A respiratory rate detection method, device, mobile terminal and storage medium

Abstract

The present invention discloses a respiratory rate detection method, device, mobile terminal and storage medium provided by an embodiment of the present invention, the method comprising: obtaining first multi-axis acceleration data and first angular velocity data of an object to be detected; inputting the first multi-axis acceleration data and the first angular velocity data into a first model, so that the first model generates a one-dimensional respiratory decision signal after multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data; inputting the one-dimensional respiratory decision signal into the first model, so that the first model calculates the respiratory rate of the object to be detected according to the one-dimensional respiratory decision signal. The accuracy of respiratory rate detection can be improved by using the embodiment of the present invention.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a respiratory rate detection method, device, mobile terminal and storage medium. Background Art

[0002] Respiration rate is an important vital sign of human beings, which can be combined with other physiological indicators to indicate the health status of a person or the condition of a patient. Therefore, in daily health monitoring, self-chronic disease monitoring and hospitalization, respiratory rate monitoring equipment that can continuously collect and reliably is an important device in demand.

[0003] However, in the prior art, respiratory rate detection equipment is mostly used in hospital monitoring, such as wearing a tension detection breathing belt or finger clip on the chest, which not only causes discomfort to the patient, but also cannot be carried around for a long time for continuous measurement because it needs to be electrically connected to a large machine such as a monitor. At present, the wrist-worn respiratory rate detection method mainly uses photoplethysmograph (PPG) signals to process and obtain an estimate of the respiratory rate, and the available information is limited in dimension. If the available information dimension is blindly expanded, the interference between multi-dimensional information data is large, and the data collection accuracy is not high, which ultimately leads to the inability to guarantee the accuracy of respiratory rate detection.

[0004] In summary, the respiratory rate detection method in the prior art has the problem of low accuracy. Summary of the invention

[0005] The embodiments of the present invention provide a respiratory rate detection method, device, mobile terminal and storage medium, which improve the accuracy of respiratory rate detection.

[0006] A first aspect of an embodiment of the present application provides a respiratory rate detection method, comprising:

[0007] Acquire first multi-axis acceleration data and first angular velocity data of the object to be detected;

[0008] Inputting the first multi-axis acceleration data and the first angular velocity data into the first model, so that the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data;

[0009] The one-dimensional breathing decision signal is input into the first model, so that the first model calculates the breathing rate of the object to be detected according to the one-dimensional breathing decision signal.

[0010] In a possible implementation manner of the first aspect, the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data, specifically:

[0011] The first model obtains multi-axis respiratory signal characteristics according to the first multi-axis acceleration data and the first angular velocity data;

[0012] After multi-axis fusion processing of multi-axis respiratory signal features, a one-dimensional respiratory decision signal is generated.

[0013] In a possible implementation manner of the first aspect, first multi-axis acceleration data and first angular velocity data of the object to be detected are obtained, specifically:

[0014] Acquire initial angular velocity data and initial multi-axis acceleration data of the object to be detected;

[0015] Calculating a first change rate of the initial angular velocity data and a second change rate of the initial multi-axis acceleration data within a preset time period;

[0016] When the first change rate satisfies a first preset condition, performing noise reduction processing on the initial angular velocity data to generate and acquire first angular velocity data;

[0017] When the second change rate meets the second preset condition, the initial multi-axis acceleration data is subjected to noise reduction processing to generate and acquire first multi-axis acceleration data.

[0018] In a possible implementation manner of the first aspect, the initial angular velocity data is collected by a gyroscope, and the initial multi-axis acceleration data is collected by a multi-axis acceleration sensor, and both the gyroscope and the multi-axis acceleration sensor are arranged at the wrist of the object to be detected.

