Classification of wheeze in respiratory sounds by linear discriminant method

The aim of this study is classification of wheeze and non-wheeze using some selected features and detection of wheeze in respiratory sound signals acquired from patients with asthma and COPD. Taking into consideration that wheeze, having a sinusoidal waveform, has a different behavior in time-frequency domain from that of non-wheeze signals, features are chosen as kurtosis, Renyi entrophy, f50/f90 ratio and zero-crossing irregularity. Upon calculation of these features for each wheeze and non-wheeze portion, the whole data scattered as two classes in four dimensional feature space is projected using Fisher Discriminant Analysis (FDA) onto the single dimensional space that separates the two classes best. Observing that the two classes are visually well separated in this new space, Neyman-Pearson hypothesis testing is applied. Finally, the success rate has been found to be %94.9 for the training set, and leave-one-out approach together with the above methodology yields a success rate of %93.5 for the test set. Ending up with these results for both training and test sets, one can conclude that selected features and methodology are meaningful.

[1]  Richard O. Duda,et al.  Pattern Classification by Iteratively Determined Linear and Piecewise Linear Discriminant Functions , 1966, IEEE Trans. Electron. Comput..

[2]  J. G. Gander,et al.  An introduction to signal detection and estimation , 1990 .

[3]  D. Scuse,et al.  A comparison of neural network models for wheeze detection , 1995, IEEE WESCANEX 95. Communications, Power, and Computing. Conference Proceedings.

[4]  H. Pasterkamp,et al.  Respiratory sounds. Advances beyond the stethoscope. , 1997, American journal of respiratory and critical care medicine.

[5]  E. H. Dooijes,et al.  Classification of Asthmatic Breath Sounds: Preliminary Results of the Classifying Capacity of Human Examiners versus Artificial Neural Networks , 1999, Comput. Biomed. Res..

[6]  Aintree Chest,et al.  Current methods used for computerized respiratory sound analysis , 2000 .

[7]  Stavros M. Panas,et al.  WED: An efficient wheezing-episode detector based on breath sounds spectrogram analysis , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[8]  Antoni Homs-Corbera,et al.  Time-frequency detection and analysis of wheezes during forced exhalation , 2004, IEEE Transactions on Biomedical Engineering.

[9]  T. Penzel,et al.  On Applying Continuous Wavelet Transform in Wheeze Analysis , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[10]  N. Malmurugan,et al.  Neural classification of lung sounds using wavelet coefficients , 2004, Comput. Biol. Medicine.

[11]  Y.P. Kahya,et al.  A Multi-Channel Device for Respiratory Sound Data Acquisition and Transient Detection , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[12]  Hüseyin Polat,et al.  Combining Neural Network and Genetic Algorithm for Prediction of Lung Sounds , 2005, Journal of Medical Systems.

[13]  Leontios J. Hadjileontiadis,et al.  Wheeze detection based on time-frequency analysis of breath sounds , 2007, Comput. Biol. Medicine.

[14]  Zümray Dokur,et al.  Respiratory sound classification by using an incremental supervised neural network , 2009, Pattern Analysis and Applications.