Wavelength selection and outlier detection in reduced rank linear models
First Claim
1. A method for selecting useful channels in a non-invasive medical device comprising:
- embedding a discrete predictor problem into continuous space of a predictor preweighting;
executing an optimization algorithm to optimize a preweighting vector, wherein the optimization algorithm determines the relative importance of the each predictor;
constructing n different models, wherein a kth model comprises the k most important predictors;
comparing the models using an information criterion to allow for automatic selection of a subset of the predictors; and
deriving an analytical Jacobian of the partial least squares regression vector with respect to the predictor weighting to optimize the predictor weighting and select useful channels for use in the non-invasive medical device.
3 Assignments
0 Petitions
Accused Products
Abstract
There is provided an optimization system and method for identifying useful channels. The method for selecting useful channels includes embedding a discrete predictor problem into continuous space of a predictor preweighting and executing an optimization algorithm to optimize a preweighting vector, wherein the optimization algorithm determines the relative importance of the each predictor. Also, the method includes constructing n different models, wherein a kth model comprises the k most important predictors and comparing the models using an information criterion to allow for automatic selection of a subset of the predictors. Additionally, an analytical Jacobian of the partial least squares regression vector is derived with respect to the predictor weighting to optimize the predictor weighting and select useful channels for use in the non-invasive medical device.
923 Citations
15 Claims
-
1. A method for selecting useful channels in a non-invasive medical device comprising:
-
embedding a discrete predictor problem into continuous space of a predictor preweighting; executing an optimization algorithm to optimize a preweighting vector, wherein the optimization algorithm determines the relative importance of the each predictor; constructing n different models, wherein a kth model comprises the k most important predictors; comparing the models using an information criterion to allow for automatic selection of a subset of the predictors; and deriving an analytical Jacobian of the partial least squares regression vector with respect to the predictor weighting to optimize the predictor weighting and select useful channels for use in the non-invasive medical device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A system for identifying useless predictors comprising:
-
a memory storing a predictor preweighting algorithm embedded with a discrete predictor problem; and a processor communicatively coupled to the memory and configured to execute the algorithm to, wherein execution of the algorithm by the processor comprises; executing an optimization algorithm to optimize a preweighting vector, wherein the optimization algorithm determines the relative importance of the each predictor; constructing n different models, wherein a kth model comprises the k most important predictors; automatically selecting a subset of predictors by comparing the models using an information criterion; and deriving an analytical Jacobian of the partial least squares regression vector with respect to the predictor weighting to optimize the predictor weighting and select useful channels for use in the non-invasive medical device. - View Dependent Claims (12, 13, 14, 15)
-
Specification