High-precision snore detection method based on deep learning

Abstract

Obstructive sleep apnea hypopnea syndrome (OSAHS) is a sleep-related respiratory disease, and sleep snoring is its most common and direct feature. However, the current snoring detection methods require a lot of medical manpower and medical equipment resources, resulting in many OSAHS patients can not be treated in time. Therefore, this paper proposes a snore detection method based on deep learning and a snore dataset. The detection method first calculates the time-domain waveform, spectrogram, and Mel-spectrogram for each audio segment in the snore dataset. Then, the snore is recognized by convolution neural network. To better apply this method to mobile devices and intelligent devices, MobileNetV2 is selected as the detection network to classify snoring and non-snoring images. The experimental results show that the proposed method can accurately recognize snores with 95.00% accuracy. And the spectrogram can better reflect the difference between snoring and non-snoring images.

A New High-Precision and Lightweight Detection Model for Illegal Construction Objects Based on Deep Learning

“…Ishii et al [64] employed CNN for the classification of multispectral satellite images, and adapted the fully connected layers to convolutional layers for processing images of varying resolutions. Xu et al [19] utilized deep learning based techniques alongside guided filters to isolate constructions from high-resolution images. Prathap and Afanasyev [65] adopted an enhanced version of UNet for detecting constructions.…”

“…As machine learning and image processing technology advance, the detection technology of illegal buildings has achieved a certain degree of automation or semi-automation [15] . Building image segmentation [16] , Hough transform [17] , K-Means [18] , and classification based on machine learning [19] are used to detect changes in building areas. Nevertheless, these approaches necessitate manual extraction of illegal building characteristics, and the detection accuracy is inadequate.…”