An evolutionary algorithm to discover quantitative association rules in multidimensional time series

Martínez-Ballesteros, M.; Martínez‐Álvarez, Francisco; Troncoso, Alicia; Riquelme, José C.

doi:10.1007/s00500-011-0705-4

Cited by 41 publications

(33 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a preliminary step, the QARGA algorithm [31] has been applied to several datasets of different nature to avoid the dependence between the results and the datasets. In particular, the realworld and public datasets described in Section 4.2 have been used to obtain five hundred QAR for each dataset (5 executions of 100 rules per dataset).…”

Section: Principal Component Analysismentioning

confidence: 99%

“…To fulfill this task, this subset is generated accord- ing to a principal component analysis (PCA). The QARGA algorithm [31] has been used to check the new fitness function composed of the selected measures versus the original fitness function based on a weighting scheme that involved several evaluation measures such as support, confidence, number of attributes and amplitude of intervals of the attributes belonging to the rules. In particular, datasets from the public Bilkent University Function Approximation (BUFA) repository [24] have been used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Selecting the best measures to discover quantitative association rules

et al. 2014

Self Cite

View full text Add to dashboard Cite

The majority of the existing techniques to mine association rules typically use the support and the confidence to evaluate the quality of the rules obtained. However, these two measures may not be sufficient to properly assess their quality due to some inherent drawbacks they present. A review of the literature reveals that there exist many measures to evaluate the quality of the rules, but that the simultaneous optimization of all measures is complex and might lead to poor results. In this work, a principal components analysis is applied to a set of measures that evaluate quantitative association rules' quality. From this analysis, a reduced subset of measures has been selected to be included in the fitness function in order to obtain better values for the whole set of quality measures, and not only for those included in the fitness function. This is a general-purpose methodology and can, therefore, be applied to the fitness function of any algorithm. To validate if better results are obtained when using the function fitness composed of the subset of measures proposed here, the existing QARGA algorithm has been applied to a wide variety of datasets. Finally, a comparative analysis of the results obtained by means of the application of QARGA with the original fitness function is provided, showing a remarkable improvement when the new one is used.

show abstract

Section: Principal Component Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Selecting the best measures to discover quantitative association rules

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main motivation of this paper is to extend preliminary works such as the proposed algorithms called QARGA [51,52] and EQAR [53], to a multi-objective approach based on the NSGA-II algorithm able to deal with biological problems. In particular, a non-dominated multi-objective evolutionary algorithm is proposed in this work which is able to find QAR in databases with continuous attributes avoiding the discretization step.…”

Section: Mining Association Rules: a Reviewmentioning

confidence: 99%

“…The proposed algorithm extends the main features of QARGA [51,52] and EQAR [53] adding new features to improve the AR mining task. The most important improvement achieved in GarNet is related with solving the main drawbacks caused by the weighted objective scheme existing in the fitness function.…”

Section: Evolutionary Process Of Garnetmentioning

confidence: 99%

See 1 more Smart Citation

Discovering gene association networks by multi-objective evolutionary quantitative association rules

Martínez-Ballesteros

Nepomuceno-Chamorro

Riquelme

2014

Journal of Computer and System Sciences

Self Cite

View full text Add to dashboard Cite

In the last decade, the interest in microarray technology has exponentially increased due to its ability to monitor the expression of thousands of genes simultaneously. The reconstruction of gene association networks from gene expression profiles is a relevant task and several statistical techniques have been proposed to build them. The problem lies in the process to discover which genes are more relevant and to identify the direct regulatory relationships among them. We developed a multi-objective evolutionary algorithm for mining quantitative association rules to deal with this problem. We applied our methodology named GarNet to a well-known microarray data of yeast cell cycle. The performance analysis of GarNet was organized in three steps similarly to the study performed by Gallo et al. GarNet outperformed the benchmark methods in most cases in terms of quality metrics of the networks, such as accuracy and precision, which were measured using YeastNet database as true network. Furthermore, the results were consistent with previous biological knowledge. 1.IntroductionSince late 1990s, the interest in microarray technology has exponentially increased due to its ability to monitor the expression of thousands of genes simultaneously. Microarray technology has revolutionized the biological research because it allows to study thousand of genes or even whole genomes [1].As molecular biology is rapidly evolving into a quantitative science, it increasingly relies on computational algorithms to make sense of high-throughput data. One of the main goals in Microarray analysis is the reconstruction of gene regulatory processes and a key task is the inference of regulatory interactions among genes from gene expression data [2].Our aimisto infer the relationships between genes from an organism in a particular biological process. This relationships can be modeled in several levels of abstraction, these levels range from the detailed gene regulatory processes (where a chain of intracellular reaction activates a regulatory molecule, transcription factors until a protein is synthesized) to the high models of abstraction named gene association networks. In the reconstruction of gene regulatory processes, building gene association networks has been proven to provide useful insights for such task, the reconstruction of gene regulatory processes. A gene association network can be defined as a graph in which nodes represent genes and edges represent the influence between them. Our goal in this work is the inference of gene association networks from Microarray datasets.There are several statistical methods to infer gene association networks from Microarray data. A microarray dataset is a bidimensional data structure where conditions are experiments or sources and the columns are gene expression values. In our problem the conditions will be the instances and the gene expression values will be the attributes or features. These methods range from relatively straightforward correlation-based methods to more sophisticated methods based on

show abstract

A Sensitivity Analysis for Quality Measures of Quantitative Association Rules

Martínez-Ballesteros

Martínez‐Álvarez

Troncoso

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. There exist several fitness function proposals based on a combination of weighted objectives to optimize the discovery of association rules. Nevertheless, some differences in the measures used to assess the quality of association rules could be obtained according to the values of such weights. Therefore, in such proposals it is very important the user's decision in order to specify the weights or coefficients of the optimized objectives. Thus, this work presents an analysis on the sensitivity of several quality measures when the weights included in the fitness function of the existing QARGA algorithm are modified. Finally, a comparative analysis of the results obtained according to the weights setup is provided.

show abstract

An evolutionary algorithm to discover quantitative association rules in multidimensional time series

Cited by 41 publications

References 45 publications

Selecting the best measures to discover quantitative association rules

Selecting the best measures to discover quantitative association rules

Discovering gene association networks by multi-objective evolutionary quantitative association rules

A Sensitivity Analysis for Quality Measures of Quantitative Association Rules

Contact Info

Product

Resources

About