Enhancing the scalability of a genetic algorithm to discover quantitative association rules in large-scale datasets

Abstract

Association rule mining is a well-known methodology to discover significant and apparently hidden relations among attributes in a subspace of instances from datasets. Genetic algorithms have been extensively used to find interesting association rules. However, the rule-matching task of such techniques usually requires high computational and memory requirements. The use of efficient computational techniques has become a task of the utmost importance due to the high volume of generated data nowadays. Hence, this paper aims at improving the scalability of quantitative association rule mining techniques based on genetic algorithms to handle large-scale datasets without quality loss in the results obtained. For this purpose, a new representation of the individuals, new genetic operators and a windowing-based learning scheme are proposed to achieve successfully such challenging task. Specifically, the proposed techniques are integrated into the multi-objective evolutionary algorithm named QARGA-M to assess their performances. Both the standard version and the enhanced one of QARGA-M have been tested in several datasets that present different number of attributes and instances. Furthermore, the proposed methodologies have been integrated into other existing techniques based in genetic algorithms to discover quantitative association rules. The comparative analysis performed shows significant improvements of QARGA-M and other existing genetic algorithms in terms of computational costs without losing quality in the results when the proposed techniques are applied.

Imaging and machine learning techniques for diagnosis of Alzheimer’s disease

“…Johnson et al (2014) used LRC to build a prediction model for the early diagnosis and progression of AD. A genetic algorithm (GA) (Reyes et al, 2014;Lee et al, 2015;Martínez-Ballesteros et al, 2015) is used to find the optimal features (e.g. neuropsychological tests) from the large feature space.…”

Association rule mining algorithms on high-dimensional datasets

“…Such optimization methods have been mainly used over quantitative data without a typical pre-discretization procedure. For example, fuzzy set theory can be used to generate fuzzy association rules with more practical meanings, genetic algorithms to dynamically specify appropriate support threshold and ant colony algorithms to reduce the scale of the result rules [54,55]. As also suggested in this review, association rule mining algorithms that merge diverse optimization methods might, when combined with improved computer techniques, provide researchers with tools of more practical value.…”

A Genetic Algorithm based framework for mining quantitative association rules without specifying minimum support and minimum confidence

“…This method is based on a GA that extracts good intervals in association rules. Mart nez-Ballesteros et al [39] attempted to apply GA to improve the scalability of the methods for QARM and, thus, to process large datasets without sacri cing quality. The results of the comparative analysis mirrored the signi cant improvements made by the proposed methods in the computational costs of QARGA-M and previously developed GAs without reducing the quality of the results.…”