Performing sequential forward selection and variational autoencoder techniques in soil classification based on laser-induced breakdown spectroscopy

The feasibility and accuracy of several combination classification models, , quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes (BNB), and support vector machine (SVM) classification models combined with either sequential feature selection (SFS) or dimensionality reduct...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Analytical methods Ročník 13; číslo 41; s. 4926
Hlavní autoři: Harefa, Edward, Zhou, Weidong
Médium: Journal Article
Jazyk:angličtina
Vydáno: England 28.10.2021
Témata:
ISSN:1759-9679, 1759-9679
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The feasibility and accuracy of several combination classification models, , quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes (BNB), and support vector machine (SVM) classification models combined with either sequential feature selection (SFS) or dimensionality reduction methods, for classifying soil with laser-induced breakdown spectroscopy (LIBS) had been explored in this study. Each algorithm combination was compared to assess their classification performance. After eliminating the irrelevant features of the data using sequential feature selection (SFS), the performances were all improved for the studied four classification models, and the best accuracy reached 97.88% by SFS-SVM. The dimensions of the data were then reduced using variational autoencoder (VAE), truncated singular value decomposition (TSVD), and isometric mapping (Isomap), respectively. The classification accuracy improved for all combination models with dimensionality reduction, and impressive accuracies of 98.12% from TSVD-SVM and 98.24% from VAE-SVM were obtained. These results demonstrate an effective way to reduce uncorrelated features, high dimensionality, and redundant information in the LIBS dataset. In addition, coupling classification models with feature selection and dimensionality reduction techniques could significantly optimize the classification performance of LIBS.
AbstractList The feasibility and accuracy of several combination classification models, i.e., quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes (BNB), and support vector machine (SVM) classification models combined with either sequential feature selection (SFS) or dimensionality reduction methods, for classifying soil with laser-induced breakdown spectroscopy (LIBS) had been explored in this study. Each algorithm combination was compared to assess their classification performance. After eliminating the irrelevant features of the data using sequential feature selection (SFS), the performances were all improved for the studied four classification models, and the best accuracy reached 97.88% by SFS-SVM. The dimensions of the data were then reduced using variational autoencoder (VAE), truncated singular value decomposition (TSVD), and isometric mapping (Isomap), respectively. The classification accuracy improved for all combination models with dimensionality reduction, and impressive accuracies of 98.12% from TSVD-SVM and 98.24% from VAE-SVM were obtained. These results demonstrate an effective way to reduce uncorrelated features, high dimensionality, and redundant information in the LIBS dataset. In addition, coupling classification models with feature selection and dimensionality reduction techniques could significantly optimize the classification performance of LIBS.The feasibility and accuracy of several combination classification models, i.e., quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes (BNB), and support vector machine (SVM) classification models combined with either sequential feature selection (SFS) or dimensionality reduction methods, for classifying soil with laser-induced breakdown spectroscopy (LIBS) had been explored in this study. Each algorithm combination was compared to assess their classification performance. After eliminating the irrelevant features of the data using sequential feature selection (SFS), the performances were all improved for the studied four classification models, and the best accuracy reached 97.88% by SFS-SVM. The dimensions of the data were then reduced using variational autoencoder (VAE), truncated singular value decomposition (TSVD), and isometric mapping (Isomap), respectively. The classification accuracy improved for all combination models with dimensionality reduction, and impressive accuracies of 98.12% from TSVD-SVM and 98.24% from VAE-SVM were obtained. These results demonstrate an effective way to reduce uncorrelated features, high dimensionality, and redundant information in the LIBS dataset. In addition, coupling classification models with feature selection and dimensionality reduction techniques could significantly optimize the classification performance of LIBS.
