A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri

dc.contributor.author	Μελαγράκη, Γεωργία	el
dc.contributor.author	Αφαντίτης, Ανδρέας	el
dc.contributor.author	Σαρίμβεης, Χαράλαμπος Κ.	el
dc.contributor.author	Ιγγλέση-Μαρκοπούλου, Όλγα	el
dc.contributor.author	Αλεξανδρίδης, Αλέξανδρος Π.	el
dc.date.accessioned	2015-06-04T12:38:36Z
dc.date.available	2015-06-04T12:38:36Z
dc.date.issued	2015-06-04
dc.identifier.uri	http://hdl.handle.net/11400/15054
dc.rights	Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ηνωμένες Πολιτείες	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.source	http://link.springer.com/	en
dc.subject	Neural network
dc.subject	QSTR
dc.subject	RBF architecture
dc.subject	Toxicity
dc.subject	Vibrio fischeri
dc.subject	Νευρωνικό δίκτυο
dc.subject	τοξικότητα
dc.title	A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri	en
heal.type	journalArticle
heal.classification	Science
heal.classification	Physics
heal.classification	Επιστήμη
heal.classification	Φυσική
heal.classificationURI	http://zbw.eu/stw/descriptor/15685-2
heal.classificationURI	http://zbw.eu/stw/descriptor/15669-0
heal.classificationURI	N/A-Επιστήμη
heal.classificationURI	N/A-Φυσική
heal.keywordURI	http://id.loc.gov/authorities/subjects/sh88023359
heal.identifier.secondary	DOI 10.1007/s11030-005-9008-y
heal.language	en
heal.access	campus
heal.publicationDate	2006-05
heal.bibliographicCitation	MELAGRAKI, G., AFANTITIS, A., SARIMVEIS, H.K., IGGLESSI-MARKOPOULOU, O. & ALEXANDRIDIS, A.P. (2006). A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri. Molecular Diversity. [online] 10 (2). p. 213-221. Available from: http://link.springer.com/	en
heal.abstract	This work introduces a neural network methodology for developing QSTR predictors of toxicity to Vibrio fischeri. The method adopts the Radial Basis Function (RBF) architecture and the fuzzy means training strategy, which is fast and repetitive, in contrast to most traditional training techniques. The data set that was utilized consisted of 39 organic compounds and their corresponding toxicity values to Vibrio fischeri, while lipophilicity, equalized electronegativity and one topological index were used to provide input information to the models. The performance and predictive ability of the RBF model were illustrated through external validation and various statistical tests. The proposed methodology can be used to successfully model toxicity to Vibrio fischerifor a heterogeneous set of compounds.	en
heal.publisher	Springer Verlag	en
heal.journalName	Molecular Diversity	en
heal.journalType	peer-reviewed
heal.fullTextAvailability	true