Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 97
PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNOLOGY IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING
Edited by: Y. Tsompanakis, B.H.V. Topping
Paper 52

Data Mining Techniques for the Assessment of Factors Contributing to the Damage of Residential Houses in Australia

N.Y. Osman-Schlegel1, Z.A. Krezel1 and K.J. McManus2

1School of Architecture and Building, Deakin University, Victoria, Australia
2Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, Victoria, Australia

Full Bibliographic Reference for this paper
N.Y. Osman-Schlegel, Z.A. Krezel, K.J. McManus, "Data Mining Techniques for the Assessment of Factors Contributing to the Damage of Residential Houses in Australia", in Y. Tsompanakis, B.H.V. Topping, (Editors), "Proceedings of the Second International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 52, 2011. doi:10.4203/ccp.97.52
Keywords: data mining, chi-square test, categorical regression, artificial intelligence, databases.

Summary
Data mining is vital in order to discover information which is not obvious in a large collection of data and solving problems by analysing data already present in a database. The solution for an accurate and reliable analysis is to develop a consistent data collection method for engineering firms in a form of a uniform database to ease analysis. This paper reports on the preparation and management processes of inconsistent data relating to the damage of residential houses in Victoria, Australia. It describes the process of data mining to develop a uniform database for the Building Housing Commission (BHC) of Victoria, Australia. There are no existing specific and fully relevant databases readily available except for the incomplete paper-based and electronic-based reports. Therefore, the extraction of information from the reports is complicated and time consuming in order to extract and include all the necessary information needed for the analysis of the damage of residential houses founded on expansive soils. Two databases: Data Warehouse and Data Mart were developed. To enhance the performance of the Data Mart and the significant of the factors, statistical methods and a hybrid artificial intelligence technique were adopted. A categorical regression (CATREG) is used to determine the significant of factors that affect the ground movement of expansive soils which is the main source of the damage in residential houses. Pseudo R-square and hybrid artificial intelligence (neural network trained using a genetic algorithm) are adopted to determine the data prediction capability of the Data Mart.

With the development of a Data Warehouse, the Data Mart enabled BHC to evaluate the usefulness of the reports prepared on the reported damage to residential houses. It will also assist BHC in re-evaluating the information given by the engineering firms. This can enable BHC to distinguish between any additional or relevant and non-relevant information required in analysing damage to residential houses on expansive soils in Victoria. The Data Mart can be used to undertake different analysis such as analysing the important factors causing particular types of damage, predicting development of damage in the future and generating detailed reports with substantial filtering options. This analysis can assist in the asset management of the housing stock that needs maintenance, reconstruction or demolition. Financial and other resources can be saved as the database will not only be easy to use but also be readily available for a variety of data analyses using various programs or software.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £70 +P&P)