CN112806966A - Non-interference type early warning system and method for apnea in sleep - Google Patents
Non-interference type early warning system and method for apnea in sleep Download PDFInfo
- Publication number
- CN112806966A CN112806966A CN202110146421.5A CN202110146421A CN112806966A CN 112806966 A CN112806966 A CN 112806966A CN 202110146421 A CN202110146421 A CN 202110146421A CN 112806966 A CN112806966 A CN 112806966A
- Authority
- CN
- China
- Prior art keywords
- time
- sleep
- module
- pressure
- breathing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 208000008784 apnea Diseases 0.000 title claims abstract description 14
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 46
- 238000009529 body temperature measurement Methods 0.000 claims abstract description 24
- 230000008859 change Effects 0.000 claims abstract description 24
- 201000002859 sleep apnea Diseases 0.000 claims abstract description 18
- 238000001931 thermography Methods 0.000 claims abstract description 18
- 230000009471 action Effects 0.000 claims abstract description 13
- 238000005259 measurement Methods 0.000 claims abstract description 7
- 230000036544 posture Effects 0.000 claims description 54
- 230000008569 process Effects 0.000 claims description 8
- 230000000241 respiratory effect Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000002618 waking effect Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims 6
- 238000012544 monitoring process Methods 0.000 abstract description 21
- 238000003384 imaging method Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000019116 sleep disease Diseases 0.000 description 1
- 208000020685 sleep-wake disease Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000004861 thermometry Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4818—Sleep apnoea
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring 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 or 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
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
- A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
- A61M2021/0083—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus especially for waking up
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Hematology (AREA)
- Anesthesiology (AREA)
- Acoustics & Sound (AREA)
- Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
本发明公开了一种非干扰式睡眠中呼吸暂停预警系统及方法，该系统包括：控制中心、红外测温模块、微压力传感模块、报警模块和用户终端；红外测温模块用于采集热成像图像，微压力传感模块采集压力数据，报警模块传输呼吸暂停的报警信号，用户终端显示实时的压力数据、实时热成像图像以及告警信息；控制中心接收热成像图像和压力数据，将热成像图像流进行目标跟踪，对睡姿进行分类及记录，判断是否发生呼吸干扰动作；将微压力传感模块检测到的压力值进行判断分析，根据两次呼吸之间的压力变化值判定用户呼吸是否正常，结合呼吸干扰动作，判定睡眠呼吸是否暂停，输出报警信号。本发明能够实现无干扰测量及多方面联合监测。
The invention discloses a non-interference sleep apnea early warning system and method. The system includes: a control center, an infrared temperature measurement module, a micro-pressure sensing module, an alarm module and a user terminal; the infrared temperature measurement module is used for collecting heat Imaging images, the micro-pressure sensing module collects pressure data, the alarm module transmits an apnea alarm signal, and the user terminal displays real-time pressure data, real-time thermal imaging images and alarm information; the control center receives thermal imaging images and pressure data, and converts the thermal imaging The image stream performs target tracking, classifies and records the sleeping position, and determines whether there is a breathing interference action; judges and analyzes the pressure value detected by the micro-pressure sensing module, and determines whether the user is breathing according to the pressure change value between two breaths. Normal, combined with breathing interference action, determine whether sleep apnea is suspended, and output an alarm signal. The invention can realize non-interference measurement and multi-aspect joint monitoring.
Description
Technical Field
The invention relates to the technical field of sleep monitoring, in particular to a non-interference type apnea early warning system and a non-interference type apnea early warning method in sleep.
Background
Sleep apnea is a serious sleep disorder that occurs primarily when an individual's breathing is interrupted during sleep. Therefore, it is necessary to monitor and alarm the apnea in sleep.
One common limitation of the prior art is that the sleep condition cannot be monitored without interference, and certain influence is caused on the sleep of people. The existing sleep apnea collecting and analyzing system based on dynamic electrocardiogram and respiratory wave collection adopts a set of wearable analyzing system, a dynamic electrocardiogram recorder is used for synchronously recording dynamic electrocardiogram and respiratory wave, the acquired data are subjected to derivation and image display analysis by utilizing 2 indexes of HRV and respiratory wave, and the method for monitoring the sleep apnea condition during sleep can generate certain influence on the sleep condition of a tested person. The existing monitoring device can also be made into a portable device so as to be used at home, but also needs to wear an external device, which can also affect the sleeping condition of the tested person.
