IP Library › Granted Patent US 12,590,889
Granted Patent B2
US 12,590,889 · App. 18/311,989 · Granted Mar 31, 2026

Outlier detection for spectroscopic classification

Inventors: Chang Meng Hsiung (Redwood City, CA); Lan Sun (Santa Rosa, CA)
Assignee: VIAVI Solutions Inc.
G01N21/35G01J3/108G01N21/253G01N21/359G06F18/2411G06F18/2433G06N20/00G06V20/698G16C20/20G16C20/70G01N2201/129
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,590,889
App. No.
18/311,989
Granted
Mar 31, 2026
Kind
B2
Abstract

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.

Claims (60)

1 . A method, comprising:

receiving, by a device that includes a processor, information identifying results of a set of spectroscopic measurements of a training set of known samples and a validation set of known samples;

causing, by the device, one or more spectrometers to perform one or more spectroscopic measurements of an unknown sample;

receiving, by the device and based on causing the one or more spectrometers to perform the one or more spectroscopic measurements of the unknown sample, information identifying a result of the one or more spectroscopic measurements of the unknown sample; and

causing, by the device, one or more actions based on a local classification model indicating that the unknown sample is an outlier sample,

the local classification model being based on an aggregated classification model and the result of the one or more spectroscopic measurements of the unknown sample, and

the aggregated classification model being based on the information identifying the results of the set of spectroscopic measurements of the training set and the validation set.

2 . The method of claim 1 , wherein the aggregated classification model includes at least one class relating to a material of interest for a spectroscopic determination.

3 . The method of claim 1 , wherein the aggregated 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.

4 . The method of claim 1 , further comprising:

selecting a set of top classes from the aggregated classification model; and

generating the local classification model by generating a set of local classes of the local classification model based on the set of top classes from the aggregated classification model,

wherein a particular local class, of the set of local classes, includes the unknown sample.

5 . The method of claim 4 , further comprising:

determining that the local classification model indicates that the unknown sample is the outlier sample based on an evaluation of the unknown sample relative to the particular local class or the set of local classes.

6 . The method of claim 1 , wherein causing the one or more actions comprises:

providing output indicating that the outlier sample is included in a no-match class.

7 . A system, comprising:

one or more memories; and

one or more processors, coupled to the one or more memories, configured to:

receive information identifying results of a set of spectroscopic measurements;

cause one or more spectrometers to perform one or more spectroscopic measurements of an unknown sample;

receive, based on the one or more spectrometers being caused to perform the one or more spectroscopic measurements of the unknown sample, information identifying a result of the one or more spectroscopic measurements of the unknown sample; and

cause one or more actions based on a local classification model indicating that the unknown sample is an outlier sample,

the local classification model being based on an aggregated classification model and the result of the one or more spectroscopic measurements of the unknown sample, and

the aggregated classification model being based on the information identifying the results of the set of spectroscopic measurements.

8 . The system of claim 7 , wherein the aggregated classification model includes at least one class relating to a material of interest for a spectroscopic determination.

9 . The system of claim 7 , wherein the aggregated 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.

10 . The system of claim 7 , wherein the one or more processors are further configured to:

select a set of top classes from the aggregated classification model; and

generate the local classification model by generating a set of local classes of the local classification model based on the set of top classes from the aggregated classification model,

wherein a particular local class, of the set of local classes, includes the unknown sample.

11 . The system of claim 10 , wherein the one or more processors are further configured to:

determine that the local classification model indicates that the unknown sample is the outlier sample based on an evaluation of the unknown sample relative to the particular local class.

12 . The system of claim 7 , wherein the one or more processors are further configured to:

determine that the local classification model indicates that the unknown sample is the outlier sample based on an evaluation of the unknown sample relative to the set of local classes.

13 . The system of claim 7 , wherein the one or more processors, to cause the one or more actions, are configured to:

provide output indicating that the outlier sample is included in a no-match class.

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, cause the one or more processors to:

receive information identifying results of a set of spectroscopic measurements of a training set of known samples and a validation set of known samples;

cause one or more spectrometers to perform one or more spectroscopic measurements of an unknown sample;

receive, based on the one or more spectrometers being caused to perform the one or more spectroscopic measurements of the unknown sample, information identifying a result of the one or more spectroscopic measurements of the unknown sample; and

cause one or more actions based on a local classification model indicating information regarding the unknown sample,

the local classification model being based on an aggregated classification model and the result of the one or more spectroscopic measurements of the unknown sample, and

the aggregated classification model being based on the information identifying the results of the set of spectroscopic measurements of the training set and the validation set.

15 . The non-transitory computer-readable medium of claim 14 , wherein the aggregated classification model includes at least one class relating to a material of interest for a spectroscopic determination.

16 . The non-transitory computer-readable medium of claim 14 , wherein the aggregated 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.

17 . The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions further cause the one or more processors to:

generate the local classification model by generating a set of local classes of the local classification model; and

determine that the local classification model indicates that the unknown sample is an outlier sample based on an evaluation of the unknown sample relative to the set of local classes.

18 . The method of claim 1 , further comprising:

causing the one or more spectrometers to perform the set of spectroscopic measurements of the training set and the validation set,

wherein the information identifying the results of the set of spectroscopic measurements of the training set and the validation set are received based on causing the one or more spectrometers to perform the set of spectroscopic measurements of the training set and the validation set.

19 . The system of claim 7 , wherein the one or more processors are further configured to:

cause the one or more spectrometers to perform the set of spectroscopic measurements on a training set of known samples and a validation set of known samples; and

wherein the one or more processors, to receive the information identifying the results of the set of spectroscopic measurements, are configured to:

receive the information identifying the results of the set of spectroscopic measurements based on the set of spectroscopic measurements being performed on the training set and the validation set.

20 . The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions further cause the one or more processors to:

cause the one or more spectrometers to perform the set of spectroscopic measurements of the training set and the validation set.

