A sleep stage analysis method and device based on electroencephalogram signals

Abstract

The present invention provides a sleep staging analysis method and device based on electroencephalogram (EEG) signals, belonging to the field of data analysis technology. The method and device specifically include: using sleep staging results corresponding to different trusted monitoring positions to determine the staging deviation period in the sleep analysis results, determining the matching situation between the EEG signals of different trusted monitoring positions at different times and monitoring data of other dimensions, and combining the deviation between the EEG signals at different times and other trusted monitoring positions to determine the abnormal change time of different trusted monitoring positions. Based on the distribution data of the abnormal change time of different trusted monitoring positions in the staging deviation period and the period before the staging deviation period, when it is determined that a reference monitoring position exists in the staging deviation period, the reference monitoring position is used to determine the sleep staging result in the staging deviation period, thereby improving the accuracy of the sleep staging result.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and in particular relates to a sleep staging analysis method and device based on electroencephalogram (EEG) signals. Background Art

[0002] The human body is generally divided into four levels during sleep. Level one is the sleep latency period, level two is the light sleep period, and levels three and four are the deep sleep periods, which are the strongest stages for restoring physical fitness and brain power. Therefore, it is crucial to identify and process the human body's sleep stages for targeted sleep adjustment measures.

[0003] In the process of identifying and processing human sleep stages, existing technical solutions often use physiological signals to identify and process human sleep stages. Specifically, similar technical solutions are provided in invention patent applications CN202410964543.9 "An automatic sleep staging method, system, device and storage medium" and CN202410875978.6 "A sleep staging method based on deep learning". However, the above technical solutions all have the following technical problems:

[0004] When performing sleep stage identification and processing, the existing technical solutions ignore the consistency of EEG signals in different parts of the body. The human body will inevitably turn over during sleep, which may cause the monitoring status of the EEG signal to have poor contact and other problems, making it difficult to accurately implement sleep stage processing.

[0005] In response to the above technical problems, the present application specifically provides a sleep staging analysis method and device based on EEG signals. Summary of the Invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present application provides a sleep staging analysis method based on EEG signals, specifically comprising:

[0008] S1 determines similarities of the EEG signal monitoring data at different locations based on the EEG signal monitoring data at different locations, and determines a credible monitoring location among the locations using the similarities;

[0009] S2: when it is determined that the monitoring data meets the requirements based on the similarity of the monitoring data at the credible monitoring locations, determining the sleep staging results corresponding to the different credible monitoring locations using the analysis results of the EEG signal monitoring data at different credible monitoring locations, and determining the staging deviation period in the sleep analysis result using the sleep staging results corresponding to the different credible monitoring locations;

[0010] S3 determines the matching between the EEG signals of different trusted monitoring locations at different times and the monitoring data of other dimensions, and determines the abnormal change moments of different trusted monitoring locations based on the deviation between the EEG signals at different times and other trusted monitoring locations;

[0011] S4 determines the sleep staging result in the staging deviation period using the reference monitoring position when determining the presence of a reference monitoring position in the staging deviation period based on the distribution data of abnormal change moments of different credible monitoring positions in the staging deviation period and the period preceding the staging deviation period.

[0012] The beneficial effects of the present invention are:

[0013] By utilizing the similarity of the EEG signal monitoring data at different positions, the credible monitoring position among the positions is determined, thereby realizing the deviation of the EEG signal monitoring data between other positions, and determining the credible monitoring position among the monitoring positions, thereby avoiding the technical problem of inaccurate measurement results of some positions due to looseness or abnormal measurement status, and laying the foundation for further ensuring the accuracy of sleep staging results, and avoiding the interference of abnormal measurement data.

