Problem of optimal pertinent parameter selection in buried conductive tag recognition

Beheim, Larbi; Zitouni, Adel; Belloir, Fabien

doi:10.1109/isp.2003.1275819

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several material improvements were carried out on our detector [16], but the identification of the codes always poses problems because of the similarity between the codes, the non-linearity of the answer according to the depth and the choice of a suitable coding of the signals [17]. To solve these problems, various methods of classifications were proposed.…”

Section: Application In Buried Tag Identificationmentioning

confidence: 99%

A New RBF Classifier for Buried Tag Recognition

Beheim¹,

Zitouni²,

Belloir³

2005

Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems

View full text Add to dashboard Cite

This article presents noticeable performances improvement of an RBF neural classifier. Based on the Mahalanobis distance, this new classifier increases relatively the recognition rate while decreasing remarkably the number of hidden layer neurons. We obtain thus a new very general RBF classifier, very simple, not requiring any adjustment parameter, and presenting an excellent ratio performances/neurons number. A comparative study of its performances is presented and illustrated by examples on real databases. We present also the recognition improvements obtained by applying this new classifier on buried tag. amounts determining his structure, i.e. the number of hidden neurons Nh and the

show abstract

Section: Application In Buried Tag Identificationmentioning

confidence: 99%