Assignments (4)
RELEASE OF SECURITY INTEREST AT REEL/FRAME 73189/0873 Recorded May 28, 2026
From: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS ADMINISTRATIVE AGENT
To: INERTIAL LABS, INC.; VIAVI SOLUTIONS INC.; VIAVI SOLUTIONS LICENSING LLC
Reel/Frame 075642/0381 →
SECURITY INTEREST Recorded Nov 14, 2025
From: VIAVI SOLUTIONS INC.; VIAVI SOLUTIONS LICENSING LLC; INERTIAL LABS, INC.
To: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS AGENT
Reel/Frame 073571/0137 →
SECURITY AGREEMENT Recorded Oct 21, 2025
From: INERTIAL LABS, INC.; VIAVI SOLUTIONS INC.; VIAVI SOLUTIONS LICENSING LLC
To: WELLS FARGO BANK, NATIONAL ASSOCIATION, AS ADMINISTRATIVE AGENT
Reel/Frame 073189/0873 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 4, 2023
From: HSIUNG, CHANG MENG; SUN, LAN
To: VIAVI SOLUTIONS INC.
Reel/Frame 063537/0578 →
Continuity (5)
Continuation 17248333 · Jan 20, 2021
Continuation In Part 17072437 · Oct 16, 2020
Continuation 16130732 · Sep 13, 2018
Provisional Application 62622637 · Jan 26, 2018
Related Publication 20230273121A1 · Aug 31, 2023
References Cited (114)
US 4673289A · Gaucher · 1987 [cited by applicant]
US 7133710B2 · Acosta et al. · 2006 [cited by applicant]
US 7873205B2 · Okuda et al. · 2011 [cited by applicant]
US 8189892B2 · Dimirova et al. · 2012 [cited by applicant]
US 9435728B2 · Tsukii et al. · 2016 [cited by applicant]
US 9513167B2 · Hargreaves et al. · 2016 [cited by applicant]
US 9824434B2 · Tzao et al. · 2017 [cited by applicant]
US 10309894B2 · Hsiung et al. · 2019 [cited by applicant]
US 10401312B2 · Takis et al. · 2019 [cited by applicant]
US 10489550B2 · Roder et al. · 2019 [cited by applicant]
US 10810408B2 · Hsiung et al. · 2020 [cited by applicant]
US 10839527B2 · Zhang et al. · 2020 [cited by applicant]
US 11009452B2 · Hsiung · 2021 [cited by applicant]
US 11461690B2 · Szeto et al. · 2022 [cited by applicant]
US 12099003B2 · Hsiung et al. · 2024 [cited by applicant]
US 20030028358A1 · Niu et al. · 2003 [cited by applicant]
US 20040077950A1 · Marshik-Geurts et al. · 2004 [cited by applicant]
US 20050124074A1 · Shelley et al. · 2005 [cited by applicant]
US 20070008523A1 · Kaye et al. · 2007 [cited by applicant]
US 20070148697A1 · Delaney et al. · 2007 [cited by applicant]
US 20070192035A1 · Schweitzer et al. · 2007 [cited by applicant]
US 20100211329A1 · Farquharson et al. · 2010 [cited by applicant]
US 20100217537A1 · Neiss et al. · 2010 [cited by applicant]
US 20110237446A1 · Treado et al. · 2011 [cited by applicant]
US 20120034647A1 · Herzog et al. · 2012 [cited by applicant]
US 20120134559A1 · Suzuki et al. · 2012 [cited by applicant]
US 20130256534A1 · Micheels et al. · 2013 [cited by applicant]
US 20130311136A1 · Blonshine et al. · 2013 [cited by applicant]
US 20150066377A1 · Parchen et al. · 2015 [cited by applicant]
US 20150102216A1 · Roder et al. · 2015 [cited by applicant]
US 20150154286A1 · Lightner et al. · 2015 [cited by applicant]
US 20150204833A1 · O'Brien et al. · 2015 [cited by applicant]
US 20160127405A1 · Kasahara · 2016 [cited by applicant]
US 20180365535A1 · Gesley et al. · 2018 [cited by applicant]
US 20210034838A1 · Hsiung et al. · 2021 [cited by applicant]
US 20210142038A1 · Hsiung et al. · 2021 [cited by applicant]
US 20210215597A1 · Hsiung · 2021 [cited by applicant]
US 20220405644A1 · Szeto et al. · 2022 [cited by applicant]
CN 101504363A · 2009 [cited by applicant]
CN 103364359A · 2013 [cited by applicant]
CN 105829869A · 2016 [cited by applicant]
CN 106483083A · 2017 [cited by applicant]
CN 106772417A · 2017 [cited by applicant]
CN 107229819A · 2017 [cited by applicant]
CN 107480690A · 2017 [cited by applicant]
CN 107561024A · 2018 [cited by applicant]
EP 1992939A1 · 2008 [cited by applicant]
EP 3136270A1 · 2017 [cited by applicant]
JP S6113139A · 1986 [cited by applicant]
JP H07234941A · 1995 [cited by applicant]
JP 2003139693A · 2003 [cited by applicant]
JP 2004294360A · 2004 [cited by applicant]
JP 2005534428A · 2005 [cited by applicant]
JP 2009276967A · 2009 [cited by applicant]
