Sleep snoring sound classification detecting method and system based on depth learning

Abstract

The invention discloses a sleep snoring sound classification detecting method based on depth learning. The method mainly comprises the steps of collecting sleep sound signals of a patient to be detected all night long through a sensor, detecting sonic sections in the sleep sound signals, and obtaining a sonic section map in the sleep sound signals; adopting depth learning for performing snoring sound and non-snoring sound classification on the sonic section map, and reserving a pure-snoring sound recognition result; then, adopting the depth learning for classifying four types of snore sounds for the pure-snoring sound recognition result, and completing automatic recognition and detection on snoring sounds of the patient suffering from obstructive sleep apnea-hypopnea syndrome (OSAHS); according to the snoring sound recognizing and detecting result, counting the number of snoring sounds of each type of the patient to be detected all night long, and obtaining an AHI index of the patientto be detected all night long. The invention further discloses a detecting system of the sleep snoring sound classification detecting method based on depth learning. The method and system can effectively and accurately evaluate whether or not a snoring object falls ill and evaluate the illness degree, and data references are provided for the patient suffering from the OSAHS.

Description

technical field [0001] The invention relates to the technical field of disease detection, in particular to a method and system for classifying and detecting sleep snoring based on deep learning. Background technique [0002] Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a relatively serious sleep-disordered breathing. Sometimes snoring accompanied by apnea or low respiratory flow. Apnea refers to the situation where the patient's breathing airflow disappears for more than 10 seconds while sleeping, and hypopnea refers to the situation where the patient's respiratory airflow intensity is less than 50% of the basic value while sleeping, and the blood oxygen concentration drops below 96% of the normal level. . [0003] For the detection of OSAHS, the traditional method is to monitor and measure the patient's sleep for 6 to 7 hours through a polysomnography device, which can record and analyze EEG (electroencephalogram), ECG (electrocardiogram), EOG (electrooculogram) ...

AI Technical Summary

Problems solved by technology

[0003] For the detection of OSAHS, the traditional method is to monitor and measure the patient's sleep for 6 to 7 hours through a polysomnography device, which can record and analyze EEG (electroencephalogram), ECG (electrocardiogram), EOG (electrooculogram) , EMG (electromyography), snoring, blood oxygen saturation, respiratory rate, body position and other physical sign parameters during sleep. This method is accurate and reliable, but because more than 15 leads need to be placed on the patient, it affects the patient Normal sleep state, and it is expensive, and the information obtained through polysomnography (PSG) must use manual identification of problems, which is very inconvenient, people are looking for cost-effective and reliable auxiliary diagnostic methods

Images