RF Fingerprinting for Contraband Wireless Devices Identification, Detection and Tracking in Correctional Facilities, Starkville, Mississippi, 2020-2022 (ICPSR 38650)
Version Date: Jul 13, 2023 View help for published
Principal Investigator(s): View help for Principal Investigator(s)
Bo Tang, Mississippi State University;
John E. Ball, Mississippi State University;
Maxwell Young, Mississippi State University
https://doi.org/10.3886/ICPSR38650.v1
Version V1
Summary View help for Summary
The growing use of contraband wireless devices, particularly cell phones, smuggled in correctional facilities, is a significant problem across the country. Inmates behind bars may use these devices to organize gang activities, run drug operations, and even plan escapes, which may threaten the safety and welfare of other inmates, prison employees and the general public. To combat the use of contraband cell phones, some radio-based technologies have been investigated, which primarily fall into the following three categories:
- radio jamming systems which disrupt the communication link between the wireless device and the transceiver outside of the prison by continuously transmitting on the same radio frequencies as the contraband wireless device, and thus make the device unusable behind bars;
- managed access systems (MAS) which build a private micro-cellular network over the whole facility in which all radio transmissions to carrier networks, e.g., calls or messages originating from inside or outside prisons, are captured, and only those authorized transmissions from and/or to a "white list" of preregistered wireless devices are allowed; and
- passive detection systems which identify and localize various sources of unapproved wireless transmissions from prisons.
It has been known that a jamming system may interfere with authorized calls including public safety communications (e.g., 9-1-1 calls), particularly when multiple frequency bands are involved, and a MAS is usually prohibitively expensive in its installation and operation due to the needs of covering many different commercial networks and frequency bands with an optimized footprint. In contrast, the detection system offers a passive solution in that detection systems do not transmit any radio signals and thus do not interfere with other transmissions. Therefore, the overall objective of this project is to develop an effective and low-cost contraband interdiction system (CIS) for identifying, localizing, and tracking unauthorized wireless devices such as cell phones and WiFi devices in correctional facilities, through the use and development of advanced machine learning algorithms for fingerprinting radio frequency (RF) signals originating from an unauthorized wireless device.
Citation View help for Citation
Export Citation:
Funding View help for Funding
Subject Terms View help for Subject Terms
Geographic Coverage View help for Geographic Coverage
Smallest Geographic Unit View help for Smallest Geographic Unit
None
Distributor(s) View help for Distributor(s)
Study Purpose View help for Study Purpose
The overall objective of this project is to develop an effective and low-cost contraband interdiction system (CIS) for identifying, localizing, and tracking unauthorized wireless devices such as cell phones and WiFi devices in correctional facilities, through the use and development of advanced machine learning algorithms for fingerprinting radio frequency (RF) signals originating from an unauthorized wireless device.
Study Design View help for Study Design
The overview of the proposed contraband wireless device detection system consists of hardware and software components. The hardware component is a receiver with multiple antennas, each of which receives the wireless signal at different locations. The received wireless signals carry unique characteristics of the device, known as device fingerprints and unique information (e.g., arrival strength and phase angle) of their propagation paths, known as location fingerprints. The software component takes the received multi-channel signals as input and applies RF signal analysis approaches including mathematical models and machine learning algorithms to differentiate devices and locations.
To achieve the project goals and objectives, the study team developed and implemented the following three types of methods: device fingerprinting, location fingerprinting, and content summarization. For further technical details for each method please refer to the related publications.
Time Method View help for Time Method
Universe View help for Universe
Lab-controlled cellphones that were configured in LTE or WiFi modes.
Unit(s) of Observation View help for Unit(s) of Observation
Data Type(s) View help for Data Type(s)
Description of Variables View help for Description of Variables
The device fingerprinting dataset (DS1) include 3,668 data packets (cases) from 10 wireless devices. Each packet includes the device ID and its first 400 IQ samples (401 total variables). Each IQ sample is a complex value, representing the I channel and Q channel measurements.
The device localization dataset (DS2) includes 3,120,000 data samples (cases) from six rooms from a building at Mississippi State University. Each sample contains the MAC address (recoded) of the cellphone, transmitter name, location (room), purpose (training or testing), packet ID, angle of arrival of the packet, and the complex IQ samples (imaginary and real) from four antennas (15 total variables).
Response Rates View help for Response Rates
Not applicable
Presence of Common Scales View help for Presence of Common Scales
None
HideOriginal Release Date View help for Original Release Date
2023-07-13
Version History View help for Version History
2023-07-13 ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:
- Checked for undocumented or out-of-range codes.
Notes
The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.
This dataset is maintained and distributed by the National Archive of Criminal Justice Data (NACJD), the criminal justice archive within ICPSR. NACJD is primarily sponsored by three agencies within the U.S. Department of Justice: the Bureau of Justice Statistics, the National Institute of Justice, and the Office of Juvenile Justice and Delinquency Prevention.