CN114767064A - Child sleep monitoring method and system and electronic device - Google Patents

Abstract

The invention discloses a method for monitoring sleep of children, belonging to the field of medical signal processing. The heart rate signal of the sensor is processed and the sleep situation is comprehensively judged. By placing sensors in four positions on the two upper arms, chest and abdomen, when the sleeping position changes to compress one sensor, the other sensors can continue to work to prevent false alarms; by placing sensors on the chest Sensors are installed on the clothes corresponding to the abdomen, which can monitor breathing problems caused by sleep obstruction; early warning of life-threatening events, reminders and records of general negative events; good ability to distinguish sleeping positions, and low false alarms. The present invention also relates to a children's sleep monitoring system and device for implementing the above-mentioned children's sleep monitoring method.

Description

A child sleep monitoring method, system and electronic device

technical field

The present invention relates to the field of medical monitoring, in particular to a method, system and electronic device for monitoring children's sleep.

Background technique

Sleep is very important for physical and mental health, especially for growing children. But there are huge problems with sleep monitoring in children. Due to the slender wrist of children, the wearable watch is easy to slip off and leak light; children's heart power is small, the heart rate is fast, and the sleeping position is not fixed. Submerged and disturbed by adults; camera-based/radar sleep monitoring systems are also affected by sleeping posture and have limited accuracy when covered with thick quilts.

SUMMARY OF THE INVENTION

In order to overcome the deficiencies of the prior art, one of the objectives of the present invention is to provide a child sleep monitoring method that is not affected by sleeping posture and environment and has high measurement accuracy.

In order to overcome the deficiencies of the prior art, the second purpose of the present invention is to provide a child sleep monitoring system that is not affected by sleeping posture and environment and has high measurement accuracy.

In order to overcome the deficiencies of the prior art, the third purpose of the present invention is to provide a child sleep monitoring device that is not affected by sleeping posture and environment and has high measurement accuracy.

One of the objects of the present invention adopts the following technical scheme to realize:

A method for monitoring sleep in children, comprising the following steps:

Install the triaxial acceleration sensor: Install the 4 triaxial acceleration sensors on the outside of the clothes on the upper arms, chest and abdomen respectively;

Collecting information: Each of the three-axis acceleration sensors collects respiration and heart rate signals:

Process the breathing signal of each of the three-axis acceleration sensors: filter the breathing signal of each of the three-axis acceleration sensors, and perform Fourier transform on the filtered signal. When the transformed signal has a breathing wave , obtain and record the breathing waveform through meyer wavelet transformation, when the transformed signal does not have breathing wave, judge whether it is in a compressed state, in a breathing disorder or in a body motion state through the strength and comparison of the overall signal;

Process the heart rate signal of each of the three-axis acceleration sensors: filter the heart rate of each of the three-axis acceleration sensors, and perform Fourier transform on the filtered signal. When the transformed signal has a heart rate cycle, Extract the periodic heart rate, when the transformed signal does not have a heart rate period, judge whether it is in a compressed state by the strength of the overall signal or calculate the periodicity of the heartbeat by distinguishing the energy density;

Comprehensive judgment of sleep situation: discard the breathing signals and heart rate signals of the four triaxial acceleration sensors in the compressed state, and comprehensively analyze the remaining signals to judge whether the child is in a state of irregular body movement, respiratory obstruction or normal state, and respectively Irregular body movement state and respiratory obstruction will be warned, and the normal state will be recorded.

Further, in the step of comprehensively judging the sleep situation, judging respiratory obstruction is determined by three-axis acceleration sensors in the chest and abdomen, and when the thorax expands and the abdomen contracts, it is breathing obstruction.

Further, in the step of processing the heart rate signal of each of the three-axis acceleration sensors, it is determined whether there is a heart rate cycle by whether there is a significant peak value in the transformed signal.