[0019] In a possible implementation manner of the first aspect, noise reduction processing is performed, specifically:

[0020] calculating a first signal amplitude variance of the initial angular velocity data, and when the first signal amplitude variance does not satisfy a third preset condition, filtering a first noise in the initial angular velocity data to generate the first angular velocity data;

[0021] The second signal amplitude variance of the initial multi-axis acceleration data is calculated. When the second signal amplitude variance does not meet the fourth preset condition, the second noise in the initial multi-axis acceleration data is filtered to generate the first multi-axis acceleration data; wherein the frequencies of the first noise and the second noise are both preset frequencies.

[0022] A second aspect of an embodiment of the present application provides a respiratory rate detection device, including: an acquisition module, a generation module and a detection module;

[0023] Wherein, the acquisition module is used to acquire first multi-axis acceleration data and first angular velocity data of the object to be detected;

[0024] The generating module is used for inputting the first multi-axis acceleration data and the first angular velocity data into the first model, so that the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data;

[0025] The detection module is used to input the one-dimensional breathing decision signal into the first model, so that the first model calculates the breathing rate of the object to be detected according to the one-dimensional breathing decision signal.

[0026] In a possible implementation of the second aspect, the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing on the first multi-axis acceleration data and the first angular velocity data, specifically:

[0027] The first model obtains multi-axis respiratory signal characteristics according to the first multi-axis acceleration data and the first angular velocity data;

[0028] After multi-axis fusion processing of multi-axis respiratory signal features, a one-dimensional respiratory decision signal is generated.

[0029] In a possible implementation manner of the second aspect, first multi-axis acceleration data and first angular velocity data of the object to be detected are obtained, specifically:

[0030] Acquire initial angular velocity data and initial multi-axis acceleration data of the object to be detected;

[0031] Calculating a first change rate of the initial angular velocity data and a second change rate of the initial multi-axis acceleration data within a preset time period;

[0032] When the first change rate satisfies a first preset condition, performing noise reduction processing on the initial angular velocity data to generate and acquire first angular velocity data;

[0033] When the second change rate meets the second preset condition, the initial multi-axis acceleration data is subjected to noise reduction processing to generate and acquire first multi-axis acceleration data.

[0034] A third aspect of an embodiment of the present application provides a mobile terminal, including a processor and a memory, the memory storing a computer-readable program code, and the processor implements the steps of the above-mentioned breathing rate detection method when executing the computer-readable program code.

[0035] A fourth aspect of an embodiment of the present application provides a storage medium, which stores a computer-readable program code. When the computer-readable program code is executed, the steps of the above-mentioned respiratory rate detection method are implemented.

[0036] Compared with the prior art, an embodiment of the present invention provides a respiratory rate detection method, device, mobile terminal and storage medium, the method comprising: acquiring first multi-axis acceleration data and first angular velocity data of an object to be detected; inputting the first multi-axis acceleration data and the first angular velocity data into a first model, so that the first model generates a one-dimensional respiratory decision signal after performing multi-axis fusion processing on the first multi-axis acceleration data and the first angular velocity data; inputting the one-dimensional respiratory decision signal into the first model, so that the first model calculates the respiratory rate of the object to be detected according to the one-dimensional respiratory decision signal.

[0037] Its beneficial effect is that: after the embodiment of the present invention performs multi-axis fusion processing on the first multi-axis acceleration data and the first angular velocity data through the first model, a one-dimensional breathing decision signal is generated; and the breathing rate of the object to be detected is calculated based on the one-dimensional breathing decision signal. The embodiment of the present invention can, on the basis of using multi-dimensional information data (i.e., angular velocity data and multi-axis acceleration data), ensure the multi-dimensionality of the data, and at the same time, by converting the multi-axis breathing signal characteristics into a one-dimensional breathing decision signal, and then calculating the breathing rate based on the one-dimensional breathing decision signal, thereby avoiding interference between multi-dimensional information data, and can further improve the accuracy of breathing rate detection.

