Leonardo C. T. Bezerra - Página Pessoal
       

Leonardo Bezerra

Researcher/Professor, Instituto Metrópole Digital, Universidade Federal do Rio Grande do Norte, Brasil

I received a Ph.D. degree in engineering sciences from Université Libre de Bruxelles, Belgium, in 2016. I presented my thesis entitled "A component-wise approach to multi-objective evolutionary algorithms: from flexible frameworks to automatic design" on July 4th 2016.

Since 2009, I have been researching artificial intelligence techniques and their application to optimization problems. My thesis on the automated engineering of metaheuristic algorithms for the context of multiobjective optimization was written under the supervision of Thomas Stützle and Manuel López-Ibáñez.

Currently, I am a Professor at Instituto Metrópole Digital from Universidade Federal do Rio Grande do Norte (UFRN, Brazil), starting collaborations with researchers interested in refined optimization models, computational intelligence techniques, automated algorithm engineering, and Big Data models.


contact   leobezerra at imd.ufrn.br
RESEARCH FIELDS
  • Refined optimization models: multi-objective / dynamic / stochastic
  • Computational intelligence: metaheuristics / machine learning / deep learning
  • Automated algorithm engineering: selection / configuration / design / analysis
  • Big data
TEACHINGACTIVITIES
2017+Basic data structures / Programming (C++), Universidade Federal do Rio Grande do Norte (UFRN), Brazil
2016Design and analysis of algorithms, Universidade Federal da Paraíba (UFPB), Brazil
2013+Swarm Intelligence, Université Libre de Bruxelles (ULB), Belgium
2011Advanced algorithms / Algorithms, Universidade Federal do Rio Grande do Norte (UFRN), Brazil
Reviewing

Evolutionary Computation, IEEE Transactions on Evolutionary Computation, Swarm Intelligence, IMA Journal of Management Mathematics, Journal of Artificial Intelligence Research
Conferences

Reviewer: HM 2013, PPSN 2014, IEEE CEC 2017

PC Member: GECCO 2013-17

Local Comittee Member: ANTS 2012, 2014
PRESENTATIONS
Talks and Conferences

To DE or not to DE? Multi-objective differential evolution revisited from a component-wise perspective
[03/30/2015] Evolutionary Multi-Criterion Optimization (EMO 2015), Guimarães, Portugal.

Automatic design of evolutionary algorithms for multi-objective combinatorial optimization
[09/16/2014] Parallel Problem Solving from Nature (PPSN 2014), Ljubljana, Slovenia.

Deconstructing multi-objective evolutionary algorithms
[02/20/2014] Learning and Intelligent Optimization (LION 2014), Gainesville, FL, United States.

An analysis of local search for the bi-objective bidimensional knapsack problem
[02/04/2014] LAE, Universidade Federal do Rio Grande do Norte (UFRN), Natal, RN, Brazil.
[04/03/2013] Evolutionary Computation for Combinatorial Optimization (EvoCOP 2013), Vienna, Austria.

Automatic generation of multi-objective ACO algorithms for the bi-objective knapsack
[04/08/2013] Alpen-Adria Universität Klagenfurt / Lakeside Labs, Klagenfurt, Austria.
[08/23/2012] LAE, Universidade Federal do Rio Grande do Norte (UFRN), Natal, RN, Brazil.
[09/13/2012] Eighth International Conference on Swarm Intelligence (ANTS 2012), Brussels, Belgium.

GRACE: A generational randomized ACO for the multiobjective shortest path problem
[10/21/2011] IRIDIA, CoDE, Université Libre de Bruxelles (ULB), Brussels, Belgium.

Workshops

Automatic design of multi-objective evolutionary algorithms
[09/14/2014] Parallel Problem Solving from Nature (PPSN 2014), Ljubljana, Slovenia.

Minicourses

The IRACE package: iterated racing for automatic algorithm configuration.
[03/17/2015] LAE, Universidade Federal do Rio Grande do Norte (UFRN), Natal, RN, Brazil.
[01/30/2013] LAE, Universidade Federal do Rio Grande do Norte (UFRN), Natal, RN, Brazil.


PUBLICATIONS
Theses

Leonardo C. T. Bezerra. A component-wise approach to multi-objective evolutionary algorithms: from flexible frameworks to automatic design. PhD thesis, IRIDIA, École polytechnique, Université Libre de Bruxelles, Belgium, 2016. (pdf bib)

Leonardo C. T. Bezerra. Metaheuristics for multi-objective optimisation: automatic design using flexible frameworks. Rapport d'avancement de recherches pour la Formation Doctorale en Sciences de L'ingenieur, IRIDIA, CoDE, Université Libre de Bruxelles, 2013. (pdf bib)

Leonardo C. T. Bezerra. Uma colônia de formigas para o caminho mais curto multiobjetivo. Master's thesis, Departamento de Informática e Matemática Aplicada, 2011. (pdf bib)

Journals

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Automatically designing state-of-the-art multi- and many-objective evolutionary algorithms. Evolutionary Computation, 2019. Accepted. (bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. A large-scale experimental evaluation of high-performing multi- and many-objective evolutionary algorithms. Evolutionary Computation, 26:521--656, 2018. Accepted. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Automatic component-wise design of multi-objective evolutionary algorithms. IEEE Transactions on Evolutionary Computation, 20:403--417, 2016. (pdf bib)

Leonardo C. T. Bezerra, Elizabeth F. G. Goldbarg, Luciana S. Buriol, and Marco C. Goldbarg. Analyzing the impact of MOACO components: An algorithmic study on the multi-objective shortest path problem. Expert Systems with Applications, 40:345--355, 2013. (pdf bib)