In addition, infrared thermal imaging techniques have been used in some studies to monitor sleep breathing. The basic principle of this method is to capture the temperature fluctuation around the nose and mouth during breathing and determine the breathing condition by analyzing the results of the fluctuation. Meanwhile, some researches advocate that a face capture system is adopted when the infrared thermal imaging technology is used for monitoring the sleep breathing condition; the main limitation of monitoring by using the infrared thermal imaging technology is that if the sleeping posture is changed, the sleeping breathing condition is difficult to output accurately under the condition that the face tracking cannot be performed accurately. If a face recognition system is added, the difficulty in compiling the algorithm is increased for the first time, and point-to-point recognition is needed; the second monitoring data is richer, for example, if the face recognition system is not added, when the tested person embeds the head into a quilt, the temperature fluctuation is slightly insufficient only by testing.
There is also a wearable ring that can monitor heart rate, blood oxygen saturation level, perfusion index, and amount of movement during sleep, while monitoring blood flow only through capillaries in the finger. Although sleep monitoring can be performed through data such as capillary flow, the products have the limitation that early warning cannot be timely achieved. The device uses vibration prompt and can tell the user a complete sleep state report, but in terms of alarm effect, the alarm by using vibration is not enough to solve the early warning problem of sleep apnea, and the alarm cannot be given timely and effectively.
In summary, the prior art generally has some disadvantages, including: the use of the monitoring method is greatly limited because complete non-interference monitoring cannot be achieved, monitoring data are too single, and an alarm cannot be timely and effectively sent out.
Disclosure of Invention
The invention provides a non-interference type sleep apnea early warning system and a non-interference type sleep apnea early warning method in order to overcome the defects and shortcomings in the prior art, solves the problem that the sleep of a detected person is affected in the prior art, can monitor the sleep breathing condition of the detected person in a completely natural condition, and realizes non-interference measurement and multi-aspect combined monitoring.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a non-interference type early warning system for apnea in sleep, which comprises: the system comprises a control center, an infrared temperature measurement module, a micro-pressure sensing module, an alarm module and a user terminal;
the infrared temperature measurement module, the micro-pressure sensing module, the alarm module and the user terminal are all connected with the control center;
the system comprises an infrared temperature measurement module, a micro-pressure sensing module, an alarm module and a user terminal, wherein the infrared temperature measurement module is used for collecting thermal imaging images, the micro-pressure sensing module is used for collecting pressure data, the alarm module is used for transmitting alarm signals of apnea, and the user terminal is used for displaying real-time pressure data, real-time thermal imaging images and alarm information;
the control center is used for receiving the thermal imaging image and the pressure data, carrying out target tracking on the thermal imaging image flow, classifying and recording sleeping postures and judging whether breathing interference action occurs or not;
judging and analyzing the pressure value detected by the micro-pressure sensing module, judging whether the breath of the user is normal according to the pressure change value between two breaths, judging whether the sleep breath is suspended or not by combining the breath interference action, and outputting an alarm signal.
According to the preferable technical scheme, the system is further provided with a camera module, the camera module is connected with the control center, and the camera module is used for collecting camera video stream data.
As a preferred technical solution, the pressure sensor is made of a flexible material.
The invention also provides an early warning method of the non-interference type apnea early warning system in sleep, which comprises the following steps:
carrying out target tracking on a thermal imaging image stream acquired by an infrared temperature measurement module, constructing a BP neural network for sleep posture classification training, obtaining a sleep posture classifier, classifying and recording the sleep posture by the sleep posture classifier, and judging whether the current sleep posture is the same as the sleep posture at the last moment;
detecting a face area as an interested area of the infrared temperature measurement module, acquiring an average gray value of the interested area, performing Kalman filtering on the average gray value, and calculating the time of adjacent wave crests of filtered data to be used as a breathing cycle;
setting the number n of breathing cycles, and if the number n of the calculated breathing cycles exceeds the set normal breathing cycle range, determining that the breathing is abnormal;
judging and analyzing the pressure value detected by the micro-pressure sensing module, and judging that the breath of the user is normal if the pressure change value between two breaths is smaller than a preset value; if the pressure change value between two breaths is a preset value or exceeds the preset value and the next pressure value from the micro-pressure sensor is not received in the normal breathing time interval, recording the current time;
judging whether the sleeping posture of the current time is the same as the sleeping posture of the previous time by the sleeping posture classifier, and if not, judging that a breathing interference action occurs; if no breathing interference action occurs, the sleep apnea is judged, and an alarm signal is output.
