University of Oulu

Chanaka Ganewattha, Zaheer Khan, Janne Lehtomäki, and Matti Latva-aho. 2023. Hardware-accelerated Realtime Drift-awareness for Robust Deep Learning on Wireless RF Data. ACM Trans. Reconfigurable Technol. Syst. 16, 2, Article 19 (March 2023), 29 pages.

Hardware-accelerated real-time drift-awareness for robust deep learning on wireless RF data

Saved in:
Author: Ganewattha, Chanaka1; Khan, Zaheer1; Lehtomäki, Janne J1;
Organizations: 1Centre for Wireless Communications, University of Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2.3 MB)
Persistent link:
Language: English
Published: Association for Computing Machinery, 2023
Publish Date: 2023-09-14


Proactive and intelligent management of network resource utilization (RU) using deep learning (DL) can significantly improve the efficiency and performance of the next generation of wireless networks. However, variations in wireless RU are often affected by uncertain events and change points due to the deviations of real data distribution from that of the original training data. Such deviations, which are known as dataset drifts, can subsequently lead to a shift in the corresponding decision boundary degrading the DL model prediction performance. To address these challenges, we present hardware-accelerated real-time radio frequency (RF) analytics and drift-awareness modules for robust DL predictions. We have prototyped the proposed design on a Zynq-7000 System-on-Chip that contains an FPGA and an embedded ARM processor. We have used Xilinx Vivado design suite for synthesis and analysis of the HDL design for the proposed solution. To detect dataset drifts, the proposed solution adopts a distance-based technique on FPGA to quantify in real-time the change between the prediction distribution obtained from DL predictions and data distribution of input streaming samples. Using various performance metrics, we have extensively evaluated the performance of the proposed solution and shown that it can significantly improve the DL model robustness in the presence of dataset drifts.

see all

Series: ACM transactions on reconfigurable technology and systems
ISSN: 1936-7406
ISSN-E: 1936-7414
ISSN-L: 1936-7406
Volume: 16
Issue: 2
Pages: 1 - 29
Article number: 19
DOI: 10.1145/3563394
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Copyright information: © 2023 Copyright held by the owner/author(s). This work is licensed under a Creatice Commons Attribution International 4.0 License.