arXiv subjects

Madeline Ausdemore

Publications and source records attributed to Madeline Ausdemore.

3 recordsLinked to original sources

arXiv2019

Deconvolution of dust mixtures by latent Dirichlet allocation in forensic science

Dust particles recovered from the soles of shoes may be indicative of the sites recently visited by an individual, and, in particular, of the presence of an individual at a particular site of interest, e.g., the scene of a crime. By describing the dust profile of a given site by a multinomial distribution over a fixed number of dust particle types, we can define the probability distribution of the mixture of dust recovered from the sole of a shoe via Latent Dirichlet Allocation. We use Variational Bayesian Inference to study the parameters of the model, and use their resulting posterior distributions to make inference on (a) the contributions of sites of interest to a dust mixture, and (b) the particle profiles associated with these sites.

stat.AP↗

arXiv2019

Two-stage approach for the inference of the source of high-dimension and complex chemical data in forensic science

Forensic scientists are often criticised for the lack of quantitative support for the conclusions of their examinations. While scholars advocate for the use of a Bayes factor to quantify the weight of forensic evidence, it is often impossible to assign the necessary probability measures to perform likelihood-based inference for high-dimensional and complex data. To address this issue, we revisit a two-stage inference framework and leverage the properties of kernel functions to offer a method that allows for statistically supporting the inference of the identity of source of sets of trace and control objects by way of a single test. Our method is generic in that it can be easily tailored to any type of data encountered in forensic science or pattern recognition, and our method does not depend on the dimension or the type of the considered data. The application of our method to paint evidence shows that this type of evidence carries substantial probative value. Finally, our approach can easily be extended to other evidence types such as glass, fibres and dust.

stat.ME↗

arXiv2018

Review of several false positive error rate estimates for latent fingerprint examination proposed based on the 2014 Miami Dade Police Department study

During the past decade, several studies have been conducted to estimate the false positive error rate (FPR) associated with latent fingerprint examination. The so-called Black-box study by Ulery et al. is regularly used to support the claim that the FPR in fingerprint examination is reasonably low (0.1%). The Ulery et al.'s estimate of the FPR is supported by the results of the extensive study of the overall fingerprint examination process by Langenburg. In 2014, the Miami Dade Police Department (MDPD) Forensic Services Bureau conducted research to study the false positive error rate associated with latent fingerprint examination. They report that approximately 3.0% of latent fingerprint examinations result in a false positive conclusion. Their estimate of the FPR becomes as high as 4.2% when inconclusive decisions are excluded from the calculation. In their 2016 report, the President's Council of Advisors on Science and Technology (PCAST) proposes that the MDPD FPR estimate be used to inform jurors that errors occur at a detectable rate in fingerprint examination; more specifically, they declare that false positives may occur as often as 1 in 18 cases. The large discrepancy between the FPR estimates reported by Ulery et al. and Langenburg on the one hand, and the MDPD on the other hand, causes a great deal of controversy. In this paper, we review the MDPD study and the various error rate calculations that have been proposed to interpret its data. To assess the appropriateness of the different proposed estimates, we develop a model that re-creates the MDPD study. This model allows us to estimate the expected number of false positive conclusions that should be obtained with any proposed FPR and compare this number to the actual number of erroneous identifications observed by MDPD.

stat.AP↗