As a preferred technical scheme, the sleeping posture classifier classifies and records sleeping postures, and the method specifically comprises the following steps:
let the set of user's sleep postures be C ═ C1，C2，C3Establishing a corresponding data set, wherein the data set is { supine, lying on the left side, lying on the right side };
the BP neural network is trained by adopting the corresponding data set to obtain a sleeping posture classifier;
the sleeping posture classifier outputs a judgment result, when the sleeping posture at the current time is different from the sleeping posture at the previous time, the time t when the sleeping posture changes is stored, and finally the ordered vector S of the sleeping posture change time in the sleeping process is obtainedall＝[t1，t2，…tN]。
As a preferred technical solution, the obtaining of the average gray value of the region of interest specifically includes:
where rm, rn are the width and height of the region of interest, respectively, and k represents an arbitrary time instant.
As a preferred technical scheme, the kalman filtering is performed on the average gray value, and the specific calculation formula is as follows:
zk＝ASk+υk
Pk|k-1＝APk-1|k-1AT+Q
Kk＝Pk|k-1AT(APk|k-1AT+R)-1
Pk|k＝(I-KkA)Pk|k-1
wherein A represents a measurement state transition matrix, upsilonkN (0, R) represents the observed noise satisfying the Gaussian distribution, R represents the measurement noise covariance, zkRepresents the observed value at time k and,
representing the a priori state estimate at time k,
respectively representing the posterior state estimated values of k-1 and k time; pk|k-1Representing the prior estimated covariance, P, of time kk-1|k-1、Pk|kRespectively representing the posterior state estimation covariance of k-1 and k time; q represents a process noise covariance matrix; kkRepresenting the kalman gain.
As a preferred technical solution, the calculating time of adjacent peaks of the filtered data and using the time as a breathing cycle includes:
at the k-th moment, if satisfied
And is
Then time k
The first peak point is denoted as Cl＝k；
The time difference between two adjacent peaks is the respiratory cycle calculated from the peak point of the first wave, i.e. Tl＝Cl-Cl-1；
Normal breathing cycle range is set to [ T ]low,Thigh]。
As a preferred technical solution, the output alarm signal specifically adopts any one or more of the following alarm modes:
the method comprises the steps of waking up a user by vibration, notifying family members of the user by a bound mobile phone and notifying a rescue unit at the place by a network.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) according to the invention, data acquisition is carried out through the infrared temperature measurement module and the micro-pressure sensing module, the infrared temperature measurement module acquires data in a mode of not directly contacting with a human body, and noise and light which influence sleep are not generated; the micro-pressure sensing module collects data in a mode of embedding the micro-pressure sensing module into the mattress, and if the micro-pressure sensing module is in a normal sleep state, the vibration awakening mode cannot be started, so that the problem that the sleep of a detected person is influenced in the prior art is solved, the breathing state of the detected person in sleep can be monitored in a completely natural state, and non-interference measurement and multi-aspect combined monitoring are realized.
(2) The invention can immediately send out an alarm when the time for stopping breathing reaches the dangerous time (the brain can be irreversibly damaged in 4-6 minutes), thereby achieving the effect of timely alarming.
Drawings
FIG. 1 is a schematic structural framework diagram of a non-intrusive sleep apnea warning system in accordance with the present invention;
FIG. 2 is a schematic flow chart of a non-intrusive sleep apnea warning method according to the present invention;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Examples
As shown in fig. 1, the present embodiment provides a non-interference type early warning system for sleep apnea, which includes: the device comprises a control center, a camera module, an infrared temperature measurement module, a micro-pressure sensing module and an alarm module.
