Adaptive Decomposition and Extraction Network of Individual Fingerprint Features for Specific Emitter Identification

Overview

This project implemented SEI-ADE for Specific Emitter Identification and tested on multiple types of electromagnetic datasets.

Training datasets and test datasets

Relevant training data sets and test data sets will be released in the near future.

The dataset for the demonstration is placed on Baidu's website: https://pan.baidu.com/s/1qXTtAGy3jV1KjgqnuTfbBA?pwd=zjnc

Example Output

• The Mark map, Waveform and spectrum of 2-channel signals decomposed by DNet


Best Model

*Our trained model is placed on Baidu's website: https://pan.baidu.com/s/1DxwBkp8oNU-EzR_zrLRrzg?pwd=zjnc

This repository was developed and tested in PyTorch 1.5.

How to run

• Intall required dependencies as listed in environment.yml
• Run [run_train_spk.sh] for training and [run_test.sh] for testing