其中I_e为某时刻的信号强度，p_i为出现I_e的概率，H_s为特定时间区间的熵值，通过滑窗计算固定时间内的熵值，画出熵值波动曲线，并对其周期性进行测评(频域变换并寻找显著尖峰)，如能找到明显周期性，则采用熵的方式来获得心率。Further, in the step of processing the heart rate signal of each of the three-axis acceleration sensors, distinguishing the heartbeat calculation period by energy density is specifically: then try to obtain the heart rate by means of information entropy, and the entropy calculation formula is:

where I _e is the signal strength at a certain time, pi is the probability of I _{e appearing, H s is} the entropy value in a specific time interval, the entropy value in a fixed time is calculated through the sliding window, the entropy value fluctuation curve is drawn, and the Periodic evaluation (frequency domain transformation and looking for significant spikes), if obvious periodicity can be found, the entropy method is used to obtain the heart rate.

Further, in the step of comprehensively judging the sleep situation, the recording of the normal state is specifically: the final breathing signal is obtained by weighting the data of the four triaxial acceleration sensors.

Further, in the step of comprehensively judging the sleep situation, the recording of the normal state is specifically: the final heart rate signal is obtained by weighting the data of the four triaxial acceleration sensors through Kalman filtering.

Further, in the step of comprehensively judging the sleep situation, when the child is in a state of respiratory obstruction, when the respiratory obstruction is frequent but the duration is short, the child is reminded to change the body position; when the respiratory obstruction persists and the heart rate is weakened, an early warning is given.

Further, in the process of filtering the breathing signal of each of the three-axis acceleration sensors, the reserved signal is 0.13-0.66Hz, that is, 7.8-39.6bpm; when filtering the heart rate signal of each of the three-axis acceleration sensors In the process, the first step separates the 4-11Hz signal, and the second step retains the signal at 0.8-3.5Hz, that is, 48-210bpm.

The second purpose of the present invention adopts the following technical scheme to realize:

A child sleep monitoring system is used for implementing any one of the above-mentioned child sleep monitoring methods.

The third purpose of the present invention adopts the following technical scheme to realize:

A sleep monitoring setup for children, including

four triaxial acceleration sensors, the four triaxial acceleration sensors are respectively installed outside the clothes of the children's upper arms, chest and abdomen;

processor;

a memory in communication with the processor;

The memory stores data collected by the four three-axis acceleration sensors and instructions executable by the processor, where the instructions are executed by the processor to implement any one of the above-mentioned methods for monitoring sleep in children.

Compared with the prior art, the child sleep monitoring method of the present invention places sensors at four positions on the two upper arms, the chest and the abdomen. When the sleeping position changes to compress one sensor, the other sensors can continue to work to prevent false alarms; by placing sensors on the chest and abdomen Sensors are installed on the corresponding clothing, which can monitor breathing problems caused by sleep obstruction; have a good ability to distinguish apnea, shortness of breath, and respiratory obstruction; give early warning of life-threatening events, and remind and record general negative events; Good discrimination ability for sleeping positions (left and right lateral position, prone position, etc.), low false alarm (compared to radar waves and other means); good measurement ability for heart rate and pulse intensity, self-correction of measurement through sleeping position; Through the analysis of body movement, respiration, and heart rate, data related to sleep quality is obtained. Due to the light weight of children, the use of pressure sensor technology mode will result in a low signal-to-noise ratio, but the acceleration sensor measurement will not be affected.

Description of drawings

Fig. 1 is the flow chart of the children's sleep monitoring method of the present invention;

Fig. 2 is a flow chart of processing the breathing signal of each three-axis acceleration sensor;

3 is a flowchart of processing the heart rate signal of each of the three-axis acceleration sensors;

Fig. 4 is the flow chart of comprehensively judging sleep situation;

5 is a schematic diagram of the implementation of the child sleep monitoring method of the present invention;

6 is a perspective view of the patch;

Fig. 7 is the original data of respiration signal;

