The issues of assessing the reliability of experts’ opinions are common for Russian and Anglo-Saxon legal proceedings. In the Russian legislation there are no legal norms or regulated rules defining this procedure. At the same time, in the USA there is Rule 702 “Expert Witness Testimony” of the Federal Code of Evidence which establishes four criteria that courts should consider when assessing the admissibility of the testimony of a forensic expert. Besides, based on court decisions, Fry and Daubert standards have been adopted. They determine criteria for methods used in conducting forensic examination in the United States. The article analyzes and evaluates the compliance of expert methods applied in Russia with the Fry and Daubert standards. The analysis shows that not all methods meet the criteria of Daubert standard. In particular, the structures of the so-called subjective methods do not provide calculations of a known or potential error rate as well as a mechanism for monitoring the conduct of various stages of a study. The article also discusses other foreign projects aimed at minimizing erroneous conclusions and reforming the system of forensic examination: the Innocence project, reports prepared by the US National Academy of Sciences (NAS report) and the US Presidential Council for Science and Technology (PCAST report). The authors believe that it is essential for the Russian legislation to develop criteria for evaluating experts’ opinions, research methods and scientific validity of the obtained results as well as the to formulate the appropriate norms.
1 February 2024 in Programming and Computer Software
This paper discusses the use of a fully connected neural network to classify images of firing pin impressions. The purpose of this work is to investigate the effectiveness of clone images of firing pin impressions in improving the quality of training of fully connected neural networks. Another purpose of the work is to estimate the accuracy of multigroup classification of firing pin impressions left by different firearms by using a neural network. The scientific novelty of this work is in the use of augmentation for creating images of firing pin impressions to increase the number of objects in the training dataset and to artificially improve the feature diversity of objects of each class. The conducted investigation shows that the accuracy of classification of the analyzed objects reaches approximately 84% for a fixed value of the classification criterion and 94–98% when the classification is carried out based on three maximum signals on output neurons. The work is of interest to developers of automated ballistic identification systems.
23 May 2022 in Izvestiya of Saratov University. Economics. Management. Law
Introduction. The aim of the work is to increase the efficiency of identification of firearms by images of firing pin marks in the automatic mode. The relevance of the task is determined by the low efficiency of the known methods of automatic identification of firearm by the firing pin marks with individual topological types of individualizing features. This affects the investigation of crimes related to the use of firearms. Formation of clone images. A training sample was formed; it included 140 original images of firing pin marks from 50 classes, on the basis of which about 1000 clone images were made with slightly modified individualizing features. In this case a specific specimen of a firearm is meant as a class. Neural network training. A fully connected neural network with the following architecture was used as a classifier: an input layer of neurons; two hidden layers; an output layer. The input layer included 2500 neurons, the first hidden layer was made up of 625 neurons, the second hidden layer contained 156 neurons; the output layer consisted of 50 neurons (in accordance with the number of the classes). Evaluation of the calculation results. The prediction accuracy of the trained neural network was estimated according to the Accuracy metric, which is the ratio of the number of correct predictions to the total number of predictions. The prediction accuracy for the maximum signal on one output neuron was 81%, and when the maximum signals on three output neurons were taken into account, the accuracy was about 91%. Conclusions. The research has shown the possibility of classification of the images of firing pin marks by weapons using a fully connected neural network, as well as the effectiveness of using artificially generated clone images of firing pin marks for training a fully connected neural network in cases with a small number of initial objects.