School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China.
Department of Otolaryngology, Beijing Hospital, National Center of Gerontology, Beijing, China.
Biomed Mater Eng. 2020;31(3):143-155. doi: 10.3233/BME-201086.
Snoring source analysis is essential for an appropriate surgical decision for both simple snorers and obstructive sleep apnea/hypopnea syndrome (OSAHS) patients.
As snoring sounds carry significant information about tissue vibrations within the upper airway, a new feature entitled compressed histogram of oriented gradients (CHOG) is proposed to recognize vibration patterns of the snoring source acoustically by compressing histogram of oriented gradients (HOG) descriptors via the multilinear principal component analysis (MPCA) algorithm.
Each vibration pattern corresponds to a sole or combinatorial vibration among the four upper airway soft tissues of soft palate, lateral pharyngeal wall, tongue base, and epiglottis. 1037 snoring events from noncontact sound recordings of 76 simple snorers or OSAHS patients during drug-induced sleep endoscopy (DISE) were evaluated.
With a support vector machine (SVM) as the classifier, the proposed CHOG achieved a recognition accuracy of 89.8% for the seven observable vibration patterns of the snoring source categorized in our most recent work.
The CHOG outperforms other single features widely used for acoustic analysis of sole vibration site.
对于单纯性打鼾者和阻塞性睡眠呼吸暂停低通气综合征（OSAHS）患者，打鼾源分析对于做出恰当的手术决策至关重要。
由于打鼾声携带了上气道组织振动的重要信息，因此提出了一种新的特征，即压缩方向梯度直方图（CHOG），通过多线性主成分分析（MPCA）算法对方向梯度直方图（HOG）描述符进行压缩，从而从声学上识别打鼾源的振动模式。
每个振动模式对应于软腭、侧咽壁、舌根和会厌四个上气道软组织中的单一或组合振动。对 76 例接受药物诱导睡眠内镜（DISE）检查的单纯性打鼾者或 OSAHS 患者的非接触性声音记录中的 1037 次打鼾事件进行了评估。
使用支持向量机（SVM）作为分类器，我们最近的研究将打鼾源的七种可观察到的振动模式分为七类，提出的 CHOG 对其的识别准确率达到了 89.8%。
与其他用于单一振动部位声学分析的常用特征相比，CHOG 的性能表现更好。
