Blind separation of fluorescence spectra using sparse non-negative matrix factorization on right hand factor

Sparse non‐negative matrix factorization on right side factor (SNMF/R) has better performance in feature extraction than non‐negative matrix factorization. In this work, SNMF/R was first used to separate the overlapped three‐dimensional fluorescence spectra of polycyclic aromatic hydrocarbons mixtur...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of chemometrics Jg. 29; H. 8; S. 442 - 447
Hauptverfasser: Yang, Ruifang, Zhao, Nanjing, Xiao, Xue, Yu, Shaohui, Liu, Jianguo, Liu, Wenqing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Chichester Blackwell Publishing Ltd 01.08.2015
Wiley Subscription Services, Inc
Schlagworte:
Algorithms
Aquatic environment
component recognition
Factorization
Fluorescence
Lakes
Matrix
Polycyclic aromatic hydrocarbons
Rivers
sparse non-negative matrix factorization
Spectra
Three dimensional
three-dimensional fluorescence spectra
Water analysis
Water sampling
ISSN:0886-9383, 1099-128X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Sparse non‐negative matrix factorization on right side factor (SNMF/R) has better performance in feature extraction than non‐negative matrix factorization. In this work, SNMF/R was first used to separate the overlapped three‐dimensional fluorescence spectra of polycyclic aromatic hydrocarbons mixtures in pure water, lake water, and river water, respectively. It is found that the similarity coefficients between the acquired three‐dimensional spectra and the corresponding reference spectra with random initials are all above 0.80; the recognition rate of SNMF/R is higher than that of PARAFAC and non‐negative matrix factorization algorithms, especially in the case of lake water and river water samples. In addition, SNMF/R does not need any initialization scheme designing during spectra separation. These results demonstrate that SNMF/R is an appropriate algorithm to separate the overlapped fluorescence spectra of polycyclic aromatic hydrocarbons in aquatic environment accurately and effectively. Copyright © 2015 John Wiley & Sons, Ltd. Sparse non‐negative matrix factorization on right side factor (SNMF/R) was used to separate the overlapped three‐dimensional fluorescence spectra of polycyclic aromatic hydrocarbons mixtures in pure water, lake water, and river water, respectively. Results illustrate that SNMF/R can extract source spectra more accurately with similarity coefficients between the recognized three‐dimensional spectra and the reference spectra of all above 0.80 and recognition rate higher than that of PARAFAC and NMF algorithms.
Bibliographie:Natural Science Foundation of China - No. 61378041\61308063
ArticleID:CEM2723
Equipment Function Development Technology Innovation Project of Chinese Academy of Science - No. yg2012071
istex:3281D7B8001E4603306936E4556F26DCE904A8B2
ark:/67375/WNG-CGVBV9BW-W
Anhui Province Outstanding Youth Science Foundation - No. 1108085J19; No. 1508085JGD02
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0886-9383
1099-128X
DOI:10.1002/cem.2723