A non-contact sleep apnea detection method, device and system

Abstract

The embodiment of the present invention discloses a contactless sleep apnea detection method, device and system, the method comprising: performing continuous sampling according to a preset sampling interval within the radar setting range through radar waves; first analyzing and judging whether there is a person within the detection range according to the collected signal, and if there is a person and he has not left the radar setting range, further analyzing and judging whether apnea has occurred; sending the detection result to the management end by wired or wireless means, so that the management end can analyze the detection result and display the status, and when apnea is detected, an alarm is issued, and the detection end is controlled to also display an alarm. Detecting whether a person has apnea in a non-contact manner can prevent suffocation; having a real-time warning function, the efficiency is significantly improved; at the same time, it can automatically detect whether a person exists to avoid false alarms; the apnea detection speed is faster, and apnea can generally be detected in about 3 seconds.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of medical device technology, and specifically to a contactless sleep apnea detection method, device and system. Background Art

[0002] Sleep apnea syndrome is a common sleep disorder in adults. The main cause of this disease is upper airway obstruction. It has many complications such as hypertension, arrhythmia, cardiovascular and cerebrovascular diseases, and respiratory failure. These diseases can cause patients to suffer from sleep defects, reduced work efficiency, reduced memory and reaction ability, and thus increase the incidence of accidents. Apnea is a serious threat to human health, so it is extremely necessary to detect and remotely monitor apnea. For the elderly and infants, because of their limited mobility, they are more likely to suffocate and cannot be warned in time. Therefore, nursing homes, infant confinement care centers, and families are more concerned about the breathing conditions of the elderly and infants. Once apnea occurs, timely intervention is required.

[0003] Currently, hospitals have some wearable devices, such as sleep monitors and ventilators, to collect and analyze the respiratory signals of test objects, such as patients. Such solutions require relatively expensive equipment costs and manpower consumption, and the contact-based respiratory signal collection has a great restraining effect on patients, affecting their sleep quality and thus reducing the accuracy of the test. The detection of smart devices such as mobile phones is also very easy to cause misjudgment because they are non-professional equipment, external interference and inaccurate algorithms.

[0004] In the prior art, there is sleep apnea detection based on chest movement signals, which modulates inaudible sound waves of 18-20kHz through FMCW technology. The resolution of human motion at the same distance is worse than that of 60GHz radar, resulting in poor resolution in actual operation. The accuracy of peak (frequency) calculation is improved by increasing the FFT window sampling processing period, but the real-time performance is very weak and cannot reflect the breathing state at the time in real time, while slowing down the speed of detecting suffocation (pause of breathing). In addition, under the current conditions, if it is not static or not facing the chest cavity, there will be great interference, that is, there will be incorrect or wrong chest movement signal aggregation; the method is mainly used for the detection and analysis of apnea and shallow breathing under static conditions, facing the front of the chest cavity. There is also a respiratory signal acquisition part that uses radar reflection signals to collect the respiratory signals of the detection object, such as a patient lying on a hospital bed or a patient being detected, in real time and contactlessly and transmit them wirelessly. However, this method does not use the phase calculation and difference of the echo and subsequent calculation and judgment. In addition, because of the echo reflection of static objects (such as walls, chairs, etc.), the value after ADC sampling is not accurate. Even if there is no one in the range (there is someone outside the range), the respiratory signal can be detected, that is, the signal may be wrong. Summary of the invention

[0005] To this end, the embodiments of the present invention provide a contactless sleep apnea detection method, device and system to solve the problems of existing sleep apnea detection methods, such as high equipment and labor costs, low accuracy, prone to false alarms, and slow detection of suffocation (apnea).

[0006] In order to achieve the above purpose, the embodiment of the present invention provides the following technical solutions:

[0007] According to a first aspect of an embodiment of the present invention, a contactless sleep apnea detection method is provided, the method comprising:

[0008] Continuous sampling is performed by radar waves within the radar setting range according to the preset sampling interval;

[0009] Firstly, the collected signals are analyzed to determine whether there is anyone in the detection range. If there is someone and he / she has not left the radar setting range, further analysis is performed to determine whether apnea occurs.

