A machine learning approach to analysis and classification of measurements in cultural heritage

Treatment of spectral information is an essential tool for the examination of various cultural heritage materials. Raman Spectroscopy has become an everyday practice for compound identification due to its non-intrusive nature, but often it can be a complex operation. Spectral identification and anal...

Πλήρης περιγραφή

Αποθηκεύτηκε σε:

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς:	Sevetlidis, Vasileios, Σεβετλίδης, Βασίλειος
Άλλοι συγγραφείς:	Παυλίδης, Γιώργος
Γλώσσα:	English
Δημοσίευση:	2020
Θέματα:	Raman spectroscopy machine learning mineral identification φασματοσκοπία Raman εκμάθηση μηχανών ορυκτολογική ταυτοποίηση Raman spectroscopy (URL: http://id.loc.gov/authorities/subjects/sh85111278) Machine learning (URL: http://id.loc.gov/authorities/subjects/sh85079324) Cultural property (URL: http://id.loc.gov/authorities/subjects/sh97000183)
Διαθέσιμο Online:	http://hdl.handle.net/11610/19962
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

_version_	1828460673552613376
author	Sevetlidis, Vasileios Σεβετλίδης, Βασίλειος
author2	Παυλίδης, Γιώργος
author_facet	Παυλίδης, Γιώργος Sevetlidis, Vasileios Σεβετλίδης, Βασίλειος
author_sort	Sevetlidis, Vasileios
collection	DSpace
description	Treatment of spectral information is an essential tool for the examination of various cultural heritage materials. Raman Spectroscopy has become an everyday practice for compound identification due to its non-intrusive nature, but often it can be a complex operation. Spectral identification and analysis on artists' materials is being done with the aid of already existing spectral databases and spectrum matching algorithms. We demonstrate that with a machine learning method called Extremely Randomised Trees, we can learn a model in a supervised learning fashion, able to accurately match an entire-spectrum range into its respective mineral. Our approach was tested and was found to outperform the state-of-the-art methods on the corrected RRUFF dataset, while maintaining low computational complexity and inherently supporting parallelisation.
id	oai:hellanicus.lib.aegean.gr:11610-19962
institution	Hellanicus
language	English
publishDate	2020
record_format	dspace
spelling	oai:hellanicus.lib.aegean.gr:11610-199622025-02-11T12:25:23Z A machine learning approach to analysis and classification of measurements in cultural heritage Sevetlidis, Vasileios Σεβετλίδης, Βασίλειος Παυλίδης, Γιώργος Εφαρμοσμένες Αρχαιολογικές Επιστήμες (Διατμηματικό) Raman spectroscopy machine learning mineral identification φασματοσκοπία Raman εκμάθηση μηχανών ορυκτολογική ταυτοποίηση Raman spectroscopy (URL: http://id.loc.gov/authorities/subjects/sh85111278) Machine learning (URL: http://id.loc.gov/authorities/subjects/sh85079324) Cultural property (URL: http://id.loc.gov/authorities/subjects/sh97000183) Treatment of spectral information is an essential tool for the examination of various cultural heritage materials. Raman Spectroscopy has become an everyday practice for compound identification due to its non-intrusive nature, but often it can be a complex operation. Spectral identification and analysis on artists' materials is being done with the aid of already existing spectral databases and spectrum matching algorithms. We demonstrate that with a machine learning method called Extremely Randomised Trees, we can learn a model in a supervised learning fashion, able to accurately match an entire-spectrum range into its respective mineral. Our approach was tested and was found to outperform the state-of-the-art methods on the corrected RRUFF dataset, while maintaining low computational complexity and inherently supporting parallelisation. 2020-02-21T11:23:47Z 2020-02-21T11:23:47Z 2018-06-11 http://hdl.handle.net/11610/19962 en Αναφορά Δημιουργού - Παρόμοια Διανομή 4.0 Διεθνές http://creativecommons.org/licenses/by-sa/4.0/ 59 σ. application/pdf Ρόδος
spellingShingle	Raman spectroscopy machine learning mineral identification φασματοσκοπία Raman εκμάθηση μηχανών ορυκτολογική ταυτοποίηση Raman spectroscopy (URL: http://id.loc.gov/authorities/subjects/sh85111278) Machine learning (URL: http://id.loc.gov/authorities/subjects/sh85079324) Cultural property (URL: http://id.loc.gov/authorities/subjects/sh97000183) Sevetlidis, Vasileios Σεβετλίδης, Βασίλειος A machine learning approach to analysis and classification of measurements in cultural heritage
title	A machine learning approach to analysis and classification of measurements in cultural heritage
title_full	A machine learning approach to analysis and classification of measurements in cultural heritage
title_fullStr	A machine learning approach to analysis and classification of measurements in cultural heritage
title_full_unstemmed	A machine learning approach to analysis and classification of measurements in cultural heritage
title_short	A machine learning approach to analysis and classification of measurements in cultural heritage
title_sort	machine learning approach to analysis and classification of measurements in cultural heritage
topic	Raman spectroscopy machine learning mineral identification φασματοσκοπία Raman εκμάθηση μηχανών ορυκτολογική ταυτοποίηση Raman spectroscopy (URL: http://id.loc.gov/authorities/subjects/sh85111278) Machine learning (URL: http://id.loc.gov/authorities/subjects/sh85079324) Cultural property (URL: http://id.loc.gov/authorities/subjects/sh97000183)
url	http://hdl.handle.net/11610/19962
work_keys_str_mv	AT sevetlidisvasileios amachinelearningapproachtoanalysisandclassificationofmeasurementsinculturalheritage AT sebetlidēsbasileios amachinelearningapproachtoanalysisandclassificationofmeasurementsinculturalheritage AT sevetlidisvasileios machinelearningapproachtoanalysisandclassificationofmeasurementsinculturalheritage AT sebetlidēsbasileios machinelearningapproachtoanalysisandclassificationofmeasurementsinculturalheritage

A machine learning approach to analysis and classification of measurements in cultural heritage

Παρόμοια τεκμήρια