In this embodiment, the control center is responsible for processing and analyzing all data monitored in the system, if the analysis result is normal, the data will not be used, and if the analysis result is abnormal, even after apnea occurs during sleep, the data is delivered to the alarm module to alarm in time.
Wherein the monitored data comprises: the system comprises camera shooting video stream data captured by a camera shooting module, a thermal imaging image obtained by an infrared temperature measurement module and pressure sensing data.
In this embodiment, the camera module is used for capturing camera video stream data, and the camera module may not be used in the process of determining sleep breathing, and the RGB diagram and the camera video stream data are not used, and the addition is to enrich the functions of the whole system.
The processing mode of the control center also comprises the step of transmitting the analysis data to the user terminal, and the user terminal can directly display real-time monitoring video, real-time infrared imaging and related analysis information.
In this embodiment, the infrared temperature measurement module covers the bed and the area 0.5m nearby, and two sides of the bed head are respectively provided with one infrared temperature measurement module, so that the accurate temperature change can be obtained under the condition of sleeping on one side, and meanwhile, the infrared temperature measurement module is far away from the window, the air conditioner and other irrelevant factors influencing the temperature change.
As shown in fig. 2, the present embodiment provides a non-interference type sleep apnea warning method, which performs target tracking on a thermal imaging video stream obtained by an infrared temperature measurement module, classifies user behaviors, and analyzes a current sleeping posture of a user.
The sleeping posture analysis is carried out according to the following steps:
(1) defining a set of sleep postures of a user as C ═ C1，C2，C3Establishing a corresponding data set, wherein the data set is { supine, lying on the left side, lying on the right side };
(2) constructing a BP neural network for sleeping posture classification, and training by using the data set to obtain a sleeping posture classifier;
(3) using the classifier in (2) for real-time video analysis, a time-varying classifier result Ψ (t) ∈ C can be obtained, if Ψ (t) ═ Ψ (t) ∈ C-) The sleeping posture is not changed at the time t, if psi (t) ≠ psi (t)-) The sleeping posture changes at the time t, psi (t)-) Storing the time of occurrence of the change of the sleeping posture into S as the result of the classifier at the previous timeallFinally, the ordered vector S of the sleeping posture change time of the user in the sleeping process can be obtainedall＝[t1，t2，…tN]；
(4) If t is presentk∈SallK > m satisfies tk-tk-mIf the number of the positive changes is less than tau, m is a set normal number, tau is a set time parameter, the change of the sleeping posture can be regarded as the drastic change of the sleeping posture, and finally the total times of the drastic change of the sleeping posture can be counted as K;
in this embodiment, the face detection adopts a relatively mature algorithm, such as a V & J algorithm, which mainly uses haar features and an Adaboost classifier.
In this embodiment, the detected face region is used as the ROI (region of interest) of the infrared thermometry module, and H ∈ Rrm *rnWherein rm and rn are the width and height of the ROI respectively, and the period of estimating the nose temperature change can be converted into the period of estimating the change of the gray value of the infrared image because the temperature in the infrared image obtained by the infrared temperature measurement module can influence the gray value in the H image; since the video recording frame rate is usually 30fps, one frame is taken out every 3 frames, and the following strategies are adopted:
a. when k is obtained, the average gray scale value of the ROI is:
b. calculating the period of change of the average gray value of the ROI area, wherein the change of the average gray value is the physiological activity of a similar period under the normal condition, so that the change of the average gray value is the similar period change corresponding to the change of the average gray value, and the period of respiration can be estimated by solving two peaks (or troughs) of the average gray value;
c. however, due to the noise existing in the environment and the like, in order to obtain small peaks and troughs caused by respiration rather than noise or other reasons, kalman filtering is introduced to reprocess the obtained average gray value:
zk＝ASk+υk (1)
Pk|k-1＝APk-1|k-1AT+Q (3)
Kk＝Pk|k-1AT(APk|k-1AT+R)-1 (4)
Pk|k＝(I-KkA)Pk|k-1 (6)
where A is a measured state transition matrix, upsilonkN (0, R) is the observed noise satisfying the Gaussian distribution, R is the measured noise covariance, which is generally observed and a known condition for the filter; z is a radical ofkIs the observed value at time k;
is an estimate of the a priori state at time k,
the posterior state estimated values at the k-1 and k moments respectively; pk|k-1Is the prior estimated covariance of time k, Pk-1|k-1、Pk|kThe posterior state estimation covariance at the time of k-1 and k is respectively; q is a process noise covariance matrix; kkIs the Kalman gain;
for a set of data obtained continuously, peaks are obtained according to the following strategy:
if at time k, it is satisfied
And is
Then time k
The first peak point is denoted as Cl＝k；
The time difference between two adjacent peaks is the respiratory cycle calculated from the peak point of the first wave, i.e. Tl＝Cl-Cl-1；
Setting Normal respiratory cycle Range [ Tlow,Thigh]And judging the abnormal breathing condition:
and if the continuous n calculated breathing cycles are not in the range, judging that the breathing is abnormal. The value of n influences the judgment accuracy, when n is too small, misjudgment is easy to occur, when n is too large, the judgment time can be delayed, and in severe cases, the treatment time can be missed.
