OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

An on-line platform for supporting DSS-research collaboration (EWG-DSS Collab-Net Version 5)

Turet, Jean and Moura, Jadielson and Cabral, Ana Paula and Dargam, Fatima and Zaraté, Pascale and Linden, Isabelle An on-line platform for supporting DSS-research collaboration (EWG-DSS Collab-Net Version 5). (2019) In: 5th International Conference on Decision Support Systems Technologies (ICDSST 2019), 27 May 2019 - 29 May 2019 (Funchal, Madeira, Portugal).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
447kB

Abstract

Over the past few years, a growing concern has taken place among authorities over crimes committed worldwide. It has not been different in Brazil. High crime rates have encouraged government authorities involved in public safety to identify solutions to minimize crimes considered VCA (Violent Crime Against Assets). In this context, one alternative to both plan and manage security is in the division of ISA (Integrated Security Areas) neighborhoods. However, the local government needs to identify the degree of crime severity of each ISA in order to establish prevention policies and, therefore, resources management, which will make it possible for the Secretariat for Social Defense and other entities involved to establish sets of actions intending to minimize the crime rate. Furthermore, it is evident that changes are constantly happening in the crime behavior tendencies in each ISA, requiring a different set of daily actions from authorities. Therefore, the purpose of this study is to analyze the crime behavior in the region under study based on data provided by the website “onde fui roubado” and classify each ISA according to the severity of the crime through algorithms of classification of machine learning. Data analysis will take place from the KDD methodology and Big Data tools will be used to handle the large volume of data. Thus, this paper presents a framework that will allow the identification of the crimes severity in each ISA based on Big Data and Machine Learning.

Item Type:Conference or Workshop Item (Paper)
Additional Information:https://icdsst2019.files.wordpress.com/2019/06/icdsst2019_proceedings_final.pdf
HAL Id:hal-02421562
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Universidade Federal de Pernambuco - UFPE (BRAZIL)
Other partners > SimTech Simulation Technology (AUSTRIA)
Other partners > Université de Namur - UNamur (BELGIQUE)
Laboratory name:
Statistics:download
Deposited On:17 Dec 2019 10:11

Repository Staff Only: item control page