Lucas Tsutsui da Silva

I am a PhD candidate at UNSW Sydney, working with semi-supervised learning for object detection funded by SmartSat CRC. My research focuses on improving the efficiency of semi-supervised object detection methods to execute them on nanosatellites. I hold a Master's degree in Computer Science and Computational Mathematics (2020) from the Institute of Mathematics and Computer Sciences (ICMC) of the University of São Paulo (USP), Brazil. During my master's research, I created an open-source tool named EmbML to produce classification models for resource-constrained hardware such as low-power microcontrollers. I also have a Bachelor's degree in Computer Engineering (2016) from the Federal University of Mato Grosso do Sul (UFMS), Brazil. Currently, my research interests include semi-supervised learning, object detection, and edge computing.

Education

• University of New South Wales (UNSW), Sydney, Australia

  • PhD degree in Computer Science

  • Research title: Semi-Supervised Learning for Automatic Improvement of Onboard Object Detection Models on Small Satellites

  • Supervisor: Dr Gustavo Batista 

  • Period: February 2023 - August 2026 (expected)
    
    

• Universidade de São Paulo (ICMC-USP), São Carlos, Brazil

  • Master's degree in Computer Science and Computational Mathematics

  • Research title: Evaluating classification models for resource-constrained hardware (online access in English)

  • Supervisor: Dr Gustavo Batista 

  • Period: July 2017 - September 2020

• Universidade Federal de Mato Grosso do Sul (UFMS), Campo Grande, Brazil

  • Bachelor's degree in Computer Engineering

  • Period: 2011 - 2016

• Portland State University, Portland, USA

  • Non-degree international student in Computer Engineering

  • Period: August 2014 - June 2015

Experience

• Temporary professor at CPAN-UFMS

  • Teaching courses for the Information Systems undergraduate program

    • Artificial Intelligence (2022/2)

    • Introduction to Digital Systems (2022/2)

    • Fundamentals of Computing Theory (2022/1)

    • and others

  • Period: March 2022 - January 2023

• Postgraduate researcher at ICMC-USP

  • Worked on my master's research at the Computational Intelligence Laboratory (LABIC) from the ICMC-USP, supervised by Dr Gustavo Batista

  • This research focused on adapting classification models to execute on low-power embedded systems

  • We published the results of this work in two peer-reviewed conferences and one scientific journal

  • Period: July 2017 - September 2020

• Undergraduate researcher at FACOM-UFMS

  • Worked at the High-Performance Computing Systems Laboratory (LSCAD) from the UFMS, supervised by Dr Luciano Gonda

  • This research focused on studying Wireless Sensor Networks applied to precision agriculture

  • We developed and tested an Arduino-based system that communicates with a server computer using XBee radio

  • Period: August 2012 - May 2014

Publications

• DA SILVA, Lucas Tsutsui; SOUZA, Vinicius M. A.; BATISTA, Gustavo E. A. P. A. An Open-Source Tool for Classification Models in Resource-Constrained Hardware. In: IEEE Sensors Journal, vol. 22, no. 1. IEEE, 2022. p. 544-554. Online access 

• DA SILVA, Lucas Tsutsui; SOUZA, Vinicius M. A.; BATISTA, Gustavo E. A. P. A. EmbML Tool: supporting the use of supervised learning algorithms in low-cost embedded systems. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2019. p. 1633-1637. Online access 

• DA SILVA, Lucas Tsutsui; SOUZA, Vinicius M. A.; BATISTA, Gustavo E. A. P. A. Uma Ferramenta de Suporte ao Uso de Classificadores em Sistemas Embarcados. In: Anais do 14º Simpósio Brasileiro de Automação Inteligente. SBA, 2019. Online access 

Academic Achievements

• Honorable Mention in South America Brazil Region (Brazil Finals) - ACM International Collegiate Programming Contest (2013). my ICPCID 

• Honorable Mention in South America Brazil (First phase) – ACM International Collegiate Programming Contest (2012 and 2015).

• Third Place in Latin American Robotics Competition – IEEE Standard Educational Kits (SEK) category (2012).