Title: Testing the system non-linearity in snoring sound via neural networks

Authors: Takahiro Emoto; Udantha R. Abeyratne; Masatake Akutagawa; Yohsuke Kinouchi; Shinsuke Konaka

Addresses: Institute of Technology and Science, The University of Tokushima, 2-1 Minamijyousanjima-cho, Tokushima 770-8506, Japan. ' School of Info. Tech. and Electrical Engineering, The University of Queensland, St. Lucia, Brisbane QLD4072, Australia. ' Institute of Technology and Science, The University of Tokushima, Japan 2-1 Minamijyousanjima-cho, Tokushima 770-8506, Japan. ' Institute of Technology and Science, The University of Tokushima, Japan 2-1 Minamijyousanjima-cho, Tokushima 770-8506, Japan. ' Institute of Technology and Science, The University of Tokushima, Japan 2-1 Minamijyousanjima-cho, Tokushima 770-8506, Japan

Abstract: Obstructive sleep apnea (OSA) is a serious disease caused by the collapse of upper airways during sleep. OSA is almost always accompanied by snoring. While snoring is not currently used in the clinical diagnosis of OSA, there have been intense efforts recently to model snoring for that purpose. Conventional approach is to treat snores as the outcome of a linear process and apply techniques such as linear prediction coding (LPC). However, the snores are likely to have diagnostically relevant non-linearities that cannot be captured by linear techniques. In this paper, we investigate the non-linearity of snores and develop a novel measure, as a possible characterisation index. The method is based on artificial neural networks (NN). The developed method was tested on a database of 27 subjects (5568 snoring episodes), categorised into two groups based on their respiratory disturbance index (RDI).

Keywords: obstructive sleep apnea; OSA; snoring sounds; artificial neural networks; ANNs; nonlinearity; snores; respiratory disturbance index.

DOI: 10.1504/IJMEI.2011.042875

International Journal of Medical Engineering and Informatics, 2011 Vol.3 No.3, pp.299 - 310

Published online: 07 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article