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 and detection of snoring events. Commercially available electronic components were assembled for recording audio, pulse, and respiration signals. Its software was implemented for off-line processing of the acquired signals in C++ and MATLAB environments. The linear and nonlinear features of the signals were extracted and characterized using spectral energy distribution, entropy, and largest Lyapunov exponent (LLE). The performance of the system was evaluated with real physiological data gathered from 14 chronic snorers. Analysis of the cases indicated that the system identified the snoring events with an accuracy of 88.22%, sensitivity of 94.91%, and positive predictive value of 90.95%. This high level of validation confirmed the reliability and utility of the system in detecting snoring.