An adaptive band-pass filtering method combined with principal component analysis derived respiratory rate from 3D acceleration data with a mean absolute error of approximately 10% across various body activities.
Observational (n=12)
No
Does an adaptive band-pass filtering method combined with principal component analysis improve the accuracy of respiration rate estimation from 3D acceleration data in healthy subjects?
An adaptive band-pass filtering method combined with PCA accurately estimates dynamic respiration rate from 3D acceleration data during various body activities, outperforming spatial acceleration-based algorithms.
Absolute Event Rate: 10% vs 30%
Respiratory monitoring is widely used in clinical and healthcare practice to detect abnormal cardiopulmonary function during ordinary and routine activities. There are several approaches to estimate respiratory rate, including accelerometer(s) worn on the torso that are capable of sensing the inclination changes due to breathing. In this article, we present an adaptive band-pass filtering method combined with principal component analysis to derive the respiratory rate from three-dimensional acceleration data, using a body sensor network platform previously developed by us. In situ experiments with 12 subjects indicated that our method was capable of offering dynamic respiration rate estimation during various body activities such as sitting, walking, running, and sleeping. The experimental studies also suggested that our frequency spectrum-based method was more robust, resilient to motion artifact, and therefore outperformed those algorithms primarily based on spatial acceleration information.
Liu et al. (Fri,) conducted a observational in Healthy (n=12). Adaptive band-pass filtering combined with principal component analysis (ADR5) vs. Wavelet decomposition and nonadaptive band-pass filters was evaluated on Mean absolute error of derived respiratory rate compared to reference CO2 analysis. An adaptive band-pass filtering method combined with principal component analysis derived respiratory rate from 3D acceleration data with a mean absolute error of approximately 10% across various body activities.