no code implementations • 8 Aug 2022 • Hosein Zarini, Narges Gholipoor, Mohamad Robat Mili, Mehdi Rasti, Hina Tabassum, Ekram Hossain
It is numerically demonstrated that, in the first step, employing the Xavier initialization technique to fine-tune the LSM results in at most 26% lower LSM prediction variance and as much as 46% achievable spectral efficiency (SE) improvement over the existing counterparts, when an RIS of size 11x11 is deployed.
no code implementations • 1 Jun 2022 • Hosein Zarini, Mohammad Robat Mili, Mehdi Rasti, Pedro H. J. Nardelli, Mehdi Bennis
In this paper, we propose an accurate two-phase millimeter-Wave (mmWave) beamspace channel tracking mechanism.
no code implementations • 12 Oct 2021 • Hosein Zarini, Mohammad Robat Mili, Mehdi Rasti, Sergey Andreev, Pedro H. J. Nardelli
First inspired by transfer learning, we fine-tune the pre-trained off-the-shelf GoogleNet classifier, to learn analog beam selection as a multi-class mapping problem.
no code implementations • 30 Aug 2020 • Hosein Zarini, Ata Khalili, Hina Tabassum, Mehdi Rasti
In particular, we formulate a joint optimization problem of power control and scheduling (i. e., user association and subcarrier allocation) in secondary tier to maximize total achievable QoE for the secondary users.