FEATURE EXTRACTION AND CLASSIFICATION OF SNORE RELATED SOUNDS

机译：与雪有关的声音的特征提取和分类

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

The aim of this study is to analyze the snore relatedrnsounds (SRSs) recorded from 12 obstructive sleeprnapnea/hypopnea (OSAH) patients and 8 healthy subjectsrnduring sleep and classify into four groups by using therndecision tree classification algorithm. Firstly, SRSs werernsegmented as apnea,/hypopnea, breathing, silence andrnnormal snore parts from records. After segmentation,rnmodel order is evaluated by Akaike’s Final PredictionrnError (FPE) and parts are fitted to autoregressive (AR)rnmodel. We used model order, pitch period and energy ofrnsegments for classifier inputs. It is observed fromrnexperimental results that training and test accuracy arernsequentially %97.17 and %88.07. This results show thatrnthe model order, pitch period and energy of parts arernefficient parameters to analyze and separate SRSs asrnapnea/hypopnea, breathing, silence and normal snorernsegment and can be used for diagnosing snore soundrndisorders.

机译：本研究旨在分析12例阻塞性睡眠呼吸暂停/低通气（OSAH）患者和8位健康受试者在睡眠期间记录的打ore相关声音（SRS），并使用决策树分类算法将其分为四组。首先，SRS被细分为呼吸暂停，呼吸不足，呼吸，沉默和正常打sn部位。分割后，模型的阶次由Akaike的最终预测误差（FPE）评估，零件拟合到自回归（AR）模型。我们使用模型顺序，基音周期和段能量细分作为输入。从实验结果可以看出，训练和测试准确性分别为％97.17和％88.07。该结果表明，模型顺序，音调周期和部件能量是分析和分离SRS呼吸暂停/呼吸不足，呼吸，沉默和正常呼吸节段的有效参数，可用于诊断打sn声音障碍。

著录项

来源
《Proceedings of the 13th IASTED international conference on Signal and image processing.》|2011年|p.177-182|共6页
会议地点 Dallas TX(US);Dallas TX(US)
作者
Haydar Ank??han; Derya Y?lmaz;
展开▼
作者单位

Department of Biomedical Equipment Technology, Baskent University, Ankara, Turkey hankishan@baskent.edu.tr;

Faculty of Engineering, Department of Electric-Electronics Engineering, Ba?kent University, Ankara, Turkey derya@baskent.edu.tr;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类信号处理;信号处理;
关键词
OSA; snore sound classification; decision tree algorithm;

机译：OSA; s声分类;决策树算法;

相似文献

外文文献
中文文献
专利

1. An automated snoring sound classification method based on local dual octal pattern and iterative hybrid feature selector [J] . Tuncer Turker, Akbal Erhan, Dogan Sengul Biomedical signal processing and control . 2021,第Jana期

机译：一种基于局部双八大模式和迭代混合特征选择器的自动打鼾声音分类方法
2. A Bag of Wavelet Features for Snore Sound Classification [J] . Qian Kun, Schmitt Maximilian, Janott Christoph, Annals of Biomedical Engineering: The Journal of the Biomedical Engineering Society . 2019,第4期

机译：一袋小波特征，用于打鼾声音分类
3. Signal shape feature for automatic snore and breathing sounds classification [J] . Emoto Takahiro, Kashihara Masato, Abeyratne Udantha R., Physiological measurement . 2014,第12期

机译：信号形状功能可自动打sn和呼吸音分类
4. FEATURE EXTRACTION AND CLASSIFICATION OF SNORE RELATED SOUNDS [C] . Haydar Ank??han, Derya Y?lmaz IASTED international conference on signal and image processing . 2011

机译：组件提取和打鼾相关声音的分类
5. Feature extraction from the image of straight-edge objects and dynamic image/feature classification using non-iterative neural networks. [D] . Chanekasit, Sirikanlaya. 2004

机译：使用非迭代神经网络从直边物体的图像中提取特征并进行动态图像/特征分类。
6. Comparison of SVM and ANFIS for Snore Related Sounds Classification by Using the Largest Lyapunov Exponent and Entropy [O] . Haydar Ankışhan, Derya Yılmaz 2013

机译：SVM和ANFIS在使用最大Lyapunov指数进行打Sn相关声音分类中的比较和熵
7. Heart sound feature extraction and classification using autoregressive power spectral density (AR-PSD) and statistics features [O] . Domy Kristomo, Risanuri Hidayat, Indah Soesanti, 2016

机译：使用自回归功率谱密度（AR-PSD）和统计特征的心声特征提取和分类

FEATURE EXTRACTION AND CLASSIFICATION OF SNORE RELATED SOUNDS

摘要

著录项

相似文献

相关主题

期刊订阅