[0014] Based on the distribution data of abnormal change moments of different trusted monitoring positions in the installment deviation period and the previous period of the installment deviation period, the reference monitoring positions in the installment deviation period are determined. Not only the differences in the reliability of monitoring data due to the differences in the number of abnormal change moments in the installment deviation period among different trusted monitoring positions are taken into account, but also the differences in the reliability of data in the installment deviation period due to the differences in the number of abnormal change moments in the previous period are taken into account, thereby realizing the screening of reference monitoring positions with higher reliability.

[0015] A further technical solution is that the similarity of the monitoring data of the electroencephalogram signal includes the similarity of the monitoring data of the electroencephalogram data at different moments.

[0016] A further technical solution is that the method for determining the credible monitoring location in the location is:

[0017] Based on the similarity of the monitoring data of the EEG signals at different locations, determining the data deviation between the monitoring data of the EEG signals at the location and other locations at different times;

[0018] Determine the average value of the deviations at different times using the average value of the data deviations from the monitoring data of the EEG signals at other locations at different times;

[0019] The data deviation moments at the moment are determined based on the deviation average values ​​at different moments, and the credible monitoring positions in the positions are determined according to the number of the data deviation moments.

[0020] A further technical solution is that the data deviation moment is the moment when the deviation average value does not meet the requirements.

[0021] A further technical solution is that when there is no reference monitoring position, the sleep staging result in the staging deviation period cannot be determined.

[0022] In a second aspect, the present invention provides a computer device comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned sleep staging analysis method based on EEG signals when running the computer program.

[0023] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0026] Figure 1 It is a flow chart of a sleep stage analysis method based on EEG signals;

[0027] Figure 2 is a flow chart of a method for determining a trusted monitoring location in a location;

[0028] Figure 3 It is a flow chart to confirm that the monitoring data meets the requirements;

[0029] Figure 4 is a flow chart of a method for determining the time of abnormal change of a credible monitoring position;

[0030] Figure 5 is a flow chart of a method for determining a reference monitoring position for a staged deviation period. DETAILED DESCRIPTION

[0031] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0032] The human body will inevitably turn over during sleep, which may cause problems such as poor contact in the monitoring of EEG signals. Therefore, it is necessary to identify monitoring devices with poor measurement accuracy in order to accurately realize the stage processing of sleep.

[0033] According to the data deviation of the monitoring data of the EEG signals of the location and other locations at different times, the average value of the data deviation of the monitoring data of the EEG signals of other locations at different times is used to determine the average value of the deviation at different times. The data deviation moment at each moment is determined based on the average value of the deviation at different times. When the proportion of the number of data deviation moments is less than 0.05, the location is determined to be a credible monitoring location.

[0034] When the number of credible monitoring locations is greater than the preset number of locations, it is determined that the monitoring data meets the requirements.

[0035] The amplitude of the EEG signal is determined based on the monitoring data of the EEG signal, and the sleep staging result is determined based on the staging result corresponding to the amplitude. The period when there is a deviation in the sleep staging results corresponding to different reliable monitoring positions is used as the staging deviation period.

[0036] The abnormal change moment is the moment when the monitoring data does not match the monitoring data of other dimensions or the average value of the deviation from the monitoring data of other reliable monitoring locations does not meet the requirements.

[0037] The reference monitoring position is a credible monitoring position where the number of abnormal change moments in the installment deviation period accounts for less than 0.02, and there is no abnormal change moment in the previous period.

[0038] Example 1

[0039] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, the present application provides a sleep stage analysis method based on EEG signals, which specifically includes:

[0040] S1 determines similarities of the EEG signal monitoring data at different locations based on the EEG signal monitoring data at different locations, and determines a credible monitoring location among the locations using the similarities;

[0041] Furthermore, the similarity of the monitoring data of the electroencephalogram signal includes data similarity of the monitoring data of the electroencephalogram data at different moments.

