Hierarchical Interpretable Construction Algorithm for Data Analysis

In low-computation modeling tasks, the Incremental Constructive Algorithm (ICA) shows good performance. However, it relying on horizontal network expansion for model building limits its mapping ability. Thus, it struggles to capture deep feature relations in complex data and can not meet accuracy ne...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 30th International Conference on Automation and Computing (ICAC) S. 1 - 5
Hauptverfasser: Dai, Wei, Duan, MingZi, Nan, Jing
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 27.08.2025
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In low-computation modeling tasks, the Incremental Constructive Algorithm (ICA) shows good performance. However, it relying on horizontal network expansion for model building limits its mapping ability. Thus, it struggles to capture deep feature relations in complex data and can not meet accuracy needs in complex predictions. This paper proposes the Hierarchical Incremental Construction Algorithm (HICA) by combining ICA interpretability control strategy and DNNs deep stacking structure. HICA has hierarchical propagation. It uses the previous layer residual as the next layer predicted value and the previous hidden layer output matrix as input. It can dynamically add hidden layers and iteratively replace actual outputs with expected ones for better generalization. Nodes are selected by an interpretability-based geometric control strategy. Experiments prove HICA accuracy advantage and lower computational cost.
AbstractList In low-computation modeling tasks, the Incremental Constructive Algorithm (ICA) shows good performance. However, it relying on horizontal network expansion for model building limits its mapping ability. Thus, it struggles to capture deep feature relations in complex data and can not meet accuracy needs in complex predictions. This paper proposes the Hierarchical Incremental Construction Algorithm (HICA) by combining ICA interpretability control strategy and DNNs deep stacking structure. HICA has hierarchical propagation. It uses the previous layer residual as the next layer predicted value and the previous hidden layer output matrix as input. It can dynamically add hidden layers and iteratively replace actual outputs with expected ones for better generalization. Nodes are selected by an interpretability-based geometric control strategy. Experiments prove HICA accuracy advantage and lower computational cost.
Author Duan, MingZi
Dai, Wei
Nan, Jing
Author_xml – sequence: 1
  givenname: Wei
  surname: Dai
  fullname: Dai, Wei
  email: weidai@cumt.edu.cn
  organization: China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China
– sequence: 2
  givenname: MingZi
  surname: Duan
  fullname: Duan, MingZi
  email: mingziduan@cumt.edu.cn
  organization: China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China
– sequence: 3
  givenname: Jing
  surname: Nan
  fullname: Nan, Jing
  email: jingnan@cumt.edu.cn
  organization: China University of Mining and Technology,School of Information and Control Engineering,Xuzhou,China
BookMark eNo1j8tOwzAQRY0ECyj9AyT8Ayl-TeJZRuHRSpVYwL5ynDG1lDqVYxb9eyIBqyudxdG5d-w6TYkYe5RiI6XAp13XdjXoBjdKKFiYxBpqccXW2KDVWoICA_qWddtI2WV_jN6NfJcK5XOm4vqReDelueRvX-KUeDt-TTmW44mHKfNnVxxvkxsvc5zv2U1w40zrv12xj9eXz25b7d_flpB9FVGXCr0lUGi065U0FEIP2APZRgtjBZlhiVTeBjTSoAEwXhhthtDYWkgx6BV7-LVGIjqcczy5fDn8P9M_87dH9g
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICAC65379.2025.11196560
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331525453
EndPage 5
ExternalDocumentID 11196560
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i93t-9c8e52943ab214effb59b5e8730480e4d1112c8f941494554c0434df786010d3
IEDL.DBID RIE
IngestDate Sat Oct 25 03:16:25 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-9c8e52943ab214effb59b5e8730480e4d1112c8f941494554c0434df786010d3
PageCount 5
ParticipantIDs ieee_primary_11196560
PublicationCentury 2000
PublicationDate 2025-Aug.-27
PublicationDateYYYYMMDD 2025-08-27
PublicationDate_xml – month: 08
  year: 2025
  text: 2025-Aug.-27
  day: 27
PublicationDecade 2020
PublicationTitle 2025 30th International Conference on Automation and Computing (ICAC)
PublicationTitleAbbrev ICAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.9198035
Snippet In low-computation modeling tasks, the Incremental Constructive Algorithm (ICA) shows good performance. However, it relying on horizontal network expansion for...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accuracy
Computational efficiency
Computational modeling
Convergence
Data analysis
Geometry
geometry control strategy
Heuristic algorithms
hierarchical deep structure
Interpretable constructive algorithm
Network architecture
Prediction algorithms
Stacking
Title Hierarchical Interpretable Construction Algorithm for Data Analysis
URI https://ieeexplore.ieee.org/document/11196560
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27TsMwFLVoxcAEiCDe8sCaPvyIfccqUJWlqgRDt8qxr6FSSREEvh_bbagYGNgiK5J9bflx7HvOIeSWWRvgDZi84BULAIWHdbByNlcgw4gb7Q26ZDahplM9n8NsS1ZPXBhETMln2Iuf6S3fre1nvCrrh3kJUSymQzpKFRuy1jZnaziA_kM5KgvJVeSfMNlr__7lm5K2jfHhPys8ItmOgEdnP1vLMdnD-oSUk2VkCyfzkhXdZQtWK6TRd7NVgqWj1fM6YP6XVxpOpPTONIa22iMZeRzfP5WTfOuBkC-BNzlYjZKB4KZiQ4HeVxIqiTrMS6EHKFxoIbPagwhIR4SjgR0ILpxXOgItx09Jt17XeEYoRGE-5aS3BoQpwEjJULBhYaLPNPpzksX4F28bkYtFG_rFH-WX5CD2crxeZeqKdEOMeE327Vez_Hi_SUPzDblnkCI
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFL1oFXSlYsW3WbidPvKYSZZltLRYS8EuuiuZ5EYLfYhWv98kzlhcuHA3hIHkJuRxknvOAbilxnh4o3SSsoJ6gML8OlhYk2RK-BHX0mm00WwiGw7lZKJGJVk9cmEQMSafYSN8xrd8uzIf4aqs6eelCmIx27ATrLNKulaZtdVuqWY_7-SpYFlgoFDRqP7_5ZwSN47uwT-rPIT6hoJHRj-byxFs4fIY8t4s8IWjfcmcbPIFizmS4LxZacGSzvx55VH_y4L4Mym502tNKvWROjx178d5LyldEJKZYutEGYmCKs50QdscnSuEKgRKPzO5bCG3voXUSKe4xzrcHw5MizNuXSYD1LLsBGrL1RJPgaggzZdZ4YxWXKdKC0GR03aqg9M0ujOoh_inr98yF9Mq9PM_ym9grzd-HEwH_eHDBeyHHg-XrTS7hJqPF69g13yuZ-9v13GYvgBuHZNr
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%3Abook&rft.genre=proceeding&rft.title=2025+30th+International+Conference+on+Automation+and+Computing+%28ICAC%29&rft.atitle=Hierarchical+Interpretable+Construction+Algorithm+for+Data+Analysis&rft.au=Dai%2C+Wei&rft.au=Duan%2C+MingZi&rft.au=Nan%2C+Jing&rft.date=2025-08-27&rft.pub=IEEE&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FICAC65379.2025.11196560&rft.externalDocID=11196560