Key result
A digital signal processing system using an NLMS adaptive filter achieved a 96% detection rate for extracting seismocardiographic data from moving adult subjects.
Adaptive filtering using an NLMS design achieves a 96% detection rate for seismocardiographic recordings in moving subjects, offering a promising technique for continuous monitoring.
May enable motion-robust SCG monitoring; leaves open clinical validation before practice adoption.
This paper presents a novel method of extracting seismocardiographic (SCG) data from moving adult subjects recorded via micro-electromechanical (MEMS) accelerometers. A digital signal processing system based on the normalized least mean square (NLMS) adaptive filter design is developed in MATLAB to process the signals collected from the MEMS sensor node. Standardized experiments were performed on 40 moving adult subjects. False-positives were ruled out for a more precise detection rate. The research on sliding ensemble average was also conducted to find the minimum required window size. The results indicate a detection rate of 96% and a sliding window size of 32 intervals for robust continuous monitoring, showing that adaptive filtering could be a promising technique for the cancellation of motion noise artifacts from SCG recordings in moving subjects.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2016) studied Moving adult subjects (n=40). Normalized least mean square (NLMS) adaptive filter was evaluated on Detection rate of seismocardiographic signals. A digital signal processing system using an NLMS adaptive filter achieved a 96% detection rate for extracting seismocardiographic data from moving adult subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: