RF-Fingerprint-BT-IoT: Real-world Frequency Hopping Bluetooth dataset from IoT devices for RF fingerprinting

Citation Author(s):
Anu
Jagannath
Marconi-Rosenblatt AI/ML Innovation Lab, ANDRO Computational Solutions, LLC.
Jithin
Jagannath
Marconi-Rosenblatt AI/ML Innovation Lab, ANDRO Computational Solutions, LLC.
Submitted by:
Anu Jagannath
Last updated:
DOI:
10.21227/364j-6j73
Data Format:
Link to Paper:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

A real-world radio frequency (RF) fingerprinting dataset for commercial off-the-shelf (COTS) Bluetooth emitters under challenging testbed setups is presented in this dataset. The dataset includes emissions from 10 COTS IoT emitters (2 laptops and 8 commercial chips) that are captured with a National Instruments Ettus USRP X300 radio outfitted with a UBX160 daughterboard and a VERT2450 antenna. The receiver is tuned to record a 2 MHz bandwidth of the spectrum centered at the 2.414 GHz frequency. This is a first-of-its-kind dataset for fingerprinting Bluetooth emitters under challenging and diverse indoor laboratory setups. The dataset is split into two:  Day1 and Day2 each of which is recorded in a different time frame, location, and testbed setup to enable critical generalization test of the trained deep learning (DL) model. The authors suggest training the DL model with the Day1 dataset which is a simpler setup with recordings under varied Bluetooth signal strengths followed by evaluating the generalization capability of the model with Day2 dataset which is a challenging and vastly different setup compared to Day1. This evaluation will validate the real-world deployment capability of the trained DL model. The dataset follows the SigMF specifications with certain field extensions to facilitate the fingerprinting application and include additional metadata fields. Each capture is of length 40 Mega Samples (MS) and is associated with a JSON metadata file.   

Instructions: 

The dataset contains two separate Bluetooth datasets collected under different time frames, locations, and testbed setups.

  1. Day1BT.tar.gz: Collected under line-of-sight conditions at varying distances per emitter as indicated in the associated JSON metadata file of each capture. The transmitter-receiver separation ranges from 1.6 ft to 9.8 ft in steps of 0.8 ft.
  2. Day2BT.tar.gz: Collected under a challenging and rich multipath scattering scenario with maximum separation between the emitter and receiver being 24.2 ft. Each emitter is placed in the corners of the indoor laboratory as indicated by the lab layout picture with the receiver placed stationary at the center of the laboratory.

Each dataset contains a binary capture file (.dat) and an associated JSON metadata file (.meta.json). The capture file contains complex64 inphase-quadrature (IQ) samples and the JSON contains the metadata which characterizes the data capture environment.

How to cite this dataset? Please cite the original paper.

Bibtex:

@article{Jagannath2022, author = "Anu Jagannath and Jithin Jagannath", title = "{Embedding-Assisted Attentional Deep Learning for Real-World RF Fingerprinting of Bluetooth}", year = "2022", month = "9", url = "https://www.techrxiv.org/articles/preprint/Embedding-Assisted_Attentiona...", doi = "10.36227/techrxiv.20767315.v1" } 

Plain text:

A.Jagannath and J.Jagannath, "Embedding-Assisted Attentional Deep Learning for Real-World RF Fingerprinting of Bluetooth" TechRxiv. Preprint 2022. https://doi.org/10.36227/techrxiv.20767315.v1