liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Estimating the Temperature of Heat-exposed Bone via Machine Learning Analysis of SCI Color Values: A Pilot Study
Linköping University, Department of Management and Engineering, Commercial and Business Law. Linköping University, Faculty of Arts and Sciences. Department of Biochemistry and Biophysics, Stockholm University, Stockholm, Sweden; UCLA/Getty Conservation Programme, Cotsen Institute of Archaeology, UCLA, Los Angeles, CA, US.
Institute of History and Archaeology, University of Tartu, Tartu, Estonia; School of Humanities, Tallinn University, Tallinn, Estonia.
Department of Philosophy, History, Culture and Art Studies, University of Helsinki, Helsinki, Finland.
Institute of History and Archaeology, University of Tartu, Tartu, Estonia.
Show others and affiliations
2019 (English)In: Journal of Forensic Sciences, ISSN 0022-1198, E-ISSN 1556-4029, Vol. 64, no 1, p. 190-195Article in journal (Refereed) Published
Abstract [en]

Determining maximum heating temperatures of burnt bones is a long-standing problem in forensic science and archaeology. In this pilot study, controlled experiments were used to heat 14 fleshed and defleshed pig vertebrae (wet bones) and archaeological human vertebrae (dry bones) to temperatures of 400, 600, 800, and 1000 degrees C. Specular component included (SCI) color values were recorded from the bone surfaces with a Konica-Minolta cm-2600d spectrophotometer. These color values were regressed onto heating temperature, using both a traditional linear model and the k-nearest neighbor (k-NN) machine-learning algorithm. Mean absolute errors (MAE) were computed for 1000 rounds of temperature prediction. With the k-NN approach, the median MAE prediction errors were 41.6 degrees C for the entire sample, and 20.9 degrees C for the subsample of wet bones. These results indicate that spectrophotometric color measurements combined with machine learning methods can be a viable tool for estimating bone heating temperature.

Place, publisher, year, edition, pages
Wiley-Blackwell Publishing Inc., 2019. Vol. 64, no 1, p. 190-195
Keywords [en]
forensic science; forensic anthropology; cremains; burned bone; color measurement; regression analysis
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:liu:diva-153961DOI: 10.1111/1556-4029.13858ISI: 000454935900025PubMedID: 30001473Scopus ID: 2-s2.0-85050911145OAI: oai:DiVA.org:liu-153961DiVA, id: diva2:1281563
Available from: 2019-01-22 Created: 2019-01-22 Last updated: 2019-02-01Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records BETA

Warmlander, Sebastian K T S

Search in DiVA

By author/editor
Warmlander, Sebastian K T S
By organisation
Commercial and Business LawFaculty of Arts and Sciences
In the same journal
Journal of Forensic Sciences
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 18 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf