no code implementations • 15 May 2023 • Theo Chow, Usman Raza, Ioannis Mavromatis, Aftab Khan
In order to simultaneously reduce communication traffic and maintain the integrity of inference models, we introduce FLARE, a novel lightweight dual-scheduler FL framework that conditionally transfers training data, and deploys models between edge and sensor endpoints based on observing the model's training behaviour and inference statistics, respectively.
no code implementations • 8 Mar 2021 • Peizheng Li, Han Cui, Aftab Khan, Usman Raza, Robert Piechocki, Angela Doufexi, Tim Farnham
Finally, an ablation study of the training dataset shows that, in both office and sport hall scenarios, after reusing the feature extraction layers of the base model, only 55% of the training data is required to obtain the models' accuracy similar to the base models.
no code implementations • 16 Oct 2020 • Peizheng Li, Han Cui, Aftab Khan, Usman Raza, Robert Piechocki, Angela Doufexi, Tim Farnham
Meanwhile, using a well-organised architecture, the neural network models can be trained directly with raw data from the CSI and localisation features can be automatically extracted to achieve accurate position estimates.
no code implementations • 30 May 2019 • Aftab Khan, Tim Farnham, Roget Kou, Usman Raza, Thajanee Premalal, Aleksandar Stanoev, William Thompson
High accuracy localisation technologies exist but are prohibitively expensive to deploy for large indoor spaces such as warehouses, factories, and supermarkets to track assets and people.
1 code implementation • 28 Aug 2018 • Shengyang Li, Usman Raza, Aftab Khan
The LoRaWAN based Low Power Wide Area networks aim to provide long-range connectivity to a large number of devices by exploiting limited radio resources.
Networking and Internet Architecture
1 code implementation • 15 Oct 2016 • Orestis Georgiou, Usman Raza
Low Power Wide Area (LPWA) networks are making spectacular progress from design, standardisation, to commercialisation.
Networking and Internet Architecture