one or many users to be measured per unit time in sleep state
The multiaxis acceleration value of one or more sampled points；Wherein the user to be measured is the sample.Specifically, user to be measured is monitored
Sampled point setting position and quantity it is identical as the setting position of the sampled point of collecting sample above-mentioned and quantity, each monitoring
The sampled point of user to be measured and the direction of the axis of the acceleration of the sampled point of collecting sample above-mentioned and quantity are also identical.
In some embodiments, sleep monitoring device as the aforementioned, it is described according to the activity classifier by the activity
Information classification, comprising: judge whether the action message is greater than or equal to upper-level threshold and is less than or equal to lower threshold.Specifically, sentence
The y axis of each collection point of the collected user to be measured and acceleration value of z-axis is no is greater than or equal to every time in the disconnected unit time
Upper-level threshold and be less than or equal to lower threshold.
In some embodiments, sleep monitoring device as the aforementioned, it is described to obtain the user to be measured according to classification results
Activity in sleep state, comprising: if the result judged is yes, it is determined that the action message is non-activity；Such as
The result judged described in fruit is is not, it is determined that the action message is to have activity.Specifically, if the result of the judgement is
It is then to abandon the acceleration value；If the result judged is is not, the acceleration value is denoted as once may be living
It is dynamic.Then counting the possible movable number in setting time can described in judgement if the number is lower than a preset value
Movable it can not influence sleep quality；If the number is higher than the preset value, calculated wherein not using DB-SCAN clustering algorithm
Be concerned with movable quantity.All irrelevant activities occurred in a short time can be classified as the seat in a stage by the clustering algorithm
Vertical uneasiness.
It can be seen from the above description that the present invention realizes following technical effect: being based on contactless acceleration value
Static information and multidate information when acquisition device is to sleep quality are monitored, i.e. the body appearance to human body in sleep state
Gesture and activity are monitored, and are avoided invading subject's privacy, are not influenced the ortho of user, application method is easy to learn and price just
Preferably, it is suitble to when long-term household monitoring sleep body gesture to prevent or treat related disease.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific
Hardware and software combines.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (22)
1. a kind of sleep monitor method, which comprises the following steps:
The standard sleep information of collecting sample；
Classifier is obtained using the standard sleep information as training set training；
Monitor information of the user to be measured in sleep state；
The information is classified according to the classifier；
The sleep state of the user to be measured is obtained according to classification results.
2. sleep monitor method according to claim 1, which is characterized in that
The standard sleep information of the collecting sample, comprising: the standard static sleep info of collecting sample, the standard of collecting sample
Active sleep information；The standard static sleep info of the collecting sample, the standard body including collecting sample in sleep state
Body information；The standard Active sleep information of the collecting sample, the standard actions information including collecting sample in sleep state；
It is described to obtain classifier for the standard sleep information as training set training, comprising: to make the standard physical information
Body gesture classifier is obtained for training set training, obtains activity classification for the standard actions information as training set training
Device；
Information of the monitoring user to be measured in sleep state, comprising: monitor body letter of the user to be measured in sleep state
Breath, monitors action message of the user to be measured in sleep state；
It is described that the information is classified according to the classifier, comprising: to be believed the body according to the body gesture classifier
Breath classification, classifies the action message according to the activity classifier；
It is described to obtain the sleep state of the user to be measured according to classification results, comprising: to be obtained according to classification results described to be measured
Body gesture of the user in sleep state obtains activity of the user to be measured in sleep state according to classification results.
3. sleep monitor method according to claim 1, which is characterized in that the standard sleep information of the collecting sample,
It include: within the set time, to acquire one or many samples one or more sampled point in sleep state per unit time
Multiaxis acceleration value.
4. sleep monitor method according to claim 2, which is characterized in that described using the standard physical information as instruction
Practice training and get body gesture classifier, wherein the body gesture classification includes: empty bed and lying posture.
5. sleep monitor method according to claim 2 or 4, which is characterized in that described to make the standard physical information
Body gesture classifier is obtained for training set training, wherein the body gesture classification includes: empty bed, sitting posture and lying posture.
6. sleep monitor method according to claim 5, which is characterized in that described using the standard physical information as instruction
Practice training and get body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture, lies on the back, prostrate, left side
Sleeping and right side is sleeping.
7. sleep monitor method according to claim 2, which is characterized in that described using the standard actions information as instruction
Practice training and get activity classifier, wherein the class of activity includes non-activity and has activity；The non-activity, including keep
The body gesture；It is described to have activity, converting mutually, keeping carrying out in the case of the body gesture including the body gesture
Activity.
8. according to claim the 7 sleep monitor methods stated, which is characterized in that it is described using the standard actions information as instruction
Practice training get activity classifier, comprising: according to the non-activity information determine non-activity signal value upper-level threshold and/or under
Threshold.
