Data feature selection based on Artificial Bee Colony algorithm

Schiezaro, Mauricio; Pedrini, Hélio

doi:10.1186/1687-5281-2013-47

Cited by 147 publications

(95 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The main idea consists of reducing the number of possible paths visited by ants in some works, as well as modified pheromone update rules. Other approaches such as Artificial Bee Colony [9,20] and Gravitational Search Algorithm [1,15] have been also employed to the same context. Basically, the main idea of these methods is to convert the position of the agents (bats, particles, harmonies, etc.)…”

Section: Introductionmentioning

confidence: 99%

Binary Flower Pollination Algorithm and Its Application to Feature Selection

Rodrigues

Yang

Souza

et al. 2014

Studies in Computational Intelligence

View full text Add to dashboard Cite

The problem of feature selection has been paramount in the last years, since it can be as important as the classification step itself. The main goal of feature selection is to find out the subset of features that optimize some fitness function, often in terms of a classifier's accuracy or even the computational burden for extracting each feature. Therefore, the approaches to feature selection can be modeled as optimization tasks. In this chapter, we evaluate a binary-constrained version of the Flower Pollination Algorithm (FPA) for feature selection, in which the search space is a boolean lattice where each possible solution, or a string of bits, denotes whether a feature will be used to compose the final set. Numerical experiments over some public and private datasets have been carried out and comparison with Particle Swarm Optimization, Harmony Search and Firefly Algorithm has demonstrated the suitability of the FPA for feature selection.

show abstract

Section: Introductionmentioning

confidence: 99%

Binary Flower Pollination Algorithm and Its Application to Feature Selection

Rodrigues

Yang

Souza

et al. 2014

Studies in Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Naïve Bayes Classifier has been used in [10] to classify the CTG data in to three classes. In [11], a feature selection method based on Artificial Bee Colony algorithm is reported. Further, in [12] feature selection method based on Artificial Bee Colony algorithm and Support Vector Machines for medical datasets classification is proposed.…”

Section: Introductionmentioning

confidence: 99%

Opposition Based Firefly Algorithm Optimized Feature Subset Selection Approach for Fetal Risk Anticipation

Subha¹,

Murugan²

2016

MLAIJ

View full text Add to dashboard Cite

Recently huge amount of data is available in the field of medicine that helps the doctors in diagnosing diseases when analysed. Data mining techniques can be applied to these medical data to extract knowledge so that disease prediction becomes accurate and easier. In this work, cardiotocogram (CTG) data is analysed using Support Vector Machine (SVM) for predicting fetal risk. Opposition based firefly algorithm (OBFA) is proposed to extract the relevant features that maximise the classification performance of SVM.The obtained results show that opposition based firefly algorithm outperforms the standard firefly algorithm (FA).

show abstract

“…Naïve Bayes Classifier has been used in [10] to classify the CTG data in to three classes. In [11], a feature selection method based on Artificial Bee Colony algorithm has been presented. Further, in [12], a feature selection method has been reported which is based on Artificial Bee Colony algorithm and Support Vector Machines for medical datasets classification.…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithm Based Feature Subset Selection for Fetal State Classification

Velappan

Murugan

Prabha

et al. 2015

JCTECS

View full text Add to dashboard Cite

Abstract-Huge amount of data are available in the field of medicine which are used for diagnosing the diseases by analysing them. Presently, prediction of diseases are made easier and accurate by employing various data mining techniques to extract information from these medical data. This paper presents an improved method of classifying the cardiotocogram data using Multiclass Support Vector Machine (MSVM) through an optimized feature subset produced by Genetic Algorithm (GA). Various performance metrics have been evaluated and the experimental results exhibit improved performance when using optimized feature set comparing to the full feature set.

show abstract

Data feature selection based on Artificial Bee Colony algorithm

Cited by 147 publications

References 30 publications

Binary Flower Pollination Algorithm and Its Application to Feature Selection

Binary Flower Pollination Algorithm and Its Application to Feature Selection

Opposition Based Firefly Algorithm Optimized Feature Subset Selection Approach for Fetal Risk Anticipation

Genetic Algorithm Based Feature Subset Selection for Fetal State Classification

Contact Info

Product

Resources

About