Brain Inspired Cognitive Systems 2008

Abstract

The most unacceptable structural damage of porous asphalt top layers is the loss of stones leading to raveling. Therefore it is important to predict when the porous asphalt top layer will achieve a critical level of raveling so as to allocate funds for necessary maintenance. SHRP-NL database including eight provinces of the Netherlands was used as the data resource. Artificial Neural Network (ANN) was employed to predict severity of raveling having input parameters related to historical raveling and climate, construction and traffic factors. An ANN is able to forecast raveling low with a high correlation factor (R 2 =0.986), raveling moderate with ( R 2 =0.926) and raveling high with (R 2 =0.976). Besides another ANN provided sensitivity analysis indicating the relative contribution of factors related to climate (58%), traffic factor (14%), thickness (6%), roughness (12%) and age (10%) for raveling low and high but for raveling moderate climate (46%), traffic factor (15%), thickness (15%), roughness (13%) and age (11%) are the results. Color Contours illustrated that heavy traffic, low thickness and high roughness cause raveling on old asphalt especially in cold rainy days. ANN proved to be a powerful technique to predict and analyze raveling opening great opportunities for development of ANN models for other detriments.

AMCAT Utility to Engineering and Computer Science Students

“…Awareness is defined as the capability of being aware or conscious about some information. Students' awareness refers to the consciousness or awareness level of students with regard to AMCAT (Chalmers, 1997;Hussain et al, 2009). Personal Benefits.…”