Computational Modeling, An Artificial Intelligence Approach Using Neural Networks As Non Parametric Modeling
1432 WordsJan 12, 20166 Pages
The Ccost estimate is important for projects throughout its life cycle, starting from feasibility studies till tendering stage and developing BOQ, it provides significant information that even may serve project budgeting and controlling if reliable.
This paper presents a comparison between two cost estimate predictive modeling, an artificial intelligence approach using neural networks as non-parametric modeling; and multiplely regression modeling that represents advanced engineering statics - a parametric modeling.
Results show that neural networks have advantages when dealing with data that for which there is little a priori knowledge of the appropriate cost estimate relationship to select for regression modeling. However, in cases where an appropriate CER can be identified, regression models have significant advantages in terms of accuracy, variability, model creation and model examination. Both simulated and actual data sets are used for comparison.
Our research is applied for a specific package of construction projects (concrete work) based on 17 projects with a 115 records.
Key words: construction projects, cost estimate. Concrete work, neural network, multiply regression.
Cost estimate is the productive process used to quantify cost and price the resources to achieve project scope; the output can be used for many purposes throughout project life cycle such as: Determining the economic feasibility