[0042] Specifically, such as Figure 2 As shown, the method for determining the credible monitoring position in the position is:

[0043] Based on the similarity of the monitoring data of the EEG signals at different locations, determining the data deviation between the monitoring data of the EEG signals at the location and other locations at different times;

[0044] Determine the average value of the deviations at different times using the average value of the data deviations from the monitoring data of the EEG signals at other locations at different times;

[0045] The data deviation moments at the moment are determined based on the deviation average values ​​at different moments, and the credible monitoring positions in the positions are determined according to the number of the data deviation moments.

[0046] Furthermore, the data deviation moment is the moment when the deviation average value does not meet the requirements.

[0047] Optionally, when the number of data deviation moments in the location is within a preset number range, the location is determined to be a credible monitoring location.

[0048] In another possible embodiment, a method for determining a trusted monitoring location among the locations is:

[0049] Based on the similarity of the monitoring data of the EEG signals at different locations, determining the data deviation between the monitoring data of the EEG signals at the location and other locations at different times;

[0050] Determine the average value of the deviations at different times using the average value of the data deviations from the monitoring data of the EEG signals at other locations at different times;

[0051] A plausible monitoring position among the positions is determined based on an average value of the deviation average values ​​at different times.

[0052] In another possible embodiment, a method for determining a trusted monitoring location among the locations is:

[0053] S11 determines the data deviation between the monitoring data of the EEG signals at the position and the monitoring data of the EEG signals at other positions at different times based on the similarity of the monitoring data of the EEG signals at different positions;

[0054] Optionally, when it is necessary to determine in the above steps that the data deviation of the monitoring data of the EEG signals of other locations at different times meets the requirements, the position is determined to be a trusted monitoring position; when there is a moment when the data deviation of the monitoring data of the EEG signals of other locations does not meet the requirements, and it is determined that there is no moment when the monitoring data deviation does not meet the requirements, the position is determined to be a trusted monitoring position.

[0055] Furthermore, in another case, when there are moments when the monitoring data deviation does not meet the requirements, the number of moments when the monitoring data deviation does not meet the requirements is obtained. When the number of moments when the monitoring data deviation does not meet the requirements is greater than the preset number of moments, it is determined that the location does not belong to a trusted monitoring location. When the number of moments when the monitoring data deviation does not meet the requirements is not greater than the preset number of moments, the process goes to step S12, where whether the requirements are met is determined by means of a threshold.

[0056] S12 divides the monitoring data of the EEG signal at the position into a plurality of segmented time periods according to a unit time length, determines data deviation values ​​of the EEG signal at the position in different segmented time periods according to data deviation amounts of the monitoring data of the EEG signal at other positions at different moments in different segmented time periods, and determines segmented time period deviation amounts of the different segmented time periods using the data deviation values;

[0057] Optionally, in the above steps, it is necessary to determine the data deviation value of the EEG signals at other locations in different segmented time periods based on the data deviation amount of the monitoring data at different moments in different segmented time periods. Specifically, it can be determined based on the preset deviation value corresponding to the data deviation amount.

[0058] In a possible embodiment, if the data deviation values ​​of the EEG signals of other locations in different segmented time periods all meet the requirements in the above steps, the location is determined to be a trusted monitoring location. When there is a segmented time period in which the data deviation values ​​of the EEG signals of other locations do not meet the requirements, the number of locations in which the data deviation values ​​in different segmented time periods do not meet the requirements is obtained.

[0059] At this time, if there are split time periods in which the number of positions whose data deviation values ​​do not meet the requirements is greater than the preset number of positions, it is necessary to further determine that the number of split time periods in which the number of positions whose data deviation values ​​do not meet the requirements is greater than the preset number of positions is greater than the preset number of split time periods, then determine that the position does not belong to a credible monitoring position. At this time, if there are split time periods in which the number of positions whose data deviation values ​​do not meet the requirements is greater than the preset number of positions and the number of split time periods is not greater than the preset number of split time periods, use the data deviation value to determine the split time period deviation amount of different split time periods. When the number of split time periods in which the split time period deviation amount does not meet the requirements is greater than the preset number of split time periods, then determine that the position does not belong to a credible monitoring position. If the number of split time periods in which the split time period deviation amount does not meet the requirements is not greater than the preset number of split time periods, proceed to step S13, where whether the requirements are met is determined by means of a threshold.

