Russian Federation
employee
Volgograd Academy of the Russian Internal Affairs Ministry (Kafedry issledovaniya dokumentov UNK EKD, Nachal'nik kafedry)
employee from 01.01.2020 until now
Volgograd, Russian Federation
The article is concerned with the possibilities and prospects of using artificial intelligence technologies to identify individuals prone to commit violent crimes. The article describes examples of successful use of neural networks for evaluating human appearance features and identifying complex interrelations between various parameters of human appearance, behavior, and mental state. The article presents the algorithm that allows to test the hypothesis of the dependence of facial morphology on neurobiological features associated with a person's propensity for violent behavior. To identify statistically significant differences in anthropometric facial parameters between groups of individuals with typical development and those with diagnosed deviations in social behavior and mental development, an algorithm for automating the process of coding and placing anthropometric points was used. The algorithm was tested to identify weaknesses in the study and formulate suggestions for further work on the project.
artificial intelligence, artificial intelligence technologies, violent crimes, serial crimes, features of appearance, anthropometric parameters, diagnostic research, mental development, forensic habitoscopy.
1. Theoretical studies on the creation of a complex of technological solutions (artificial intelligence) for processing big data in the field of internal affairs: report on research work (final) code: "Semantics". M., 2021. 237 p.
2. Clark EA, Kessinger J, Duncan SE, Bell MA, Lahne J, Gallagher DL and O'Keefe SF (2020) The Facial Action Coding System for Characterization of Human Affective Response to Consumer Product-Based Stimuli: A Systematic Review. Front. Psychol. 11:920. doi:https://doi.org/10.3389/fpsyg.2020.00920. URL: https://www.frontiersin.org/journals/psychology/articles/https://doi.org/10.3389/fpsyg.2020.00920/full
3. Wang Y, Wang J, Liu X and Zhu T (2021) Detecting Depression Through Gait Data: Examining the Contribution of Gait Features in Recognizing Depression. Front. Psychiatry 12:661213. doi:https://doi.org/10.3389/fpsyt.2021.661213. URL: https://translated.turbopages.org/journals/psychiatry/articles/10.3389/fpsyt.2021.661213/full
4. Gashkarimov V.R., Sultanova R.I., Efremov I.S., Asadullin A.R. Using machine learning methods in diagnosing and predicting clinical features of schizophrenia: a narrative review of the literature // Consortium Psychiatricum. 2023. Vol. 4. No. 3. Pp. 43–53. DOI:https://doi.org/10.17816/CP11030, ISSN: 2712-7672 / 2713-2919. doi:https://doi.org/10.1177/0886260520913641. URL: https://pubmed.ncbi.nlm.nih.gov/32306866/ (accessed: 04/28/2025).5 A high-precision neural network was taught to recognize criminals. URL: https://naked-science.ru
5. Sverhtochnuyu neyroset' nauchili raspoznavat' prestupnikov. URL: https://naked-science.ru (data obrascheniya: 28.04.2025).
