Clustering Learned CNN Features from Raw I/Q Data for Emitter Identification

Abstract

Specific Emitter Identification (SEI) is the act of matching a received signal to an emitter using a database of radio frequency (RF) features belonging to known transmitters. SEI systems are of vital importance to the military for applications such as early warning systems, emitter tracking, and emitter location, and, more recently, have been used in cognitive radio systems to enforce Dynamic Spectrum Access (DSA) rules [1], [2]. This work investigates using Convolutional Neural Networks (CNNs) as feature learners and extractors, paired with the clustering algorithm DBSCAN, to perform SEI. The process through which emitter-specific features are extracted from raw I/Q data streams is described in detail, including the CNN architecture, design, and training. Extensive performance analysis demonstrates the effectiveness of the proposed approach in identifying emitters, and shows that features extracted from CNNs can be used to differentiate between devices unseen in training.