Multi-Label Classification with Optimal Thresholding for Multi-Composition Spectroscopic Analysis

Simple item page
dc.contributor.authorGan, Luyun
dc.contributor.authorYuen, Brosnan
dc.contributor.authorLu, Tao
dc.date.accessioned2019-12-18T22:46:47Z
dc.date.available2019-12-18T22:46:47Z
dc.date.copyright2019en_US
dc.date.issued2019
dc.description.abstractIn this paper, we implement multi-label neural networks with optimal thresholding to identify gas species among a multiple gas mixture in a cluttered environment. Using infrared absorption spectroscopy and tested on synthesized spectral datasets, our approach outperforms conventional binary relevance-partial least squares discriminant analysis when the signal-to-noise ratio and training sample size are sufficient.en_US
dc.description.reviewstatusRevieweden_US
dc.description.scholarlevelFacultyen_US
dc.description.sponsorshipThis research was funded by the Nature Science and Engineering Research Council of Canada (NSERC) Discovery (Grant No. RGPIN-2015-06515), Defense Threat Reduction Agency (DTRA) Thrust Area 7, Topic G18 (Grant No. GRANT12500317), and the Nvidia Corporation TITAN-X GPU grant.en_US
dc.identifier.citationGan, L. & Yuen, B. & Lu, T. (2019). Multi-Label Classification with Optimal Thresholding for Multi-Composition Spectroscopic Analysis. Machine Learning & Knowledge Extraction, 1(4), 1084-1099. https://doi.org/10.3390/make1040061en_US
dc.identifier.urihttps://doi.org/10.3390/make1040061
dc.identifier.urihttp://hdl.handle.net/1828/11389
dc.language.isoenen_US
dc.publisherMachine Learning & Knowledge Extractionen_US
dc.subjectmulti-label classification
dc.subjectinfrared absorption spectroscopy
dc.subjectsupervised learning
dc.subjectfeedforward neural networks
dc.subjectbinary relevance
dc.subject.departmentDepartment of Electrical and Computer Engineering
dc.titleMulti-Label Classification with Optimal Thresholding for Multi-Composition Spectroscopic Analysisen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Gan_Luyun_MachLearnKnowlExtra_2019.pdf
Size:
1.56 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Faculty and Staff Publications
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.