| Title |
Data Mining to Predict Steel-Rebar Quantity on Parametric Cost Estimating Model - Focused on Comparison of OLAP and Clustering Method - |
| Authors |
Cho Jae-Ho ; Chun Jae-Youl |
| Keywords |
Data Mining ; OLAP(On-line Analytical Processing) ; Clustering ; Quantity ; Parametric Cost Estimating |
| Abstract |
The purpose of this study is to develop a parametric cost estimating model for the early design stage by using OLAP (On-line Analytical Processing) and Clustering Method based on the case of quantity data related to architectural design features. The multidimensional characteristics of OLAP defines parameter to architectural design features associated with quantity volume change. OLAP technique analyzes a subject data by multi-dimensional points of view; it supports query, analysis, and comparison of required information by diverse queries. Also, Clustering method can predict the quantity volume information through the concept of average formula by clustering similar cases that depend on the character of the project. The estimated results of the clustering results can be used as a knowledge based model that support to predict quantity volume by impact factors on parametric cost estimating method. In this study, after estimating the concrete quantity with standard measure of method, and then suggest how to predict the steel-rebar ratio against the concrete volume. For estimating methods in the field of data mining, OLAP and clustering methods were utilized. And their strengths and weaknesses were analyzed. |