[0060] S13 determines a position credibility value of the position based on the segmented period deviations of different segmented periods, and uses the position credibility value to determine whether the position is a credible monitoring position.

[0061] It should be noted that the location credibility value of the location is determined based on the difference between the preset value and the segmentation time deviation of different segmentation time periods. When the location credibility value is greater than the preset threshold, it is determined to be a credible monitoring location.

[0062] S2: when it is determined that the monitoring data meets the requirements based on the similarity of the monitoring data at the credible monitoring locations, determining the sleep staging results corresponding to the different credible monitoring locations using the analysis results of the EEG signal monitoring data at different credible monitoring locations, and determining the staging deviation period in the sleep analysis result using the sleep staging results corresponding to the different credible monitoring locations;

[0063] It should be noted that if Figure 3 As shown, determining that the monitoring data meets the requirements specifically includes:

[0064] Determining a basic credibility value of the credible monitoring location based on the proportion of the number of credible monitoring locations;

[0065] Determine the deviation of the monitoring data at different times between the different credible monitoring locations based on the similarity of the monitoring data between the different credible monitoring locations, and use the deviation of the monitoring data at different times to determine the data similarity value between the different credible monitoring locations;

[0066] The data credibility value of the monitoring data is determined according to the product of the average value of the data similarity values ​​between different credible monitoring positions and the basic credibility value, and the data credibility value is used to determine whether the monitoring data meets the requirements.

[0067] Furthermore, the data similarity value between the credible monitoring locations is determined according to an average value of deviations of monitoring data between different credible monitoring locations at different times.

[0068] It should be noted that the data credibility value ranges from 0 to 1, wherein when the data credibility value is greater than a preset credibility value threshold, it is determined that the monitoring data meets the requirements.

[0069] In another embodiment, when the data credibility value does not meet the requirements, it is determined that the phased processing cannot be performed.

[0070] Furthermore, the sleep staging result corresponding to the credible monitoring position is determined according to the preset staging result corresponding to the monitoring data of the electroencephalogram signal at the credible monitoring position.

[0071] Specifically, the staging deviation period in the sleep analysis result is a period during which the sleep staging results corresponding to different credible monitoring locations are inconsistent.

[0072] S3 determines the matching between the EEG signals of different trusted monitoring locations at different times and the monitoring data of other dimensions, and determines the abnormal change moments of different trusted monitoring locations based on the deviation between the EEG signals at different times and other trusted monitoring locations;

[0073] It should be noted that the monitoring data of other dimensions include respiratory rate and heart rate.

[0074] Further, such as Figure 4 As shown, the method for determining the abnormal change moment of the credible monitoring position is:

[0075] Based on the matching of the EEG signal at the time and the monitoring data of other dimensions, determining the deviation of the endpoints within the preset signal range corresponding to the EEG signal and the monitoring data of other dimensions, and determining the EEG signal deviation value at the time using the deviation;

[0076] Determining the deviation amount from other credible monitoring positions based on the deviation between the EEG signal at the time and other credible monitoring positions, and determining the position comparison deviation value at the time based on the average value of the deviation amounts of different other credible monitoring positions;

[0077] The moment deviation value of the moment is determined based on the average value of the EEG signal deviation value and the position comparison deviation value, and the moment deviation value is used to determine whether the moment is an abnormal change moment.

[0078] Specifically, the EEG signal deviation value is determined based on an average value of preset deviation values ​​corresponding to deviations of endpoints within a preset signal range corresponding to monitoring data of other dimensions.

[0079] It should be noted that, when the moment deviation value of the moment is greater than the preset deviation value threshold, the moment is determined to be an abnormal change moment.