[0010] The detection results are sent to the management end via wired or wireless means so that the management end can analyze the detection results and display the status. When apnea is detected, an alarm is issued and the detection end is controlled to also display an alarm.

[0011] Furthermore, based on the collected signals, we first analyze and determine whether there is anyone within the detection range. If there is someone and he has not left the radar setting range, we specifically include:

[0012] Perform Fourier transform on the ADC sampling data to obtain a series of complex data;

[0013] If the amplitude A of a certain number of frames in a continuous plurality of frames of data is greater than the first preset threshold, it is determined that there is a person, where The current frame is the nth frame, the previous frame is the mth frame, and the plural form of the nth frame data is a n +b n i, the plural form of the mth frame data is a m +b m i;

[0014] The distance, speed and angle between the person and the radar are calculated based on the radar reflection wave to determine whether the person has left the range set by the radar.

[0015] Further, analyzing and determining whether apnea occurs specifically includes:

[0016] Compare the amplitudes of multiple frames of data obtained by continuous sampling, and perform arc tangent operation on the complex number corresponding to the larger amplitude value to obtain the phase of the current frame;

[0017] Subtract the phase of the previous frame from the phase of the current frame to get the phase difference, and filter out the noise to get the phase difference value B 1 ;

[0018] For the phase difference value B 1 Perform low-pass filtering to obtain the phase difference value C 1 ;

[0019] If we continue to sample the phase difference value B of the continuous n frames 1 , B 2 , ..., Bn are all lower than the second preset threshold, and the phase difference C 1 , C 2 , ..., Cn is lower than the third preset threshold, it is determined that apnea occurs.

[0020] Furthermore, the method further comprises:

[0021] Breath-holding verification training is performed for different types of people to obtain second preset thresholds and third preset thresholds that match the different types of people.

[0022] Furthermore, the different types of people are divided into children, adults and the elderly according to age groups.

[0023] According to a second aspect of an embodiment of the present invention, a contactless sleep apnea detection device is provided, the device comprising:

[0024] A radar sensing radio frequency module is used to continuously sample at a preset sampling interval within a radar setting range through radar waves;

[0025] The processing module is used to first analyze and determine whether there is a person within the detection range according to the collected signal. If there is a person and he has not left the radar setting range, further analyze and determine whether apnea occurs;

[0026] The transmission module is used to send the detection results to the management end via wired or wireless means so that the management end can analyze the detection results and display the status. When apnea is detected, an alarm is issued and the detection end is controlled to also display an alarm.

[0027] According to a third aspect of an embodiment of the present invention, a contactless sleep apnea detection system is proposed, characterized in that the system comprises a contactless sleep apnea detection device as described above and a management terminal connected to the detection device.

[0028] According to a fourth aspect of an embodiment of the present invention, a computer storage medium is provided, characterized in that the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a contactless sleep apnea detection device to execute the contactless sleep apnea detection method as described in any of the above items.

[0029] The embodiments of the present invention have the following advantages:

[0030] The embodiment of the present invention proposes a contactless sleep apnea detection method, device and system, the method comprising: continuous sampling at a preset sampling interval within the radar setting range by radar waves; firstly analyzing and judging whether there is a person within the detection range according to the collected signal, and if there is a person and he has not left the radar setting range, further analyzing and judging whether apnea has occurred; sending the detection result to the management end by wired or wireless means, so that the management end can analyze the detection result and display the status, and when apnea is detected, an alarm is issued, and the detection end is controlled to display the alarm in the same manner. Detecting whether a person has apnea in a non-contact manner can prevent suffocation; having a real-time warning function, the efficiency is significantly improved; at the same time, it can automatically detect whether a person exists to avoid false alarms; the apnea detection speed is faster, and apnea can generally be detected in about 3 seconds. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0032] Figure 1 A schematic flow chart of a contactless sleep apnea detection method provided in Example 1 of the present invention;