JP 2010527017A · 2010 [cited by applicant]
JP 2011027656A · 2011 [cited by applicant]
JP 2013535686A · 2013 [cited by applicant]
JP 2017049246A · 2017 [cited by applicant]
JP 2018040787A · 2018 [cited by applicant]
JP 2019522802A · 2019 [cited by applicant]
JP 2019526851A · 2019 [cited by applicant]
TW I284200B · 2007 [cited by applicant]
TW 200741192A · 2007 [cited by applicant]
TW 201504614A · 2015 [cited by applicant]
TW 201546640A · 2015 [cited by applicant]
TW 201617030A · 2016 [cited by applicant]
TW 201709110A · 2017 [cited by applicant]
TW 201802709A · 2018 [cited by applicant]
WO 2004012586A2 · 2004 [cited by applicant]
WO 2005069188A1 · 2005 [cited by applicant]
WO 2006056024A1 · 2006 [cited by applicant]
WO 2011077765A1 · 2011 [cited by applicant]
WO 2012019118A1 · 2012 [cited by applicant]
WO 2014165331A1 · 2014 [cited by applicant]
WO 2015080001A1 · 2015 [cited by applicant]
WO 2016139649A2 · 2016 [cited by applicant]
WO 2017127822A1 · 2017 [cited by applicant]
WO 2017136464A1 · 2017 [cited by applicant]
WO 2017174580A1 · 2017 [cited by applicant]
WO 2018017467A1 · 2018 [cited by applicant]
Michiel Debruyne, “An Outlier Map for Support Vector Machine Classification”, vol. 3, No. 4, 1566-1580 2009 (Year: 2009). [cited by examiner]
Forni O., et al., “Independent Component Analysis Classification of Laser Induced Breakdown Spectroscopy Spectra, ”Spectrochimia Acta Part B, 2013, vol. 86, pp. 31-41. [cited by applicant]
Shengnan W., et al., “Outlier Sample Analysis on Near Infrared Spectroscopy Determination for Flour Ash, ”2013 Fifth Conference on Measuring Technology and Mechatronics Automation, 2013, pp. 781-784. [cited by applicant]
Unnikrishnan V.K., et al., “Analytical Predictive Capabilities of Laser Induced Breakdown Spectroscopy (LIBS) With Principal Component Analysis (PCA) for Plastic Classification, ”RSC Advances, 2013, vol. 3, pp. 25872-25… [cited by applicant]
Peng D., et al., “Detection and Quantification of Adulteration of Sesame Oils with Vegetable Oil using Gas 1 Chromatography and Multivariate Data Analysis,” Food Chemistry, 2015, vol. 188, pp. 415-421. DOI: 10.1016/j.fo… [cited by applicant]
Extended European Search Report for Application No. EP23157642.2, mailed on May 24, 2023, 8 pages. [cited by applicant]
Aggarwal C.C., “Chapter 1 An Introduction to Outlier Analysis,” Outlier Analysis, Second Edition, Nov. 25, 2016, Springer International Publishing, pp. 1-34. XP055597620. [cited by applicant]
Baassou et al., “An Accurate SVM-based Classification Approach for Hyperspectral Image Classification,” International Conference on Geoinformatics, Jun. 2013, pp. 1-7. [cited by applicant]
Dubuisson B., et al., “A Statistical Decision Rule With Incomplete Knowledge About Classes,” Pattern Recognition, Jan. 1993, vol. 26 (1), pp. 155-165. XP055568901. [cited by applicant]
Extended European Search Report for Application No. EP19150264.0, malled on Jun. 26, 2019, 12 pages,. [cited by applicant]
Extended European Search Report for Application No. EP19150386.1, mailed on Jul. 1, 2019, 8 pages. [cited by applicant]
Extended European Search Report for Application No. EP21204170.1, mailed on Apr. 14, 2022, 10 pages. [cited by applicant]
Haiyan Fu., et al., “A Comprehensive Quality Evaluation Method by FT-NIR Spectroscopy and Chemometric: Fine classification and Untargeted Authentication Against Multiple Frauds For Chinese Ganoderma Lucidum,” Spectrochi… [cited by applicant]
Hanczar B., et al., “Combination of One-Class Support Vector Machines for Classification with Reject Option,” Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Part 1, Lecture Notes in … [cited by applicant]
Jiyu Peng., et al., “Fast Detection of Tobacco Mosaic Virus Infected Tobacco Using Laser Induced Breakdown Spectroscopy,” Scientific Reports, 2017, vol. 7, pp. 44551. [cited by applicant]
Lascola et al., “A Piecewise Local Partial Least Squares (PLS) Method for the Quantitative Analysis of Plutonium Nitrate Solutions,” Applied Spectroscopy, 2017, vol. 71 (12), pp. 2579-2594. [cited by applicant]
