Baseline Deep Learning Detectors for Radar Detection in the 3.5 GHz CBRS Band

Description

This project aims to create a comprehensive framework for generating radio frequency (RF) datasets, designing deep learning (DL) detectors, and evaluating their detection performance using both simulated and experimental test data. The proposed tools and techniques are developed in the context of dynamic spectrum use for the 3.5 GHz Citizens Broadband Radio Service (CBRS), but they can be utilized and expanded for standardization of machine learned spectrum awareness technologies and methods. This dataset consists of pre-trained DL models for radar detection in the CBRS band using simulated waveforms. The code for creating and using these models is available at https://github.com/usnistgov/BaselineDeepLearningRadarDetectors.

Resources

Name Format Description Link
47 https://data.nist.gov/od/ds/mds2-2380/ResNet50-SpectroMaxHold_model_V1.h5.sha256
47 https://data.nist.gov/od/ds/mds2-2380/CNN5-Spectro_model_V1.h5.sha256
47 https://data.nist.gov/od/ds/mds2-2380/CNN4-Spectro_model_V1.h5.sha256
47 https://data.nist.gov/od/ds/mds2-2380/CNN3-SpectroMaxHold_model_V1.h5.sha256
5 Spectrogram max-hold pretrained model (MobileNetV2) https://data.nist.gov/od/ds/mds2-2380/MobileNetV2-SpectroMaxHold_model_V1.h5
5 Spectrogram pretrained model (CNN5) https://data.nist.gov/od/ds/mds2-2380/CNN5-Spectro_model_V1.h5
5 Spectrogram pretrained model (CNN4) https://data.nist.gov/od/ds/mds2-2380/CNN4-Spectro_model_V1.h5
5 Spectrogram max-hold pretrained model (CNN3) https://data.nist.gov/od/ds/mds2-2380/CNN3-SpectroMaxHold_model_V1.h5
0 https://doi.org/10.18434/mds2-2380
47 https://data.nist.gov/od/ds/mds2-2380/MobileNetV2-SpectroMaxHold_model_V1.h5.sha256
5 Spectrogram max-hold pretrained model (ResNet50) https://data.nist.gov/od/ds/mds2-2380/ResNet50-SpectroMaxHold_model_V1.h5
47 https://data.nist.gov/od/ds/mds2-2380/Xception-SpectroMaxHold_model_V1.h5.sha256
5 Spectrogram max-hold pretrained model (Xception) https://data.nist.gov/od/ds/mds2-2380/Xception-SpectroMaxHold_model_V1.h5

Tags

  • 3-5-ghz-cbrs-radar-detection-deep-learning-radio-frequency-signals-spectrum-mlsa

Topics

Categories