2009 · 19 citations · 16 references
EngineeringBioengineeringBiomedical EngineeringBiomedical Signal ProcessingPhysiological Systems ModelingTime Series AnalysisDigital Signal ProcessingHemodynamicsPhysiological Signal AcquisitionVital SignsVital Signs AssessmentArterial Oxygen SaturationBandpass FilteringBandpass FiltersIndependent Component AnalysisOxygen SaturationOxygen Saturation MeasurementPulse OximetersPulse Oximetry
We examine various independent component analysis (ICA) digital signal processing algorithms for estimating the arterial oxygen saturation (SpO2) as measured by a reflective pulse oximeter. The ICA algorithms examined are FastICA, Maximum Likelihood ICA (ICAML), Molgedey and Schuster ICA (ICAMS), and Mean Field ICA (ICAMF). The signal processing includes pre-processing bandpass filtering to eliminate noise, and post-processing by calculating the SpO2. The algorithms are compared to the commercial state-of-the-art algorithm Discrete Saturation Transform (DST) by Masimo Corporation. It is demonstrated that ICAMS and ICAMF perform up to 13% better than DST. PPG recordings are done with a reflective pulse oximetry sensor integrated in an Electronic Patch. This system is intended for patients with chronic heart and lung conditions.
16
Information theory, inference, and learning algorithms
Choice Reviews Online · 2004 · 6.6K citations
Adaptive noise cancelling: Principles and applications
Bernard Widrow, John R. Glover, J. McCool et al. · Proceedings of the IEEE · 1975 · 3.9K citations