US 12,481,726 B2
Reduced false positive identification for spectroscopic quantification
ChangMeng Hsiung, Redwood City, CA (US)
Assigned to VIAVI SOLUTIONS INC., Chandler, AZ (US)
Filed by VIAVI Solutions Inc., Chandler, AZ (US)
Filed on Aug. 1, 2023, as Appl. No. 18/363,060.
Application 18/363,060 is a continuation of application No. 17/301,234, filed on Mar. 30, 2021, granted, now 11,775,616.
Application 17/301,234 is a continuation of application No. 16/034,901, filed on Jul. 13, 2018, granted, now 11,009,452, issued on May 18, 2021.
Claims priority of provisional application 62/622,641, filed on Jan. 26, 2018.
Prior Publication US 2023/0385383 A1, Nov. 30, 2023
Int. Cl. G06F 18/2411 (2023.01); G01N 21/25 (2006.01); G01N 21/27 (2006.01); G06F 18/2433 (2023.01); G01N 21/17 (2006.01); G01N 21/359 (2014.01)
CPC G06F 18/2411 (2023.01) [G01N 21/255 (2013.01); G01N 21/27 (2013.01); G06F 18/2433 (2023.01); G01N 2021/1748 (2013.01); G01N 21/359 (2013.01); G01N 2201/129 (2013.01); G06F 2218/12 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
generating, by a control device and using a machine learning technique, a single class representing a quantification model by aggregating multiple classes corresponding to multiple concentrations of a component in a training set; and
one or more of:
using the single class representing the quantification model to perform spectroscopic quantification of an unknown sample, or
providing, to one or more other control devices and for utilization in spectroscopic quantification of other unknown samples, the single class representing the quantification model.