Specific Emitter Identification based on CNN and Transformer
Authors:
- 8 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 571-575
Abstract
Specific emitter identification(SEI) plays an increasingly crucial and potential role in both military and civilian scenarios. It refers to a process to discriminate individual emitters from each other by analyzing extracted characteristics from given radio signals. In this paper, we present a novel radiation source identification method named CNNFormer based on a hybrid architecture of Convolutional Neural Network and Transformer, harnessing the strengths of both architectures to enhance feature extraction and sequence modeling. We demonstrate the effectiveness of our approach on simulation datasets, achieving state-of-the-art accuracy in emitter identification. We showcase outstanding performance of our method on simulation datasets, achieving 98.29% three-class identification accuracy the emitter dataset with three devices and 97.60% ten-class identification accuracy on an RF fingerprint dataset with ten XSPR transmitters. Furthermore, our model allows for insight into the key features contributing to identification. This work contributes to enhancing the security and reliability of wireless communication systems.Keywords
This publication has 20 references indexed in Scilit:
- Complex Convolutional Neural Network for Signal Representation and Its Application to Radar Emitter RecognitionIEEE Communications Letters, 2023
- Specific Emitter Identification via Contrastive LearningIEEE Communications Letters, 2023
- Few-Shot Specific Emitter Identification via Deep Metric Ensemble LearningIEEE Internet of Things Journal, 2022
- Specific Emitter Identification Based on Complex Fourier Neural NetworkIEEE Communications Letters, 2021
- A Transformer Based Approach for Open Set Specific Emitter Identification2021
- Online Non-Cooperative Radar Emitter Classification From Evolving and Imbalanced Pulse StreamsIEEE Sensors Journal, 2020
- A Robust RF Fingerprinting Approach Using Multisampling Convolutional Neural NetworkIEEE Internet of Things Journal, 2019
- Deep Learning Based Transmitter Identification using Power Amplifier Nonlinearity2019
- Specific Emitter Identification via Convolutional Neural NetworksIEEE Communications Letters, 2018
- Deep Residual Learning for Image Recognition2016