Fig. 8 is the respiration waveform after the respiration signal is transformed by meyer wavelet.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be another intermediate component through which it is fixed. When a component is said to be "connected" to another component, it can be directly connected to the other component or there may be another intermediate component present at the same time. When a component is said to be "disposed on" another component, it may be directly disposed on the other component or there may be another intermediate component present at the same time. The terms "vertical," "horizontal," "left," "right," and similar expressions are used herein for illustrative purposes only.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Fig. 1 to Fig. 4 are the flow charts of the children's sleep monitoring method of the present invention, and the children's sleep monitoring method comprises the following steps:

Install the triaxial acceleration sensor: Install the 4 triaxial acceleration sensors on the outside of the clothes on the upper arms, chest and abdomen respectively;

Collected information: Each three-axis acceleration sensor collects respiration and heart rate signals:

Process the breathing signal of each three-axis acceleration sensor: filter the breathing signal of each of the three-axis acceleration sensors, perform Fourier transform on the filtered signal, and when the transformed signal has a breathing wave, pass Meyer wavelet transform is used to obtain and record the respiratory waveform (see Figure 7-8, which is a comparison diagram of the signal before and after the meyer wavelet transform). When there is no respiratory wave in the transformed signal, it is judged by the strength of the overall signal that it is in a compressed state. , in a breathing disorder or in a state of physical activity;

Process the heart rate signal of each of the three-axis acceleration sensors: filter the heart rate of each of the three-axis acceleration sensors, and perform Fourier transform on the filtered signal. When the transformed signal has a heart rate cycle, Extract the periodic heart rate, when the transformed signal does not have a heart rate period, judge whether it is in a compressed state by the strength of the overall signal or calculate the periodicity of the heartbeat by distinguishing the energy density;

Comprehensive judgment of sleep situation: discard the breathing signals and heart rate signals of the four triaxial acceleration sensors in the compressed state, and comprehensively analyze the remaining signals to judge whether the child is in a state of irregular body movement, respiratory obstruction or normal state, and respectively Irregular body movement state and respiratory obstruction are warned, and the normal state is recorded.

The steps of installing the three-axis acceleration sensor are shown in Figure 5, specifically: the three-axis acceleration sensor adopts the method of patch (as shown in Figure 6), the x-axis specifically refers to the direction that the dial surface is perpendicular to the arm, and the y-axis refers to the direction of the arm. The patch is parallel to the direction of the arm, and the z-axis is specifically the direction perpendicular to the patch face. Each patch contains a three-axis acceleration sensor, which can sense the orientation and vibration of the patch. The sampling rate is 50Hz, the measurement range is ±1g, and the accuracy is set to 14 bits.

Four triaxial accelerometers were installed on the outside of the clothing on the two upper arms, the chest and the abdomen, respectively. In the present application, four triaxial acceleration sensors are installed on the outside of the clothes on the two upper arms, the chest and the abdomen, respectively. Compared with the wrist, the patch is more suitable on the chest and upper arm. If the patch is placed on the wrist, such as a smart watch, the measurement of respiratory data is degraded. The optimal measurement point for respiration is the thoracic region. There are some technologies that put pressure sensors (such as PVDF, pressure film) on the chest, but because the pressure sensors need to be close to the skin, the tight fit is not comfortable and affects sleep. The acceleration sensor is not limited by this, the clothing does not need to be tight, and the sensor is placed on the chest, upper arm, and abdomen, which does not limit the movement of the chest during breathing. At present, the accelerometer hardware used in smart watches and wristbands can achieve high accuracy in hardware technology. However, due to the need to consider strenuous exercise scenarios and data storage in daily activities, the measurement range of most product designs is as high as ±16g, so the final resolution The rate is only 1mg-16mg, it cannot make a fine measurement of the heartbeat intensity, and the signal-to-noise ratio is low in the non-tight situation. The present invention uses the patch only for sleep, can limit the measurement range to ±1g, still collects common 14-bit data, and can measure the acceleration of 0.1mg at a minimum, can reduce restrictions on the texture of pajamas, and reduce the cost of the entire system ( Only the patch is provided, no special underwear material is required).

