Joint 1D and 2D Neural Networks for Automatic Modulation Recognition
Abstract
The digital communication and radar community has recently manifested more interest in using data-driven approaches for tasks such as modulation recognition, channel estimation and distortion correction. In this research we seek to apply an object detector for parameter estimation to perform waveform separation in the time and frequency domain prior to classification. This enables the full automation of detecting and classifying simultaneously occurring waveforms. We leverage a lD ResNet implemented by O'Shea et al. in [1] and the YOLO v3 object detector designed by Redmon et al. in [2]. We conducted an in depth study of the performance of these architectures and integrated the models to perform joint detection and classification. To our knowledge, the present research is the first to study and successfully combine a lD ResNet classifier and Yolo v3 object detector to fully automate the process of AMR for parameter estimation, pulse extraction and waveform classification for non-cooperative scenarios. The overall performance of the joint detector/ classifier is 90 at 10 dB signal to noise ratio for 24 digital and analog modulations.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 2020
- Accession Number
- AD1113904
Entities
People
- Luis M. Rosario-morel
Organizations
- Air Force Institute of Technology