Snore recognition device based on ZYNQ and deep learning

Abstract

The invention discloses a snore recognition device based on ZYNQ and deep learning. The snore recognition device comprises a snore collection module, an SD card storage module, a snore preprocessing module, a general convolutional neural network accelerator IP, a snore judgment module and a conclusion display module. The snore collection module is used for collecting audios of the detected patientin the whole night sleep state; the SD card storage module is used for snore data storage and data interaction in the data calculation process; the snore preprocessing module is used for preprocessing the data before the data enters the network; the general convolutional neural network accelerator IP is used for calculation of an Effect NeT network algorithm derivation part; the snore judgment module is used for counting based on the network calculation result and identifying the snore according to the AHI index; the conclusion display module is used for displaying a result; and the device has the advantages that the data processing speed is high, the portable equipment does not need to use an upper computer, and transplantation and development are facilitated.

Description

technical field [0001] The invention relates to the technical field of snoring recognition, in particular to a snoring recognition device based on ZYNQ and deep learning. Background technique [0002] Obstructive Sleep Apnea Hyperpnoea Syndrome (OSAHS) is a chronic sleep-breathing disease with unknown etiology. One of the clinical manifestations of OSAHS is nocturnal sleep snoring with apnea. Apnea usually causes hypoxia and hypercapnia, which can easily lead to a series of complications such as hypertension, coronary heart disease, and cerebrovascular disease. Therefore, it is very important to diagnose OSAHS as early as possible. [0003] Based on the above problems, an OSAHS identification device is very necessary. At present, a series of studies have been made in related fields and the identification of OSAHS can be realized. After investigation, most hospitals use a dedicated diagnostic device-polysomnography. (PSG), PSG is expensive, and the device is more likely to a...

AI Technical Summary

Problems solved by technology

[0003] Based on the above problems, an OSAHS identification device is very necessary. At present, a series of studies have been made in related fields and the identification of OSAHS can be realized. After investigation, most hospitals use a dedicated diagnostic device-polysomnography. (PSG), PSG is expensive, and the device is more likely to affect sleep, but interfere with the test

Images