Book Chapter10.1007/978-3-319-12568-8_52
Evolutionary Multi-Objective Approach for Prototype Generation and Feature Selection
Alejandro Rosales-Pérez,Jesus A. Gonzalez,Carlos A. Coello-Coello,Carlos A. Reyes-García,Hugo Jair Escalante +4 more
- 02 Nov 2014
- pp 424-431
TL;DR: 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 thenumber of features.
read more
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 multi-objective 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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Intelligent facial emotion recognition using a layered encoding cascade optimization model
Siew Chin Neoh,Li Zhang,Kamlesh Mistry,Mohammed Alamgir Hossain,Chee Peng Lim,Nauman Aslam,Philip Kinghorn +6 more
- 01 Sep 2015
TL;DR: A layered cascade optimization model is developed for facial emotion recognition and two layered cascade-based evolutionary algorithms are proposed for feature selection that focus on within-class and between-class variations for feature optimization.
63
Prototype Generation Using Multiobjective Particle Swarm Optimization for Nearest Neighbor Classification
Weiwei Hu,Ying Tan +1 more
TL;DR: In this paper, particle swarm optimization is applied to prototype generation and two novel methods for improving the classification performance are presented: a fitness function named error rank and the multiobjective (MO) optimization strategy.
42
A novel multi-objective genetic algorithm approach to address class imbalance for disease diagnosis
TL;DR: A GA-based undersampling technique with a weighted fitness function to determine the trade-off between sensitivity and specificity followed by a multi-objective genetic algorithm (MOGA) approach to address the class imbalance problem for disease diagnosis is proposed.
14
Discretization-based Feature Selection as a Bi-level Optimization Problem
TL;DR: Bi-DFS (Bi-level Discretization-based Feature Selection) as discussed by the authors models the feature selection task as a bi-level optimization problem and then solves it using an improved version of an existing co-evolutionary algorithm, named I-CEMBA.
12
Three-objective constrained evolutionary instance selection for classification: Wrapper and filter approaches
TL;DR: In this paper , the authors proposed three-objective constrained optimization models to formulate instance selection wrapper and filter methods (separately) for classification problems, which are solved with multiobjective evolutionary algorithms and multioriental differential evolution.
6
References
Approximating the Nondominated Front Using the Pareto Archived Evolution Strategy
Joshua Knowles,David Corne +1 more
TL;DR: The Pareto Archived Evolution Strategy (PAES) as discussed by the authors is a (1 + 1) evolution strategy employing local search but using a reference archive of previously found solutions in order to identify the approximate dominance ranking of the current and candidate solution vectors.
Prototype Selection for Nearest Neighbor Classification: Taxonomy and Empirical Study
TL;DR: A taxonomy based on the main characteristics presented in prototype selection is proposed and an experimental study involving different sizes of data sets is conducted for measuring their performance in terms of accuracy, reduction capabilities, and runtime.
A Taxonomy and Experimental Study on Prototype Generation for Nearest Neighbor Classification
Isaac Triguero,Joaquín Derrac,Salvador García,Francisco Herrera +3 more
- 01 Jan 2012
TL;DR: This paper provides a survey of PG methods specifically designed for the NN rule, and proposes a taxonomy based on the main characteristics presented in them that is appropriate for application to different datasets.
Differential evolution for optimizing the positioning of prototypes in nearest neighbor classification
TL;DR: A complete study of the performance of four recent advances in differential evolution is provided and the good synergy obtained by the combination of a prototype selection stage with an optimization of the positioning of prototypes previous to nearest neighbor classification is shown.
129
Multi-granulation method for information fusion in multi-source decision information system
TL;DR: The experimental results show that the proposed multi-source fusion method can always find a set of thresholds, which makes the fusion effect better than the mean fusion.
96