Changes in sleeping position will compress the patch, at which time the accuracy of respiration measurement decreases, so the patch needs to be placed in four positions to prevent false alarms. When the chest is compressed, the frequency spectrum can be analyzed to determine the significance of the breathing peak. When the amplitude of the breathing wave is obviously suppressed, jump to the sensor of the upper arm. The data processing method of the upper arm is the same as that of the chest. In the sleep state, it is extremely unlikely that the chest, abdomen, and arms on both sides are simultaneously pressed, so the patent of the present invention can avoid abnormal breathing data and false warnings caused by the sleeping position. Another advantage of this design is that when the chest breathing wave is not periodic, the other three patches can be used to determine whether there is current physical movement or a synchronized breathing irregularity event.

A patch placed on the abdomen is mainly used to monitor breathing problems caused by sleep obstruction. The gold standard for measuring respiration is nasal airflow, typically accompanied by periodic thoracic movements. However, in some patients with respiratory obstruction, although they try to breathe (thoracic rise and fall), the airflow is very small, resulting in a decrease in blood oxygen. One of the methods to distinguish respiratory obstruction is to measure the movement of the chest and abdomen. If the thorax and the abdomen expand simultaneously, it is normal breathing. If the chest expands and the abdomen contracts, it is respiratory obstruction. Because the abdominal patch is only to distinguish whether the breathing is blocked, it does not need to be close to the skin and does not produce any resistance to breathing. There is another advantage to abdominal measurements. That is, there are large blood vessels in the abdomen, and there is no rib blockage. When the blood vessels are pulsating, there is still vibration perpendicular to the abdomen, which can complement the heart vibration transmitted by the body and reduce false alarms. The vascular pulsation has a larger amplitude when it is slightly compressed (refer to the upper arm sphygmomanometer, when the external pressure reaches the average blood pressure, the vascular pulsation amplitude is the largest), so even when lying prone, it is possible to distinguish whether there is a risk of cardiac arrest, Dramatically reduce the false alarm rate for a single chest patch.

The steps of collecting information are as follows: measure the breathing rate of each patch independently, because the sleep breathing component is concentrated at 0.13-0.66 Hz, ie, 7.8-39.6 bpm, and the signal outside the frequency band is regarded as noise. Each patch independently measures the heart rate. Children's heart rate is faster than adults, so the heart rate window is set to 0.8-3.5Hz, that is, 48-210bpm, which can be individually adjusted according to the user's age. Due to the elastic vibration of the body caused by each heart beat The signal is between 4-11Hz. Before calculating the heart rate, the external interference is eliminated by band-pass filtering of 4-11Hz, and then the second band-pass filtering is performed through the heart rate window (0.8-3.5Hz), which can effectively obtain the stable signal. heart rate signal

The specific steps of processing the breathing signal of each triaxial acceleration sensor are as follows: in the filtering process, the reserved signal is 0.13-0.66Hz, that is, 7.8-39.6bpm; the Fourier transform window is a 30s window. Whether there is a breathing wave is judged by whether there is a significant peak. The strength of the overall signal is judged by whether the maximum amplitude is less than 25 mg.

The steps of processing the heart rate signal of each of the three-axis acceleration sensors are as follows: in the filtering process, the first step is to separate the 4-11Hz signal, and the external interference is eliminated through 4-11Hz bandpass filtering, and the second step retains the signal. At 0.8-3.5Hz, ie 48-210bpm. The window of the Fourier transform is a window of 10s. The presence or absence of a heart rate cycle is judged by the presence of significant peaks. The strength of the overall signal is judged by whether the maximum amplitude is less than 2 mg. The specific calculation of the periodicity of heartbeat by energy density is: Then try to obtain the heart rate by means of information entropy. The calculation formula of entropy is:

Calculate the entropy value in a fixed time through the sliding window, draw the entropy value fluctuation curve, and evaluate its periodicity. If obvious periodicity can be found, the entropy method is used to obtain the heart rate.

