| Grant number: | 17/02073-6 |
| Support type: | Scholarships in Brazil - Doctorate |
| Effective date (Start): | June 01, 2017 |
| Status: | Discontinued |
| Field of knowledge: | Physical Sciences and Mathematics - Computer Science - Computational Mathematics |
| Cooperation agreement: | Coordination of Improvement of Higher Education Personnel (CAPES) |
| Principal Investigator: | Hélio Pedrini |
| Grantee: | Dalton Ieda Fazanaro |
| Home Institution: | Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil |
| Associated research grant: | 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?, AP.TEM |
| Associated scholarship(s): | 19/11266-8 - Network model for crime forecasting, BE.EP.DR |
Abstract The earliest studies in the Science of Criminology are attributed to the late nineteenth century. Over the decades, Criminology has witnessed its sociological essence encompassing practices from other areas of knowledge, characterizing itself as an inherently interdisciplinary science from the beginning. The adoption of concepts of the Exact Sciences in investigations in Criminology presents as a recent and ascending movement, originating a new field of research known as Computational Criminology, which uses theories of Applied Mathematics and Computer Science to offer solutions to problems and questions in Criminology through mathematical models and computational methods. Two of the most outstanding tasks in this area are mapping and predicting crimes. While the former intends to identify criminal patterns in time and space, the second attempts to infer the likelihood that a particular type of crime will occur in a particular location. The present proposal for a PhD project focuses essentially on predicting crimes, since this is still an incipient task and subject to relevant and innovative scientific contributions, made possible by the improvement of computational power and the technological advances experienced in the last decades. In order to do so, the use of complex networks and Petri nets is suggested. These choices are due to their dynamic and robust graphic nature, supposedly adequate to deal with the scalability and complexity of the criminal data obtained today. Finally, in addition to the construction of a new mathematical and computational model of prediction and inference, the project will also offer a social contribution, by using criminal statistics from Sao Paulo state and Federal government for its validation. (AU) | |