Forecasting Multi-Level Deep Learning Autoencoder Architecture (MDLAA) for Parametric Prediction based on Convolutional Neural Networks

This study presents a data-driven framework for anomaly detection, which is a significant process in modern computing, as the detection of an abnormal signal can prevent a high-risk decision. The proposed Multi-Level Deep Learning Autoencoder Architecture (MDLAA) is used to encode high dimensional i...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Engineering, technology & applied science research Ročník 15; číslo 2; s. 21279 - 21283
Hlavní autori: Ayub, Nasir, Sarwar, Nadeem, Ali, Arshad, Khan, Hamayun, Din, Irfanud, Alqahtani, Abdullah M., Abdulnabi, Mohamed Shabbir Hamza, Ali, Aitizaz
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: 03.04.2025
ISSN:2241-4487, 1792-8036
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This study presents a data-driven framework for anomaly detection, which is a significant process in modern computing, as the detection of an abnormal signal can prevent a high-risk decision. The proposed Multi-Level Deep Learning Autoencoder Architecture (MDLAA) is used to encode high dimensional input data using CNNs for anomaly detection in High Dimensional Input Datasets (HDDs). MDLAA is based on unsupervised learning, which has a strong theoretical foundation and is widely used for the detection of anomalies in HDDs, but a few limitations significantly reduce its performance. The proposed MDLAA combines multilevel convolutional layers and data preprocessing. The performance of the proposed model was evaluated on a benchmark dataset. Using feature engineering, the proposed algorithm assists in the detection of anomalies that are present in data structures, especially when compared to the ResNet101 feature extractor. The results show that given adequate data, the proposed technique outperformed other previously implemented deep learning approaches and classification models, showing an overall improvement of 2.3% in terms of MSE, F1-score, precision, and accuracy.
AbstractList This study presents a data-driven framework for anomaly detection, which is a significant process in modern computing, as the detection of an abnormal signal can prevent a high-risk decision. The proposed Multi-Level Deep Learning Autoencoder Architecture (MDLAA) is used to encode high dimensional input data using CNNs for anomaly detection in High Dimensional Input Datasets (HDDs). MDLAA is based on unsupervised learning, which has a strong theoretical foundation and is widely used for the detection of anomalies in HDDs, but a few limitations significantly reduce its performance. The proposed MDLAA combines multilevel convolutional layers and data preprocessing. The performance of the proposed model was evaluated on a benchmark dataset. Using feature engineering, the proposed algorithm assists in the detection of anomalies that are present in data structures, especially when compared to the ResNet101 feature extractor. The results show that given adequate data, the proposed technique outperformed other previously implemented deep learning approaches and classification models, showing an overall improvement of 2.3% in terms of MSE, F1-score, precision, and accuracy.
Author Ali, Aitizaz
Abdulnabi, Mohamed Shabbir Hamza
Din, Irfanud
Sarwar, Nadeem
Alqahtani, Abdullah M.
Khan, Hamayun
Ayub, Nasir
Ali, Arshad
Author_xml – sequence: 1
  givenname: Nasir
  surname: Ayub
  fullname: Ayub, Nasir
– sequence: 2
  givenname: Nadeem
  surname: Sarwar
  fullname: Sarwar, Nadeem
– sequence: 3
  givenname: Arshad
  surname: Ali
  fullname: Ali, Arshad
– sequence: 4
  givenname: Hamayun
  surname: Khan
  fullname: Khan, Hamayun
– sequence: 5
  givenname: Irfanud
  surname: Din
  fullname: Din, Irfanud
– sequence: 6
  givenname: Abdullah M.
  surname: Alqahtani
  fullname: Alqahtani, Abdullah M.
– sequence: 7
  givenname: Mohamed Shabbir Hamza
  surname: Abdulnabi
  fullname: Abdulnabi, Mohamed Shabbir Hamza
– sequence: 8
  givenname: Aitizaz
  surname: Ali
  fullname: Ali, Aitizaz
BookMark eNotkLFOwzAYhC1UJErpxAt4BKEUO3FiZ4xaCkgpdIA5cpzfEEjj6rdTxBPw2rSFW-50J93wnZNR73og5JKzmVBMiVsI2uMs52l6QsZc5nGkWJKNyDiOBY-EUPKMTL3_YHtlKhMyHpOfpUMw2oe2f6OroQttVMIOOroA2NISNPaHpRiCg964BpAWaN7bACYMCPRqtSiL4ppah3StUW8gYGvoGqFpTWhdT2vtoaH7MHf9znXDodQdfYIBjxa-HH76C3Jqdedh-u8T8rq8e5k_ROXz_eO8KCPDRZpGOs1za5VWicmZ0bKxqoaMmTQWqVBKNYxzzqTUTDU2FoZJpSVXcc0sa2JVJxNy8_dr0HmPYKstthuN3xVn1RFjdcRYHTAmv-YlaaU
Cites_doi 10.48084/etasr.7384
10.1109/ACCESS.2019.2942485
10.1007/s13735-022-00227-8
