特征纹理图驱动的鼾声分类

房玉; 谢童; 刘栋博; 王维博

doi:10.16152/j.cnki.xdxbzr.2026-01-011

您当前的位置：

首页 >

文章列表页 >

特征纹理图驱动的鼾声分类

智能感知与计算 | 更新时间：2026-02-24

- 特征纹理图驱动的鼾声分类
- Classification of snore based on feature texture image
- 西北大学学报（自然科学版） 2026年56卷第1期页码：118-127
- 作者机构：
  
  西华大学　电气与电子信息学院，四川　成都　610039
- 作者简介：
  
  房玉，女，副教授，从事信号与信息处理研究，Yfang_123@163.com。
  刘栋博，男，副教授，从事模式识别、智能系统研究，liudb@mail.xhu.edu.cn。
- 基金信息：
  
  国家自然科学青年基金(61901393);国家自然科学基金(61571371);教育部春晖计划(202201500)
- DOI：10.16152/j.cnki.xdxbzr.2026-01-011
  中图分类号： TP399
- 收稿：2025-09-20，
  
  修回：2025-11-05，
  
  纸质出版：2026-02-25
- 稿件说明：
移动端阅览
房玉, 谢童, 刘栋博, 等. 特征纹理图驱动的鼾声分类[J]. 西北大学学报（自然科学版）, 2026,56(1):118-127.

FANG Yu, XIE Tong, LIU Dongbo, et al. Classification of snore based on feature texture image[J]. Journal of Northwest University (Natural Science Edition), 2026, 56(1): 118-127.
房玉, 谢童, 刘栋博, 等. 特征纹理图驱动的鼾声分类[J]. 西北大学学报（自然科学版）, 2026,56(1):118-127. DOI： 10.16152/j.cnki.xdxbzr.2026-01-011.

FANG Yu, XIE Tong, LIU Dongbo, et al. Classification of snore based on feature texture image[J]. Journal of Northwest University (Natural Science Edition), 2026, 56(1): 118-127. DOI： 10.16152/j.cnki.xdxbzr.2026-01-011.

摘要

鼾声分类是辅助医生进行睡眠呼吸暂停综合征（obstructive sleep apnea-hypopnea syndrome，OSAHS）等相关疾病预诊筛查的重要工具。目前基于音频信号时频域特征对病理性鼾声的分类精确度不高，无法满足临床需求，针对此问题，提出了一种基于高维特征纹理（feature texture，FT）图的鼾声信号分类方法。首先，对数据进行预处理，提出连续呼吸事件质量因子确定呼吸信号连续分析的数量范围；然后，提取51维时频域特征并应用ReliefF算法对特征进行筛选组合；接着，对不同的特征集进行归一化、灰度转换，构建特征纹理灰度图，并求取其水平、垂直梯度矩阵；最后，通过RGB三通道串联构建FT图。实验采用卷积神经网络对健康受试者和OSAHS患者的整晚呼吸音信号提取的FT图进行图像分类。结果表明，FT图对呼吸声、正常鼾声、OSAHS鼾声进行分类的准确率达到了97.2%，可以为后续睡眠疾病管理和研究提供参考。

Abstract

Snoring classification serves as a crucial tool for physicians in prescreening obstructive sleep apnea-hypopnea syndrome (OSAHS) and related sleep disorders. Current research on pathological snoring classification based on time-frequency domain features of audio signals faces limitations in classification accuracy

failing to meet clinical demands. To address this

we propose a high-dimensional snoring signal classification method utilizing feature texture (FT) images. The approach commences with data preprocessing

introducing a continuous respiratory event quality factor to determine the appropriate range of continuous respiratory signals. Subsequently

51 time-frequency domain features are extracted and refined through the ReliefF algorithm for optimal feature selection and combination. These feature sets undergo normalization and grayscale conversion to construct feature texture grayscale images. Horizontal and vertical gradient matrices are derived from these images

which are then concatenated across RGB channels to form FT images. Experiments employ a convolutional neural network (CNN) to classify FT images derived from overnight respiratory sound signals of healthy subjects and OSAHS patients. Classification tests encompass breathing sounds

normal snoring

and OSAHS pathological snoring

revealing that the FT image approach achieves a classification accuracy of 97.2%

offering a promising foundation for subsequent sleep disorder management and research endeavors.

关键词

Keywords

references

MIROSHNICHENKO N A , PIKHTILEVA N A . Snoring and obstructive sleep apnea syndrome as possible causes of auditory and tubal disorders [J ] . The Bulletin of Contemporary Clinical Medicine , 2021 , 14 ( 6 ): 46 - 50 .

黄志华 , 赵智慧 , 赵青 . 心血管疾病患者阻塞性睡眠呼吸暂停评估与管理专家共识(2024版) [J ] . 中国循环杂志 , 2024 , 39 ( 5 ): 417 - 432 .

HUANG Z H , ZHAO Z H , ZHAO Q . Expert consensus on the evaluation and management of obstructive sleep apnea in patients with cardiovascular disease (2024 edition) [J ] . Chinese Circulation Journal , 2024 , 39 ( 5 ): 417 - 432 .

LEEY H . Implications of obstructive sleep-related breathing disorder in dentistry: Focus on snoring and obstructive sleep apnea [J ] . Dental Research and Oral Health , 2022 , 5 ( 4 ): 74 - 82 .

