Publication:
Long short term memory networks for predicting resilient Modulus of stabilized base material subject to wet-dry cycles

Simple item page
dc.citedby0
dc.contributor.authorAl?Zubi M.A.en_US
dc.contributor.authorAhmad M.en_US
dc.contributor.authorAbdullah S.en_US
dc.contributor.authorKhan B.J.en_US
dc.contributor.authorQamar W.en_US
dc.contributor.authorAbdullah G.M.S.en_US
dc.contributor.authorGonz�lez-Lezcano R.A.en_US
dc.contributor.authorPaul S.en_US
dc.contributor.authorEL-Gawaad N.S.A.en_US
dc.contributor.authorOuahbi T.en_US
dc.contributor.authorKashif M.en_US
dc.contributor.authorid59367651300en_US
dc.contributor.authorid58731610900en_US
dc.contributor.authorid59368453700en_US
dc.contributor.authorid57219363485en_US
dc.contributor.authorid57942731100en_US
dc.contributor.authorid56606096100en_US
dc.contributor.authorid6506844399en_US
dc.contributor.authorid56814165800en_US
dc.contributor.authorid56815070500en_US
dc.contributor.authorid16507205100en_US
dc.contributor.authorid59412207600en_US
dc.date.accessioned2025-03-03T07:41:26Z
dc.date.available2025-03-03T07:41:26Z
dc.date.issued2024
dc.description.abstractThe resilient modulus (MR) of different pavement materials is one of the most important input parameters for the mechanistic-empirical pavement design approach. The dynamic triaxial test is the most often used method for evaluating the MR, although it is expensive, time-consuming, and requires specialized lab facilities. The purpose of this study is to establish a new model based on Long Short-Term Memory (LSTM) networks for predicting the MR of stabilized base materials with various additives during wet-dry cycles (WDC). A laboratory dataset of 704 records has been used using input parameters, including WDC, ratio of calcium oxide to silica, alumina, and ferric oxide compound, Maximum dry density to the optimal moisture content ratio (DMR), deviator stress (�d), and confining stress (�3). The results demonstrate that the LSTM technique is very accurate, with coefficients of determination of 0.995 and 0.980 for the training and testing datasets, respectively. The LSTM model outperforms other developed models, such as support vector regression and least squares approaches, in the literature. A sensitivity analysis study has determined that the DMR parameter is the most significant factor, while the �d parameter is the least significant factor in predicting the MR of the stabilized base material under WDC. Furthermore, the SHapley Additive exPlanations approach is employed to elucidate the optimal model and examine the impact of its features on the final result. ? The Author(s) 2024.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo27928
dc.identifier.doi10.1038/s41598-024-79588-5
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85209185571
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85209185571&doi=10.1038%2fs41598-024-79588-5&partnerID=40&md5=91ed931143c6d7cb3b2e157ab829b20f
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/36143
dc.identifier.volume14
dc.publisherNature Researchen_US
dc.sourceScopus
dc.sourcetitleScientific Reports
dc.subjectaluminum oxide
dc.subjectcalcium oxide
dc.subjectferric oxide
dc.subjectsilicon dioxide
dc.subjectarticle
dc.subjectcomputer interface
dc.subjectleast square analysis
dc.subjectlong short term memory network
dc.subjectmoisture
dc.subjectsensitivity analysis
dc.subjectShapley additive explanation
dc.subjectsupport vector machine
dc.titleLong short term memory networks for predicting resilient Modulus of stabilized base material subject to wet-dry cyclesen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS