no code implementations • 26 May 2023 • Elahe Rahimian, Golara Javadi, Frederick Tung, Gabriel Oliveira
Multi-task networks rely on effective parameter sharing to achieve robust generalization across tasks.
1 code implementation • 29 Nov 2022 • Mansooreh Montazerin, Elahe Rahimian, Farnoosh Naderkhani, S. Farokh Atashzar, Svetlana Yanushkevich, Arash Mohammadi
Additionally, the CT-HGR framework can perform instantaneous recognition using sEMG image spatially composed from HD-sEMG signals.
no code implementations • 27 Oct 2022 • Soheil Zabihi, Elahe Rahimian, Amir Asif, Arash Mohammadi
Advancements in Biological Signal Processing (BSP) and Machine-Learning (ML) models have paved the path for development of novel immersive Human-Machine Interfaces (HMI).
no code implementations • 27 Oct 2022 • Mansooreh Montazerin, Elahe Rahimian, Farnoosh Naderkhani, S. Farokh Atashzar, Hamid Alinejad-Rokny, Arash Mohammadi
At the same time, advancements in acquisition of High-Density sEMG signals (HD-sEMG) have resulted in a surge of significant interest on sEMG decomposition techniques to extract microscopic neural drive information.
no code implementations • 12 Oct 2022 • Zohreh Hajiakhondi-Meybodi, Arash Mohammadi, Ming Hou, Elahe Rahimian, Shahin Heidarian, Jamshid Abouei, Konstantinos N. Plataniotis
Most existing datadriven popularity prediction models, however, are not suitable for the coded/uncoded content placement frameworks.
no code implementations • 28 Mar 2022 • Soheil Zabihi, Elahe Rahimian, Amir Asif, Arash Mohammadi
In other words, we propose a hybrid framework based on the transformer architecture, which is a relatively new and revolutionizing deep learning model.
1 code implementation • 25 Jan 2022 • Mansooreh Montazerin, Soheil Zabihi, Elahe Rahimian, Arash Mohammadi, Farnoosh Naderkhani
The proposed Vision Transformer-based Hand Gesture Recognition (ViT-HGR) framework can overcome the aforementioned training time problems and can accurately classify a large number of hand gestures from scratch without any need for data augmentation and/or transfer learning.
no code implementations • 31 Dec 2021 • Soheil Zabihi, Elahe Rahimian, Fatemeh Marefat, Amir Asif, Pedram Mohseni, Arash Mohammadi
Objective: The paper focuses on development of robust and accurate processing solutions for continuous and cuff-less blood pressure (BP) monitoring.
no code implementations • 1 Dec 2021 • Zohreh Hajiakhondi Meybodi, Arash Mohammadi, Elahe Rahimian, Shahin Heidarian, Jamshid Abouei, Konstantinos N. Plataniotis
As a consequence of the COVID-19 pandemic, the demand for telecommunication for remote learning/working and telemedicine has significantly increased.
no code implementations • 17 Oct 2021 • Elahe Rahimian, Soheil Zabihi, Amir Asif, Dario Farina, S. Farokh Atashzar, Arash Mohammadi
Advances in biosignal signal processing and machine learning, in particular Deep Neural Networks (DNNs), have paved the way for the development of innovative Human-Machine Interfaces for decoding the human intent and controlling artificial limbs.
no code implementations • 1 Oct 2021 • Soheil Zabihi, Elahe Rahimian, Soumya Sharma, Sean K. Sethi, Sara Gharabaghi, Amir Asif, E. Mark Haacke, Mandar S. Jog, Arash Mohammadi
Brain iron deposition, in particular deep gray matter nuclei, increases with advancing age.
no code implementations • 25 Sep 2021 • Elahe Rahimian, Soheil Zabihi, Amir Asif, Dario Farina, S. Farokh Atashzar, Arash Mohammadi
We propose a novel Vision Transformer (ViT)-based neural network architecture (referred to as the TEMGNet) to classify and recognize upperlimb hand gestures from sEMG to be used for myocontrol of prostheses.
no code implementations • 11 Nov 2020 • Elahe Rahimian, Soheil Zabihi, Amir Asif, Dario Farina, Seyed Farokh Atashzar, Arash Mohammadi
This work is motivated by the recent advances in Deep Neural Networks (DNNs) and their widespread applications in human-machine interfaces.
1 code implementation • 9 Nov 2019 • Elahe Rahimian, Soheil Zabihi, Seyed Farokh Atashzar, Amir Asif, Arash Mohammadi
The proposed innovative XceptionTime is designed by integration of depthwise separable convolutions, adaptive average pooling, and a novel non-linear normalization technique.