[0038] In addition, since in the embodiment of the present invention, the gyroscope and multi-axis acceleration sensor that collect angular velocity data and multi-axis acceleration data are both arranged at the wrist of the object to be detected, the subtle movement information of the wrist driven by the human body when the human body exhales and inhales can be collected, the accuracy of data collection is improved, thereby further ensuring the accuracy of respiratory rate detection; at the same time, wearing the gyroscope and multi-axis acceleration sensor on the wrist improves comfort and portability, realizes 24-hour uninterrupted monitoring of the respiratory rate, and reflects the health status of the user to be detected more timely and effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a respiratory rate detection method provided by one embodiment of the present invention;

[0040] Figure 2 is a structural schematic diagram of a respiratory rate detection device provided by an embodiment of the present invention;

[0041] Figure 3 It is a structural schematic diagram of a respiratory rate detection system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0043] Reference Figure 1 , is a flow chart of a respiratory rate detection method provided by an embodiment of the present invention, including: S101-S103:

[0044] S101: Acquire first multi-axis acceleration data and first angular velocity data of an object to be detected.

[0045] In this embodiment, the obtaining of the first multi-axis acceleration data and the first angular velocity data of the object to be detected is specifically:

[0046] Acquiring initial angular velocity data and initial multi-axis acceleration data of the object to be detected;

[0047] calculating a first change rate of the initial angular velocity data and a second change rate of the initial multi-axis acceleration data within a preset time period;

[0048] When the first change rate satisfies a first preset condition, performing noise reduction processing on the initial angular velocity data to generate and acquire the first angular velocity data;

[0049] When the second change rate meets a second preset condition, the initial multi-axis acceleration data is subjected to noise reduction processing to generate and acquire the first multi-axis acceleration data.

[0050] Furthermore, the first change rate satisfies a first preset condition, specifically:

[0051] When the first change rate is less than a first preset value, it is determined that the first change rate meets the first preset condition, and at the same time it is determined that the signal quality of the initial angular velocity data is excellent, so after further noise reduction processing is performed on the initial angular velocity data with excellent signal quality, the first angular velocity data is generated and acquired.

[0052] Furthermore, the second change rate satisfies a second preset condition, specifically:

[0053] When the second change rate is less than a second preset value, it is determined that the second change rate meets the second preset condition, and at the same time, it is determined that the signal quality of the initial multi-axis acceleration data is excellent, so the initial multi-axis acceleration data with excellent signal quality is further subjected to noise reduction processing, and the first multi-axis acceleration data is generated and acquired.

[0054] In a specific embodiment, the initial angular velocity data is collected by a gyroscope, and the initial multi-axis acceleration data is collected by a multi-axis acceleration sensor. Both the gyroscope and the multi-axis acceleration sensor are arranged at the wrist of the object to be detected.

[0055] Wherein, the setting axis of the gyroscope completely coincides with the setting axis of the multi-axis acceleration sensor.

[0056] In a specific embodiment, the noise reduction process is specifically:

[0057] calculating a first signal amplitude variance of the initial angular velocity data, and when the first signal amplitude variance does not satisfy a third preset condition, filtering a first noise in the initial angular velocity data to generate the first angular velocity data;

[0058] Calculate the second signal amplitude variance of the initial multi-axis acceleration data, and when the second signal amplitude variance does not meet the fourth preset condition, filter the second noise in the initial multi-axis acceleration data to generate the first multi-axis acceleration data; wherein the frequencies of the first noise and the second noise are both preset frequencies.

[0059] Furthermore, the first signal amplitude variance does not satisfy a third preset condition, specifically: when the first signal amplitude variance is greater than a third preset value, it is determined that the first signal amplitude variance does not satisfy the third preset condition, and at the same time it is determined that real-time and effective digital filtering of the initial angular velocity data is required, and after filtering the first noise in the initial angular velocity data, the first angular velocity data is generated.

[0060] Furthermore, the second signal amplitude variance does not satisfy the fourth preset condition, specifically: when the second signal amplitude variance is greater than a fourth preset value, it is determined that the second signal amplitude variance does not satisfy the fourth preset condition, and at the same time it is determined that real-time and effective digital filtering of the initial multi-axis acceleration data is required to filter out the second noise in the initial multi-axis acceleration data to generate the first multi-axis acceleration data.