In the embodiment, in the aspect of the micro-pressure sensing module, if the pressure variation value between two breaths is smaller than a preset value, it is determined that the user breathes normally, and the breath data is continuously monitored and analyzed; when the pressure change value between two breaths is a preset value or exceeds the preset value and the next pressure value from the micro-pressure sensor is not received in the normal breathing time interval, recording the current time t, combining the combined analysis of the infrared temperature measurement sleeping posture classifier, and if the result psi (t) ≠ psi (t) of the sleeping posture classifier is obtained-) Namely, the user has the actions of turning over and the like, and then the breathing interference action is judged "Monitoring and analyzing the respiration data continuously; and if the imaging module does not display that the user generates the breathing interference action, judging that the sleep apnea of the user occurs. No matter what kind of sleeping posture a person takes during sleeping, the person can recognize and recognize the heat changed by breathing.
In this embodiment, the alarm mode in an emergency is as follows: the method comprises the following steps of waking a user by vibration, notifying family members of the user by a bound mobile phone, notifying rescue units such as a hospital where the user is located by a network and timely performing first aid on the user, wherein any one or more of the alarm modes are adopted;
in the invention, a mode of monitoring by combining remote monitoring, infrared imaging and micro-pressure sensing is adopted, so that a measured person can have a plurality of variables monitored in one-time monitoring, and the breathing condition in the sleeping process can be monitored safely, effectively and non-intrusively.
The invention also adopts a micro-pressure sensor for monitoring to prevent the following phenomena: when sleeping, the quilt covers the head to influence the recognition function of the camera. The operation and monitoring system of the invention is not in contact with the testee, and the pressure sensor is made of flexible material, so that the testee is in a natural sleep state, and the monitoring result is more accurate.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (9)
1. A non-interfering early warning system for apnea in sleep, comprising: the system comprises a control center, an infrared temperature measurement module, a micro-pressure sensing module, an alarm module and a user terminal;
the infrared temperature measurement module, the micro-pressure sensing module, the alarm module and the user terminal are all connected with the control center;
the system comprises an infrared temperature measurement module, a micro-pressure sensing module, an alarm module and a user terminal, wherein the infrared temperature measurement module is used for collecting thermal imaging images, the micro-pressure sensing module is used for collecting pressure data, the alarm module is used for transmitting alarm signals of apnea, and the user terminal is used for displaying real-time pressure data, real-time thermal imaging images and alarm information;
the control center is used for receiving the thermal imaging image and the pressure data, carrying out target tracking on the thermal imaging image flow, classifying and recording sleeping postures and judging whether breathing interference action occurs or not;
judging and analyzing the pressure value detected by the micro-pressure sensing module, judging whether the breath of the user is normal according to the pressure change value between two breaths, judging whether the sleep breath is suspended or not by combining the breath interference action, and outputting an alarm signal.
2. The non-interfering early warning system for sleep apnea, according to claim 1, further comprising a camera module, wherein the camera module is connected to the control center, and the camera module is used for collecting camera video stream data.
