Short bio

Leonardo Tomazeli Duarte received the B.S. and M.Sc. degrees in electrical engineering from the University of Campinas (UNICAMP), Brazil, in 2004 and 2006, respectively, and the Ph.D. degree from the Grenoble Institute
of Technology (Grenoble INP), France, in 2009. Since 2011, he has been with the School of Applied Sciences (FCA) at UNICAMP, Limeira, Brazil, where he is currently an assistant professor. He is also a member with the Operational Research Centre (at FCA/UNICAMP) and with the Laboratory of Signal Processing for Communications (DSPCom lab). He is a Senior Member of the IEEE.

At FCA/UNICAMP, he has been teaching statistics, probability and machine learning for undergraduate and graduate students from industrial engineering, management sciences, nutrition and sports science.  

My Lattes CV (in portuguese) here.

Research interests

Signal Processing

  • Blind Source Separation (BSS) and Independent Component Analysis (ICA)
  • BSS in nonlinear models (Post-nonlinear and polynomial mixtures)
  • Blind compensation of nonlinear distortions 
  • Sparse signal processing
  • Bayesian methods for signal processing (using Markov Chain Monte Carlo (MCMC) methods)
  • Evolutionary computation for signal processing
  • Applications
    • Seismic signal processing (Multiple attenuation, separation of seismic events and denoising)
    • Signal processing methods for chemical sensor arrays (ion-selective electrodes (ISE) and  ion-sensitive field-effect transistor (ISFET) arrays) 
    • Signal processing for statistical process control (SPC)

Operations Research (since 2014)

  • Multiple-criteria decision analysis (MCDA)
  • Unsupervised schemes for adjusting MCDA algorithms (e.g. the fuzzy measure coefficients in the Choquet integral formalism for decision making)
  • New methods to deal with the interaction between decision criteria
  • Methodological aspects of data envelopment analysis (DEA)
  • Applications
    • Evaluation in sport sciences
    • R&D and Innovation Project Selection