6533b821fe1ef96bd127b4bf

RESEARCH PRODUCT

Semi-blind Source Extraction Methods: Application to the measurement of non-contact physiological signs

subject

description

Non-contact physiological measurements are highlydesirable in many biomedical fields such asdiagnosis of infants, geriartic patients, patients withextreme physical trauma, and fitness and well-being.Remote photoplethysmography is increasingly beingused for non-contact measurement of heart rate fromvideos which is one of the most common biomedicalproperty required for most medical diagnosis. Oneof the common techniques for performing remotephotoplethysmography involves using Blind SourceSeparation (BSS) methods to extract the cardiacsignal from video data.In this context, the objective of this thesis is todevelop different methods in the field of extractionand separation of sources by improving upontraditional BSS methods. These novel semiblindsource extraction methods are integratedwith biophysical constraints, and applied tothe application of remote photoplethysmographymeasurement. In addition, one of these methodsis extended to measure the spatial distribution ofphotoplethysmographic signals of the skin.Remote photoplethysmography aims to measurebiophysical parameters such as heart rate and heartrate variability by quantifying the periodic changes inskin color due to the rhythmic beating of the heart.These changes manifest in the image data obtainedfrom simple video cameras, which is processedto generate a temporal signal representing thecardiac signal. We have improved existing methodsby incorporating the ubiquitous property of quasiperiodicityof biophysical signals such as cardiac andneurological signals. Quasi-periodic signals havehigher autocorrelation than non-periodic signals.This observation was combined with independentcomponent analysis techniques and GeneralizedEigenvalue Decomposition (GEVD) to develop semiblindsource extraction methods.