[0080] Optionally, the method for determining the abnormal change moment of the trusted monitoring position is:

[0081] S31 determines the deviation of endpoints within a preset signal range corresponding to the EEG signal and the monitoring data of other dimensions based on the matching condition of the EEG signal at the moment and the monitoring data of other dimensions;

[0082] It should be further explained that, in the above step S31, it is necessary to further determine that when the EEG signal at the moment has monitoring data of other dimensions that are not within the preset signal range, the moment is determined to be an abnormal change moment.

[0083] Furthermore, if there is no monitoring data of other dimensions that is not within the preset signal range, and it is determined that the deviations of adjacent endpoints within the preset signal range corresponding to the monitoring data of different other dimensions are all within the preset deviation range, then the moment is determined to be the abnormal change moment;

[0084] Only when there is monitoring data of other dimensions whose deviation of the adjacent endpoints within the corresponding preset signal range is not within the preset deviation range, it is necessary to proceed to the next step, in which the requirements are determined by means of a threshold.

[0085] S32: determining the amount of deviation from other credible monitoring positions based on the deviation between the EEG signal at the moment and other credible monitoring positions;

[0086] In an optional embodiment, if the number of other trusted monitoring positions whose deviation amount does not meet the requirements is greater than the preset number of trusted positions, the moment is determined to be an abnormal change moment. When the number of other trusted monitoring positions whose deviation amount does not meet the requirements is not greater than the preset number of trusted positions, it is necessary to determine the position comparison deviation child.

[0087] S33 determines the position comparison deviation value at the moment according to the average value of the deviation amounts of different other credible monitoring positions, determines the EEG signal deviation value at the moment using the deviation situation, determines the moment deviation value at the moment based on the average value of the EEG signal deviation value and the position comparison deviation value, and determines whether the moment is an abnormal change moment using the moment deviation value.

[0088] Optionally, in the above steps, if the position comparison deviation value does not meet the requirements, the moment is determined to be an abnormal change moment. Only when the position comparison deviation value meets the requirements: the deviation situation is used to determine the EEG signal deviation value at the moment, and the moment deviation value at the moment is determined based on the average value of the EEG signal deviation value and the position comparison deviation value, and the moment deviation value is used to determine whether the moment is an abnormal change moment. Specifically, when it is greater than the preset deviation value, it is determined to be an abnormal change moment.

[0089] S4 determines the sleep staging result in the staging deviation period using the reference monitoring position when determining the presence of a reference monitoring position in the staging deviation period based on the distribution data of abnormal change moments of different credible monitoring positions in the staging deviation period and the period preceding the staging deviation period.

[0090] It should be noted that if Figure 5 As shown, the method for determining the reference monitoring position of the phased deviation period is:

[0091] Determine the number ratio of the abnormal change moments of the trusted monitoring location based on the distribution data of the abnormal change moments of the trusted monitoring location in the installment deviation period, and determine the abnormal value of the period data of the trusted monitoring location in the installment deviation period based on the number ratio;

[0092] Determine the number of abnormal change moments in the previous period based on the distribution data of abnormal change moments in the previous period of the installment deviation period, determine the abnormal weight values ​​of different abnormal change moments in the previous period based on the time deviation between the abnormal change moments in different previous periods and the installment deviation period, and determine the sum of abnormal values ​​by summing the number of abnormal weight values ​​of the abnormal change moments in the previous period;

[0093] The comprehensive abnormal value of the phase deviation period at the credible monitoring position is determined based on the product of the abnormal value sum and the period data abnormal value, and the comprehensive abnormal value is used to determine whether the credible monitoring position is a reference monitoring position.

[0094] Further, determining whether the credible monitoring position is a reference monitoring position by using the comprehensive abnormal value specifically includes:

[0095] When there is a credible monitoring location with a comprehensive abnormal value less than the preset abnormal value threshold, the credible monitoring location with the smallest comprehensive abnormal value is used as the reference monitoring location;

[0096] When there is no credible monitoring location whose comprehensive abnormal value is less than the preset abnormal value threshold, it is determined that there is no reference monitoring location.