Maniruzzaman et al., “Accurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers,” Journal of Medical Systems, Springer, Apr. 10, 2018, vol. 42 (5), pp. 1-17, XP036507803. [cited by applicant]
Mertens., “Transformation, Normalization and Batch Effect in the Analysis of Mass Spectrometry Data for Omics Studies,” Department of Medical Statistics, Leiden University Medical Center, Jun. 20, 2016, pp. 1-34. [cited by applicant]
Pasquini C., “Near Infrared Spectroscopy: A Mature Analytical Technique With New Perspectives—A Review,” Analytica Chimica Acta, Oct. 2018, vol. 1026, pp. 8-36. XP055597813. [cited by applicant]
Quan H., et al., “Estimate of standard deviation for a log-transformed variable using arithmetic means and standard deviations,” Statistics in Medicine, 2003, vol. 22, pp. 2723-2736. [cited by applicant]
Scholkopf B., et al., “Estimating the Support of a High-Dimensional Distribution,” Neural Computation, Jul. 2001, vol. 13 (7), pp. 1443-1471. Retrieved from Internet: [URL:https://www.mitpressjournals.org/doi/abs/10.116… [cited by applicant]
Smith-Moritz A. M., et al., “Combining Multivariate Analysis And Monosaccharide Composition Modeling to Identify Plant Cell Wall Variations By Fourier Transform Near Infrared spectroscopy,” Plant Methods, 2011, vol. 7, … [cited by applicant]
Sun et al., “Pharmaceutical Raw Material Identification Using Miniature Near-Infrared (MicroNIR) Spectroscopy and Supervised Pattern Recognition Using Support Vector Machine,” Applied Spectroscopy, Mar. 2016, vol. 70 (5… [cited by applicant]
Tao B., et al., “Implementing Multi-Class Classifiers by One-Class Classification Methods,” The 2006 IEEE International Joint Conference on Neural Network, IEEE Operations Center, Piscataway, NJ, USA, Jul. 2006, pp. 327… [cited by applicant]
Tax D.M.J., et al., “Support Vector Domain Description,” Pattern Recognition Letters, Nov. 1999, vol. 20 (11-13) pp. 1191-1199. XP004490753. [cited by applicant]
Eo S.H., et al., “Outlier Detection using Projection Quantile Regression for Mass Spectrometry Data with Low Replication,” BMC Research Notes, May 2012, vol. 5 (1), 9 pages, XP021129869. [cited by applicant]
Flem B., et al., “In Situ Analysis of Trace Elements in Quartz Using Laser Ablation Inductively Coupled Plasma Mass Spectrometry,” In: Quartz: Deposits, Mineralogy and Analytics, Springer Geology, Jan. 2012, pp. 219-236… [cited by applicant]
Liu Z.C., et al., “Outlier Detection in Near-infrared Spectroscopic Analysis by Using Monte Carlo Cross-validation,” Science in China Series B: Chemistry, Jul. 2008, vol. 51(8), pp. 751-759, XP055574331. [cited by applicant]
Changlong, W., et al., “Similar Spectrum Matching Prediction Soil Organic Matter and Cation Exchange,” Transactions of the Chinese Society of Agricultural Engineering, vol. 30(1), pp. 81-88, Jan. 1, 2014. [cited by applicant]
Dan, L., et al., “Based on Multi-classifier C5.0 Decision Tree Vegetation Classification Method Law,” Journal of Graphics, vol. 38(5), pp. 722-72815 Oct. 2017. [cited by applicant]
Yun, X., et al., “Based on Near Infrared Spectroscopy Clustering Method for Samples with Known Categories,” Transactions of the Chinese Society of Agricultural Engineering, vol. 27(8), pp. 345-349 Aug. 2011. [cited by applicant]
Nie, P., et al., “Potential of Visible and Near Infrared Spectroscopy and Pattern Recognition for Rapid Quantification of Notoginseng Powder with Adulterants,” Sensors, vol. 13(10), p. 13820-13834, Oct. 14, 2013. doi: 1… [cited by applicant]
Efenberger-Szmechtyk M., et al., “Implementation of Chemometrics in Quality Evaluation of Food and Beverages,” Critical Reviews in Food Science and Nutrition, Jul. 2017, vol. 58(10), pp. 1747-1766. [cited by applicant]
Heibati, M., et al., “Assessment of Drinking Water Quality at the Tap Using Fluorescence Spectroscopy,” Water Research, vol. 125 (2017), pp. 1-10, http://dx.doi.Org/10.1016/j.watres.2017.08.020. [cited by applicant]