[0061] S102: Inputting the first multi-axis acceleration data and the first angular velocity data into the first model, so that the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data.

[0062] In this embodiment, the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data, specifically:

[0063] The first model acquires multi-axis respiratory signal characteristics according to the first multi-axis acceleration data and the first angular velocity data;

[0064] After multi-axis fusion processing is performed on the multi-axis respiratory signal features, the one-dimensional respiratory decision signal is generated.

[0065] Among them, the multi-axis respiratory signal characteristics are quasi-periodic changes of breathing. Further, the embodiment of the present invention can ensure the multi-dimensional amount of available information while using multi-dimensional information data (i.e. angular velocity data and multi-axis acceleration data), by converting the multi-axis respiratory signal characteristics into a one-dimensional respiratory decision signal, and then calculating the respiratory rate based on the one-dimensional respiratory decision signal, thereby avoiding interference between multi-dimensional information data, and can further improve the accuracy of respiratory rate detection.

[0066] Furthermore, the one-dimensional breathing decision signal is the breathing signal on the best axis among the multiple axes, and the best axis is the axis where the breathing signal is clearest. The best axis is not limited to the set axes (X-axis, Y-axis and Z-axis) on the gyroscope and multi-axis acceleration sensor, and can be a fusion of the set axes.

[0067] S103: Inputting the one-dimensional breathing decision signal into the first model, so that the first model calculates the breathing rate of the subject to be detected according to the one-dimensional breathing decision signal.

[0068] In this embodiment, after the one-dimensional breathing decision signal is input into the first model, the first model calculates the breathing rate of the object to be detected according to a preset algorithm and the one-dimensional breathing decision signal. The preset algorithm includes: statistics and machine learning algorithm, energy spectrum density algorithm, peak detection algorithm and other algorithms that consider prior historical data.

[0069] For further explanation of the respiratory rate detection device, please refer to Figure 2 , Figure 2 It is a structural schematic diagram of a respiratory rate detection device provided by an embodiment of the present invention, comprising: an acquisition module 201, a generation module 202 and a detection module 203.

[0070] Wherein, the acquisition module 201 is used to acquire first multi-axis acceleration data and first angular velocity data of the object to be detected;

[0071] The generating module 202 is used for inputting the first multi-axis acceleration data and the first angular velocity data into the first model, so that the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data;

[0072] The detection module 203 is used to input the one-dimensional breathing decision signal into the first model, so that the first model calculates the breathing rate of the object to be detected according to the one-dimensional breathing decision signal.

[0073] In this embodiment, the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data, specifically:

[0074] The first model acquires multi-axis respiratory signal characteristics according to the first multi-axis acceleration data and the first angular velocity data;

[0075] After multi-axis fusion processing is performed on the multi-axis respiratory signal features, the one-dimensional respiratory decision signal is generated.

[0076] In a specific embodiment, the obtaining of the first multi-axis acceleration data and the first angular velocity data of the object to be detected is specifically:

[0077] Acquiring initial angular velocity data and initial multi-axis acceleration data of the object to be detected;

[0078] calculating a first change rate of the initial angular velocity data and a second change rate of the initial multi-axis acceleration data within a preset time period;

[0079] When the first change rate satisfies a first preset condition, performing noise reduction processing on the initial angular velocity data to generate and acquire the first angular velocity data;

[0080] When the second change rate meets a second preset condition, the initial multi-axis acceleration data is subjected to noise reduction processing to generate and acquire the first multi-axis acceleration data.

[0081] For further explanation of the respiration rate detection system, please refer to Figure 3 , Figure 3 It is a result schematic diagram of a respiratory rate detection system provided by an embodiment of the present invention, including: a gyroscope 301, a multi-axis acceleration sensor 302, an MCU chip 303, a data storage module 304 and a wireless communication module 305.

