Mateus S. Gilbert

Mateus S. Gilbert

D.Sc. student

UFRJ

LIP6

Biography

Mateus S. Gilbert is a D.Sc. student in Electrical Engineering at the Electrical Engineering Program of the Alberto Luiz Coimbra Institute of Graduate Studies and Research in Engineering (PEE/COPPE/UFRJ) and Ph.D student in Information and Communication Technology at the Sorbonne University (SU) in a joint supervisoin program, co-supervised by prof. Miguel Elias M. Campista, prof. Marcello L. R. de Campos, prof. Marcelo Dias de Amorim, and prof. Anne Fladenmuller since march 2024.

In 2024, he received his M.Sc. in Electric Engineering at the PEE/COPPE/UFRJ. Previously in 2022, he received his B.Sc. in Electronic and Computer Engineering at the UFRJ Polytechnic School and B.Math at the UFRJ Intitute of Mathematics. He is a research student in the Grupo de Teleinformática e Automação (GTA), since 2019. Between November 2024 and April 2026, stayed at the Laboratoire d’Informatique de Paris 6 (LIP6) during his joint supervision period at SU. His research interests include neural networks, deep learning, IoT, mobile networks, computer vision, wireless communication, edge computing, and data science.

Interests
  • Neural Networks
  • Deep Learning
  • Mobile Networks
  • Edge Computing
  • IoT
  • Wireless Communication
  • Computer Vision
  • Data Science
Education

  • DSc in Electric Engineering

    COPPE/UFRJ

  • PhD in Information and Communication Techology

    SU

  • MSc in Electric Engineering, 2024

    COPPE/UFRJ

  • BMath, 2022

    UFRJ Institute of Mathematics

  • BSc in Electronic and Computer Engineering, 2022

    UFRJ Polytechnic School

Recent Publications

Search for an older work by filtering publications.
Congesion-Game-Inspired Server Selection for Edge DNN Inference
Selecting the best DNN in a heterogeneous mobile wireless network is challenging, particularly in partition-prone networks. This work addresses this problem by proposing congesion-game-inspired selection algorithms resilient to node mobility and network disconnections.
Mateus S. Gilbert, Nicolas Peugnet, Anne Fladenmuller, Kinda Khawam, Marcello L. R. de Campos, Miguel Elias M. Campista, Marcelo Dias de Amorim
Sep 16, 2026
PDF Cite DOI
Early-Exit Criteria for Edge Semantic Segmentation
Given the success of Early-Exit DNNs (EE-DNNs) with image classification, this work proposes exit criteria to assist EE-DNN inference on edge semantic segmentation.
Mateus S. Gilbert, Roberto G. Pacheco, Rodrigo S. Couto, Anne Fladenmuller, Marcelo Dias de Amorim, Marcello L. R. de Campos, Miguel Elias M. Campista
Sep 3, 2025
PDF Cite DOI
Asymmetric Autoencoders: an NN alternative for resource-constrained devices in IoT networks
Many recent publications resort to DNNs to deal with IoT data. Models with multiple layers and other parameters can be hard to implement with resource-constrained devices given its computational and energy demands. This work proposes an autoencoder models that aims to mitigate these issues.
Mateus S. Gilbert, Marcello L. R. de Campos, Miguel Elias M. Campista
Apr 1, 2024
PDF Cite DOI

Contact