[0097] It should be noted that when there is no reference monitoring position, the sleep staging result in the staging deviation period cannot be determined.

[0098] Example 2

[0099] In a second aspect, the present invention provides a computer device comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned sleep staging analysis method based on EEG signals when running the computer program.

[0100] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0101] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A sleep stage analysis method based on EEG signals, characterized in that: Specifically include: Based on the monitoring data of the EEG signals at different locations, determining similarities in the monitoring data of the EEG signals at different locations, and determining a credible monitoring location among the locations using the similarities; When it is determined that the monitoring data meets the requirements based on similarity of the monitoring data at the credible monitoring locations, the sleep staging results corresponding to the different credible monitoring locations are determined based on analysis results of the EEG signal monitoring data at different credible monitoring locations, and the sleep staging results corresponding to the different credible monitoring locations are used to determine the staging deviation period in the sleep staging results; Determine the matching between EEG signals at different trusted monitoring locations at different times and monitoring data from other dimensions, and determine the time of abnormal changes at different trusted monitoring locations based on the deviation between EEG signals at different times and other trusted monitoring locations; According to the distribution data of abnormal change moments of different credible monitoring positions in the stage deviation period and the period before the stage deviation period, when it is determined that there is a reference monitoring position in the stage deviation period, the reference monitoring position is used to determine the sleep stage result in the stage deviation period.

2. The sleep stage analysis method based on EEG signals according to claim 1, wherein: The similarity of the monitoring data of the electroencephalogram signal includes the similarity of the monitoring data of the electroencephalogram signal at different moments.

3. The sleep staging analysis method based on EEG signals according to claim 1, wherein: The method for determining the credible monitoring position in the position is: Based on the similarity of the monitoring data of the EEG signals at different locations, determining the data deviation between the monitoring data of the EEG signals at the location and other locations at different times; Determine the average value of the deviations at different times using the average value of the data deviations from the monitoring data of the EEG signals at other locations at different times; The data deviation moments at the moment are determined based on the deviation average values ​​at different moments, and the credible monitoring positions in the positions are determined according to the number of the data deviation moments.

4. The sleep staging analysis method based on EEG signals according to claim 3, wherein: The data deviation moment is the moment when the deviation average value does not meet the requirements.

5. The sleep stage analysis method based on EEG signals according to claim 3, characterized in that: When the number of data deviation moments in the location is within a preset number range, the location is determined to be a credible monitoring location.

6. The sleep staging analysis method based on EEG signals according to claim 1, wherein: Determine that the monitoring data meets the requirements, including: Determining a basic credibility value of the credible monitoring location based on the proportion of the number of credible monitoring locations; Determine the deviation of the monitoring data at different times between the different credible monitoring locations based on the similarity of the monitoring data between the different credible monitoring locations, and use the deviation of the monitoring data at different times to determine the data similarity value between the different credible monitoring locations; The data credibility value of the monitoring data is determined according to the product of the average value of the data similarity values ​​between different credible monitoring positions and the basic credibility value, and the data credibility value is used to determine whether the monitoring data meets the requirements.

7. The sleep stage analysis method based on EEG signals according to claim 6, characterized in that: The data similarity value between the credible monitoring locations is determined according to an average value of deviations of monitoring data between different credible monitoring locations at different times.

8. The sleep staging analysis method based on EEG signals according to claim 6, characterized in that: When the data credibility value does not meet the requirements, it is determined that the instalment processing cannot be performed.

9. The sleep staging analysis method based on EEG signals according to claim 1, wherein: When there is no reference monitoring position, the sleep staging result in the staging deviation period cannot be determined.

10. A computer device comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, a sleep staging analysis method based on EEG signals according to any one of claims 1 to 9 is executed.

Images