10.1016/j.ijcard.2020.11.053
10.1186/s40537-019-0179-2
10.1016/j.asoc.2022.109486
10.3390/electronics9111963
10.1007/978-3-030-11723-8_16
10.1007/s42979-024-02831-3
10.1109/JAS.2017.7510313
10.1049/2024/8821891
10.1109/JSEN.2020.3035846
10.1145/2689746.2689747
10.48084/etasr.3801
10.1145/3097983.3098052
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.48084/etasr.9155
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1792-8036
EndPage 21283
ExternalDocumentID 10_48084_etasr_9155
GroupedDBID .4S
5VS
AAYXX
ADBBV
AEGXH
ALMA_UNASSIGNED_HOLDINGS
ARCSS
BCNDV
CITATION
EBS
EDO
EJD
ITG
ITH
KWQ
OK1
RNS
TUS
ID FETCH-LOGICAL-c1455-a599ff8a83c90ca7df8be60c52454888d0111077a08df24c078a7182b0f0d28b3
ISSN 2241-4487
IngestDate Sun Nov 09 14:48:33 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License https://creativecommons.org/licenses/by/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1455-a599ff8a83c90ca7df8be60c52454888d0111077a08df24c078a7182b0f0d28b3
OpenAccessLink https://doi.org/10.48084/etasr.9155
PageCount 5
ParticipantIDs crossref_primary_10_48084_etasr_9155
PublicationCentury 2000
PublicationDate 2025-04-03
PublicationDateYYYYMMDD 2025-04-03
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-03
  day: 03
PublicationDecade 2020
PublicationTitle Engineering, technology & applied science research
PublicationYear 2025
References 306508
306519
306509
306515
306516
306517
306518
306511
306522
306512
306523
306513
306524
306514
306525
306520
306510
306521
References_xml – ident: 306516
  doi: 10.48084/etasr.7384
– ident: 306524
  doi: 10.1109/ACCESS.2019.2942485
– ident: 306525
– ident: 306513
  doi: 10.1007/s13735-022-00227-8
– ident: 306510
  doi: 10.1016/j.ijcard.2020.11.053
– ident: 306515
  doi: 10.1186/s40537-019-0179-2
– ident: 306523
  doi: 10.1016/j.asoc.2022.109486
– ident: 306514
  doi: 10.3390/electronics9111963
– ident: 306518
– ident: 306511
  doi: 10.1007/978-3-030-11723-8_16
– ident: 306521
  doi: 10.1007/s42979-024-02831-3
– ident: 306509
  doi: 10.1109/JAS.2017.7510313
– ident: 306517
  doi: 10.1049/2024/8821891
– ident: 306520
  doi: 10.1109/JSEN.2020.3035846
– ident: 306512
  doi: 10.1145/2689746.2689747
– ident: 306519
  doi: 10.48084/etasr.3801
– ident: 306522
– ident: 306508
  doi: 10.1145/3097983.3098052
SSID ssj0000686472
ssib044735913
ssib050383323
Score 2.3079915
Snippet This study presents a data-driven framework for anomaly detection, which is a significant process in modern computing, as the detection of an abnormal signal...
SourceID crossref
SourceType Index Database
StartPage 21279
Title Forecasting Multi-Level Deep Learning Autoencoder Architecture (MDLAA) for Parametric Prediction based on Convolutional Neural Networks
Volume 15
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1792-8036
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044735913
  issn: 2241-4487
  databaseCode: M~E
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FwgEOiKd4aw89gJBhs7br9dEqRT20USWK1Fs0fiyNVJzIdkJ74cr_5Jcws-u1NxWHcuDiOFZs2Z4vM9_Ozn7D2K7SFdk2DzB0l0G0J4ogr_D_uFdp5B9pWkgdmWYTyWymzs7Sk8nkt1sLs7lI6lpdXqar_2pqPIbGpqWz_2Du4aJ4APfR6LhFs-P2RoanZpsFtKac2SyvDY6oMAg9S7Vycqrf3mfrbkkaliQlkfmTCcg4jz8dZRmlC6gE8QSofIt0_Klco1zY1uIU_EqaaNhf1pv-cdDYJPVhPkxtebuV9h-FD8ms3ZDSN-CDngy7VUa9BtGQq86u1nbiCNrFUE78BZoftj58BmXV56DBtNk2Lq9pz6EcIsq5TfUewne4Wtd-tkPGpkgmHJ0iMY4Ah5Q2SFfWaScpenVhhVQGrx576JVbLlra9jV9vMfvtpXO9WASKaEiglAHbfOBdPTHmOnqBK6F0qHAEYdW5vS5OXlOJ99it2USpxQ8jn8eOJ8XUetnb6aY1HnCsKdslk0oUvinHonu0e0yU3P9j-PNecTKY0inD9j9fmjDMwvJh2xS1Y_YPc_uj9kvD5zcAycncHIHTu6Bk_vg5G8NNN9xBCYfgclHYHIDTI47W8DkFpjcAfMJ-_r54HT_MOhbgQQFKekHgG5DawUqLFJRQFJqhS5FFLGMcMitVIlhaiqSBIQqtYwKJL6ArEvmQotSqjx8ynbqZV09Y1zS6wWdaogh0kqAhCmx7jCnYATT52zXvcf5yiq-zP9izhc3-9lLdneE8Su20zXr6jW7U2y6Rdu8MVD4A745oqg
linkProvider ISSN International Centre
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=Forecasting+Multi-Level+Deep+Learning+Autoencoder+Architecture+%28MDLAA%29+for+Parametric+Prediction+based+on+Convolutional+Neural+Networks&rft.jtitle=Engineering%2C+technology+%26+applied+science+research&rft.au=Ayub%2C+Nasir&rft.au=Sarwar%2C+Nadeem&rft.au=Ali%2C+Arshad&rft.au=Khan%2C+Hamayun&rft.date=2025-04-03&rft.issn=2241-4487&rft.eissn=1792-8036&rft.volume=15&rft.issue=2&rft.spage=21279&rft.epage=21283&rft_id=info:doi/10.48084%2Fetasr.9155&rft.externalDBID=n%2Fa&rft.externalDocID=10_48084_etasr_9155
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2241-4487&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2241-4487&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2241-4487&client=summon