[0033] Figure 2 This is a structural schematic diagram of a contactless sleep apnea detection system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0034] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Example 1

[0036] like Figure 1 As shown, this embodiment proposes a contactless sleep apnea detection method, the method comprising:

[0037] S100, continuously sampling according to a preset sampling interval within a radar setting range through radar waves;

[0038] S200, first analyzing and determining whether there is anyone within the detection range according to the collected signal, and if there is someone and he / she has not left the radar setting range, further analyzing and determining whether apnea occurs;

[0039] S300, sending the detection results to the management end via wired or wireless means, so that the management end can analyze the detection results and display the status, and issue an alarm when apnea is detected, and control the detection end to also display an alarm.

[0040] Furthermore, based on the collected signals, we first analyze and determine whether there is anyone within the detection range. If there is someone and he has not left the radar setting range, we specifically include:

[0041] Perform Fourier transform on the ADC sampling data to obtain a series of complex data;

[0042] If the amplitude A of a certain number of frames in a continuous plurality of frames of data is greater than the first preset threshold, it is determined that there is a person, where The current frame is the nth frame, the previous frame is the mth frame, and the plural form of the nth frame data is a n +b n i, the plural form of the mth frame data is a m +b m i;

[0043] The distance, speed and angle between the person and the radar are calculated based on the radar reflection wave to determine whether the person has left the range set by the radar.

[0044] Specifically, for example, within the detection range of 0.1 meters to 5 meters set by the radar, many complex values ​​will be obtained. The sets of two complex values ​​of the current frame and the previous frame are retained, and the value of the amplitude A of multiple frames is calculated to be the largest, which indicates where the person may be. Exemplarily, if 80 frames of data in 100 consecutive frames are greater than 200 (or a certain threshold set by other settings) or 50 frames of data are greater than 300 (or a certain threshold set by other settings), and the distance of the radar is within the range, it is judged that there is a person; further, if 80 frames of data in 100 consecutive frames are greater than 200 (or a certain threshold set by other settings), it is judged that the human body has micro-movement; if 50 frames of data in 100 consecutive frames are greater than 300 (or a certain threshold set by other settings), it is judged that the human body has a large movement. The time of each frame can be set, for example, one frame is 50 milliseconds. In addition, the threshold set here is also proportional to the performance of the actual antenna design. The better the performance, the better the reflected wave, so the set threshold needs to be partially trained and adjusted.

[0045] Further, analyzing and determining whether apnea occurs specifically includes:

[0046] Compare the amplitudes of multiple frames of data obtained by continuous sampling, and perform arc tangent operation on the complex number corresponding to the larger amplitude value to obtain the phase of the current frame;

[0047] Subtract the phase of the previous frame from the phase of the current frame to get the phase difference, and filter out the noise to get the phase difference value B 1 ;

[0048] For the phase difference value B 1 Perform low-pass filtering to obtain the phase difference value C 1 ;

[0049] If we continue to sample the phase difference value B of the continuous n frames 1 , B 2 ,……,B n are lower than the second preset threshold, and the phase difference C 1 , C 2 ,……,C n If the breathing rate is lower than the third preset threshold, it is determined that apnea has occurred.

[0050] Specifically, the presence of a person can be determined by the larger amplitude value of multiple consecutive frames of data, and the point can be continuously sampled, and the phase difference of multiple consecutive frames can be calculated to determine whether the person has apnea. The filtering can be processed by IIR filtering. For a specific operation example, the typical breathing rate of a normal person is about 12-20 times per minute, and that of a child is about 20-30 times. The corresponding breathing of the filter can be set to 3 to 36 times per minute, that is, the frequency per second is 0.05-0.6Hz, so as to filter out all ranges of the true value as much as possible.

