no code implementations • 1 Nov 2023 • Alexander James Fernandes, Ioannis Psaromiligkos
A key benefit of both methods compared to the traditional least squares (LS) solution is that they exploit the structure of the tensor model to obtain decoupled estimates of all communication channels.
no code implementations • 29 Sep 2023 • Pavel Sinha, Ioannis Psaromiligkos, Zeljko Zilic
We propose an automatic segmentation method for lumen and media with irregular contours in IntraVascular ultra-sound (IVUS) images.
no code implementations • 29 Jun 2023 • Pavel Sinha, Ioannis Psaromiligkos, Zeljko Zilic
Our proposed CNN architecture is fully compatible with the end-to-end learning mechanism of typical CNN architectures and learns the subband decomposition from the input dataset.
no code implementations • 12 Jan 2023 • Alexander James Fernandes, Ioannis Psaromiligkos
We consider the problem of channel estimation in a multiple-input-multiple-output (MIMO) full-duplex (FD) wireless communication system assisted by a reconfigurable intelligent surface (RIS) with hardware impairments (HI) occurring at the transceivers and RIS elements.
no code implementations • 7 Jan 2022 • Onur Karatalay, Ioannis Psaromiligkos, Benoit Champagne
In this paper, we address the problem of resource allocation with respect to task partitioning, computation resources and transmit power in a D2D-aided fog computing scenario, aiming to minimize the expected total energy consumption under probabilistic constraints on the processing time.
no code implementations • 2 Mar 2021 • Pavel Sinha, Ioannis Psaromiligkos, Zeljko Zilic
We propose a convolutional neural network (CNN) architecture for image classification based on subband decomposition of the image using wavelets.