A review of soft computing methods based cost estimation techniques


Dikmen S. U., Akbiyikli R.

Construction and Building Research Conference of the Royal Institution of Chartered Surveyors, COBRA 2009, Cape-Town, South Africa, 10 - 11 September 2009, pp.1776-1788 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Cape-Town
  • Country: South Africa
  • Page Numbers: pp.1776-1788
  • Keywords: Cost estimation, Fuzzy logic, Neural networks, Soft computing
  • Istanbul Kültür University Affiliated: Yes

Abstract

Neural networks and fuzzy logic method are both computing tools known as soft computing methods. Neural networks are inspired by the internal structure and operation of the brain, whereas fuzzy logic is inspired by the natural language and linguistic approaches to problem solving. In the field of construction engineering and management estimating the probable costs is an important task requiring a great deal of intuition and experience. Thus a great deal of decision making is required while estimating the costs of a either a future or an ongoing project. In that respect, neural networks and fuzzy set theory inherently have the characteristics to form a decision support system. These soft computation tools were being used successfully in other fields of civil engineering since early 1980's. Though not extensively, they are also applied to various aspects of construction management starting in 90's and in the recent years. This paper will present a comprehensive review of the use of both neural networks and fuzzy logic method as a decision support tool for cost estimation. © RICS.