To overcome the problem of outlier data in the regression analysis for numerical-based damage spectra, the C4.5 decision tree learning algorithm is used to predict damage in reinforced concrete buildings in future earthquake scenarios. Reinforced concrete buildings are modelled as single-degree-of-freedom systems and various time-history nonlinear analyses are performed to create a dataset of damage indices.Subsequently, two decision trees are trained using the qualitative interpretations of those indices. The first decision tree determines whether damage occurs in an RC building. Consequently, the second decision tree predicts the severity of damage as repairable, beyond repair, or collapse.

The task of positioning temporary facilities on a construction site has long been recognized as a factor of great influence on the cost of projects. This paper proposes the use of a recently developed harmony search (HS) algorithm to solve the problem of assigning a set of predetermined facilities to a set of preallocated locations within a construction site. Experiments with different parameter settings were conducted, and an alternative approach was used with a modified HS algorithm to overcome shortcomings of the original method. The proposed algorithm shows a rapid convergence to an optimum solution during the early stages of algorithm progress. In addition, comparisons with different variations of the HS algorithm and genetic algorithm (GA) are presented to demonstrate the efficiency of the proposed method and HS methodology in solving facility layout problems.

No abstract

No abstract