Comprehensively judging sleep conditions also includes: four-patch breathing, heart rate data integration steps, four-patch breathing, heart rate data integration steps are: there is a certain difference between the heart rate and breathing output by each sensor, and due to different data quality, breathing It is also different from the error of heart rate extraction. In order to minimize the measurement error, Kalman filtering and data quality weighting are adopted for integration.

By comparing with the gold standard, we can predict the quality of the data, that is, how much the error of a single measurement will be under certain noise and spectral dispersion. The larger the error, the less trustworthy the data and the lower the weight. Since respiration can undergo abrupt changes (such as a sudden decrease to 0, holding your breath), Kalman filtering based on time series is not applicable, and the final measured value of respiration is weighted by four sensors.

Since the amplitude of heart rate is weaker and the range of variation is limited, Kalman filtering steps can be added. In the time series, the heart rate data output by each sensor is composed of the previous data and the change trend, and the change trend generally conforms to the Gaussian distribution, that is, the heart rate is unlikely to undergo a huge mutation. For example, if the previous data (t-1) is extremely reliable, and the current data (t) is less reliable, it can be passed

HR(t-1)+k _t *(HR _m (t)-HR _m (t-1)) (2)

to predict the current heart rate, and compare it with HR _m (t) to reduce the measurement error, where HR (t-1) is the heart rate value of the previous measurement (heart rate), and HR _m (t) is the current independent measurement of the heart rate value. , the subscript m stands for measurement, which means measurement. k _t is calculated as follows: Suppose P(t|t-1) represents the probability that the previous data is HR _m (t-1) and the current data is HR _m (t), and r _t represents the reliability of the current HR _m measurement , then k _t =P(t|t-1)/[P(t|t-1)+r _t ]. The calculation method of r _t is the ratio of the spectral energy occupied by the peak with the highest amplitude after the Fourier transform to the overall spectral energy. The final measurement of heart rate is weighted by four Kalman filtered heart rates.

Comprehensively judge the less harmful sleep apnea events in the sleep situation, remind parents through mobile phones, slow down through intervention measures such as turning over, and provide relevant data to parents to help determine whether medical intervention is required.

Through the smart sleep patch, the present application can monitor children's sleep in a low-cost and unconstrained manner, without being disturbed by the environment, and being comfortable to use. Good discrimination ability for apnea, shortness of breath, and respiratory obstruction; early warning of life-threatening events, reminders and records of general negative events; good discrimination ability for sleeping positions (left and right lateral positions, prone, etc.), false Low alarm (compared to radar waves and other means); has better measurement ability for heart rate and pulse intensity, and can self-correct the measurement through sleeping posture; obtain sleep quality-related data by analyzing body movement, respiration, and heart rate. Due to the low weight of the child, the technical mode with the pressure sensor will result in a too low signal-to-noise ratio, but the accelerometer measurement will not be affected.

The present application also relates to a child sleep monitoring system for implementing the child sleep monitoring method.

The present application also relates to a child sleep monitoring device for implementing the child sleep monitoring method. The child sleep monitoring device includes four patches, a processor and a memory. The memory is connected in communication with the processor. The memory stores instructions that can be executed by the processor and stores the breathing and heart rate information collected by the four patches. The instructions are executed by the processor. The above method for monitoring sleep in children.

The above examples only represent several embodiments of the present invention, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can be made, which are all equivalent modifications to the above embodiments according to the essential technology of the present invention. and evolution, these all belong to the protection scope of the present invention.

