Leonardo Tomazeli Duarte

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, Université Grenoble Alpes), France, in 2009. Since 2011, he has been with the School of Applied Sciences (FCA) at UNICAMP, Limeira, Brazil, where he is currently an associate professor. He is the Scientific Coordinator of the Track "Method" within the Brazilian Institute of Data Science (BI0S), one of the Brazilian Applied Research Center on Artificial Intelligence. He is also a member with the Laboratory of Data Analysis and Decision Aiding (LAD2/CPO) and with the Laboratory of Signal Processing for Communications (DSPCom lab). He is a Senior Member of the IEEE. In 2016, he was a Visiting Professor at the École de Génie Industriel (GI-Grenoble INP, France). Since 2015, he has been recipient of the National Council for Scientific and Technological Development (CNPq, Brazil) productivity research grant. In 2017, he was the recipient of UNICAMP "Zeferino Vaz" Academic Recognition Award (for research and teaching performance at UNICAMP). In 2022, he was elected Affiliated Member (up to 40 years old) of the Brazilian Academy of Sciences (ABC).

Research interests

My research interests center around the broad area of data science and lie primarily in the fields of signal processing, decision aiding and machine learning, and also in the interplays between these fields. I have been working on the development and analysis of methods and on applications in different areas, from geophysics to chemical sensors. My research has been funded by national and international research agencies (such as FAPESP, CNPq, CAPES, and CNRS) and also by means of partnerships with private and public institutions.

Signal Processing

• Signal separation and latent variable analysis (LVA), including Independent Component Analysis (ICA), Sparse Component Analysis (SCA) and Non-negative Matrix Factorization (NMF)

• Blind source separation in nonlinear models 

• Blind compensation of nonlinear distortions

• Multi-objective optimization for signal processing

• Machine learning for signal processing (Bayesian methods, neural networks, unsupervised learning) 

• Applications of signal processing methods (e.g. in geophysics, chemical sensors, statistical process control and sports)

Decision aiding & Machine Learning

• Multiple-criteria decision analysis (MCDA)

• Unsupervised (data-driven) schemes for adjusting MCDA algorithms

• Models based on the Choquet integral

• Interpretability and fairness in MCDA and Machine Learning

• Missing data in decision methods

• Applications (e.g. evaluation in sport sciences, supplier selection, problems in industry, and project selection)

Teaching

Undergraduate classes

• Statistics and Probability for Engineers

• Biostatistics

• Introduction to data science and information

• Introduction to machine learning and decision aiding

Graduate classes

• Machine learning

• Mutiple-criteria decision aiding

• Foundations of data science