- author = "Mohammadreza Mirzahosseini and Yacoub M. Najjar and Amir Hossein Alavi and Amir Hossein Gandomi",
- title = "{ANN}-Based Prediction Model for Rutting Propensity of Asphalt Mixtures",
- booktitle = "The 92nd Transportation Research Board (TRB) Annual Meeting",
- year = "2013",
- pages = "Paper No. 13--2180",
- address = "Washington, D.C., USA",
- publisher_address = "USA",
- month = jan # " 13-17",
- organisation = "Transportation Research Board, National Research Council",
- keywords = "genetic algorithms, genetic programming, gene expression programming, multi expression programming simulated annealing, ANN",
-
URL = "
http://amonline.trb.org/2013-1.264263/13-2180-1-1.291788",
-
URL = "
http://assets.conferencespot.org/fileserver/file/45736/filename/2vd3kv.pdf",
- size = "18 pages",
- abstract = "This paper investigates the applicability of artificial neural network (ANN) for the prediction of the flow number of dense asphalt-aggregate mixtures. Percentages of coarse aggregate, filler, bitumen, air voids, voids in mineral aggregate, and Marshall Quotient were employed as the predictor variables. A comprehensive experimental database was used for the development of the model. The statistical measures of coefficient of determination, coefficient of efficiency, root mean squared error, and mean absolute error were used to evaluate the performance of the model. Sensitivity and parametric analyses were conducted and discussed. The ANN model accurately characterises the flow number of asphalt mixtures resulting in a very good prediction performance. The proposed model remarkably outperforms several existing prediction models for the flow number of asphalt mixtures.",
-
notes = "'the entire database were compared with those provided
by the gene expression programming (GEP), multi
expression programming (MEP) (29), and hybrid GP and
simulated annealing (GP/SA) models.'
slides http://assets.conferencespot.org/fileserver/file/45735/filename/39e6f1.pdf 'The proposed ANN model significantly outperforms the existing models.' GEP MEP GP/SA
11 Mohammadreza Mirzahosseini* 12 Kansas State University 13 Department of Civil Engineering 14 Manhattan, KS 66506.
19 Yacoub M. Najjar 20 Department of Civil Engineering 21 University of Mississippi 22 University, MS 38677.
27 Amir HosseinAlavi 28 Iran University of Science and Technology 29 School of Civil Engineering 30 Tehran, Iran
34 Amir HosseinGandomi 35 The University of Akron 36 Department of Civil Engineering 37 Akron, OH 44325.
",
