Steel Sheet Incremental Cold Shaping Improvements Using Hybridized Genetic Algorithms with Support Vector Machines and Neural Networks

Puigpinós, Laura; Villar, José R.; Sedano, Javier; Corchado, Emilio; Ciurana, Joaquim

doi:10.1007/978-3-642-24094-2_22

Cited by 1 publication

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first one is a specific NN+GA wrapper feature selection method for estimating the maximum depth problem, while the second approach makes use of SVM instead of NN for determining whether a set of operation conditions would produce a faulty piece or not. Preliminary studies [14] show that this combination leads to a valid solution for the SSICS problem.…”

Section: Genetic Algorithms and Feature Selectionmentioning

confidence: 97%

“…Instead, we present the general case in the algorithms, and when it is said that a model is trained, the reader should consider which problem (the two-class or the regression problem) is related to the use of NN or SVM. The decision on how to fix the parameters for the model was based on preliminary studies and the corresponding experimentation was carried out [14].…”

Section: Ga+svm+nn Feature Selectionmentioning

confidence: 99%

“…In a previous study, a method for estimating the operating conditions in SSICS was developed [14]. In that study, feature selection NN and SVM were used for choosing the most promising features.…”

Section: Introductionmentioning

confidence: 99%

“…1.1. Next Section is concerned with the description of the GA FS proposed from the original study [14]. Section 3 deals with a discussion on several issues for improving this algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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: Genetic Algorithms and Feature Selectionmentioning

confidence: 97%

Section: Ga+svm+nn Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…1.1. Next Section is concerned with the description of the GA FS proposed from the original study [14]. Section 3 deals with a discussion on several issues for improving this algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations