Optimized Gas Sensor Array with AI for Distinguishing and Classifying Similar Odorants

This study presents a novel approach for odorant classification by integrating advanced machine learning techniques with an electronic nose (e-nose) system. The system's performance was evaluated with four distinct volatile organic compounds (VOCs)-eucalyptol, 2-nonanone, eugenol, and 2-phenyle...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE sensors journal S. 1
Hauptverfasser: Cava, Carlos Eduardo, Sun, Helin, Huang, Shirong, Cuniberti, Gianaurelio
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 2025
Schlagworte:
Boosting Algorithms
Electronic Nose System
Gas Sensors
LDA
Machine Learning
Metal Oxide
Odorant Classification
Semiconductor
ISSN:1530-437X, 1558-1748
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This study presents a novel approach for odorant classification by integrating advanced machine learning techniques with an electronic nose (e-nose) system. The system's performance was evaluated with four distinct volatile organic compounds (VOCs)-eucalyptol, 2-nonanone, eugenol, and 2-phenylethanol-along with odorless air as a reference. Data acquisition was performed using commercial gas sensors, and the collected VOC data were analyzed usingmultiple machine learning algorithms. Among these, Random Forest and CatBoost achieved the highest classification accuracy (97.1%), demonstrating superior performance in balancing precision and recall. Linear Discriminant Analysis (LDA) was employed to visualize odorant class separation in two and three dimensions, revealing distinct clusters with some overlap between eucalyptol and eugenol. Feature importance analysis identified key predictors for classification, while the confusion matrix highlighted potential areas for improvement, particularly in distinguishing chemically similar odors. The results indicate that the proposed system is highly effective for odorant discrimination, and further optimizations could enhance its accuracy in more complex classification scenarios.
AbstractList This study presents a novel approach for odorant classification by integrating advanced machine learning techniques with an electronic nose (e-nose) system. The system's performance was evaluated with four distinct volatile organic compounds (VOCs)-eucalyptol, 2-nonanone, eugenol, and 2-phenylethanol-along with odorless air as a reference. Data acquisition was performed using commercial gas sensors, and the collected VOC data were analyzed usingmultiple machine learning algorithms. Among these, Random Forest and CatBoost achieved the highest classification accuracy (97.1%), demonstrating superior performance in balancing precision and recall. Linear Discriminant Analysis (LDA) was employed to visualize odorant class separation in two and three dimensions, revealing distinct clusters with some overlap between eucalyptol and eugenol. Feature importance analysis identified key predictors for classification, while the confusion matrix highlighted potential areas for improvement, particularly in distinguishing chemically similar odors. The results indicate that the proposed system is highly effective for odorant discrimination, and further optimizations could enhance its accuracy in more complex classification scenarios.
Author Cuniberti, Gianaurelio
Cava, Carlos Eduardo
Sun, Helin
Huang, Shirong
Author_xml – sequence: 1
  givenname: Carlos Eduardo
  orcidid: 0000-0002-7315-9966
  surname: Cava
  fullname: Cava, Carlos Eduardo
  email: carloscava@utfpr.edu.br
  organization: Associate Professor, Federal University Of Technology, Paraná, Brazil
– sequence: 2
  givenname: Helin
  surname: Sun
  fullname: Sun, Helin
  email: helin.sun@mailbox.tu-dresden.de
  organization: Institute for Materials Science and Max Bergmann Center for Biomaterials, Master Student, TUD Dresden University of Technology, Dresden, Germany
– sequence: 3
  givenname: Shirong
  surname: Huang
  fullname: Huang, Shirong
  email: shirong.huang@tu-dresden.de
  organization: Institute for Materials Science and Max Bergmann Center for Biomaterials, Researcher and Group Leader, TUD Dresden University of Technology, Dresden, Germany
– sequence: 4
  givenname: Gianaurelio
  orcidid: 0000-0002-6574-7848
  surname: Cuniberti
  fullname: Cuniberti, Gianaurelio
  email: gianaurelio.cuniberti@tu-dresden.de
