Citation

Mandel M, Israelsohn Azulay O, Zidon Y, Tsach T, Cohen Y. J. Forensic Sci. 2018; 63(4): 1269-1274.

Affiliation

Israel National Police Division of Identification and Forensic Science, Bar Lev Haim 1, Jerusalem, 91906, Israel.

Copyright

(Copyright © 2018, American Society for Testing and Materials, Publisher John Wiley and Sons)

DOI

10.1111/1556-4029.13711

PMID

29964343

Abstract

Classification of particles as gunshot residues (GSRs) is conducted using a semiautomatic approach in which the system first classifies particles based on an automatic elemental analysis, and then, examiners manually analyze particles having compositions which are characteristic of or consistent with GSRs. Analyzing all the particles in the second stage is time consuming with many particles classified by the initial automated system as being potentially GSRs excluded as such by the forensic examiner. In this paper, a new algorithm is developed to improve the initial classification step. The algorithm is based on a binary tree that was trained on almost 16,000 particles from 43 stubs used to sample hands of suspects. The classification algorithm was tested on 5,900 particles from 23 independent stubs and performed very well in terms of false positive and false negative rates. A routine use of the new algorithm can reduce significantly the analysis time of GSRs.

© 2017 American Academy of Forensic Sciences.

Language: en

Keywords

SEM-EDX; elemental analysis; forensic science; gunshot residue conformation; regression tree; supervised learning