Claims (10)

1. a child sleep monitoring method, is characterized in that, comprises the following steps: Install the triaxial acceleration sensor: Install the 4 triaxial acceleration sensors on the outside of the clothes on the upper arms, chest and abdomen respectively; Collecting information: Each of the three-axis acceleration sensors collects respiration and heart rate signals: Process the breathing signal of each of the three-axis acceleration sensors: filter the breathing signal of each of the three-axis acceleration sensors, and perform Fourier transform on the filtered signal. When the transformed signal has a breathing wave , obtain and record the breathing waveform through meyer wavelet transformation, when the transformed signal does not have breathing wave, judge whether it is in a compressed state, in a breathing disorder or in a body motion state through the strength and comparison of the overall signal; Process the heart rate signal of each of the three-axis acceleration sensors: filter the heart rate of each of the three-axis acceleration sensors, and perform Fourier transform on the filtered signal. When the transformed signal has a heart rate cycle, Extract the periodic heart rate, and when the transformed signal does not have a heart rate period, judge whether it is in a compressed state through the strength and comparison of the overall signal, or determine the periodicity of the heartbeat by energy density; Comprehensive judgment of sleep situation: discard the breathing signals and heart rate signals of the four triaxial acceleration sensors in the compressed state, and comprehensively analyze the remaining signals to judge whether the child is in a state of irregular body movement, respiratory obstruction or normal state, and respectively Irregular body movement state and respiratory obstruction will be warned, and the normal state will be recorded. 2. child sleep monitoring method according to claim 1, is characterized in that: in described comprehensively judging sleep situation step, judging respiratory obstruction is judged by the triaxial acceleration sensor of chest and abdomen, when chest expands, when abdomen shrinks Obstruction of breathing. 3. The sleep monitoring method for children according to claim 1, characterized in that: in the step of processing the heart rate signal of each of the three-axis acceleration sensors, it is judged whether there is a significant peak value in the signal after the frequency domain transformation Heart rate cycle. 4. The sleep monitoring method for children according to claim 3, characterized in that: in the step of processing the heart rate signal of each of the three-axis acceleration sensors, if the frequency domain transformation fails to find a significant peak, then the energy density To try heart rate fitting, the heartbeat calculation periodicity is distinguished by energy density. Specifically: try to obtain heart rate by means of information entropy. The calculation formula of entropy is:

where I _e is the signal strength at a certain time, pi is the probability of I _{e appearing, H s is} the entropy value in a specific time interval, the entropy value in a fixed time is calculated through the sliding window, the entropy value fluctuation curve is drawn, and the Periodic evaluation (frequency domain transformation and looking for significant spikes), if obvious periodicity can be found, the entropy method is used to obtain the heart rate. 5. The method for monitoring sleep in children according to claim 1, wherein in the step of comprehensively judging sleep conditions, the normal state is recorded as follows: the final breathing signal is obtained by weighting the data of four triaxial acceleration sensors, wherein The data weight is the signal quality index, which is calculated by the proportion of the overall frequency domain energy occupied by the frequency domain peaks. 6. child sleep monitoring method according to claim 1 is characterized in that: in comprehensively judging sleep situation step, the normal state is recorded and is specifically: the data of four three-axis acceleration sensors of final heart rate signal are after Kalman filtering. weighted. 7. children's sleep monitoring method according to claim 1 is characterized in that: in comprehensively judging sleep situation step, when children are in a state of respiratory obstruction, when respiratory obstruction is frequent but duration is short, remind children that need to change position; when Provides an early warning when respiratory obstruction persists and the heart rate decreases. 8. The child sleep monitoring method according to claim 1, wherein in the process of filtering the breathing signal of each of the three-axis acceleration sensors, the reserved signal is 0.13-0.66 Hz, that is, 7.8-39.6 bpm; In the process of filtering the heart rate signal of each of the three-axis acceleration sensors, the first step separates the 4-11 Hz signal, and the second step retains the signal at 0.8-3.5 Hz, that is, 48-210 bpm. 9 . A child sleep monitoring system, wherein the child sleep monitoring system is used to implement the child sleep monitoring method according to any one of claims 1 to 8 . 10. A child sleep monitoring setting, characterized in that: comprising: four triaxial acceleration sensors, the four triaxial acceleration sensors are respectively installed outside the clothes of the children's upper arms, chest and abdomen; processor; a memory in communication with the processor; The memory stores data collected by the four triaxial acceleration sensors and instructions executable by the processor to implement the child of any one of claims 1-8 Sleep monitoring methods.

Images