9. sleep monitor method according to claim 1, which is characterized in that the monitoring user to be measured is in sleep state
Information, comprising: within the set time, acquire one or many users to be measured per unit time in sleep state one
Or the multiaxis acceleration value of multiple sampled points；Wherein the user to be measured is the sample.
10. sleep monitor method according to claim 2, which is characterized in that it is described according to the activity classifier by institute
State action message classification, comprising: judge whether the action message is greater than or equal to upper-level threshold and is less than or equal to lower threshold.
11. sleep monitor method according to claim 10, which is characterized in that it is described according to classification results obtain it is described to
Survey activity of the user in sleep state, comprising: if the result judged is yes, it is determined that the action message is no work
It is dynamic；If the result judged is is not, it is determined that the action message is to have activity.
12. a kind of sleep monitoring device characterized by comprising acquisition module, training module, detection module, categorization module,
Determining module；
The acquisition module, the standard sleep information for collecting sample；
The training module, for obtaining classifier for the standard sleep information as training set training；
The detection module, for monitoring information of the user to be measured in sleep state；
The categorization module, for the information to be classified according to the classifier；
The determining module, for obtaining the sleep state of the user to be measured according to classification results.
13. sleep monitoring device according to claim 12, which is characterized in that
The standard sleep information of the collecting sample, comprising: the standard static sleep info of collecting sample, the standard of collecting sample
Active sleep information；The standard static sleep info of the collecting sample, the standard body including collecting sample in sleep state
Body information；The standard Active sleep information of the collecting sample, the standard actions information including collecting sample in sleep state；
It is described to obtain classifier for the standard sleep information as training set training, comprising: to make the standard physical information
Body gesture classifier is obtained for training set training, obtains activity classification for the standard actions information as training set training
Device；
Information of the monitoring user to be measured in sleep state, comprising: monitor body letter of the user to be measured in sleep state
Breath, monitors action message of the user to be measured in sleep state；
It is described that the information is classified according to the classifier, comprising: to be believed the body according to the body gesture classifier
Breath classification, classifies the action message according to the activity classifier；
It is described to obtain the sleep state of the user to be measured according to classification results, comprising: to be obtained according to classification results described to be measured
Body gesture of the user in sleep state obtains activity of the user to be measured in sleep state according to classification results.
14. sleep monitoring device according to claim 12, which is characterized in that the standard sleep of the collecting sample is believed
Breath, comprising: within the set time, acquire one or many samples one or more sampled point in sleep state per unit time
Multiaxis acceleration value.
15. sleep monitoring device according to claim 13, which is characterized in that it is described using the standard physical information as
Training set training obtains body gesture classifier, wherein the body gesture classification includes: empty bed and lying posture.
16. sleep monitoring device described in 3 or 15 according to claim 1, which is characterized in that described by the standard physical information
Body gesture classifier is obtained as training set training, wherein the body gesture classification includes: empty bed, sitting posture and lying posture.
17. sleep monitoring device according to claim 16, which is characterized in that it is described using the standard physical information as
Training set training obtains body gesture classifier, wherein the body gesture classification includes: empty bed, sitting posture, lies on the back, prostrate, a left side
It lies on one's side sleeping with right side.
18. sleep monitoring device according to claim 13, which is characterized in that it is described using the standard actions information as
Training set training obtains activity classifier, wherein the class of activity includes non-activity and has activity；The non-activity, including protect
Hold the body gesture；It is described to have activity, converting mutually including the body gesture, keep in the case of the body gesture into
Row activity.
19. sleep monitoring device according to claim 18, which is characterized in that it is described using the standard actions information as
Training set training obtains activity classifier, comprising: according to the non-activity information determine non-activity signal value upper-level threshold and/or under
Threshold.
20. sleep monitoring device according to claim 12, which is characterized in that the monitoring user to be measured is in sleep state
When information, comprising: within the set time, acquire one or many users to be measured per unit time in sleep state one
The multiaxis acceleration value of a or multiple sampled points；Wherein the user to be measured is the sample.
21. sleep monitoring device according to claim 13, which is characterized in that it is described according to the activity classifier by institute
State action message classification, comprising: judge whether the action message is greater than or equal to upper-level threshold and is less than or equal to lower threshold.
