Viavi Solutions Inc.

Lan Sun

Changmeng Hsiung

Chang Meng Hsiung

Christopher G Pederson

Marc K Von Gunten

Peng Zou

Michael Klimek

Edward Gooding

Babs Soller

A device may receive spectroscopic data associated with a dynamic process. The device may identify a pseudo steady state end point based on the spectroscopic data. The pseudo steady state end point may indicate an end of a pseudo steady state associated with the dynamic process. The device may identify a reference block and a test block based on the pseudo steady state end point, and may generate a raw detection signal associated with the reference block and a raw detection signal associated with the test block. The device may generate an averaged statistical detection signal based on the raw detection signal associated with the reference block and the raw detection signal associated with the test block, and may determine whether the dynamic process has reached a steady state based on the averaged statistical detection signal.

Dynamic process end point detection

A device may obtain a heartbeat profile of a current subject, the heartbeat profile being based on photoplethysmography (PPG) data associated with a set of wavelength channels. The device may determine a global model including a plurality of classes, each associated with a subject identifier and a blood pressure level (BPL) identifier. The device may identify a class as a closest class to the current subject based on the heartbeat profile of the current subject. The device may identify a local subject associated with the closest class based on the subject identifier associated with the closest class. The device may generate a BPL estimation model for the current subject based on heartbeat profile data for the local subject. The device may determine a BPL estimation for the current subject based on the heartbeat profile of the current subject and using the BPL estimation model.

Blood pressure estimation with photoplethysmography measurement

A device may receive a master data set for a first spectroscopic model; receive a target data set for a target population associated with the first spectroscopic model to update the first spectroscopic model; generate a training data set that includes the master data set and first data from the target data set; generate a validation data set that includes second data from the target data set and not the master data set; generate, using cross-validation and using the training data set and the validation data set, a second spectroscopic model that is an update of the first spectroscopic model; and provide the second spectroscopic model.

Cross-validation based calibration of a spectroscopic model

A device may determine end-of-phase information for a plurality of wavelength channels of photoplethysmography (PPG) data. The device may calculate a set of baseline correction points for each wavelength channel of the plurality of wavelength channels. The set of baseline correction points may be calculated based on end-of-phase information for a wavelength channel of the plurality of wavelength channels and PPG data associated with the wavelength channel. The device may perform a baseline correction for each wavelength channel of the plurality of wavelength channels. A baseline correction may be performed for the wavelength channel based on the set of baseline correction points associated with the wavelength channel and the PPG data associated with the wavelength channel. The device may generate a baseline corrected heartbeat profile using a principal component analysis of a result of baseline correcting each wavelength channel of the plurality of wavelength channels.

Baseline correction and extraction of heartbeat profiles

In some implementations, a device may identify, based on spectroscopic data, a pseudo steady state end point indicating an end of a pseudo steady state associated with the blending process. The device may identify a reference block and a test block from the spectroscopic data based on the pseudo steady state end point. The device may generate a raw detection signal associated with the reference block and a raw detection signal associated with the test block. The device may generate a statistical detection signal based on the raw detection signal associated with the reference block and the raw detection signal associated with the test block. The device may determine whether the blending process has reached a steady state based on the statistical detection signal.

Blending process end point detection

In some implementations, a device may receive spectroscopic data associated with a dynamic process. The device may generate a principal component analysis (PCA) model based on a first block of spectra from the spectroscopic data. The device may project a second block of spectra from the spectroscopic data to the PCA model generated based on the first block of spectra. The device may determine a value of a metric associated with the second block based on projecting the second block of spectra to the PCA model. The device may determine whether the dynamic process has reached an end point based on the value of the metric associated with the second block.

Rolling principal component analysis for dynamic process monitoring and end point detection

A device may obtain a master beta coefficient of a master calibration model associated with a master instrument. The master beta coefficient may be at a grid of a target instrument. The device may perform constrained optimization of an objective function, in accordance with a set of constraints, in order to determine a pair of transferred beta coefficients. The constrained optimization may be performed based on an initial pair of transferred beta coefficients, the master beta coefficient, and spectra associated with a scouting set. The device may determine, based on the pair of transferred beta coefficients, a transferred beta coefficient. The device may determine a final transferred beta coefficient based on a set of transferred beta coefficients including the transferred beta coefficient. The final transferred beta coefficient may be associated with generating a transferred calibration model, corresponding to the master calibration model, for use by the target instrument.

Focusing linear model correction and linear model correction for multivariate calibration model maintenance

A device may obtain absorption spectra data associated with tissue of a subject. The device may determine, based on the absorption spectra data, an estimate of a water content associated with the tissue. The device may determine, based on the estimate of the water content, an estimate of a hydration level of the subject. The device may perform one or more actions based on the estimate of the hydration level of the subject.

Hydration assessment using a sensor

A device may receive information identifying results of a set of spectroscopic measurements of a training set of known samples and a validation set of known samples. The device may generate a classification model based on the information identifying the results of the set of spectroscopic measurements, wherein the classification model includes at least one class relating to a material of interest for a spectroscopic determination, and wherein the classification model includes a no-match class relating to at least one of at least one material that is not of interest or a baseline spectroscopic measurement. The device may receive information identifying a particular result of a particular spectroscopic measurement of an unknown sample. The device may determine whether the unknown sample is included in the no-match class using the classification model. The device may provide output indicating whether the unknown sample is included in the no-match class.

Reduced false positive identification for spectroscopic classification

A device may receive information identifying results of a spectroscopic measurement of an unknown sample. The device may perform a first classification of the unknown sample based on the results of the spectroscopic measurement and a global classification model. The device may generate a local classification model based on the first classification. The device may perform a second classification of the unknown sample based on the results of the spectroscopic measurement and the local classification model. The device may provide information identifying a class associated with the unknown sample based on performing the second classification.

Identification using spectroscopy

In some implementations, a device may determine that an unknown sample is an outlier sample by using an aggregated classification model. The device may determine that one or more spectroscopic measurements are not performed accurately based on determining that the unknown sample is the outlier sample. The device may cause one or more actions based on determining the one or more spectroscopic measurements are not performed accurately.

Growing community of inventors

Santa Rosa, CA, United States of America

Lan Sun