PIXE based, Machine-Learning (PIXEL) supported workflow for glass fragments classification.

Abstract:

:This paper presents a structured workflow for glass fragment analysis based on a combination of Elemental Analysis using PIXE and Machine Learning tools, with the ultimate goal of standardizing and helping forensic efforts. The proposed workflow was implemented on glass fragments received from the Israeli DIFS (Israeli Police Force's Division of Identification and Forensic Sciences) that were collected from various vehicles, including glass fragments from different manufacturers and years of production. We demonstrate that this workflow can produce models with high (>80%) accuracy in identifying glass fragment's origins and provide a test-case demonstrating how the model can be applied in real-life forensic events. We provide a standard, reproducible methodology that can be used in many forensic domains beyond glass fragments, for example, Gun Shot Residue, flammable liquids, illegal substances, and more.

journal_name

Talanta

journal_title

Talanta

authors

Kaspi O,Girshevitz O,Senderowitz H

doi

10.1016/j.talanta.2021.122608

keywords:

["Forensic","Forensoinformatics","Glass fragments","Machine Learning","PIXE","Random forest"]

subject

Has Abstract

pub_date

2021-11-01 00:00:00

pages

122608

eissn

0039-9140

issn

1873-3573

pii

S0039-9140(21)00529-4

journal_volume

234

pub_type

杂志文章

相关文献

TALANTA文献大全