Polyvinylidene fluoride sensor-based method for unconstrained snoring detection

Abstract

We established and tested a snoring detection method using a polyvinylidene fluoride (PVDF) sensor for accurate, fast, and motion-artifact-robust monitoring of snoring events during sleep. Twenty patients with obstructive sleep apnea participated in this study. The PVDF sensor was located between a mattress cover and mattress, and the patients' snoring signals were unconstrainedly measured with the sensor during polysomnography. The power ratio and peak frequency from the short-time Fourier transform were used to extract spectral features from the PVDF data. A support vector machine was applied to the spectral features to classify the data into either the snore or non-snore class. The performance of the method was assessed using manual labelling by three human observers as a reference. For event-by-event snoring detection, PVDF data that contained 'snoring' (SN), 'snoring with movement' (SM), and 'normal breathing' epochs were selected for each subject. As a result, the overall sensitivity and the positive predictive values were 94.6% and 97.5%, respectively, and there was no significant difference between the SN and SM results. The proposed method can be applied in both residential and ambulatory snoring monitoring systems.

Detection of Snores Using Source Separation on an Emfit Signal

“…This spectral profile is in line with our previous study [32] where a similar power spectrum density (PSD) was found when comparing snoring and normal breathing PSDs. It is also consistent why power ratios perform well in certain SN profiles [44]. However, not all snores had the same spectral profile; Fig.…”

“…However, in our experiments, several SN profiles did not contain spectral components only in this band. Another study performed with PVDF sensors by Hwang et al used a power ratio between components above and below 10 Hz [44]. Judging from the results shown in Fig.…”

“…Snoring detection using bed mattresses has been approached in by Hwang et al [44]. Compared to their method, the presented approach adapts to the SN pattern of each subject and isolates SN from the main signal.…”

“…Despite the advantages of mattress-like sensors, few studies exist about SN detection using them. Hwang et al [44] proposed an automatic SN detection algorithm using a PVDFtype mattress sensor based on two spectral features of SN events (power ratio and peak frequency) and machine learning techniques. Also, Shin et al presented simple filtering and thresholding techniques to detect SN on an AMBT [40].…”

Patient Posture Monitoring System Based on Flexible Sensors

“…The flexible sensors can be developed by microfabrication process [34,35,36,37,38], textile weaving [39,40], or commercial materials [41]. The sensors are adapted for snoring detection system [41], mobility pattern research of a person on a bed [42], human motion sensing [43,44], and real-time health and fitness monitoring [45]. …”