The feasibility and accuracy of several combination classification models, , quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes (BNB), and support vector machine (SVM) classification models combined with either sequential feature selection (SFS) or dimensionality reduction methods, for classifying soil with laser-induced breakdown spectroscopy (LIBS) had been explored in this study. Each algorithm combination was compared to assess their classification performance. After eliminating the irrelevant features of the data using sequential feature selection (SFS), the performances were all improved for the studied four classification models, and the best accuracy reached 97.88% by SFS-SVM. The dimensions of the data were then reduced using variational autoencoder (VAE), truncated singular value decomposition (TSVD), and isometric mapping (Isomap), respectively. The classification accuracy improved for all combination models with dimensionality reduction, and impressive accuracies of 98.12% from TSVD-SVM and 98.24% from VAE-SVM were obtained. These results demonstrate an effective way to reduce uncorrelated features, high dimensionality, and redundant information in the LIBS dataset. In addition, coupling classification models with feature selection and dimensionality reduction techniques could significantly optimize the classification performance of LIBS.
Author Harefa, Edward
Zhou, Weidong
Author_xml – sequence: 1
  givenname: Edward
  orcidid: 0000-0001-8800-6244
  surname: Harefa
  fullname: Harefa, Edward
  email: wdzhou@zjnu.cn
  organization: Key Laboratory of Optical Information Detection and Display Technology of Zhejiang, Zhejiang Normal University, Jinhua, 321004, China. wdzhou@zjnu.cn
– sequence: 2
  givenname: Weidong
  orcidid: 0000-0003-3561-1998
  surname: Zhou
  fullname: Zhou, Weidong
  email: wdzhou@zjnu.cn
  organization: Key Laboratory of Optical Information Detection and Display Technology of Zhejiang, Zhejiang Normal University, Jinhua, 321004, China. wdzhou@zjnu.cn
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34610059$$D View this record in MEDLINE/PubMed
BookMark eNpNkMlOwzAURS1URAfY8AHISzYBO4njeIkqJqkSLGAdPQ8BQ2IXO6Hqd_DDuFAkVu--o_sG3TmaOO8MQqeUXFBSiEtNYUtoznh7gGaUM5GJiovJPz1F8xjfCKlEUdEjNC3KihLCxAx9PZrQ-tBb94Kj-RiNGyx0OKENBJ1QZ9RgvcPgNP6EYGHXJQeMgzdOeW0CHox6dTYNR2wdjt52WHUQo22t-vFjCdFonETCJmTW6VElIIOBd-03aWid7gQflV9vj9FhC100J_u6QM8310_Lu2z1cHu_vFplquBkyEpStlJwInOopZSKQEloQZTitSY5Lzhr21YbqHWtq5wzomrQkgpFSlYlli_Q-e_edfC754emt1GZrgNn_BiblKio8prVLFnP9tZR9kY362B7CNvmL8j8G7Pwe7I
CitedBy_id crossref_primary_10_1007_s11467_024_1427_2
crossref_primary_10_1016_j_heliyon_2024_e30228
crossref_primary_10_1002_fft2_277
crossref_primary_10_3390_diagnostics13111925
crossref_primary_10_3390_s22093129
crossref_primary_10_1515_ijeeps_2022_0118
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1039/d1ay01257f
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Sciences (General)
EISSN 1759-9679
ExternalDocumentID 34610059
Genre Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID -JG
0-7
0R~
23M
53G
6J9
705
7~J
AAEMU
AAHBH
AAIWI
AAJAE
AANOJ
AARTK
AAWGC
AAXHV
ABASK
ABDVN
ABEMK
ABJNI
ABPDG
ABRYZ
ABXOH
ACGFS
ACIWK
ACLDK
ACPRK
ADMRA
ADSRN
AEFDR
AENEX
AENGV
AESAV
AETIL
AFLYV
AFOGI