22. sleep monitoring device according to claim 21, which is characterized in that it is described according to classification results obtain it is described to
Survey activity of the user in sleep state, comprising: if the result judged is yes, it is determined that the action message is no work
It is dynamic；If the result judged is is not, it is determined that the action message is to have activity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810582893.3A CN109009139A (en) | 2018-06-07 | 2018-06-07 | Sleep monitor method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810582893.3A CN109009139A (en) | 2018-06-07 | 2018-06-07 | Sleep monitor method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109009139A true CN109009139A (en) | 2018-12-18 |
Family
ID=64612217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810582893.3A Pending CN109009139A (en) | 2018-06-07 | 2018-06-07 | Sleep monitor method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109009139A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113952587A (en) * | 2021-11-16 | 2022-01-21 | 湖北工业大学 | System for controlling playing device based on sleep state |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013150523A1 (en) * | 2012-04-01 | 2013-10-10 | Earlysense Ltd. | Monitoring, predicting and treating clinical episodes |
| WO2014151121A1 (en) * | 2013-03-15 | 2014-09-25 | Robert Bosch Gmbh | Method and system for monitoring the status and condition of an object |
| CN104138260A (en) * | 2014-07-02 | 2014-11-12 | 中山大学 | Sleeping posture multi-classifying identifying method utilizing SVM classifier |
| US20150045630A1 (en) * | 2011-02-24 | 2015-02-12 | Enhanced Surface Dynamics, Inc. | Pressure monitoring system and method |
| CN104732250A (en) * | 2015-03-25 | 2015-06-24 | 安徽农业大学 | Non-sleep-interference sleeping posture and sleeping behavior testing identification method |
| CN104720753A (en) * | 2015-03-07 | 2015-06-24 | 黎曦 | Sleeping monitoring system and method thereof |
| CN106510640A (en) * | 2016-12-13 | 2017-03-22 | 哈尔滨理工大学 | Sleep quality detection method based on overturning detection |
-
2018
- 2018-06-07 CN CN201810582893.3A patent/CN109009139A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150045630A1 (en) * | 2011-02-24 | 2015-02-12 | Enhanced Surface Dynamics, Inc. | Pressure monitoring system and method |
| WO2013150523A1 (en) * | 2012-04-01 | 2013-10-10 | Earlysense Ltd. | Monitoring, predicting and treating clinical episodes |
| WO2014151121A1 (en) * | 2013-03-15 | 2014-09-25 | Robert Bosch Gmbh | Method and system for monitoring the status and condition of an object |
| CN104138260A (en) * | 2014-07-02 | 2014-11-12 | 中山大学 | Sleeping posture multi-classifying identifying method utilizing SVM classifier |
| CN104720753A (en) * | 2015-03-07 | 2015-06-24 | 黎曦 | Sleeping monitoring system and method thereof |
| CN104732250A (en) * | 2015-03-25 | 2015-06-24 | 安徽农业大学 | Non-sleep-interference sleeping posture and sleeping behavior testing identification method |
| CN106510640A (en) * | 2016-12-13 | 2017-03-22 | 哈尔滨理工大学 | Sleep quality detection method based on overturning detection |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113952587A (en) * | 2021-11-16 | 2022-01-21 | 湖北工业大学 | System for controlling playing device based on sleep state |
| CN113952587B (en) * | 2021-11-16 | 2024-01-19 | 杨金刚 | System for controlling playing device based on sleep state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106842979B (en) | Mattress capable of assisting sleep | |
| KR100942696B1 (en) | Apparatus and Method managing quality of sleep | |
| Torres et al. | Sensor enabled wearable RFID technology for mitigating the risk of falls near beds | |
| CN103402423B (en) | Patient deterioration detects | |
| CN102448368B (en) | Method and system for providing behavioural therapy for insomnia | |
| CN108711452A (en) | The health state analysis method and system of view-based access control model | |
| JP6775922B2 (en) | Biological condition determination device and biological condition determination method | |
| CN104083152A (en) | Human body temperature monitoring method and body temperature monitoring system | |
| Kim et al. | IoT-based unobtrusive sensing for sleep quality monitoring and assessment | |
| US20210022636A1 (en) | Bio-signal detecting headband | |
| Ranasinghe et al. | Towards falls prevention: a wearable wireless and battery-less sensing and automatic identification tag for real time monitoring of human movements | |
| Hernandez et al. | Wearable motion-based heart rate at rest: A workplace evaluation | |
| US20190069829A1 (en) | Method and apparatus for monitoring urination of a subject | |
| Rajasekaran et al. | Elderly patient monitoring system using a wireless sensor network | |
| Ma et al. | A fatigue detect system based on activity recognition | |
| Conradsen et al. | Multi-modal intelligent seizure acquisition (MISA) system—a new approach towards seizure detection based on full body motion measures | |
| CN107184208A (en) | A kind of intelligent sleep monitoring eyeshade with comprehensive function | |
| Tlili et al. | A Survey on sitting posture monitoring systems | |
| Konstantas | Section 4: Sensor, Signal and Imaging Informatics: An Overview of Wearable and Implantable Medical Sensors | |
| CN109009139A (en) | Sleep monitor method and device | |
| Bourke et al. | The design and development of a long-term fall detection system incorporated into a custom vest for the elderly. | |
| Jeng et al. | Stream data analysis of body sensors for sleep posture monitoring: An automatic labelling approach | |
| Thammachote et al. | Contactless monitoring of human behaviors in bed using RSSI signals | |
| Tlili et al. | A Review on posture monitoring systems | |
| Chowdhury et al. | Wearable Real-Time Epileptic Seizure Detection and Warning 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |