Feature transformation: A genetic-based feature construction method for data summarization

Rayner Alfred, (2010) Feature transformation: A genetic-based feature construction method for data summarization. Computational Intelligence, 26 (3). pp. 337-357. ISSN 0824-7935

[img]
Preview
PDF
43Kb

Official URL: http://dx.doi.org/10.1111/j.1467-8640.2010.00362.x

Abstract

The importance of input representation has been recognized already in machine learning. This article discusses the application of genetic-based feature construction methods to generate input data for the data summarization method called Dynamic Aggregation of Relational Attributes (DARA). Here, feature construction methods are applied to improve the descriptive accuracy of the DARA algorithm. The DARA algorithm is designed to summarize data stored in the nontarget tables by clustering them into groups, where multiple records stored in nontarget tables correspond to a single record stored in a target table. This article addresses the question whether or not the descriptive accuracy of the DARA algorithm benefits from the feature construction process. This involves solving the problem of constructing a relevant set of features for the DARA algorithm by using a genetic-based algorithm. This work also evaluates several scoring measures used as fitness functions to find the best set of constructed features. © 2010 Wiley Periodicals, Inc.

Item Type:Article
Uncontrolled Keywords:Clustering data; Data summarizations; Dynamic aggregation; Feature construction, Feature transformations, Fitness functions, Genetic-based algorithms, Input datas, Machine-learning, Scoring measures
Subjects:?? QA75.5-76.95 ??
Divisions:SCHOOL > School of Engineering and Information Technology
ID Code:1969
Deposited By:IR Admin
Deposited On:02 Mar 2011 12:43
Last Modified:17 Feb 2015 16:49

Repository Staff Only: item control page


Browse Repository
Collection
   Articles
   Book
   Speeches
   Thesis
   UMS News
Search
Quick Search

   Latest Repository

Link to other Malaysia University Institutional Repository

Malaysia University Institutional Repository