3. The system of claim 1, wherein the pressure sensor is made of a flexible material.
4. The early warning method of a non-interfering apnea early warning system according to any one of claims 1 to 3, comprising the steps of:
carrying out target tracking on a thermal imaging image stream acquired by an infrared temperature measurement module, constructing a BP neural network for sleep posture classification training, obtaining a sleep posture classifier, classifying and recording the sleep posture by the sleep posture classifier, and judging whether the current sleep posture is the same as the sleep posture at the last moment;
detecting a face area as an interested area of the infrared temperature measurement module, acquiring an average gray value of the interested area, performing Kalman filtering on the average gray value, and calculating the time of adjacent wave crests of filtered data to be used as a breathing cycle;
setting the number n of breathing cycles, and if the number n of the calculated breathing cycles exceeds the set normal breathing cycle range, determining that the breathing is abnormal;
judging and analyzing the pressure value detected by the micro-pressure sensing module, and judging that the breath of the user is normal if the pressure change value between two breaths is smaller than a preset value; if the pressure change value between two breaths is a preset value or exceeds the preset value and the next pressure value from the micro-pressure sensor is not received in the normal breathing time interval, recording the current time;
judging whether the sleeping posture of the current time is the same as the sleeping posture of the previous time by the sleeping posture classifier, and if not, judging that a breathing interference action occurs; if no breathing interference action occurs, the sleep apnea is judged, and an alarm signal is output.
5. The early warning method of the non-interfering early warning system of apnea during sleep of claim 4, wherein said sleeping posture classifier classifies and records sleeping postures, the concrete steps include:
let the set of user's sleep postures be C ═ C1，C2，C3Establishing a corresponding data set, wherein the data set is { supine, lying on the left side, lying on the right side };
the BP neural network is trained by adopting the corresponding data set to obtain a sleeping posture classifier;
the sleeping posture classifier outputs a judgment result, when the sleeping posture at the current time is different from the sleeping posture at the previous time, the time t when the sleeping posture changes is stored, and finally the ordered vector S of the sleeping posture change time in the sleeping process is obtainedall＝[t1，t2，…tN]。
6. The early warning method of the non-interfering sleep apnea early warning system according to claim 4, wherein the average gray value of the region of interest is obtained by a specific calculation formula:
where rm, rn are the width and height of the region of interest, respectively, and k represents an arbitrary time instant.
7. The early warning method of the non-interfering sleep apnea early warning system according to claim 4, wherein the average gray value is subjected to Kalman filtering, and the specific calculation formula is as follows:
zk＝ASk+υk
Pk|k-1＝APk-1|k-1AT+Q
Kk＝Pk|k-1AT(APk|k-1AT+R)-1
Pk|k＝(I-KkA)Pk|k-1
wherein A represents a measurement state transition matrix, upsilonkN (0, R) represents the observed noise satisfying the Gaussian distribution, R represents the measurement noise covariance, zkRepresents the observed value at time k and,
representing the a priori state estimate at time k,
respectively representing the posterior state estimated values of k-1 and k time; pk|k-1Representing the prior estimated covariance, P, of time kk-1|k-1、Pk|kRespectively representing the posterior state estimation covariance of k-1 and k time; q represents the process noise covariance momentArraying; kkRepresenting the kalman gain.
