no code implementations • 28 Feb 2024 • Koffi Kossi, Stephane Coulombe, Christian Desrosiers, Ghyslain Gagnon
In this paper, we developed a parametric model for estimating the perceived audiovisual quality in videoconference services.
no code implementations • 19 May 2021 • Ngoc T. Nguyen, Toan Q. Bui, Ghyslain Gagnon, Pascal Giard, Georges Kaddoum
Moreover, a data scrambling circuit is implemented to eliminate the bias effect and increase the randomness of the bitstream generated from the chaotic signals.
1 code implementation • 22 Mar 2021 • Antoine Langevin, Marc-André Carbonneau, Mohamed Cheriet, Ghyslain Gagnon
In this paper we address these issues and propose an energy disaggregation approach based on the variational autoencoders framework.
1 code implementation • 16 Dec 2020 • Marc-André Carbonneau, Julian Zaidi, Jonathan Boilard, Ghyslain Gagnon
While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement.
no code implementations • 13 Apr 2020 • Marouane Hachimi, Georges Kaddoum, Ghyslain Gagnon, Poulmanogo Illy
In 5G networks, the Cloud Radio Access Network (C-RAN) is considered a promising future architecture in terms of minimizing energy consumption and allocating resources efficiently by providing real-time cloud infrastructures, cooperative radio, and centralized data processing.
no code implementations • 6 Oct 2017 • Marc-André Carbonneau, Eric Granger, Ghyslain Gagnon
In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances.
1 code implementation • 11 Dec 2016 • Marc-André Carbonneau, Veronika Cheplygina, Eric Granger, Ghyslain Gagnon
Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag.
no code implementations • 4 Oct 2016 • Marc-André Carbonneau, Eric Granger, Yazid Attabi, Ghyslain Gagnon
The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 6 parameters can be tuned automatically.