Visual Analytics of Machine Learning Methods: a practical essay from crime data in São Paulo

• Grant number: 17/05416-1
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: May 01, 2017
• End date: December 22, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Luis Gustavo Nonato
• Grantee: Germain García Zanabria
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry, AP.CEPID
• Associated scholarship(s): 19/04434-1 - Analysis of Crime Patterns in São Paulo City, BE.EP.DR

Abstract

Machine learning and visualization methods have long been operating as complementary tools in many data analysis applications. However, methods from those two fields have not been properly integrated to benefit each other. Specifically, few has been done to incorporate visualization tools within machine learning frameworks, leveraging the analytical capability of visualization techniques to make learning processes more understandable and steerable. This project aims to fill this gap, building upon visualization mechanisms to uncover phenomena hidden in machine learning procedures, allowing users to fine tune tools according to specific data in order to improve the effectiveness of machine learning methods in particular scenarios. In collaboration with the Center for the Study of Violence - NEV - USP, we will employ the proposed methodology in a specific application, namely, the analysis of crime patterns in São Paulo city. Therefore, besides the technical contributions, the present project offers a unique opportunity for researchers from Cepid-CEMEAI and Cepid-NEV to collaborate.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

GARCIA-ZANABRIA, GERMAIN; GOMEZ-NIETO, ERICK; SILVEIRA, JAQUELINE; POCO, JORGE; NERY, MARCELO; ADORNO, SERGIO; NONATO, LUIS G.; IEEE. Mirante: A visualization tool for analyzing urban crimes. 2020 33RD SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2020), v. N/A, p. 8-pg., 2020-01-01. (17/05416-1, 19/04434-1, 13/07375-0, 19/10560-0)

GARCIA-ZANABRIA, GERMAIN; RAIMUNDO, MARCOS M.; POCO, JORGE; NERY, MARCELO BATISTA; SILVA, CLAUDIO T.; ADORNO, SERGIO; NONATO, LUIS GUSTAVO. CriPAV: Street-Level Crime Patterns Analysis and Visualization. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, v. 28, n. 12, p. 16-pg., 2022-12-01. (13/07923-7, 14/12236-1, 17/05416-1, 16/04391-2, 19/04434-1)

GARCIA, GERMAIN; SILVEIRA, JAQUELINE; POCO, JORGE; PAIVA, AFONSO; NERY, MARCELO BATISTA; SILVA, CLAUDIO T.; ADORNO, SERGIO; NONATO, LUIS GUSTAVO. CrimAnalyzer: Understanding Crime Patterns in Sao Paulo. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, v. 27, n. 4, p. 2313-2328, APR 1 2021. (16/04391-2, 14/12236-1, 17/05416-1)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

ZANABRIA, Germain García. Visual Crime Pattern Analysis. 2021. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.