201 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author정회일-
dc.date.accessioned2017-09-12T02:00:34Z-
dc.date.available2017-09-12T02:00:34Z-
dc.date.issued2015-11-
dc.identifier.citationTALANTA, v. 144, Page. 960-968en_US
dc.identifier.issn0039-9140-
dc.identifier.issn1873-3573-
dc.identifier.urihttp://www.sciencedirect.com/science/article/pii/S0039914015301557?via%3Dihub-
dc.identifier.urihttp://hdl.handle.net/20.500.11754/29078-
dc.description.abstractSupervised neighborhood preserving embedding (SNPE), a nonlinear dimensionality reduction method, was employed to represent near-infrared (NIR) and Raman spectral features of agricultural samples (Angelica gigas, sesame, and red pepper), and the newly constructed variables were used to discriminate their geographical origins. This study was done to evaluate the potential of SNPE for recognizing minute spectral differences between classes by preserving local relationships, in comparison with widely adopted linear feature representation methods such as principal component analysis (PCA) and partial least squares (PLS). For this purpose, diffuse reflectance NIR spectral datasets of Angelica gigas, sesame, and red pepper, and a Raman spectral dataset of the same red pepper were prepared. The spectra were represented into new variables in reduced dimensions by PCA, PLS, neighborhood preserving embedding (NPE), and SNPE, and the represented variables were used to determine the geographical origins of samples by using the k-nearest neighbor (k-NN) and support vector machine (SVM). The combination of SNPE and SVM differentiated the geographical origins with improved accuracy. Overall results demonstrate that SNPE is a valuable alternative feature representation method, especially when complex and highly overlapping vibrational spectra are used for analysis. (C) 2015 Elsevier B.V. All rights reserved.en_US
dc.description.sponsorshipThis research of Hoeil Chung was supported by Advanced Production Technology Development Program, Ministry of Agriculture, Food and Rural Affairs (MAFRA) (Project: 314033-02). This research of Hyeseon Lee was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF-2014R1A1A1037234).en_US
dc.language.isoenen_US
dc.publisherELSEVIER SCIENCE BVen_US
dc.subjectNonlinear feature extraction methodsen_US
dc.subjectLocally linear embeddingen_US
dc.subjectSupervised neighborhood preserving embeddingen_US
dc.subjectDiscrimination of geographical originsen_US
dc.subjectVibrational spectroscopyen_US
dc.titleExploring supervised neighborhood preserving embedding (SNPE) as a nonlinear feature extraction method for vibrational spectroscopic discrimination of agricultural samples according to geographical originsen_US
dc.typeArticleen_US
dc.relation.volume144-
dc.identifier.doi10.1016/j.talanta.2015.07.028-
dc.relation.page960-968-
dc.relation.journalTALANTA-
dc.contributor.googleauthorLee, Sanguk-
dc.contributor.googleauthorHwang, Jinyoung-
dc.contributor.googleauthorLee, Hyeseon-
dc.contributor.googleauthorChung, Hoeil-
dc.relation.code2015000399-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF NATURAL SCIENCES[S]-
dc.sector.departmentDEPARTMENT OF CHEMISTRY-
dc.identifier.pidhoeil-
Appears in Collections:
COLLEGE OF NATURAL SCIENCES[S](자연과학대학) > CHEMISTRY(화학과) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE