期刊
ARCHIVES OF ACOUSTICS
卷 48, 期 1, 页码 3-12出版社
POLSKA AKAD NAUK, POLISH ACAD SCIENCES, INST FUNDAMENTAL TECH RES PAS
DOI: 10.24425/aoa.2022.142906
关键词
snoring recognition; wavelet packet transform; feature selection; machine learning
类别
This paper proposes an automatic snoring detection system based on the wavelet packet transform (WPT) and eXtreme Gradient Boosting (XGBoost) classifier, which recognizes snoring sounds using the enhanced episodes by the generalization subspace noise reduction algorithm. The feature selection technology based on correlation analysis is applied to select the most discriminative WPT features. Experimental results show that WPT is effective in analyzing snoring and non-snoring sounds.
Snoring is a typical and intuitive symptom of the obstructive sleep apnea hypopnea syndrome (OSAHS), which is a kind of sleep-related respiratory disorder having adverse effects on people's lives. Detecting snoring sounds from the whole night recorded sounds is the first but the most important step for the snoring analysis of OSAHS. An automatic snoring detection system based on the wavelet packet transform (WPT) with an eXtreme Gradient Boosting (XGBoost) classifier is proposed in the paper, which recognizes snoring sounds from the enhanced episodes by the generalization subspace noise reduction algorithm. The feature selection technology based on correlation analysis is applied to select the most discriminative WPT features. The selected features yield a high sensitivity of 97.27% and a precision of 96.48% on the test set. The recognition performance demonstrates that WPT is effective in the analysis of snoring and non-snoring sounds, and the difference is exhibited much more comprehensively by sub-bands with smaller frequency ranges. The distribution of snoring sound is mainly on the middle and low frequency parts, there is also evident difference between snoring and non-snoring sounds on the high frequency part.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据