Date of Award
Doctor of Philosophy (PhD)
Department of Electrical and Computer Engineering
Michael A. Temple, PhD.
This dissertation introduces a GRLVQI classifier into an RF-DNA fingerprinting process and demonstrates applicability for device classification and ID verification. Unlike MDA/ML processing, GRLVQI provides a measure of feature relevance that enables Dimensional Reduction Analysis (DRA) to enhance the experimental-to-operational transition potential of RF-DNA fingerprinting. Using 2D Gabor Transform RF-DNA fingerprints extracted from experimentally collected OFDM-based 802.16 WiMAX and 802.11 WiFi device emissions, average GRLVQI classification accuracy of %C greater than or equal to 90% is achieved using full and reduced dimensional feature sets at SNR greater than or equal to 10.0 dB and SNR greater than or equal to 12.0 dB, respectively. Performance with DRA approximately 90% reduced feature sets included %C greater than or equal to 90% for 1) WiMAX features at SNR greater than or equal to 12.0 dB and 2) WiFi features at SNR greater than or equal to 13.0 dB. For device ID verification with DRA approximately 90% feature sets, GRLVQI enabled: 1) 100% ID verification of authorized WiMAX devices and 97% detection of spoofing attacks by rogue devices at SNR=18.0 dB, and 2) 100% ID verification of authorized WiFi devices at SNR=15.0 dB.
DTIC Accession Number
Reising, Donald R., "Exploitation of RF-DNA for Device Classification and Verification Using GRLVQI Processing" (2012). Theses and Dissertations. 899.