Classification of Antarctic algae by applying Kohonen neural network with 14 elements determined by inductively coupled plasma optical emission spectrometry

Optical emission spectrometers can generate results, which sometimes are not easy to interpret, mainly when the analyses involve classifications. To make simultaneous data interpretation possible, the Kohonen neural network is used to classify different Antarctic algae according to their taxonomic g...

Full description

Saved in:
Bibliographic Details
Published in:Spectrochimica acta. Part B: Atomic spectroscopy 2005-06, Vol.60 (5), p.725-730
Main Authors: Balbinot, L., Smichowski, P., Farias, S., Arruda, M.A.Z., Vodopivez, C., Poppi, R.J.
Format: Article
Language:English
Subjects:
Antarctic algae
Chemometrics
ICP OES
Kohonen neural
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Optical emission spectrometers can generate results, which sometimes are not easy to interpret, mainly when the analyses involve classifications. To make simultaneous data interpretation possible, the Kohonen neural network is used to classify different Antarctic algae according to their taxonomic groups from the determination of 14 analytes. The Kohonen neural network architecture used was 5×5 neurons, thus reducing 14-dimension input data to two-dimensional space. The input data were 14 analytes (As, Co, Cu, Fe, Mn, Sr, Zn, Cd, Cr, Mo, Ni, Pb, Se, V) with their concentrations, determined by inductively coupled plasma optical emission spectrometry in 11 different species of algae. Three taxonomic groups ( Rhodophyta, Phaeophyta and Cholorophyta) can be differentiated and classified through only their Cu content.
ISSN:0584-8547
1873-3565
DOI:10.1016/j.sab.2005.03.005