  organization: Institute for Materials Science and Max Bergmann Center for Biomaterials, Full Professor, TUD Dresden University of Technology, Dresden, Germany
BookMark eNpFkM1OwkAUhScGEwF9ABMX8wLFufPTaZcEETFEFqhx18yvjIGWzNQYfHrbQOLqnHNzz1l8IzSom9ohdAtkAkDK--fN_GVCCRUTJspccnaBhiBEkYHkxaD3jGScyY8rNErpixAopZBD9L4-tGEffp3FC5XwxtWpiXgaozrin9Bu8XSJfXd5CKkN9ed3SNtOsKotnu1USsEf-7zpNnYq4rVtoqrbdI0uvdold3PWMXp7nL_OnrLVerGcTVeZASbaTOvc0lx4Z4hhpjROaS2E4wBW6sLb3AO1jDHCBOScUqk1obqQJDdSqFKyMYLTrolNStH56hDDXsVjBaTqwVQ9mKoHU53BdJ27Uyc45_7_ASjnrGR_ljFh7g
CODEN ISJEAZ
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/JSEN.2025.3596743
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Engineering
EISSN 1558-1748
EndPage 1
ExternalDocumentID 10_1109_JSEN_2025_3596743
11124439
Genre orig-research
GrantInformation_xml – fundername: Deutsche Forschungsgemeinschaft
  grantid: 390696704
  funderid: 10.13039/501100001659
– fundername: 6G-life
  grantid: 16KISK001K
– fundername: HORIZON EUROPE Framework Programme
  grantid: 101046369
  funderid: 10.13039/100018693
– fundername: Volkswagen Foundation
  grantid: 96632; 9B396
  funderid: 10.13039/501100001663
– fundername: Bundesministerium f?r Bildung und Forschung
  funderid: 10.13039/501100002347
– fundername: Freistaat Sachsen
  funderid: 10.13039/501100014913
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TWZ
5VS
AAYXX
AETIX
AGSQL
AIBXA
CITATION
EJD
H~9
ZY4
ID FETCH-LOGICAL-c135t-bb6d265fec0c3c9ceabb55e411d7b8fd6f12d333035164227bb02b8706c75a973
IEDL.DBID RIE
ISSN 1530-437X
IngestDate Sat Nov 29 07:37:56 EST 2025
Wed Aug 27 02:00:11 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c135t-bb6d265fec0c3c9ceabb55e411d7b8fd6f12d333035164227bb02b8706c75a973
ORCID 0000-0002-6574-7848
0000-0002-7315-9966
PageCount 1
ParticipantIDs ieee_primary_11124439
crossref_primary_10_1109_JSEN_2025_3596743
PublicationCentury 2000
PublicationDate 2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 2025-00-00
PublicationDecade 2020
PublicationTitle IEEE sensors journal
PublicationTitleAbbrev JSEN
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0019757
Score 2.4176767
Snippet This study presents a novel approach for odorant classification by integrating advanced machine learning techniques with an electronic nose (e-nose) system....
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms Boosting Algorithms
Electronic Nose System
Gas Sensors
LDA
Machine Learning
Metal Oxide
Odorant Classification
Semiconductor
Title Optimized Gas Sensor Array with AI for Distinguishing and Classifying Similar Odorants
URI https://ieeexplore.ieee.org/document/11124439
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-1748
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0019757
  issn: 1530-437X
  databaseCode: RIE
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZohQQMPAqI8pIHJqS0SVzH8VhBy0OoRSqgbpFfgQ6kKE2Ryq_n7AQoAwNTHoqT6M7ne_m-Q-jMooRFgVIei2jHA40XwzrIlWdRKOHIfSocp-_YYBCPx_y-KlZ3tTDGGLf5zLTsqcvl66ma21BZG-QStBHhNVRjjJXFWt8pA84crCdIsA_fZOMqhRn4vH076g3AFQxpi1Bud93_UkJLXVWcUulv_fN3ttFmZT3ibsnuHbRisgbaWMIUbKC1qq35y2IXPQ1hQXidfBiNr8QMj8BlneYwOhcLbAOwuHuDwWjFl1bQs-d5GY_CItPYNcucuCIoPIJ3gAOMhxrmS1bM9tBjv_dwce1VjRQ8FRBaeFJGOoxoapSviOLKCCkpNZ0g0EzGqY7SINSEEJtVBH8kZFL6obQZUMWo4Izso3o2zcwBwkKEQsWUpg5pjktbXwJXQoHpRjqpaaLzL8ombyVeRuL8DJ8nlg2JZUNSsaGJ9ixVfx6sCHr4x_0jtG6HlxGQY1Qv8rk5QavqvZjM8lM3HT4BrUKxWw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwEB2xSYUDSylixwdOSClJHCf1sQLKVgJSAfUW2Y4DPZCiNkUqX8_YCduBA6csSpxoxuPZPG8ADg1KWOgp5UQhCxzUeC1cB7lyDAolHrnLhOV0N4rjVr_P76pidVsLo7W2m89005zaXH46VBMTKjtGuURtRPkszLMg8L2yXOsracAjC-yJMuziV6N-lcT0XH581TuL0Rn0WZMybvbd_1JDP_qqWLXSWfnnD63CcmU_knbJ8DWY0Xkdln6gCtahVjU2f56uw-MtLgkvg3edknMxJj10WocjfHskpsSEYEn7kqDZSk6NqOdPkzIiRUSeEtsuc2DLoEgPx0AXmNymOGPyYtyAh87Z_cmFU7VScJRHWeFIGaZ-yDKtXEUVV1pIyZgOPC-NZCtLw8zzU0qpySuiR-JHUrq-NDlQFTHBI7oBc_kw15tAhPCFajGWWaw5Lk2FCV4JhcYbDTK9BUeflE1eS8SMxHoaLk8MGxLDhqRiwxY0DFW_H6wIuv3H_QOoXdzfdJPuZXy9A4tmqDIesgtzxWii92BBvRWD8WjfTo0PFY-0og
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=Optimized+Gas+Sensor+Array+with+AI+for+Distinguishing+and+Classifying+Similar+Odorants&rft.jtitle=IEEE+sensors+journal&rft.au=Cava%2C+Carlos+Eduardo&rft.au=Sun%2C+Helin&rft.au=Huang%2C+Shirong&rft.au=Cuniberti%2C+Gianaurelio&rft.date=2025&rft.issn=1530-437X&rft.eissn=1558-1748&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FJSEN.2025.3596743&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2025_3596743
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon