The reported work assessed the classification performance of neural networks - a class of biologically inspired machine learning models that are used for classification and regression problems - on ground-truth fire debris samples, using ions that are representative of several compound classes that are typically present in ignitable liquids.
An optimal neural network model was selected from a subset of candidate models that were trained on in-silico mixed fire debris samples from the National Center for Forensic Science Substrate and Ignitable Liquid Reference Collection databases. An optimal decision threshold was determined using a defined ratio of misclassification costs. A cost ratio corresponding to a false positive classification having a cost that is 10 times greater than a false negative classification resulted in a decision threshold of log likelihood ratio of 0.966. This decision threshold resulted in a false positive rate of 0.07 and a true positive rate of 0.59 for the ground-truth validation data. This study demonstrates the selection of an optimal decision threshold using ROC analysis and exhibits the potential of neural network models for the evaluation of fire debris evidence. (publisher abstract modified)
Downloads
Similar Publications
- Harmonizing the Forensic Nomenclature for STR Loci D6S474 and DYS612
- The Off-season of Dental Cementum Investigations. A Critical Appraisal of Season-of-death Prediction in Medico-legal Investigations
- Recovery and Detection of Ignitable Liquid Residues from the Substrates by Solid Phase Microextraction – Direct Analysis in Real Time Mass Spectrometry