Motion Artifact Detection and Reduction in Bed-Based Ballistocardiogram

Abstract

Non-intrusive sleep monitoring is critical for certain populations such as severely disabled autistic children. Nocturnal disturbance analysis is an important diagnostic tool for assessing sleep issues. The objective of this paper is to detect and minimize the effects of motion artifacts in signals recorded via an unobtrusive electromechanical film-based ballistocardiogram (BCG) sensor integrated into a smart bed system. The goal is to have a reliable estimation of beat-to-beat (B-B) interval. The proposed algorithm includes two main stages: a motion detection algorithm followed by a motion artifact removal system. Motion detection involves a sequential detection algorithm in which successive data frames are compared to two thresholds: upper and lower thresholds. Each motion corrupted frame can then be reconstructed by an approach that relies on a parametric model of the BCG signal. Exploiting the fact that the underlying BCG parameters (J-peak-to-J-peak interval, J-peak-to-K-peak amplitude, and the most significant frequency component) change slowly and are correlated across time; an autoregressive model-based tracking and Wiener smoother based parameter estimation strategies are proposed. The experimental results are presented to demonstrate the effectiveness of the proposed motion artifact detection and removal algorithms. The probability of detection of 96% and high average coverage of 84% with over 90% precision for the estimated B-B intervals are achieved on recordings for 19 h of sleep from three subjects. Our novel motion detection and removal methods demonstrate the feasibility of using bed-based BCG signals for providing a reliable unobtrusive way to estimate the B-B interval in the presence of motion.

Keywords

• Autism
• autoregressive model
• ballistocardiogram
• motion artifact detection and removal
• Wiener smoothing