Reduced false positive identification for spectroscopic quantification
A device may receive information identifying results of a spectroscopic measurement performed on an unknown sample. The device may determine a decision boundary for a quantification model based on a configurable parameter, such that a first plurality of training set samples of the quantification model is within the decision boundary and a second plurality of training set samples of the quantification model is not within the decision boundary. The device may determine a distance metric for the spectroscopic measurement performed on the unknown sample relative to the decision boundary. The device may determine a plurality of distance metrics for the second plurality of training set samples of the quantification model relative to the decision boundary. The device may provide information indicating whether the spectroscopic measurement performed on the unknown sample corresponds to the quantification model.
1. A method, comprising:
providing, by a device and to a spectrometer, instructions to perform one or more spectroscopic measurements;
receiving, by the device and from the spectrometer, sets of spectra based on providing the instructions to perform the one or more spectroscopic measurements;
training, by the device, a global classification model using a hier-support vector machine (SVM)-linear classifier and a first set of spectra of the sets of spectra;
verifying, by the device, the global classification model using the hier-SVM-linear classifier and a second set of spectra of the sets of spectra; and
providing, by the device, multiple quantification models after verifying the global classification model.
2. The method of claim 1 , wherein providing the multiple quantification models comprises:
providing one or more of the multiple quantification models to a first different device associated with a first different spectrometer and to a second different device associated with a second different spectrometer.
3. The method of claim 1 , further comprising:
training and verifying multiple local quantification models associated with the global classification model,
wherein the multiple local quantification models include one or more of the multiple quantification models.
4. The method of claim 1 , wherein the multiple quantification models include:
a first quantification model corresponding to a first class of the global classification model, and
a second quantification model corresponding to a second class of the global classification model.
5. The method of claim 1 , wherein the multiple quantification models include:
a first quantification model corresponding to a first class of a local classification model generated based on the global classification model, and
a second quantification model corresponding to a second class of the local classification model.
6. The method of claim 1 , wherein the instructions to perform the one or more spectroscopic measurements comprise instructions to perform the one or more spectroscopic measurements on a training set and a validation set.
7. The method of claim 1 , wherein the multiple quantification models include:
a first quantification model for determining a concentration of a particular protein in a first type of meat identified using in-situ local modeling, and
a second quantification model for determining the concentration of the particular protein in a second type of meat identified using in-situ local modeling.
8. A device, comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
receive, from a spectrometer, sets of spectra associated with one or more spectroscopic measurements;
train a global classification model using a hier-support vector machine (SVM)-linear classifier and a first set of spectra of the sets of spectra;
verify the global classification model using the hier-SVM-linear classifier and a second set of spectra of the sets of spectra; and
provide multiple quantification models after verifying the global classification model.
9. The device of claim 8 , wherein the one or more processors, to provide the multiple quantification models, are configured to:
provide one or more of the multiple quantification models to a first different device associated with a first different spectrometer and to a second different device associated with a second different spectrometer.
10. The device of claim 8 , wherein the one or more processors are further configured to:
train multiple local quantification models associated with the global classification model,
wherein the multiple local quantification models include one or more of the multiple quantification models.
11. The device of claim 8 , wherein the multiple quantification models include:
a first quantification model corresponding to a first class of the global classification model, and
a second quantification model corresponding to a second class of the global classification model.
12. The device of claim 8 , wherein the multiple quantification models include:
a first quantification model corresponding to a first class of a local classification model generated based on the global classification model, and
a second quantification model corresponding to a second class of the local classification model.
13. The device of claim 8 , wherein the multiple quantification models include
a first quantification model for determining a concentration of a particular protein in a first type of meat identified using in-situ local modeling, and
a second quantification model for determining the concentration of the particular protein in a second type of meat identified using in-situ local modeling.
14. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
provide, to a spectrometer, instructions to perform one or more spectroscopic measurements;
receive, from the spectrometer, sets of spectra based on providing the instructions to perform the one or more spectroscopic measurements;
train a global classification model using a first set of spectra of the sets of spectra;
verify the global classification model using a second set of spectra of the sets of spectra; and
provide multiple quantification models after verifying the global classification model.
15. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, that cause the device to provide the multiple quantification models, cause the device to:
provide one or more of the multiple quantification models to a first different device associated with a first different spectrometer and to a second different device associated with a second different spectrometer.
16. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions further cause the device to:
verify multiple local quantification models associated with the global classification model,
wherein the multiple local quantification models include one or more of the multiple quantification models.
17. The non-transitory computer-readable medium of claim 14 , wherein the multiple quantification models include:
a first quantification model corresponding to a first class of the global classification model, and
a second quantification model corresponding to a second class of the global classification model.
18. The non-transitory computer-readable medium of claim 14 , wherein the multiple quantification models include:
a first quantification model corresponding to a first class of a local classification model generated based on the global classification model, and
a second quantification model corresponding to a second class of the local classification model.
19. The non-transitory computer-readable medium of claim 14 , wherein the instructions to perform the one or more spectroscopic measurements comprise instructions to perform the one or more spectroscopic measurements on a training set and a validation set.
20. The non-transitory computer-readable medium of claim 14 , wherein the multiple quantification models include:
a first quantification model for determining a concentration of a particular protein in a first type of meat identified using in-situ local modeling, and
a second quantification model for determining the concentration of the particular protein in a second type of meat identified using in-situ local modeling.