Classification of ground-truth fire debris samples using artificial neural networks

ASTM E1618-19, 2019 Sigman, 2016, Assessing evidentiary value in fire debris analysis by chemometric and likelihood ratio approaches, Forensic Sci. Int., 264, 113, 10.1016/j.forsciint.2016.03.051 LeCun, 1990, Handwritten digit recognition with a back-propagation network, Adv. Neural Inform. Process. Syst., 396 Muhammad, 2018, Convolutional neural networks based fire detection in surveillance videos, IEEE Access, 6, 18174, 10.1109/ACCESS.2018.2812835 Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 Vidaki, 2017, DNA methylation-based forensic age prediction using artificial neural networks and next generation sequencing, Forensic Sci. Int. Genet., 28, 225, 10.1016/j.fsigen.2017.02.009 Riedmiller, 1993, A direct adaptive method for faster backpropagation learning: the RPROP algorithm, IEEE Int. Conf. Neural Networks, 586, 10.1109/ICNN.1993.298623 Zong, 2014, Classification and identification of soot source with principal component analysis and backpropagation neural network, Aust. J. Forensic Sci., 46, 224, 10.1080/00450618.2013.818711 Coulson, 2018, Model effects on likelihood ratios for fire debris analysis, Forensic Chem., 7, 38, 10.1016/j.forc.2017.12.008 Allen, 2019, Application of likelihood ratios and optimal decision thresholds in fire debris analysis based on a partial least squares discriminant analysis (PLS-DA) model, Forensic Chem., 16, 10.1016/j.forc.2019.100188 Waddell, 2014, Progress toward the determination of correct classification rates in fire debris analysis II: utilizing soft independent modeling of class analogy (SIMCA), J. Forensic Sci., 59, 927, 10.1111/1556-4029.12417 Allen, 2018, Model distribution effects on likelihood ratios in fire debris analysis, Separations, 5, 44, 10.3390/separations5030044 National Center for Forensic Science, Ignitable Liquids Reference Collection and Database. Available online: https://ilrc.ucf.edu/ (accessed on 10 May 2020). National Center for Forensic Science, Substrates Database. Available online: http://ilrc.ucf.edu/substrate/index.php (accessed on 10 May 2020). American Society for Testing and Materials, 2012 Lopatka, 2015, Class-conditional feature modeling for ignitable liquid classification with substantial substrate contribution in fire debris analysis, Forensic Sci. Int., 252, 177, 10.1016/j.forsciint.2015.04.035 Frisch-Daiello, 2014, Application of self-organizing feature maps to analyze the relationships between ignitable liquids and selected mass spectral ions, Forensic Sci. Int., 236, 84, 10.1016/j.forsciint.2013.12.026 R Core Team, 2018 Frauke, 2010, neuralnet: training of neural networks, R J., 2, 30, 10.32614/RJ-2010-006 Xavier, 2011, pROC: an open-source package for R and S+ to analyze and compare ROC curves, BMC Bioinf., 12, 77, 10.1186/1471-2105-12-77 Fawcett, 2006, An introduction to ROC analysis, Pattern Recogn. Lett., 27, 861, 10.1016/j.patrec.2005.10.010 Ramos, 2013, Information-theoretical assessment of the performance of likelihood ratio computation methods, J. Forensic Sci., 58, 1503, 10.1111/1556-4029.12233 Niculescu-Mizil, 2005, Predicting good probabilities with supervised learning