AFRAH
AFRZK
AFVBQ
AGEGJ
AGRSR
AGSTE
AHGCF
AKBGW
ALMA_UNASSIGNED_HOLDINGS
ANUXI
APEMP
ASKNT
AUDPV
AZFZN
BLAPV
BSQNT
C6K
CGR
CUY
CVF
EBS
ECGLT
ECM
EE0
EF-
EIF
F5P
GGIMP
H13
HZ~
H~N
J3I
NPM
O-G
O9-
OK1
R7E
RAOCF
RCNCU
RNS
RPMJG
RRC
RSCEA
RVUXY
SLF
7X8
AKMSF
ID FETCH-LOGICAL-c370t-404fb970b2a8bbbc0a40130cc78d027375fffdea8d8d62750c8adb19c0456d8d2
IEDL.DBID 7X8
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000704196000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1759-9679
IngestDate Thu Jul 10 23:49:16 EDT 2025
Wed Feb 19 02:27:30 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 41
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c370t-404fb970b2a8bbbc0a40130cc78d027375fffdea8d8d62750c8adb19c0456d8d2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-3561-1998
0000-0001-8800-6244
PMID 34610059
PQID 2579628585
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2579628585
pubmed_primary_34610059
PublicationCentury 2000
PublicationDate 2021-10-28
PublicationDateYYYYMMDD 2021-10-28
PublicationDate_xml – month: 10
  year: 2021
  text: 2021-10-28
  day: 28
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Analytical methods
PublicationTitleAlternate Anal Methods
PublicationYear 2021
SSID ssj0069361
Score 2.3118427
Snippet The feasibility and accuracy of several combination classification models, , quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve Bayes...
The feasibility and accuracy of several combination classification models, i.e., quadratic discriminant analysis (QDA), random forest (RF), Bernoulli naïve...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 4926
SubjectTerms Bayes Theorem
Lasers
Soil
Spectrum Analysis
Support Vector Machine
Title Performing sequential forward selection and variational autoencoder techniques in soil classification based on laser-induced breakdown spectroscopy
URI https://www.ncbi.nlm.nih.gov/pubmed/34610059
https://www.proquest.com/docview/2579628585
Volume 13
WOSCitedRecordID wos000704196000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF7UevCi1md9MYIHPYQmmya7OYmIxYulB4XewmYfUJSkNm2hv8M_7EyS1pMgeEgISwJhdnbnm8d-w9hNwG0cO514nPvC6zkbeErwyHNCEuGXjU2YVc0mxGAgR6Nk2ATcyqascrUnVhu1KTTFyLucDk1yymLdTz496hpF2dWmhcYma4VBKKh1gxitswhxEtZ8qSIiFkqRrOhJw6RrArXEvTkS7ndoWZmY_t5_f26f7TbgEh5qbWizDZsfsHazfEu4bTim7w7Z17A-MICGC-pqalzpH4BDVEULZdUdB6cMVG5ggf50EzMENZ8VxH1p7BTW_K8ljHMoi_EHaALjVH1UvQ9kIw3gAw7bqYf-P2qSAXTD1btB_x-qg55EqFlMlkfsrf_0-vjsNf0ZPI2ynqHr2XNZIvyMK5llmfYVOWu-1kIaoskRkXPOWCWNNESG7GupTBYkmmAkjvFjtpUXuT1lYBR3Sax7TtgIIQVKM4vwkohOY-4i12HXK8GnqP-U1FC5LeZl-iP6DjupZy-d1EQdaUhk8ogfz_7w9Tnb4VSugmaJywvWcrj67SXb1ovZuJxeVYqF98Hw5Ruyq92W
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Performing+sequential+forward+selection+and+variational+autoencoder+techniques+in+soil+classification+based+on+laser-induced+breakdown+spectroscopy&rft.jtitle=Analytical+methods&rft.au=Harefa%2C+Edward&rft.au=Zhou%2C+Weidong&rft.date=2021-10-28&rft.issn=1759-9679&rft.eissn=1759-9679&rft.volume=13&rft.issue=41&rft.spage=4926&rft_id=info:doi/10.1039%2Fd1ay01257f&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1759-9679&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1759-9679&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1759-9679&client=summon