Bahoura Mohammed
Department of Engineering, University of Quebec at Rimouski, allée des Ursulines, Que., Canada.
Comput Biol Med. 2009 Sep;39(9):824-43. doi: 10.1016/j.compbiomed.2009.06.011. Epub 2009 Jul 24.
In this paper, we present the pattern recognition methods proposed to classify respiratory sounds into normal and wheeze classes. We evaluate and compare the feature extraction techniques based on Fourier transform, linear predictive coding, wavelet transform and Mel-frequency cepstral coefficients (MFCC) in combination with the classification methods based on vector quantization, Gaussian mixture models (GMM) and artificial neural networks, using receiver operating characteristic curves. We propose the use of an optimized threshold to discriminate the wheezing class from the normal one. Also, post-processing filter is employed to considerably improve the classification accuracy. Experimental results show that our approach based on MFCC coefficients combined to GMM is well adapted to classify respiratory sounds in normal and wheeze classes. McNemar's test demonstrated significant difference between results obtained by the presented classifiers (p<0.05).
在本文中，我们展示了为将呼吸音分类为正常和哮鸣音类别而提出的模式识别方法。我们使用接收者操作特征曲线，评估并比较了基于傅里叶变换、线性预测编码、小波变换和梅尔频率倒谱系数（MFCC）的特征提取技术，以及结合了基于矢量量化、高斯混合模型（GMM）和人工神经网络的分类方法。我们提出使用优化阈值来区分哮鸣音类别和正常类别。此外，采用后处理滤波器以显著提高分类准确率。实验结果表明，我们基于MFCC系数与GMM相结合的方法非常适合将呼吸音分类为正常和哮鸣音类别。麦克尼马尔检验表明，所提出的分类器所获得的结果之间存在显著差异（p<0.05）。
