The thesis deals with the terminology used in forensic engineering practice at the analysis of road accidents. It means defining the concepts describing specific expert research in the area of car accident analysis such as the option of evasive action and the possibility of preventing collision. Further on, the thesis focuses on the terminology used in areas closely related to analysis of road accidents namely dealing with cases of criminal activities in the field of motor vehicle insurance from an expert point of view. In this area, terms such as extent of the damage, character of the damage, correspondence of the damage and the technical acceptability of accident, are solved. These terms constitute a formal process that can serve as a tool for experts when dealing with such cases. In addition, selected terms from the technical-legal area, which the experts often encounter, are processed here. At the same time, there is no uniform approach to their evaluation from a technical perspective. Here, there is a possibility of setting the limits of a sudden change of speed and a sudden change of direction.

Ce mémoire a pour but de déterminer des nouvelles méthodes de détection de rupture et/ou de tendance. Après une brève introduction théorique sur les splines, plusieurs méthodes de détection de rupture existant déjà dans la littérature seront présentées. Puis, de nouvelles méthodes de détection de rupture qui utilisent les splines et la statistique bayésienne seront présentées. De plus, afin de bien comprendre d’où provient la méthode utilisant la statistique bayésienne, une introduction sur la théorie bayésienne sera présentée. À l’aide de simulations, nous effectuerons une comparaison de la puissance de toutes ces méthodes. Toujours en utilisant des simulations, une analyse plus en profondeur de la nouvelle méthode la plus efficace sera effectuée. Ensuite, celle-ci sera appliquée sur des données réelles. Une brève conclusion fera une récapitulation de ce mémoire. / This thesis aims to identify new change-point detection methods and/or trend in temporal data. After a brief theoretical introduction on splines, several existing change-point detection already in the literature will be presented. Then, new change-point detection methods using splines and Bayesian statistics will be presented. Moreover, in order to understand the method using Bayesian statistics, an introduction to Bayesian theory will be presented. Using simulations, we will make a comparison of the power of all these methods. Still using simulations, an analysis of the new most effective method will be performed. Then, this method will be applied to real data. A brief conclusion will make a summary of this thesis.