engleski

Lab agnostic workflow for forensic applications in car glass classification

The IAEA coordinated a research project titled ‘Enhancing Nuclear Analytical Techniques to Meet the Needs of Forensics Sciences’ (CRP F11021) with the aim of empowering accelerator and research reactor based techniques for applications in forensic sciences. One of the key topics of this project was the analysis and classification of forensic glass specimens using Ion Beam Analysis (IBA) based technique - Particle Induced X-ray Emission (PIXE). To this end, glass fragments from car side windows from different car models and manufacturers (provided by the Israeli police force) were subjected to PIXE measurements in three laboratories to determine their elemental compositions and possible glass corrosion. Major and trace elements were measured and given as an input for machine learning (ML) algorithms in order to develop classification models to determine the origin of the glass samples. First, we have developed ML models based on the results obtained at each lab. These models successfully classified glass fragments into different car models with an accuracy >80% on external test sets. Next, we demonstrated that following an appropriate pre-processing step, results from different labs could be combined into a single database that produces an allinclusive classification model. This model demonstrates good performances that matches or surpasses the performances of models derived from the individual labs. This finding paves the way towards establishing an international database that is composed of measurements from various PIXE labs. We believe that using this methodology of combining various sources of measurements will both improve model performances and make the models accessible to law enforcement agencies around the world.

PIXE ; car window glass fragments ; Machine Learning ; Databases

nije evidentirano