no code implementations • 16 Apr 2024 • Amit Kumar Bhuyan, Hrishikesh Dutta, Subir Biswas
The paper proposes a decentralized Top-k Multi-Armed Bandit (Top-k MAB) learning approach for UAV caching decisions, accommodating geotemporal disparities in content popularity and diverse content demands.
no code implementations • 16 Apr 2024 • Amit Kumar Bhuyan, Hrishikesh Dutta, Subir Biswas
In this new approach, speaker change detection is biased around detected quasi-silences, which reduces the severity of the trade-off between the missed detection and false detection rates.
no code implementations • 18 Dec 2023 • Amit Kumar Bhuyan, Hrishikesh Dutta, Subir Biswas
Functional verification and performance evaluation of the proposed caching framework is done for a wide range of network size, UAV distribution, and content popularity.
no code implementations • 14 Jan 2023 • Hrishikesh Dutta, Amit Kumar Bhuyan, Subir Biswas
Moreover, the nodes learn to self-adjust their transmission schedules using a novel DDSB framework in order to reduce bandwidth usage.
no code implementations • 14 Jan 2023 • Hrishikesh Dutta, Amit Kumar Bhuyan, Subir Biswas
It then introduces a novel learning based protocol synthesis framework that addresses specific difficulties and limitations in medium access for both random access and time slotted networks.
no code implementations • 29 Apr 2021 • Hrishikesh Dutta, Subir Biswas
This paper proposes a distributed Reinforcement Learning (RL) based framework that can be used for synthesizing MAC layer wireless protocols in IoT networks with low-complexity wireless transceivers.
no code implementations • 2 Feb 2021 • Hrishikesh Dutta, Subir Biswas
Finally, it is also shown that the online learning feature of reinforcement learning is able to make the protocol adapt to time-varying loading conditions.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 4 Jun 2019 • Yan Shi, Dezhi Feng, Subir Biswas
This paper presents a deep-learning based traffic classification method for identifying multiple streaming video sources at the same time within an encrypted tunnel.