[0082] The gyroscope 301 , the multi-axis acceleration sensor 302 , the data storage module 304 and the wireless communication module 305 are all electrically connected to the MCU chip 303 .

[0083] The gyroscope 301 and the multi-axis acceleration sensor 302 are arranged at the wrist of the object to be detected, specifically at the back of the wrist, and are used to collect angular velocity data and multi-axis acceleration data of the object to be detected, respectively.

[0084] The data storage module 304 is used to store data collected by the gyroscope 301 and the multi-axis acceleration sensor 302 .

[0085] The wireless communication module 305 is used to send the data collected by the gyroscope 301 and the multi-axis acceleration sensor 302 to the mobile terminal or the cloud server.

[0086] The MCU chip 303 is used to calculate the breathing rate of the object to be detected based on the data collected by the gyroscope 301 and the multi-axis acceleration sensor 302.

[0087] In a specific embodiment, the angular velocity data is angular velocity data in the directions of the X-axis, the Y-axis and the Z-axis, and the multi-axis acceleration data is acceleration data in the directions of the X-axis, the Y-axis and the Z-axis.

[0088] An embodiment of the present invention provides a mobile terminal, including a processor and a memory, wherein the memory stores a computer-readable program code, and when the processor executes the computer-readable program code, the steps of the above-mentioned breathing rate detection method are implemented.

[0089] An embodiment of the present invention provides a storage medium, which stores computer-readable program codes. When the computer-readable program codes are executed, the steps of the above-mentioned breathing rate detection method are implemented.

[0090] The embodiment of the present invention first obtains the first multi-axis acceleration data and the first angular velocity data of the object to be detected; then inputs the first multi-axis acceleration data and the first angular velocity data into the first model, so that the first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing on the first multi-axis acceleration data and the first angular velocity data; finally, the one-dimensional breathing decision signal is input into the first model, so that the first model calculates the breathing rate of the object to be detected according to the one-dimensional breathing decision signal.

[0091] The embodiment of the present invention performs multi-axis fusion processing on the first multi-axis acceleration data and the first angular velocity data through the first model, and then generates a one-dimensional breathing decision signal; and then calculates the breathing rate of the object to be detected based on the one-dimensional breathing decision signal. The embodiment of the present invention can, on the basis of using multi-dimensional information data (i.e., angular velocity data and multi-axis acceleration data), ensure the multi-dimensionality of the data, while converting the multi-axis breathing signal characteristics into a one-dimensional breathing decision signal, and then calculating the breathing rate based on the one-dimensional breathing decision signal, thereby avoiding interference between the multi-dimensional information data, and can further improve the accuracy of breathing rate detection.

[0092] In addition, since in the embodiment of the present invention, the gyroscope and multi-axis acceleration sensor that collect angular velocity data and multi-axis acceleration data are both arranged at the wrist of the object to be detected, the subtle movement information of the wrist driven by the human body when the human body exhales and inhales can be collected, the accuracy of data collection is improved, thereby further ensuring the accuracy of respiratory rate detection; at the same time, wearing the gyroscope and multi-axis acceleration sensor on the wrist improves comfort and portability, realizes 24-hour uninterrupted monitoring of the respiratory rate, and reflects the health status of the user to be detected more timely and effectively.

