Information-theoretic algorithm for feature selection

DOI10.1016/S0167-8655(01)00019-8MaRDI QIDQ4795085zbMATH OpenOpenAlexFDO

Authors Mark Last, A. Kandel, Oded Maimon

Publication date 20 February 2003

Published in Pattern Recognition Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0167-8655(01)00019-8

zbMATH Keywords

feature selectionclassificationinformation theoryinformation-theoretic network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99) Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science) (68P30)

Recommendations

• An adaptive heuristic for feature selection based on complementarity
• Eliminating redundancy and irrelevance using a new MLP-based feature selection method
• A multi-objective evolutionary algorithm for feature selection based on mutual information with a new redundancy measure
• Feature selection based on fuzzy joint mutual information maximization
• Feature selection algorithms in classification problems: an experimental evaluation

Cited in

(16)

• An adaptive heuristic for feature selection based on complementarity
• Intelligent sensory evaluation: Concepts, implementations, and applications
• Exploration of a hybrid feature selection algorithm
• Fast multi-label feature selection based on information-theoretic feature ranking
• Designing a hybrid intelligent mining system for credit risk evaluation
• Sobol sensitivity: a strategy for feature selection
• A linear discriminant analysis method based on mutual information maximization
• Efficient feature selection based on correlation measure between continuous and discrete features
• Mining classification rules using rough sets and neural networks
• scientific article; zbMATH DE number 1692453 (Why is no real title available?)
• Feature selection algorithms in classification problems: an experimental evaluation
• A novel feature selection using Markov blanket representative set and particle swarm optimization algorithm
• SELECT INFORMATIVE SYMPTOMS COMBINATION FOR DIAGNOSING SYNDROME
• New perspectives on multilocus ancestry informativeness
• Feature selection with ensembles, artificial variables, and redundancy elimination
• Eliminating redundancy and irrelevance using a new MLP-based feature selection method

Describes a project that uses

Uses Software

• C4.5

This page was built for publication: Information-theoretic algorithm for feature selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4795085)