Issue 3, 2003

Application of the Kohonen artificial neural network in the identification of proteinaceous binders in samples of panel painting using gas chromatography-mass spectrometry

Abstract

Historically, three types of proteinaceous matter—casein, egg and animal glue—were used as binders for pigments or as adhesives in easel and wall painting. The relative percentage content of alanine, glycine, valine, leucine, isoleucine, serine, tyrosine, phenylalanine, aspartic acid, glutamic acid, lysine, methionine, proline and hydroxyproline, as determined by GC-MS, is used for binder identification. In this paper we analyse the viability of a multivariate modelling using Kohonen's neural network to characterise the wood adhesive in 16 old samples from Italian panel paintings of the 12–16th centuries. As a training set we use the amino acid composition of 141 samples contributed by the Opificio delle Pietre Dure of Florence (Cultural Heritage Ministry, Italy). Of the 141 samples, 113 were used to train the Kohonen neural network and the remaining 28 as the evaluation set. A specificity and sensitivity of 100% was achieved in training and 92–100% in prediction depending on the assignation criteria employed. The neural network thus trained and evaluated was applied to the old samples, achieving identification of all of them. In addition, the map obtained for each amino acid provides relevant information as to its importance in the characterisation of the sample.

Supplementary files

Article information

Article type
Paper
Submitted
17 Dec 2002
Accepted
18 Feb 2003
First published
25 Feb 2003

Analyst, 2003,128, 281-286

Application of the Kohonen artificial neural network in the identification of proteinaceous binders in samples of panel painting using gas chromatography-mass spectrometry

R. Lletí, L. A. Sarabia, M. C. Ortiz, R. Todeschini and M. P. Colombini, Analyst, 2003, 128, 281 DOI: 10.1039/B212509A

To request permission to reproduce material from this article, please go to the Copyright Clearance Center request page.

If you are an author contributing to an RSC publication, you do not need to request permission provided correct acknowledgement is given.

If you are the author of this article, you do not need to request permission to reproduce figures and diagrams provided correct acknowledgement is given. If you want to reproduce the whole article in a third-party publication (excluding your thesis/dissertation for which permission is not required) please go to the Copyright Clearance Center request page.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements