Paper Info
Title
Model-based feature selection based on Radial Basis Functions and information measures
Abstract
In this paper the development of a new embedded feature selection method is presented, based on a Radial-Basis-Function Neural-Fuzzy modelling structure. The proposed method is created to find the relative importance of features in a given dataset (or process in general), with special focus on manufacturing processes. The proposed approach evaluates the impact/importance of processes features by using information theoretic measures to measure the correlation between the process features and the modelling performance. Crucially, the proposed method acts during the training of the process model; hence it is an embedded method, achieving the modelling/classification task in parallel to the feature selection task. The latter is achieved by taking advantage of the information in the output layer of the Neural Fuzzy structure; in the presented case this is a TSK-type polynomial function. Two information measures are evaluated in this work, both based on information entropy: mutual information, and cross-sample entropy. The proposed methodology is tested against two popular datasets in the literature (IRIS - plant data, AirFoil - manufacturing/design data), and one more case study relevant to manufacturing - the heat treatment of steel. Results show the good and reliable performance of the developed modelling structure, on par with existing published work, as well as the good performance of the feature selection task in terms of correctly identifying important process features.
Year
DOI
Venue
2016
10.1109/FUZZ-IEEE.2016.7737715
2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Keywords
Field
DocType
Feature selection,information entropy,information measures,Radial Basis function,Fuzzy Logic,Manufacturing
Data mining,Radial basis function,Noise measurement,Polynomial,Feature selection,Computer science,Fuzzy logic,Mutual information,Artificial intelligence,Entropy (information theory),Machine learning
Conference
ISSN
ISBN
Citations 
1544-5615
978-1-5090-0627-4
0
PageRank 
References 
Authors
0.34
17
2
Name
Order
Citations
PageRank
Georgios N. Tzagarakis100.34
George Panoutsos2577.59