no code implementations • 26 Dec 2023 • Fahri Wisnu Murti, Samad Ali, Matti Latva-aho
In this paper, a joint O-RAN/MEC orchestration using a Bayesian deep reinforcement learning (RL)-based framework is proposed that jointly controls the O-RAN functional splits, the allocated resources and hosting locations of the O-RAN/MEC services across geo-distributed platforms, and the routing for each O-RAN/MEC data flow.
no code implementations • 15 Nov 2023 • Mehdi Letafati, Samad Ali, Matti Latva-aho
This way, we make the constellation symbols sent by the transmitter, and what is inferred (reconstructed) at the receiver become as similar as possible, resulting in as few mismatches as possible.
no code implementations • 30 Oct 2023 • Mehdi Letafati, Samad Ali, Matti Latva-aho
Thanks to the outstanding achievements from state-of-the-art generative models like ChatGPT and diffusion models, generative AI has gained substantial attention across various industrial and academic domains.
no code implementations • 11 Oct 2023 • Mehdi Letafati, Samad Ali, Matti Latva-aho
In this article, we outline the applications of diffusion models in wireless communication systems, which are a new family of probabilistic generative models that have showcased state-of-the-art performance.
no code implementations • 21 Jun 2021 • Thushan Sivalingam, Samad Ali, Nurul Huda Mahmood, Nandana Rajatheva, Matti Latva-aho
Grant-free random access and uplink non-orthogonal multiple access (NOMA) have been introduced to reduce transmission latency and signaling overhead in massive machine-type communication (mMTC).
no code implementations • 17 Mar 2021 • Insaf Ismath, Samad Ali, Nandana Rajatheva, Matti Latva-aho
Access points (APs) in millimeter-wave (mmWave) and sub-THz-based user-centric (UC) networks will have sleep mode functionality.
no code implementations • 22 Feb 2021 • Madhushanka Padmal, Dileepa Marasinghe, Vijitha Isuru, Nalin Jayaweera, Samad Ali, Nandana Rajatheva
However, LiDARs are power hungry devices that generate a lot of data, and these characteristics limit their use as on-board sensors in robots.
no code implementations • 12 Jan 2021 • Thulitha Senevirathna, Bathiya Thennakoon, Tharindu Sankalpa, Chatura Seneviratne, Samad Ali, Nandana Rajatheva
This is done by restructuring the transmission data in a way that the LSTM network can identify the causal relationship between the devices.
no code implementations • 15 Sep 2020 • Insaf Ismath, K. B. Shashika Manosha, Samad Ali, Nandana Rajatheva, Matti Latva-aho
In this paper, we propose a novel deep contextual bandit (DCB) based approach to perform fast and efficient IA in mmWave based UC UD networks.
no code implementations • 13 Dec 2018 • Aidin Ferdowsi, Samad Ali, Walid Saad, Narayan B. Mandayam
For sensors having a prior information, a DIA detection approach is proposed and an optimal threshold level is derived for the difference between the actual and estimated values of sensors data which enables ACV to stay robust against cyber attacks.