Conference proceeding
Radio Modulation Classification Using Deep Residual Neural Networks
MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM), v 2022-, pp 311-317
28 Nov 2022
Abstract
We propose a new deep residual network for Automatic Modulation Classification, OPResNet-18. It achieves state-of-the-art accuracy on the RadioML 2016.10a data set. We train the proposed model and other state-of-the-art networks with augmented data by adding a Carrier Frequency Offset (CFO). We find that the previously proposed IQNet-3 is robust to CFO. We demonstrate that this robustness allows the performance of IQNet-3 to be further improved through data augmentation in contrast to existing neural networks that cannot handle CFO. Finally, we provide evidence that standard data pre-processing techniques for time-domain data that reportedly perform well in many domains do not perform as well as a simple alternative, the outer product, in the IQ domain.
Metrics
Details
- Title
- Radio Modulation Classification Using Deep Residual Neural Networks
- Creators
- Adeeb Abbas - Drexel UniversityVasil Pano - Drexel UniversityGeoffrey Mainland - Drexel UniversityKapil Dandekar - Drexel University
- Publication Details
- MILCOM 2022 - 2022 IEEE Military Communications Conference (MILCOM), v 2022-, pp 311-317
- Publisher
- IEEE
- Grant note
- CCF-1717088,CNS-1816387,CNS-1730140 / National Science Foundation (10.13039/100000001)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; Computer Science (Computing)
- Web of Science ID
- WOS:000968304600050
- Scopus ID
- 2-s2.0-85147330595
- Other Identifier
- 991021868089004721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Information Systems
- Engineering, Electrical & Electronic
- Telecommunications