A viable snore detection system: hardware and software implementations

Abstract

A stand-alone, custom-made biomedical system was introduced for long-term monitoring of sleep anddetection of snoring events. Commercially available electronic components were assembled for recording audio, pulse, andrespiration signals. Its software was implemented for off-line processing of the acquired signals in C++ and MATLABenvironments. The linear and nonlinear features of the signals were extracted and characterized using spectral energydistribution, entropy, and largest Lyapunov exponent (LLE). The performance of the system was evaluated with realphysiological data gathered from 14 chronic snorers. Analysis of the cases indicated that the system identified the snoringevents with an accuracy of 88.22%, sensitivity of 94.91%, and positive predictive value of 90.95%. This high level ofvalidation confirmed the reliability and utility of the system in detecting snoring.