郑彤 , 姚侃 , 钱轶峰 , 等 . 成年打鼾人群患阻塞性睡眠呼吸暂停的危险因素分析 [J ] . 中国口腔颌面外科杂志 , 2024 , 22 ( 2 ): 137 - 142 .

ZHENG T , YAO K , QIAN Y F , et al . Risk factors for obstructive sleep apnea in snoring adults [J ] . Chinese Journal of Oral and Maxillofacial Surgery , 2024 , 22 ( 2 ): 137 - 142 .

赵小强 , 潘毅 , 侯雨函 , 等 . 老年人阻塞性睡眠呼吸暂停综合征的诊断方法研究进展 [J ] . 中国实用医药 , 2023 , 18 ( 23 ): 165 - 169 .

ZHAO X Q , PAN Y , HOU Y H , et al . Research progress on diagnostic methods for obstructive sleep apnea syndrome in the elderly [J ] . China Practical Medicine , 2023 , 18 ( 23 ): 165 - 169 .

侯丽敏 , 刘焕成 , 施晓宇 , 等 . 基于人工神经网络的鼾声相关信号的分类 [J ] . 复旦学报(自然科学版) , 2019 , 58 ( 4 ): 530 - 536 .

HOU L M , LIU H C , SHI X Y , et al . Classification of snore-related signals based on artificial neural networks [J ] . Journal of Fudan University (Natural Science) , 2019 , 58 ( 4 ): 530 - 536 .

QIAN K , SCHMITT M , JANOTT C , et al . A bag of wavelet features for snore sound classification [J ] . Annals of Biomedical Engineering , 2019 , 47 ( 4 ): 1000 - 1011 .

FANG Y , LIU D B , ZHAO S X , et al . Improving OSAHS prevention based on multidimensional feature analysis of snoring [J ] . Electronics , 2023 , 12 ( 19 ): 4148 .

BAKHSHI A , HARIMI A , CHALUP S . CyTex: Transforming speech to textured images for speech emotion recognition [J ] . Speech Communication , 2022 , 139 : 62 - 75 .

AMIRIPARIAN S , GERCZUK M , OTTL S , et al . Snore sound classification using image-based deep spectrum features [C ] // Interspeech 2017 . Stockholm , Sweden : ISCA , 2017 : 3512 - 3516 .

DEMIR F , SENGUR A , CUMMINS N , et al . Low level texture features for snore sound discrimination [C ] // 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) . Honolulu , HI : IEEE , 2018 : 413 - 416 .

邓志平 , 王冬霞 , 马晓冬 , 等 . 基于注意力机制的NewVGG16-BiGRU鼾声分类 [J ] . 计算机应用 , 2023 , 43 ( S1 ): 276 - 280 .

DENG Z P , WANG D X , MA X D , et al . NewVGG16-BiGRU snoring classification based on attention mechanism [J ] . Journal of Computer Applications , 2023 , 43 ( S1 ): 276 - 280 .

ZHAO S X , FANG Y , WANG W B , et al . Analysis of sleeping respiratory signal utilizing frequency energy features [C ] // 2022 5th International Conference on Information Communication and Signal Processing (ICICSP) . Shenzhen , China : IEEE , 2022 : 86 - 90 .

王佳明 , 张安琪 , 郝宏燕 , 等 . 基于功率谱密度相似性的最佳心音信号选择 [J ] . 中国医学物理学杂志 , 2022 , 39 ( 11 ): 1401 - 1406 .

WANG J M , ZHANG A Q , HAO H Y , et al . Optimal heart sound signal selection based on power spectral density similarity [J ] . Chinese Journal of Medical Physics , 2022 , 39 ( 11 ): 1401 - 1406 .

DENG B Y , XUE B , HONG H , et al . Decision tree based sleep stage estimation from nocturnal audio signals [C ] // 2017 22nd International Conference on Digital Signal Processing . London , UK : IEEE , 2017 : 1 - 4 .

XUE B Y , DENG B , HONG H , et al . Non-contact sleep stage detection using canonical correlation analysis of respiratory sound [J ] . IEEE Journal of Biomedical and Health Informatics , 2020 , 24 ( 2 ): 614 - 625 .

董武亮 , 吴宁 , 彭勇 , 等 . 基于频谱特征的变压器音频监测方法研究 [J ] . 电声技术 , 2025 , 49 ( 4 ): 170 - 172 .

DOND W L , WU N , PENG Y , et al . Research on transformer audio monitoring method based on spectrum characteristics [J ] . Audio Engineering , 2025 , 49 ( 4 ): 170 - 172 .

李哲 , 陈宇 , 张博 , 等 . 基于深度学习的减压音乐重构研究 [J ] . 计算机应用与软件 , 2022 , 39 ( 8 ): 158 - 162 .

LI Z , CHEN Y , ZHANG B , et al . Research on decompression music reconstruction based on deep learning [J ] . Computer Applications and Software , 2022 , 39 ( 8 ): 158 - 162 .

李伟峰 , 周文进 . 基于频谱特征的舰船机械设备振动数据挖掘与故障定位研究 [J ] . 自动化与仪器仪表 , 2019 ( 7 ): 10 - 13 .

LI W F , ZHOU W J . Research on vibration data mining and fault location of marine machinery based on spectrum features [J ] . Automation & Instrumentation , 2019 ( 7 ): 10 - 13 .

LEI Y G , HE Z J , ZI Y Y , et al . Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs [J ] . Mechanical Systems and Signal Processing , 2007 , 21 ( 5 ): 2280 - 2294 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据