Projects per year
Abstract
This paper presents a novel Convolutional Neural Network (CNN) FPGA architecture designed to perform processing of radio data in a streaming manner without interruption. The proposed architecture is evaluated for radio modulation classification tasks implemented on an AMD RFSoC 2x2 development board and operating in real-time. The proposed architecture leverages optimisation such as the General Matrix-to-Matrix (GEMM) transform, on-chip weights, fixed-point arithmetic, and efficient utilisation of FPGA resources to achieve constant processing of a stream of samples. The performance of the proposed architecture is demonstrated through accuracy results obtained during live modulation classification, while operating at a sampling frequency of 128 MHz before decimation. The proposed architecture demonstrates promising results for real-time, time-critical CNN applications.
Original language | English |
---|---|
Pages | 1-5 |
Number of pages | 5 |
Publication status | Published - 27 Jun 2023 |
Event | 21st IEEE Interregional New Circuit and Systems (NEWCAS) Conference: An IEEE CAS Society Interregional Flagship Conference - John McIntyre Conference Centre, Edinburgh, United Kingdom Duration: 26 Jun 2023 → 28 Jun 2023 https://2023.ieee-newcas.org/ |
Conference
Conference | 21st IEEE Interregional New Circuit and Systems (NEWCAS) Conference |
---|---|
Abbreviated title | IEEE NEWCAS 2023 |
Country/Territory | United Kingdom |
City | Edinburgh |
Period | 26/06/23 → 28/06/23 |
Internet address |
Keywords
- deep learning
- wireless communications
- FPGA
- RFSoC
- AMD
- tensorflow
- MATLAB
- signal processing
Fingerprint
Dive into the research topics of 'Streaming Convolutional Neural Network FPGA architecture for RFSoC data converters'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Doctoral Training Partnership 2018-19 University of Strathclyde | MacLellan, Andrew
Stewart, R. (Principal Investigator), Crockett, L. (Co-investigator) & MacLellan, A. (Research Co-investigator)
EPSRC (Engineering and Physical Sciences Research Council)
1/10/18 → 1/01/23
Project: Research Studentship - Internally Allocated
Datasets
-
Training dataset for RFSoC Modulation Classification
MacLellan, A. (Creator), Crockett, L. H. (Supervisor) & Stewart, R. (Supervisor), University of Strathclyde, 2 May 2023
DOI: 10.15129/95f907fb-4cb2-4365-93ac-c36165053999
Dataset