Unsupervised Feature Selection in High Dimensional Spaces and Uncertainty

Villar, José R.; SUAREZ, M; Sedano, Javier; Mateos, F.

doi:10.1007/978-3-642-02319-4_68

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over recent years, there has been a significant increase in the use of artificial intelligence and soft computing (SOCO) methods to solve real world problems. Many different SOCO applications have been reported: the use of exploratory projection pursuit (EPS) and ARMAX for modelling the manufacture of steel components [3]; EPS and neural networks (NN) for determining the operating conditions in face milling operations [15] and in pneumatic drilling processes [17]; genetic algorithms and programming for trading rule extraction [4] and low quality data in lighting control systems [21]; feature selection and association rule discovery in high dimensional spaces [20] or NNs and principal component analysis and EPS in building energy efficiency [18,19].…”

Section: Introductionmentioning

confidence: 99%

Meta-heuristic improvements applied for steel sheet incremental cold shaping

et al. 2012

Self Cite

View full text Add to dashboard Cite

In previous studies, a wrapper feature selection method for decision support in steel sheet incremental cold shaping process (SSICS) was proposed. The problem included both regression and classification, while the learned models were neural networks and support vector machines, respectively. SSICS is the type of problem for which the number of features is similar to the number of instances in the data set, this represents many of real world decision support problems found in the industry. This study focuses on several questions and improvements that were left open, suggesting proposals for each of them. More specifically, this study evaluates the relevance of the different cross validation methods in the learned models, but also proposes several improvements such as allowing the number of chosen features as well as some of the parameters of the neural networks to evolve, accordingly. Well-known data sets have been use in

show abstract

Section: Introductionmentioning

confidence: 99%

Meta-heuristic improvements applied for steel sheet incremental cold shaping

et al. 2012

Self Cite

View full text Add to dashboard Cite

show abstract

Soft Computing Decision Support for a Steel Sheet Incremental Cold Shaping Process

Villar

Sedano

Corchado

et al. 2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

It is known that the complexity inherited in most of the new real world problems, for example, the cold rolled steel industrial process, increases as the computer capacity does. Higher performance requirements with a lower amount of data samples are needed due to the costs of generating new instances, specially in those processes where new technologies arise. This study is focused on the analysis and design of a novel decision support system for an incremental steel cold shaping process, where there is a lack of knowledge of which operating conditions are suitable for obtaining high quality results. The most suitable features have been found using a wrapper feature selection method, in which genetic algorithms and neural networks are hybridized. Some facts concerning the enhanced experimentation needed and the improvements in the algorithm are drawn.

show abstract