Sleep apnea monitoring method and device based on snore signal

Abstract

The invention discloses a sleep apnea monitoring method and device based on snoring sound signals. The method comprises: extracting the original snoring sound signal from the polysomnography; using a sliding frame to slide along the original snoring sound signal, and counting the signals in each sliding frame Number of vertices; according to the number of signal vertices in each sliding frame, filter out one or more candidate segments of the snoring signal corresponding to the sliding frame whose number of signal vertices is greater than the preset threshold; a preset time period before detecting each candidate segment of the snoring signal Whether an apnea event occurs within the test; according to the detection results, the selected snoring signal candidate segments are marked as the first type of snoring signal related to sleep apnea, or the second type of snoring signal not related to sleep apnea. The invention utilizes the snoring signal extracted from the polysomnography to fully analyze the correlation between the snoring signal and the breathing signal, and can monitor the snoring signal related to sleep apnea and the snoring signal not related to sleep apnea.

Description

technical field [0001] The invention relates to the field of signal processing, in particular to a sleep apnea monitoring method and device based on snoring sound signals. Background technique [0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Sleep apnea refers to a symptom of temporary cessation of breathing during sleep, which has a greater impact on human health. At present, various existing sleep monitoring devices, or medical devices specially used for diagnosing sleep apnea, monitor whether sleep apnea exists or not, based on directly collected snoring signals. There are a lot of noise signals in the signal, which will lead to technical problems of inaccurate monitoring results. Contents of the invention [0004] An embodiment of the present invention provides a sleep apnea monitoring met...

AI Technical Summary

Problems solved by technology

[0004] An embodiment of the present invention provides a sleep apnea monitoring method based on snoring signals to solve the problem of monitoring sleep apnea based on directly collected snoring signals in the prior art. The technical problem that leads to inaccurate monitoring results, the method includes: extracting the original snoring signal from the polysomnography; using a sliding frame to slide along the original snoring signal, and counting the number of signal vertices in each sliding frame; According to the number of signal vertices in the frame, one or more snoring signal candidate segments are screened out, wherein each snoring signal candidate segment is a signal segment corresponding to a sliding frame whose number of signal vertices is greater than a preset threshold; each snoring signal candidate segment is detected Whether an apnea event occurs within a preset period of time before the segment; according to the detection results, mark the candidate segments of the selected snoring signals as the first type of snoring signal or the second type of snoring signal, wherein the first type of snoring signal It is a snoring signal related to sleep apnea, and the second type of snoring signal is a snoring signal not related to sleep apnea

[0005] An embodiment of the present invention also provides a sleep apnea monitoring device based on snoring signals to solve the problem of monitoring sleep apnea based on directly collected snoring signals in the prior art. Since there are a large number of noise signals in the directly collected snoring signals, The technical problem that will lead to inaccurate monitoring results, the device includes: an original snoring signal extraction module, used to extract the original snoring signal from the polysomnogram; a signal processing module, used to slide along the original snoring signal using a sliding frame, Count the number of signal vertices in each sliding frame; the signal screening module is used to filter out one or more candidate segments of the snoring signal according to the number of signal vertices in each sliding frame, wherein each candidate segment of the snoring signal is The signal segment corresponding to the sliding frame whose number of signal vertices is greater than the preset threshold; the apnea event detection module is used to detect whether apnea event occurs in the preset time period before each snoring signal candidate segment; the signal classification module is used to detect As a result, the selected snoring signal candidate segments are marked as the first type of snoring signal or the second type of snoring signal, wherein the first type of snoring signal is a snoring signal related to sleep apnea, and the second type The snoring signal is a snoring signal not related to sleep apnea

[0006] The embodiment of the present invention also provides a computer device to solve the problem of monitoring sleep apnea based on directly collected snoring signals in the prior art. Due to the presence of a large number of noise signals in the directly collected snoring signals, the monitoring results will be inaccurate. Technical problem, the computer equipment includes a memory, a processor, and a computer program stored on the memory and operable on the processor, when the processor executes the computer program, the above-mentioned sleep apnea monitoring method based on snoring signals is realized

Images