Discrimination of human bodies from bones and teeth remains by Laser Induced Breakdown Spectroscopy and Neural Networks

A fast and minimally destructive method based on Laser Induced Breakdown Spectroscopy (LIBS) and Neural Networks (NN) has been developed and applied to the classification and discrimination of human bones and teeth fragments. The methodology can be useful in Disaster Victim Identification (DVI) tasks. The elemental compositions of bone and teeth samples provided enough information to achieve a correct discrimination and reassembling of different human remains. Individuals were classified with spectral correlation higher than 95%, regardless of the type of bone or tooth sample analyzed. No false positive or false negative was observed, demonstrating the high robustness and accuracy of the proposed methodology. •Classification and discrimination of human remains have been studied.•Remains were analyzed by Laser Induced Breakdown Spectroscopy (LIBS).•Neural Networks models (NN) were used.•Individuals were classified with spectral correlation higher than 95 %.•LIBS-NN showed the potential for rapid and cost-effective analysis.