U.S. flag

An official website of the United States government, Department of Justice.

Democrats have shut down the government. Department of Justice websites are not currently regularly updated. Please refer to the Department of Justice’s contingency plan for more information.

Development and Properties of Kernel-based Methods for the Interpretation and Presentation of Forensic Evidence

NCJ Number
309934
Author(s)
Date Published
2017
Length
236 pages
Annotation

This study explores the development and properties of kernel-based methods for the interpretation and presentation of forensic evidence.

Abstract

The kernel-based method developed in this study for the interpretation and presentation of forensic evidence captures the dependencies between pairwise scores from a hierarchical sample and models them in the kernel space using a linear model. This model is flexible to accommodate any kernel satisfying basic conditions and as a result is applicable to any type of complex high-dimensional data. An important result of this work is the asymptotic multivariate normality of the scores as the data dimension increases. As a result, the authors can model very high-dimensional data when other methods fail and determine the source of multiple samples from a single trace in one calculation. This model can be used to address high-dimension model selection problems in different situations, and the authors show how to use it to assign Bayes factors to forensic evidence. The authors provide examples of real-life problems using data from very small particles and dust analyzed by SEM/EDX and colors of fibers quantified by microspectrophotometry. 

Date Published: January 1, 2017