The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A seleção do subconjunto de recursos depende basicamente do design de uma função de critério para medir a eficácia de um recurso específico ou subconjunto de recursos e da seleção de uma estratégia de pesquisa para descobrir o melhor subconjunto de recursos. Muitas técnicas foram desenvolvidas até agora e são categorizadas principalmente em classificadores independentes. filtro abordagens e classificador dependente invólucro abordagens. As abordagens wrapper produzem bons resultados, mas são computacionalmente pouco atraentes, especialmente quando são usados classificadores neurais não lineares com algoritmos de aprendizagem complexos. O presente trabalho propõe uma abordagem híbrida em duas etapas para descobrir o melhor subconjunto de características de um grande conjunto de características em que uma medida teórica de conjuntos difusos para avaliar a qualidade de uma característica é usada em conjunto com um perceptron multicamadas (MLP) ou rede neural fractal. Classificador (FNN) para aproveitar ambas as abordagens. Embora o processo não garanta otimização absoluta, o subconjunto de recursos selecionado produz resultados quase ótimos para fins práticos. O processo consome menos tempo e é computacionalmente leve em comparação com qualquer técnica de seleção de subconjunto de recursos sequencial baseada em classificador de rede neural. O algoritmo proposto foi simulado com dois conjuntos de dados diferentes para justificar sua eficácia.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Basabi CHAKRABORTY, Goutam CHAKRABORTY, "A Neuro Fuzzy Algorithm for Feature Subset Selection" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 9, pp. 2182-2188, September 2001, doi: .
Abstract: Feature subset selection basically depends on the design of a criterion function to measure the effectiveness of a particular feature or a feature subset and the selection of a search strategy to find out the best feature subset. Lots of techniques have been developed so far which are mainly categorized into classifier independent filter approaches and classifier dependant wrapper approaches. Wrapper approaches produce good results but are computationally unattractive specially when nonlinear neural classifiers with complex learning algorithms are used. The present work proposes a hybrid two step approach for finding out the best feature subset from a large feature set in which a fuzzy set theoretic measure for assessing the goodness of a feature is used in conjunction with a multilayer perceptron (MLP) or fractal neural network (FNN) classifier to take advantage of both the approaches. Though the process does not guarantee absolute optimality, the selected feature subset produces near optimal results for practical purposes. The process is less time consuming and computationally light compared to any neural network classifier based sequential feature subset selection technique. The proposed algorithm has been simulated with two different data sets to justify its effectiveness.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_9_2182/_p
Copiar
@ARTICLE{e84-a_9_2182,
author={Basabi CHAKRABORTY, Goutam CHAKRABORTY, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Neuro Fuzzy Algorithm for Feature Subset Selection},
year={2001},
volume={E84-A},
number={9},
pages={2182-2188},
abstract={Feature subset selection basically depends on the design of a criterion function to measure the effectiveness of a particular feature or a feature subset and the selection of a search strategy to find out the best feature subset. Lots of techniques have been developed so far which are mainly categorized into classifier independent filter approaches and classifier dependant wrapper approaches. Wrapper approaches produce good results but are computationally unattractive specially when nonlinear neural classifiers with complex learning algorithms are used. The present work proposes a hybrid two step approach for finding out the best feature subset from a large feature set in which a fuzzy set theoretic measure for assessing the goodness of a feature is used in conjunction with a multilayer perceptron (MLP) or fractal neural network (FNN) classifier to take advantage of both the approaches. Though the process does not guarantee absolute optimality, the selected feature subset produces near optimal results for practical purposes. The process is less time consuming and computationally light compared to any neural network classifier based sequential feature subset selection technique. The proposed algorithm has been simulated with two different data sets to justify its effectiveness.},
keywords={},
doi={},
ISSN={},
month={September},}
Copiar
TY - JOUR
TI - A Neuro Fuzzy Algorithm for Feature Subset Selection
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2182
EP - 2188
AU - Basabi CHAKRABORTY
AU - Goutam CHAKRABORTY
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E84-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2001
AB - Feature subset selection basically depends on the design of a criterion function to measure the effectiveness of a particular feature or a feature subset and the selection of a search strategy to find out the best feature subset. Lots of techniques have been developed so far which are mainly categorized into classifier independent filter approaches and classifier dependant wrapper approaches. Wrapper approaches produce good results but are computationally unattractive specially when nonlinear neural classifiers with complex learning algorithms are used. The present work proposes a hybrid two step approach for finding out the best feature subset from a large feature set in which a fuzzy set theoretic measure for assessing the goodness of a feature is used in conjunction with a multilayer perceptron (MLP) or fractal neural network (FNN) classifier to take advantage of both the approaches. Though the process does not guarantee absolute optimality, the selected feature subset produces near optimal results for practical purposes. The process is less time consuming and computationally light compared to any neural network classifier based sequential feature subset selection technique. The proposed algorithm has been simulated with two different data sets to justify its effectiveness.
ER -