Work

Raman spectra massive classification using artificial neural networks

Year: 2014
Type: article
Abstract: This paper explores the use of Machine Learning (ML) methods to develop automated system for the identification of chemical compounds from their Raman spectra. The presence of different substances of interest whose spectra signatures are often very close to each other and the occurrence of specific hard–to–solve classification problems\nsuggested the use of an Artificial Neural Network (ANN) as software paradigm able to deal, with good performances, with on–line processing of Raman data coming from the detection system. The ANN results are discussed by comparing their performances against those of Principal Component Analysis.
Language: English
Field: Chemistry
Open Access status: green
OpenAlex ID: W1507180704
FWCI:
Cites: 12
Cited by: 2
Related to: 10