[0051] Exemplarily, if B1, B2, ..., B40 of 40 consecutive frames are all less than 0.3, C1, C2, ..., C40 of 40 consecutive frames are all less than 0.05, and the person has not left the detection area, it is determined that respiratory arrest (short-term suffocation) has occurred.

[0052] Furthermore, since the chest cavity moves back and forth during normal breathing, regardless of whether the human body has large movements, when a certain number of frames (accounting for no less than 95%) of the phase difference value B and the phase difference value C in a continuous multi-frame data are both less than the corresponding preset threshold, it is judged as apnea. For example, if there are 76 frames (accounting for about 95% of the cumulative number of frames) of B values ​​and 76 frames of C values ​​in 80 consecutive frames that are less than the corresponding threshold, it is judged as apnea.

[0053] Furthermore, the method also includes: performing breath-holding verification training for different types of people, and obtaining second preset thresholds and third preset thresholds that match the different types of people.

[0054] Furthermore, the different types of people are divided into children, adults, and the elderly according to age. Different groups of people use different thresholds after observation training, and the judgment results will be faster and more accurate. In addition, by modifying parameters such as thresholds, the method can also be applied to large pets at home.

[0055] When apnea is detected, an alarm is immediately displayed on the management end, and the detection end is controlled to issue an audible and visual alarm.

[0056] The present embodiment proposes a non-contact sleep apnea detection method, which uses radar waves to continuously sample within the radar setting range at a preset sampling interval; firstly analyze and determine whether there is anyone within the detection range based on the collected signal, and if there is someone and he has not left the radar setting range, further analyze and determine whether apnea has occurred; send the detection results to the management end via wired or wireless means, so that the management end can parse the detection results and display the status, and issue an alarm when apnea is detected, and control the detection end to also display an alarm. Detecting whether a person has apnea in a non-contact manner can prevent suffocation; it has a real-time warning function, which significantly improves efficiency; and it can automatically detect whether a person exists to avoid false alarms.

[0057] Example 2

[0058] Corresponding to the above-mentioned embodiment 1, this embodiment proposes a non-contact sleep apnea detection device, the device comprising:

[0059] A radar sensing radio frequency module is used to continuously sample at a preset sampling interval within a radar setting range through radar waves;

[0060] The processing module is used to first analyze and determine whether there is a person within the detection range according to the collected signal. If there is a person and he has not left the radar setting range, further analyze and determine whether apnea occurs;

[0061] The transmission module is used to send the detection results to the management end via wired or wireless means so that the management end can analyze the detection results and display the status. When apnea is detected, an alarm is issued and the detection end is controlled to also display an alarm.

[0062] The functions performed by the various components in the non-contact sleep apnea detection device provided by the embodiment of the present invention have been described in detail in the above embodiment 1, so they will not be described in detail here.

[0063] Example 3

[0064] Corresponding to the above-mentioned embodiment 2, the third aspect of the embodiment of the present invention provides a contactless sleep apnea detection system, such as Figure 2 As shown, the system includes a contactless sleep apnea detection device as described above and a management terminal connected to the detection device.

[0065] Example 4

[0066] Corresponding to the above embodiment, this embodiment proposes a computer storage medium, which contains one or more program instructions, and the one or more program instructions are used to be executed by a non-contact sleep apnea detection device as the method of embodiment 1.

