| dc.creator |
Terzi, O. |
|
| dc.creator |
TERZİ, Serdal |
|
| dc.creator |
SALTAN, Mehmet |
|
| dc.date |
2014-12-31T22:00:00Z |
|
| dc.date.accessioned |
2021-01-21T08:02:57Z |
|
| dc.date.available |
2021-01-21T08:02:57Z |
|
| dc.identifier |
3a400666-29fe-4ca4-82b8-1401d2fa34e8 |
|
| dc.identifier |
https://avesis.sdu.edu.tr/publication/details/3a400666-29fe-4ca4-82b8-1401d2fa34e8/oai |
|
| dc.identifier.uri |
http://acikerisim.sdu.edu.tr/xmlui/handle/123456789/80603 |
|
| dc.description |
© Civil-Comp Press, 2015.In this paper, wavelet-neuro (WN) models have been compared with artificial neural networks (ANN) models and the pavement serviceability index (PSI) equation for estimating the present serviceability ratio (PSR). The original experimental data obtained from ASHTO road tests including PSR, slope variance, rut depth, patches, cracking and longitudinal cracking are decomposed into sub-series components by using the discrete wavelet transform (DWT). Then, effective DWs have been used as input parameters in the ANN modeling. When the regression coefficient values of the WN and ANN models are examined, it has been shown that the WN model gave higher regression coefficient values than the ANN model. |
|
| dc.language |
eng |
|
| dc.rights |
info:eu-repo/semantics/closedAccess |
|
| dc.title |
Modeling the present serviceability ratio of flexible highway pavements using a wavelet-neuro approach |
|
| dc.type |
info:eu-repo/semantics/article |
|