Genetic Programming of Prototypes for Pattern Classification

Mendoza, Karlo; Graff, Mario; Morales-Reyes, Alicia

doi:10.1007/978-3-642-38628-2_11

Cited by 7 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to mention that SGPFGP classification performance is similar to that obtained by another PG method based on genetic programming [4]. However, SGPFGP obtains substantially better instance-reduction performance and is able to reduce data dimensionality.…”

Section: Classification Performance Of Prototypesmentioning

confidence: 69%

“…That is, the aim is to build artificial instances and new features to improve NN classification performance. Escalante et al have recently proposed a PG method based on genetic programming that combines instances to produce prototypes [4]. The proposed method extends that work by also allowing features generation, and by proposing a modeling framework that selects class-specific prototypes and features.…”

Section: Related Workmentioning

confidence: 96%

“…However, its performance in terms of accuracy was worse than many other strategies. Other effective methods are based on bio-inspired optimization as well, see e.g., [5,15,2,4,19]. All of these methods evolve a population of individuals (codifying prototypes) trying to maximize the classification performance.…”

Section: Related Workmentioning

confidence: 99%

“…Table 2 summarizes the main features of the benchmark. This suite has been widely used for benchmarking GP methods [21,4]. Commonly, results of PG methods are reported separately for small (data sets with less than 2,000 instances) and large (data sets with at least 2,000 instances) data sets.…”

Section: Experimental Frameworkmentioning

confidence: 99%

See 3 more Smart Citations

Simultaneous generation of prototypes and features through genetic programming

García-Limón

Morales

Morales-Reyes

2014

Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

Nearest-neighbor (NN) methods are highly effective and widely used pattern classification techniques. There are, however, some issues that hinder their application for large scale and noisy data sets; including, its high storage requirements, its sensitivity to noisy instances, and the fact that test cases must be compared to all of the training instances. Prototype (PG) and feature generation (FG) techniques aim at alleviating these issues to some extent; where, traditionally, both techniques have been implemented separately. This paper introduces a genetic programming approach to tackle the simultaneous generation of prototypes and features to be used for classification with a NN classifier. The proposed method learns to combine instances and attributes to produce a set of prototypes and a new feature space for each class of the classification problem via genetic programming. An heterogeneous representation is proposed together with ad-hoc genetic operators. The proposed approach overcomes some limitations of NN without degradation in its classification performance. Experimental results are reported and compared with several other techniques. The empirical assessment provides evidence of the effectiveness of the proposed approach in terms of classification accuracy and instance/feature reduction.

show abstract

Section: Classification Performance Of Prototypesmentioning

confidence: 69%

Section: Related Workmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

Section: Experimental Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Simultaneous generation of prototypes and features through genetic programming

García-Limón

Morales

Morales-Reyes

2014

Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among the studies that have approached the PG problem, those based on bioinspired optimization have gained popularity in recent years [1][2][3][4]6,[8][9][10]. These generally seek at optimizing a criterion related to the classification performance of the generated prototypes.…”

Section: Introductionmentioning

confidence: 99%

Evolutionary Multi-Objective Approach for Prototype Generation and Feature Selection

Rosales-Pérez

González

Coello

et al. 2014

Advanced Information Systems Engineering

Self Cite

View full text Add to dashboard Cite

Abstract. This paper introduces EMOPG+FS, a novel approach to prototype generation and feature selection that explicitly minimizes the classification error rate, the number of prototypes, and the number of features. Under EMOPG+FS, prototypes are initialized from a subset of training instances, whose positions are adjusted through a multiobjective evolutionary algorithm. The optimization process aims to find a set of suitable solutions that represent the best possible trade-offs among the considered criteria. Besides this, we also propose a strategy for selecting a single solution from the several that are generated during the multi-objective optimization process.We assess the performance of our proposed EMOPG+FS using a suite of benchmark data sets and we compare its results with respect to those obtained by other evolutionary and non-evolutionary techniques. Our experimental results indicate that our proposed approach is able to achieve highly competitive results.

show abstract