No Cover Image

Conference Paper/Proceeding/Abstract 1156 views 296 downloads

Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification

Sadeer Beden Orcid Logo, Arnold Beckmann Orcid Logo

2023 IEEE 17th International Conference on Semantic Computing (ICSC)

Swansea University Authors: Sadeer Beden Orcid Logo, Arnold Beckmann Orcid Logo

DOI (Published version): 10.1109/icsc56153.2023.00043

Abstract

This paper proposes an ontological framework that combines semantic-based methodologies and data-driven random forests (RF) to enable the integration of domain expert knowledge with machine-learning models. To achieve this, the RF classification process is firstly deconstructed and converted into se...

Full description

Published in: 2023 IEEE 17th International Conference on Semantic Computing (ICSC)
Published: IEEE 2023
Online Access: http://dx.doi.org/10.1109/icsc56153.2023.00043
URI: https://cronfa.swan.ac.uk/Record/cronfa63104
first_indexed 2023-04-10T07:31:11Z
last_indexed 2024-11-15T18:00:55Z
id cronfa63104
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-05-12T10:13:59.9724152</datestamp><bib-version>v2</bib-version><id>63104</id><entry>2023-04-10</entry><title>Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification</title><swanseaauthors><author><sid>acf0be82092335f6fb65bb51f29c46ac</sid><ORCID>0009-0009-7564-7726</ORCID><firstname>Sadeer</firstname><surname>Beden</surname><name>Sadeer Beden</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>1439ebd690110a50a797b7ec78cca600</sid><ORCID>0000-0001-7958-5790</ORCID><firstname>Arnold</firstname><surname>Beckmann</surname><name>Arnold Beckmann</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-04-10</date><deptcode>EAAS</deptcode><abstract>This paper proposes an ontological framework that combines semantic-based methodologies and data-driven random forests (RF) to enable the integration of domain expert knowledge with machine-learning models. To achieve this, the RF classification process is firstly deconstructed and converted into semantic-based rules, which are combined with external rules constructed from the knowledge of domain experts. The combined rule set is applied to an ontological reasoner for inference, producing two classifications: (1) from simulating the selected RF voting strategy, (2) from the knowledge-driven rules, where the latter is prioritised. A case study in the steel manufacturing domain is presented that uses the proposed framework for real-world predictive maintenance purposes. Results are validated and compared to typical machine-learning approaches.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2023 IEEE 17th International Conference on Semantic Computing (ICSC)</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>IEEE</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>1</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-02-01</publishedDate><doi>10.1109/icsc56153.2023.00043</doi><url>http://dx.doi.org/10.1109/icsc56153.2023.00043</url><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-05-12T10:13:59.9724152</lastEdited><Created>2023-04-10T08:18:57.1081789</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Sadeer</firstname><surname>Beden</surname><orcid>0009-0009-7564-7726</orcid><order>1</order></author><author><firstname>Arnold</firstname><surname>Beckmann</surname><orcid>0000-0001-7958-5790</orcid><order>2</order></author></authors><documents><document><filename>63104__27009__2dfb0645d4be4399ae6450f90a8ebe3a.pdf</filename><originalFilename>Towards_an_Ontological_Framework - submission.pdf</originalFilename><uploaded>2023-04-10T08:30:22.6092563</uploaded><type>Output</type><contentLength>407700</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2023-05-12T10:13:59.9724152 v2 63104 2023-04-10 Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification acf0be82092335f6fb65bb51f29c46ac 0009-0009-7564-7726 Sadeer Beden Sadeer Beden true false 1439ebd690110a50a797b7ec78cca600 0000-0001-7958-5790 Arnold Beckmann Arnold Beckmann true false 2023-04-10 EAAS This paper proposes an ontological framework that combines semantic-based methodologies and data-driven random forests (RF) to enable the integration of domain expert knowledge with machine-learning models. To achieve this, the RF classification process is firstly deconstructed and converted into semantic-based rules, which are combined with external rules constructed from the knowledge of domain experts. The combined rule set is applied to an ontological reasoner for inference, producing two classifications: (1) from simulating the selected RF voting strategy, (2) from the knowledge-driven rules, where the latter is prioritised. A case study in the steel manufacturing domain is presented that uses the proposed framework for real-world predictive maintenance purposes. Results are validated and compared to typical machine-learning approaches. Conference Paper/Proceeding/Abstract 2023 IEEE 17th International Conference on Semantic Computing (ICSC) IEEE 1 2 2023 2023-02-01 10.1109/icsc56153.2023.00043 http://dx.doi.org/10.1109/icsc56153.2023.00043 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University 2023-05-12T10:13:59.9724152 2023-04-10T08:18:57.1081789 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Sadeer Beden 0009-0009-7564-7726 1 Arnold Beckmann 0000-0001-7958-5790 2 63104__27009__2dfb0645d4be4399ae6450f90a8ebe3a.pdf Towards_an_Ontological_Framework - submission.pdf 2023-04-10T08:30:22.6092563 Output 407700 application/pdf Accepted Manuscript true true eng
title Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
spellingShingle Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
Sadeer Beden
Arnold Beckmann
title_short Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
title_full Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
title_fullStr Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
title_full_unstemmed Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
title_sort Towards an Ontological Framework for Integrating Domain Expert Knowledge with Random Forest Classification
author_id_str_mv acf0be82092335f6fb65bb51f29c46ac
1439ebd690110a50a797b7ec78cca600
author_id_fullname_str_mv acf0be82092335f6fb65bb51f29c46ac_***_Sadeer Beden
1439ebd690110a50a797b7ec78cca600_***_Arnold Beckmann
author Sadeer Beden
Arnold Beckmann
author2 Sadeer Beden
Arnold Beckmann
format Conference Paper/Proceeding/Abstract
container_title 2023 IEEE 17th International Conference on Semantic Computing (ICSC)
publishDate 2023
institution Swansea University
doi_str_mv 10.1109/icsc56153.2023.00043
publisher IEEE
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.1109/icsc56153.2023.00043
document_store_str 1
active_str 0
description This paper proposes an ontological framework that combines semantic-based methodologies and data-driven random forests (RF) to enable the integration of domain expert knowledge with machine-learning models. To achieve this, the RF classification process is firstly deconstructed and converted into semantic-based rules, which are combined with external rules constructed from the knowledge of domain experts. The combined rule set is applied to an ontological reasoner for inference, producing two classifications: (1) from simulating the selected RF voting strategy, (2) from the knowledge-driven rules, where the latter is prioritised. A case study in the steel manufacturing domain is presented that uses the proposed framework for real-world predictive maintenance purposes. Results are validated and compared to typical machine-learning approaches.
published_date 2023-02-01T05:11:53Z
_version_ 1851096840446935040
score 11.089551

Similar Items