8. The method of claim 7, wherein the time of adjacent peaks of the filtered data is calculated as the breathing cycle, and the peak obtaining step comprises:
at the k-th moment, if satisfied
And is
Then time k
The first peak point is denoted as Cl＝k；
The time difference between two adjacent peaks is the respiratory cycle calculated from the peak point of the first wave, i.e. Tl＝Cl-Cl-1；
Normal breathing cycle range is set to [ T ]low,Thigh]。
9. The method as claimed in claim 1, wherein the output alarm signal is one or more of the following alarm modes:
the method comprises the steps of waking up a user by vibration, notifying family members of the user by a bound mobile phone and notifying a rescue unit at the place by a network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110146421.5A CN112806966B (en) | 2021-02-03 | 2021-02-03 | A non-interference sleep apnea early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110146421.5A CN112806966B (en) | 2021-02-03 | 2021-02-03 | A non-interference sleep apnea early warning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112806966A true CN112806966A (en) | 2021-05-18 |
| CN112806966B CN112806966B (en) | 2022-07-26 |
Family
ID=75860814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110146421.5A Active CN112806966B (en) | 2021-02-03 | 2021-02-03 | A non-interference sleep apnea early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112806966B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113273967A (en) * | 2021-05-20 | 2021-08-20 | 贵州优品睡眠健康产业有限公司 | Sleep sign monitoring system |
| CN114190916A (en) * | 2021-12-07 | 2022-03-18 | 河南省儿童医院郑州儿童医院 | Child respiration monitoring method and system based on fabric sensor |
| CN114909790A (en) * | 2022-03-28 | 2022-08-16 | 青岛海尔空调器有限总公司 | Control method, device and equipment of air conditioner and storage medium |
| WO2023103903A1 (en) * | 2021-12-09 | 2023-06-15 | 南京舒普思达医疗设备有限公司 | Sleep characteristic-based ventilator regulation and control method and system |
| PL441747A1 (en) * | 2022-07-15 | 2024-01-22 | Healthnomic Spółka Akcyjna | System and method for diagnosing obstructive sleep apnoea |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110010014A1 (en) * | 2008-02-25 | 2011-01-13 | Kingsdown, Inc. | Systems and methods for controlling a bedroom environment and for providing sleep data |
| CN202648699U (en) * | 2012-04-20 | 2013-01-02 | 北京西润电子设备有限公司 | Multifunctional home monitoring and nursing network system |
| CN102973273A (en) * | 2012-11-29 | 2013-03-20 | 中国人民解放军第四军医大学 | Sleep respiratory function monitoring system based on infrared radiation detection |
| CN102973244A (en) * | 2012-11-16 | 2013-03-20 | 西南石油大学 | Non-contact type sleep apnea monitoring method based on infrared thermography technology and device |
| CN104504852A (en) * | 2014-10-24 | 2015-04-08 | 天津科技大学 | Image-based forewarning infant safety monitor and infant safety judging method |
| CN104834946A (en) * | 2015-04-09 | 2015-08-12 | 清华大学 | Method and system for non-contact sleep monitoring |
| CN105231995A (en) * | 2015-09-29 | 2016-01-13 | 无锡市润华碳晶地暖设备有限公司 | Sleep system |
| CN108309286A (en) * | 2017-12-15 | 2018-07-24 | 中国人民解放军第二军医大学第二附属医院 | Sleep disturbance detects treatment system |
| CN109310348A (en) * | 2016-05-19 | 2019-02-05 | 汉考克医药公司 | Postural Obstructive Sleep Apnea Detection System |
| CN110313897A (en) * | 2019-07-04 | 2019-10-11 | 合肥赛为智能有限公司 | Sleep monitoring device and its monitoring method based on silica gel air bag |
-
2021
- 2021-02-03 CN CN202110146421.5A patent/CN112806966B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110010014A1 (en) * | 2008-02-25 | 2011-01-13 | Kingsdown, Inc. | Systems and methods for controlling a bedroom environment and for providing sleep data |
| CN202648699U (en) * | 2012-04-20 | 2013-01-02 | 北京西润电子设备有限公司 | Multifunctional home monitoring and nursing network system |
| CN102973244A (en) * | 2012-11-16 | 2013-03-20 | 西南石油大学 | Non-contact type sleep apnea monitoring method based on infrared thermography technology and device |
| CN102973273A (en) * | 2012-11-29 | 2013-03-20 | 中国人民解放军第四军医大学 | Sleep respiratory function monitoring system based on infrared radiation detection |
| CN104504852A (en) * | 2014-10-24 | 2015-04-08 | 天津科技大学 | Image-based forewarning infant safety monitor and infant safety judging method |
| CN104834946A (en) * | 2015-04-09 | 2015-08-12 | 清华大学 | Method and system for non-contact sleep monitoring |
