SVM-based Efficient Sleep States Classification and Management Derived from Breath Sound Measurements

Shenghong Lin; Xiangyang Kong

doi:10.54097/ze8p7p42

Authors

Shenghong Lin
Xiangyang Kong

DOI:

https://doi.org/10.54097/ze8p7p42

Keywords:

Sleep States, Breath Sound, Spectrum Characteristics, Multiple Features, SVM

Abstract

Breath sounds (BS) contain important physiological indicators, making their analysis and detection a well-established area of study. This paper proposes a method for identifying and classifying sleep stages based on the spectral power and spectral flux of breath sounds. These multiple features effectively capture the characteristics of breath sounds, enabling efficient classification of data related to both normal and abnormal breath sounds. We employ support vector machine (SVM) classification models to achieve automatic, high-efficiency classification using the spectral characteristics of breath sounds. The high classification accuracy obtained validates the performance of the proposed feature sets and classification model. Additionally, the experimental results demonstrate that breath sounds can be used to evaluate sleep states as an alternative to commercial products.

Downloads

Download data is not yet available.

References

[1] Rechtschaffen A, Kales A, editors. A manual of standardized terminology, techniques and scoring system for sleep stages of human subject. Washington, DC: US Government Printing Office, National Institute of Health Publication; 1968.

[2] Iber C, Ancoli-Israel I, Chesson AL, Quan SF. The AASM manual for the scoring of sleep and associated events: rules, terminology, and technical specification. American Academy of Sleep Medicine; 2007.

[3] Agarwal R, Gotman J. Digital tools in polysomnography.[J]. Journal of Clinical Neurophysiology Official Publication of the American Electroencephalographic Society, 2002, 19(2):136-43.

[4] Christian B , Xavier D ,Herman-Stoïca Maria,et al.Automatic analysis of single-channel sleep EEG: validation in healthy individuals.[J].Sleep,2007(11):1587-1595.

[5] Chih-Sheng H, Chun-Ling L, Li-Wei K , et al. Knowledge-based identification of sleep stages based on two forehead electroencephalogram channels[J]. Frontiers in Neuroscience, 2014, 8:263.

[6] Stich W . Classification of sleep stages using multi-wavelet time frequency entropy and LDA[J]. Methods of Information in Medicine, 2010, 49(03):230-237.

[7] Gr?Zinger M , Jürgen Fell, R?Schke J . Neural net classification of REM sleep based on spectral measures as compared to nonlinear measures.[J]. Biological Cybernetics, 2001, 85(5):335-341.

[8] Kerkeni N, Ben Cheikh R, Bedoui MH, Alexandre Dogui M. Sleep stages classification by hierarchical artificial neural networks. IRBM 2012;33:35–40.

[9] Marina, Ronzhina, and, et al. Sleep scoring using artificial neural networks[J]. Sleep Medicine Reviews, 2012.

[10] Krakovska A, Mezeiova K. Automatic sleep scoring: A search for an optimal combination of measures[J]. Artificial Intelligence In Medicine, 2011, 53(1):25-33.

[11] Lei B , Rahman S A , Song I . Content-based classification of breath sound with enhanced features[J]. Neurocomputing, 2014, 141(oct.2):139-147.

[12] Cortes C , Vapnik V . Support-Vector Networks[J]. Machine Learning, 1995, 20(3):273-297.

[13] Burges C J C . A Tutorial on Support Vector Machines for Pattern Recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.

[14] Choi S, Jiang Z. Detection of valvular heart disorders using wavelet packet decomposition and support vector machine[J]. Expert Systems with Applications, 2008, 35(4):1679-1687.