[0067] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A non-contact sleep apnea detection method, characterized in that: The method comprises: Continuous sampling is performed by radar waves within the radar setting range according to the preset sampling interval; Firstly, the collected signals are analyzed to determine whether there is anyone in the detection range. If there is someone and he / she has not left the radar setting range, further analysis is performed to determine whether apnea occurs. The detection results are sent to the management end via wired or wireless means, so that the management end can analyze the detection results and display the status. When apnea is detected, an alarm is issued, and the detection end is controlled to also display an alarm; According to the collected signal, we first analyze and determine whether there is anyone within the detection range. If there is someone and he has not left the radar setting range, the specific steps include: Perform Fourier transform on the ADC sampling data to obtain a series of complex data; If the amplitude A of a preset number of frames in a continuous plurality of frames of data is greater than the first preset threshold, it is determined that there is a person, where The current frame is the nth frame, the previous frame is the mth frame, and the plural form of the nth frame data is a n +b n i, the plural form of the mth frame data is a m +b m i; Calculate the distance, speed and angle of the person from the radar based on the radar reflection wave to determine whether the person has left the range set by the radar; Analyze and determine whether apnea has occurred, including: Comparing the amplitudes of multiple frames of data obtained by continuous sampling, taking the complex number corresponding to the amplitude greater than the first preset threshold and performing an inverse tangent operation to obtain the phase of the current frame; The phase difference is obtained by subtracting the phase of the previous frame from the phase of the current frame, and the noise is filtered out to obtain the phase difference value B1; Performing low-pass filtering on the phase difference value B1 to obtain a phase difference value C1; If the phase difference values ​​B1, B2, ..., Bn of the continuous n frames obtained by continued sampling are all lower than the second preset threshold, and the phase difference values ​​C1, C2, ..., Cn are lower than the third preset threshold, it is determined that apnea occurs.

2. A non-contact sleep apnea detection method according to claim 1, characterized in that: The method further comprises: Breath-holding verification training is performed for different types of people to obtain second preset thresholds and third preset thresholds that match the different types of people.

3. A non-contact sleep apnea detection method according to claim 2, characterized in that: The different types of people are divided into children, adults and the elderly according to age groups.

4. A non-contact sleep apnea detection device, characterized in that: The device comprises: A radar sensing radio frequency module is used to continuously sample at a preset sampling interval within a radar setting range through radar waves; The processing module is used to first analyze and determine whether there is a person within the detection range according to the collected signal. If there is a person and he has not left the radar setting range, further analyze and determine whether apnea occurs; The transmission module is used to send the detection results to the management end by wired or wireless means, so that the management end can analyze the detection results and display the status, and issue an alarm when apnea is detected, and control the detection end to also display the alarm; According to the collected signal, we first analyze and determine whether there is anyone within the detection range. If there is someone and he has not left the radar setting range, the specific steps include: Perform Fourier transform on the ADC sampling data to obtain a series of complex data; If the amplitude A of a preset number of frames in a continuous plurality of frames of data is greater than the first preset threshold, it is determined that there is a person, where The current frame is the nth frame, the previous frame is the mth frame, and the plural form of the nth frame data is a n +b n i, the plural form of the mth frame data is a m +b m i; Calculate the distance, speed and angle of the person from the radar based on the radar reflection wave to determine whether the person has left the range set by the radar; Analyze and determine whether apnea has occurred, including: Comparing the amplitudes of multiple frames of data obtained by continuous sampling, taking the complex number corresponding to the amplitude greater than the first preset threshold and performing an inverse tangent operation to obtain the phase of the current frame; The phase difference is obtained by subtracting the phase of the previous frame from the phase of the current frame, and the noise is filtered out to obtain the phase difference value B1; Performing low-pass filtering on the phase difference value B1 to obtain a phase difference value C1; If the phase difference values ​​B1, B2, ..., Bn of the continuous n frames obtained by continued sampling are all lower than the second preset threshold, and the phase difference values ​​C1, C2, ..., Cn are lower than the third preset threshold, it is determined that apnea occurs.

5. A contactless sleep apnea detection system, characterized in that: The system comprises a contactless sleep apnea detection device as claimed in claim 4 and a management terminal connected to the detection device.

6. A computer storage medium, characterized in that: The computer storage medium includes one or more program instructions, and the one or more program instructions are used to be executed by a contactless sleep apnea detection device to perform the method according to any one of claims 1 to 3.

Images