[0093] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A respiratory rate detection method, characterized in that: include: Acquire the first multi-axis acceleration data and the first angular velocity data of the object to be detected; specifically: Acquiring initial angular velocity data and initial multi-axis acceleration data of the object to be detected; calculating a first change rate of the initial angular velocity data and a second change rate of the initial multi-axis acceleration data within a preset time period; When the first change rate satisfies a first preset condition, performing noise reduction processing on the initial angular velocity data to generate and acquire the first angular velocity data; When the second change rate satisfies a second preset condition, performing noise reduction processing on the initial multi-axis acceleration data to generate and acquire the first multi-axis acceleration data; The noise reduction processing is specifically: calculating a first signal amplitude variance of the initial angular velocity data, and when the first signal amplitude variance does not satisfy a third preset condition, filtering a first noise in the initial angular velocity data to generate the first angular velocity data; Calculating a second signal amplitude variance of the initial multi-axis acceleration data, and when the second signal amplitude variance does not meet a fourth preset condition, filtering a second noise in the initial multi-axis acceleration data to generate the first multi-axis acceleration data; wherein the frequencies of the first noise and the second noise are both preset frequencies; Inputting the first multi-axis acceleration data and the first angular velocity data into a first model, so that the first model generates a one-dimensional breathing decision signal after multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data; the one-dimensional breathing decision signal is a breathing signal on a fusion axis of a set axis in the multi-axis; The one-dimensional breathing decision signal is input into the first model so that the first model calculates the breathing rate of the object to be detected according to the one-dimensional breathing decision signal.

2. A respiratory rate detection method according to claim 1, characterized in that: The first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data, specifically: The first model acquires multi-axis respiratory signal characteristics according to the first multi-axis acceleration data and the first angular velocity data; After multi-axis fusion processing is performed on the multi-axis respiratory signal features, the one-dimensional respiratory decision signal is generated.

3. A respiratory rate detection method according to claim 1, characterized in that: The initial angular velocity data is collected by a gyroscope, and the initial multi-axis acceleration data is collected by a multi-axis acceleration sensor. The gyroscope and the multi-axis acceleration sensor are both arranged at the wrist of the object to be detected.

4. A respiratory rate detection device, characterized in that: include: Acquisition module, generation module and detection module; The acquisition module is used to acquire the first multi-axis acceleration data and the first angular velocity data of the object to be detected; specifically: Acquiring initial angular velocity data and initial multi-axis acceleration data of the object to be detected; calculating a first change rate of the initial angular velocity data and a second change rate of the initial multi-axis acceleration data within a preset time period; When the first change rate satisfies a first preset condition, performing noise reduction processing on the initial angular velocity data to generate and acquire the first angular velocity data; When the second change rate satisfies a second preset condition, performing noise reduction processing on the initial multi-axis acceleration data to generate and acquire the first multi-axis acceleration data; The noise reduction processing is specifically: calculating a first signal amplitude variance of the initial angular velocity data, and when the first signal amplitude variance does not satisfy a third preset condition, filtering a first noise in the initial angular velocity data to generate the first angular velocity data; Calculating a second signal amplitude variance of the initial multi-axis acceleration data, and when the second signal amplitude variance does not meet a fourth preset condition, filtering a second noise in the initial multi-axis acceleration data to generate the first multi-axis acceleration data; wherein the frequencies of the first noise and the second noise are both preset frequencies; The generating module is used to input the first multi-axis acceleration data and the first angular velocity data into the first model, so that the first model generates a one-dimensional breathing decision signal after multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data; the one-dimensional breathing decision signal is a breathing signal on a fusion axis of a set axis in the multi-axis; The detection module is used to input the one-dimensional breathing decision signal into the first model, so that the first model calculates the breathing rate of the object to be detected according to the one-dimensional breathing decision signal.

5. A respiratory rate detection device according to claim 4, characterized in that: The first model generates a one-dimensional breathing decision signal after performing multi-axis fusion processing according to the first multi-axis acceleration data and the first angular velocity data, specifically: The first model acquires multi-axis respiratory signal characteristics according to the first multi-axis acceleration data and the first angular velocity data; After multi-axis fusion processing is performed on the multi-axis respiratory signal features, the one-dimensional respiratory decision signal is generated.

6. A mobile terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer-readable program code, and when the processor executes the computer-readable program code, the steps of a respiratory rate detection method according to any one of claims 1 to 3 are implemented.

7. A storage medium, characterized in that: The storage medium stores computer-readable program codes, and when the computer-readable program codes are executed, the steps of a respiratory rate detection method according to any one of claims 1 to 3 are implemented.

Images