Chapters

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Automatic configuration of multi-objective optimizers and multi-objective configuration. In P. Korošec et al., editors, High-Performance Simulation Based Optimization, Studies in Computational Intelligence. Springer International Publishing, 2019. In print. (pdf bib)

Conferences

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Archiver effects on the performance of state-of-the-art multi- and many-objective evolutionary algorithms In M. López-Ibáñez et al., editors, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2019). ACM, 2019. In print. (bib)

Sabrina Oliveira, Elizabeth F. Wanner, Sérgio R. de Souza, Leonardo C. T. Bezerra, and Thomas Stützle. The hypervolume indicator as a performance measure in dynamic optimization. In K. Deb et al., editors, Evolutionary Multi-Criterion Optimization (EMO 2019), volume 11411 of Lecture Notes in Computer Science, pages 319--331. Springer International Publishing, 2019. (bib)

Carlos Vieira, Adelso Araújo, Deângela C. G. Neves, Leonardo  C. T. Bezerra. iSklearn: Assessing irace for automated machine learning. In ICML 2018 AutoML Workshop. Accepted (withdrawn due to lack of funding).

Julio Borges, Daniel Ziehr, Michael Beigl, Nélio Cacho, Allan Martins, Adelson Araújo, Leonardo  C. T. Bezerra, Simon Geisler. Time-series features for predictive policing. In Proceedings of the IEEE International Smart Cities Conference (ISC2 2018), pages 1--8. IEEE, 2018. (bib)

Adelson Araújo, Nélio Cacho, Leonardo  C. T. Bezerra, Carlos Vieira, and Julio Borges. Towards a crime hotspot detection framework for patrol planning. In International Conference on Smart City (SmartCity 2018), pages 1256--1263. IEEE, 2018. (bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. An empirical assessment of the properties of inverted generational distance on multi- and many-objective optimization. In H. Trautmann et al., editors, Evolutionary Multi-Criterion Optimization (EMO 2017), volume 10173 of Lecture Notes in Computer Science, pages 31--45. Springer International Publishing, 2017. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. To DE or not to DE? Multi-objective differential evolution revisited from a component-wise perspective. In A. Gaspar-Cunha et al., editors, Evolutionary Multi-Criterion Optimization (EMO 2015), volume 9018 of Lecture Notes in Computer Science, pages 48--63. Springer International Publishing, 2015. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Comparing decomposition-based and automatically component-wise designed multi-objective evolutionary algorithms. In A. Gaspar-Cunha et al., editors, Evolutionary Multi-Criterion Optimization (EMO 2015), volume 9018 of Lecture Notes in Computer Science, pages 396--410. Springer International Publishing, 2015. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Deconstructing multi-objective evolutionary algorithms: an iterative analysis on the permutation flowshop problem. In Panos M. Pardalos, Mauricio G.C. Resende, Chrysafis Vogiatzis, and Jose L. Walteros, editors, Learning and Intelligent Optimization (LION 2014), volume 8426 of Lecture Notes in Computer Science, pages 157--172. Springer International Publishing, 2014. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Automatic design of evolutionary algorithms for multi-objective combinatorial optimization. In Thomas Bartz-Beielstein, Jürgen Branke, Bogdan Filipič, and Jim Smith, editors, Parallel Problem Solving from Nature – PPSN XIII, volume 8672 of Lecture Notes in Computer Science, pages 508--517. Springer International Publishing, 2014. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. An analysis of local search for the bi-objective bidimensional knapsack problem. In Martin Middendorf and Christian Blum, editors, Evolutionary Computation in Combinatorial Optimization (EvoCOP 2013), volume 7832 of Lecture Notes in Computer Science, pages 85--96. Springer Berlin Heidelberg, 2013. (pdf bib)

Leonardo C. T. Bezerra, Manuel López-Ibáñez, and Thomas Stützle. Automatic generation of multi-objective ACO algorithms for the bi-objective knapsack. In M. Dorigo et al., editors, Swarm Intelligence (ANTS 2012), volume 7461 of Lecture Notes in Computer Science, pages 37--48. Springer-Verlag, 2012. (pdf bib)

Leonardo C. T. Bezerra, Elizabeth F. G. Goldbarg, Luciana S. Buriol, and Marco C. Goldbarg. GRACE: A generational randomized ACO for the multiobjective shortest path problem. In R. H. C. Takahashi et al., editors, Evolutionary Multi-Criterion Optimization (EMO 2011), volume 6576 of Lecture Notes in Computer Science. Springer, 2011. (pdf bib)

Wagner Schmitt, Leonardo César Teonácio Bezerra, Luciana Salete Buriol, Elizabeth Ferreira Gouvêa Goldbarg, Marco César Goldbarg, and Marcus Ritt. Um estudo experimental do problem de caminhos mínimos multiobjetivo. In Anais do XLIII Simpósio Brasileiro de Pesquisa Operacional (SBPO 2011), Ubatuba, SP, 2011. SBC. (pdf bib)

Selan R. dos Santos, Leonardo C. T. Bezerra, Silvano Malfatti, and Antonino A. Feitosa Neto. FAITH: A desktop virtual reality system for fingerspelling. In Proceedings of the XI Symposium on Virtual and Augmented Reality (SVR 2009), Porto Alegre, RS, 2009. SBC. Best paper award. (pdf bib)

Technical reports

Leonardo C. T. Bezerra, Elizabeth F. G. Goldbarg, Luciana S. Buriol, and Marco C. Goldbarg. Food regulated pareto multi-species: a new ACO approach for the multi-objective shortest path problem. Technical Report UFRN-DIMAP-2011-104-RT, Departamento de Informática e Matemática Aplicada, Universidade Federal do Rio Grande do Norte, 2011. (pdf bib)