Feature Extraction for Machine Learning Based Crackle Detection in Lung Sounds from a Health Survey
Feature Extraction for Machine Learning Based Crackle Detection in Lung Sounds from a Health Survey
复制标题
基于机器学习的健康调查中肺音裂纹检测的特征提取
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
L. A. Bongo
中科院分区：
文献类型：
--
作者：
Morten Grønnesby;Juan Carlos Aviles Solis;Einar J. Holsbø;H. Melbye;L. A. Bongo
近年来，许多用于记录和查看来自听诊器的声音的创新解决方案已经变得可用。然而，为了充分利用这样的设备，需要一种用于检测异常肺音的自动化方法，该方法比通常使用小且非多样的数据集开发和评估的现有方法更好。
我们提出了一种基于机器学习的方法，用于检测在大型健康调查中使用听诊器记录的肺部声音中的爆裂音。我们的方法使用209个文件进行训练和评估，这些文件由专家听众分类。我们的分析管道基于从音频文件中的小窗口提取的特征。我们评估了几种特征提取方法和分类器。我们使用175个裂纹窗口和208个正常窗口的训练集来评估管道。我们进行了100个循环的交叉验证，在循环之间对训练集进行了洗牌。培训和评估之间的比例为70%-30%。
我们发现并评估了一个5维向量，其中四个特征来自时域，一个来自频谱域。我们评估了几个分类器，发现带有径向基函数核的SVM表现最好。我们的方法对窗户中的裂纹进行分类的准确率为86%，召回率为84%，这比对卫生人员的研究更准确。低维特征向量使得SVM非常快。该模型可以在1.44秒内在普通计算机上训练完毕，并可以在1.08秒内对319种爆裂声进行分类。
我们的方法检测并可视化录制的音频文件中的单个噼啪声。它准确、快速，并且资源需求低。它可用于培训卫生人员或作为蓝牙听诊器智能手机应用程序的一部分。
In recent years, many innovative solutions for recording and viewing sounds from a stethoscope have become available. However, to fully utilize such devices, there is a need for an automated approach for detecting abnormal lung sounds, which is better than the existing methods that typically have been developed and evaluated using a small and non-diverse dataset.
We propose a machine learning based approach for detecting crackles in lung sounds recorded using a stethoscope in a large health survey. Our method is trained and evaluated using 209 files with crackles classified by expert listeners. Our analysis pipeline is based on features extracted from small windows in audio files. We evaluated several feature extraction methods and classifiers. We evaluated the pipeline using a training set of 175 crackle windows and 208 normal windows. We did 100 cycles of cross validation where we shuffled training sets between cycles. For all the division between training and evaluation was 70%-30%.
We found and evaluated a 5-dimenstional vector with four features from the time domain and one from the spectrum domain. We evaluated several classifiers and found SVM with a Radial Basis Function Kernel to perform best. Our approach had a precision of 86% and recall of 84% for classifying a crackle in a window, which is more accurate than found in studies of health personnel. The low-dimensional feature vector makes the SVM very fast. The model can be trained on a regular computer in 1.44 seconds, and 319 crackles can be classified in 1.08 seconds.
Our approach detects and visualizes individual crackles in recorded audio files. It is accurate, fast, and has low resource requirements. It can be used to train health personnel or as part of a smartphone application for Bluetooth stethoscopes.
影响因子：
4.3
作者：
Gurung, Arati;Scrafford, Carolyn G.;Tielsch, James M.;Levine, Orin S.;Check, William
通讯作者：
Check, William