| CN105231995A (en) * | 2015-09-29 | 2016-01-13 | 无锡市润华碳晶地暖设备有限公司 | Sleep system |
| CN109310348A (en) * | 2016-05-19 | 2019-02-05 | 汉考克医药公司 | Postural Obstructive Sleep Apnea Detection System |
| CN108309286A (en) * | 2017-12-15 | 2018-07-24 | 中国人民解放军第二军医大学第二附属医院 | Sleep disturbance detects treatment system |
| CN110313897A (en) * | 2019-07-04 | 2019-10-11 | 合肥赛为智能有限公司 | Sleep monitoring device and its monitoring method based on silica gel air bag |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113273967A (en) * | 2021-05-20 | 2021-08-20 | 贵州优品睡眠健康产业有限公司 | Sleep sign monitoring system |
| CN114190916A (en) * | 2021-12-07 | 2022-03-18 | 河南省儿童医院郑州儿童医院 | Child respiration monitoring method and system based on fabric sensor |
| WO2023103903A1 (en) * | 2021-12-09 | 2023-06-15 | 南京舒普思达医疗设备有限公司 | Sleep characteristic-based ventilator regulation and control method and system |
| CN114909790A (en) * | 2022-03-28 | 2022-08-16 | 青岛海尔空调器有限总公司 | Control method, device and equipment of air conditioner and storage medium |
| CN114909790B (en) * | 2022-03-28 | 2024-04-12 | 青岛海尔空调器有限总公司 | Air conditioning control method, device, equipment and storage medium |
| PL441747A1 (en) * | 2022-07-15 | 2024-01-22 | Healthnomic Spółka Akcyjna | System and method for diagnosing obstructive sleep apnoea |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112806966B (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12016655B2 (en) | Video-based patient monitoring systems and associated methods for detecting and monitoring breathing | |
| CN112806966A (en) | Non-interference type early warning system and method for apnea in sleep | |
| CN106413533B (en) | Apparatus, system and method for detecting apnea of a subject | |
| Jorge et al. | Non-contact monitoring of respiration in the neonatal intensive care unit | |
| US8790269B2 (en) | Monitoring respiration with a thermal imaging system | |
| KR102054213B1 (en) | Respiratory measurement system using thermovision camera | |
| CN108272448B (en) | A non-contact day and night monitoring method for infant physiological parameters | |
| CN104257353A (en) | Sleep apnea syndrome detecting system | |
| CN111248890A (en) | A non-contact heart rate monitoring method and system for newborns based on facial video | |
| CN104083160A (en) | Sleep state monitoring method and device based on machine vision | |
| CN109567756A (en) | A kind of sleep state detection method based on artificial intelligence mattress | |
| Massaroni et al. | Comparison of two methods for estimating respiratory waveforms from videos without contact | |
| CN111544001A (en) | A non-contact apnea detection device and method | |
| Wiede et al. | Remote respiration rate determination in video data-vital parameter extraction based on optical flow and principal component analysis | |
| CN115100159A (en) | Breathing state detection method, device, equipment and storage medium | |
| CN110811547A (en) | Multi-guide sleep monitor and sleep monitoring method | |
| Carter et al. | Deep learning-enabled sleep staging from vital signs and activity measured using a near-infrared video camera | |
| Lorato et al. | Camera-based on-line short cessation of breathing detection | |
| Olvera et al. | Noninvasive monitoring system for early detection of apnea in newborns and infants | |
| CN114652274B (en) | An intelligent sleep monitoring system with three-dimensional and multi-dimensional data | |
| TWI766471B (en) | System capable of detecting sleep breathing intensity based on wavelet transformation and spectral intensity | |
| Hanawa et al. | Nasal cavity detection in facial thermal image for non-contact measurement of breathing | |
| CN111904399A (en) | Breathing monitoring sickbed for old people | |
| US12201435B2 (en) | Vision-based patient stimulus monitoring and response system and method utilizing visual images | |
| KR102427499B1 (en) | Sleep concentration detection system using thermal imaging camera |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xin Xuegang Inventor after: Tang Shengnan Inventor after: Chen Xinlian Inventor after: Yang Xinyi Inventor after: Cai Xiang Inventor after: Huang Shengzhao Inventor after: Zhou Weihao Inventor after: Li Yuanqin Inventor before: Tang Shengnan Inventor before: Xin Xuegang Inventor before: Chen Xinlian Inventor before: Yang Xinyi Inventor before: Cai Xiang Inventor before: Huang Shengzhao Inventor before: Zhou Weihao Inventor before: Li Yuanqin |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |