Publication:
Hybrid data regression model based on the generalized adaptive resonance theory neural network

Simple item page
dc.citedby2
dc.contributor.authorWong S.Y.en_US
dc.contributor.authorYap K.S.en_US
dc.contributor.authorLim C.P.en_US
dc.contributor.authorLee E.W.M.en_US
dc.contributor.authorid55812054100en_US
dc.contributor.authorid24448864400en_US
dc.contributor.authorid55666579300en_US
dc.contributor.authorid7406966866en_US
dc.date.accessioned2023-05-29T07:27:53Z
dc.date.available2023-05-29T07:27:53Z
dc.date.issued2019
dc.descriptionArts computing; Benchmarking; E-learning; Fire protection; Fires; Learning algorithms; Neural networks; Regression analysis; Resonance; Thermal Engineering; Adaptive resonance theory; Adaptive resonance theory neural networks; Fire safety engineering; Fully online learning; Generalized Regression Neural Network(GRNN); Ordering algorithms; Regression problem; Thermal interfaces; Learning systemsen_US
dc.description.abstractThe Generalized Adaptive Resonance Theory (GART) model is a supervised online learning neural network based on an integration of Adaptive Resonance Theory (ART) and the Generalized Regression Neural Network (GRNN). It is capable of online learning, and is suitable for undertaking both classification and regression problems. In this paper, we further enhance GART (EGART) with four improvements to formulate a new EGART model. Three operating strategies for the EGART model to undertake regression problems are suggested. The first operating strategy is a fully online learning EGART model. The second operating strategy involves Ordering Algorithm for determining the presentation sequence of training samples during the initial training of EGART model. This strategy is considered as offline learning because a set of data samples must be available for the Ordering Algorithm to compute the best presentation sequence (hereinafter denoted as Ordered-EGART). The third operating strategy aims to demonstrate online learning capability of EART model (the first operating strategy) can still be resumed after training on the Ordered-EGART. It is most suitable for applications with a set of ready data samples and their sequences are predetermined by Ordering Algorithm prior to training of EGART model in offiine mode, and triggers online learning when more new data samples become available (hereinafter denoted as IO-EGART). A series of experiments with five benchmark data sets from various application domains is conducted to assess and compare the effectiveness of the EGART model and three operating strategies with those of other methods published in literature as well as two fire safety engineering problems, i.e., predicting the thermal interface height in a single compartment fire and evacuation times in the event of fire. The results and comparisons with other approaches positively demonstrate the efficacy and applicability of EGART model as a useful data regression model for tackling fire safety engineering problems. � 2020 Association for Computing Machinery. All rights reserved.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo2935454
dc.identifier.doi10.1109/ACCESS.2019.2935454
dc.identifier.epage116452
dc.identifier.scopus2-s2.0-85081097378
dc.identifier.spage116438
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85081097378&doi=10.1109%2fACCESS.2019.2935454&partnerID=40&md5=8809f4725bbc721291aa48bc520b2979
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/24850
dc.identifier.volume7
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofAll Open Access, Gold, Green
dc.sourceScopus
dc.sourcetitleIEEE Access
dc.titleHybrid data regression model based on the generalized adaptive resonance theory neural networken_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS