Specific Emitter Identification Using Convolutional Neural Network-Based IQ Imbalance Estimators

Abstract

Specific Emitter Identification is the association of a received signal to a unique emitter, and is made possible by the naturally occurring and unintentional characteristics an emitter imparts onto each transmission, known as its radio frequency fingerprint. This work presents an approach for identifying emitters using Convolutional Neural Networks to estimate the IQ imbalance parameters of each emitter, using only raw IQ data as input. Because an emitter's IQ imbalance parameters will not change as it changes modulation schemes, the proposed approach has the ability to track emitters, even as they change modulation scheme. The performance of the developed approach is evaluated using simulated quadrature amplitude modulation and phaseshift keying signals, and the impact of signal-to-noise ratio, imbalance value, and modulation scheme are considered. Further, the developed approach is shown to outperform a comparable feature-based approach, while making fewer assumptions and using less data.

A Survey on Beyond 5G Network With the Advent of 6G: Architecture and Emerging Technologies

“…Estimation of amplitude IQ imbalance ranged from -7 to 7dB is possible with 1dB estimation error. Phase IQ imbalance estimation ranges from -80° to 80° with 4° of estimation error [40] Specific Emitter identification By using the received raw IQ imbalance information, the emitter is identified by using a conventional neural network.…”

Improved algorithm for de‐interleaving radar signals with overlapping features in the dynamically varying electromagnetic environment

“…Dudczyk and Wnuk [1] proposed the SEI method based on distinctive radiated emission features and built a database to detect target radar emission. On this basis, algorithms based on intra‐pulse features such as fractal features [2], pulse envelope [3], radio frequency (RF) fingerprint [4], spectral features [5] etc. are widely used in the SEI process and achieved good recognition effects.…”

Convolutional neural network applied to specific emitter identification based on pulse waveform images

“…The intercepted signal itself and its transformed domain data are also the study objects in the process of SEI. In [23–25], the received raw in‐phase and quadrature (IQ) data streams combined with convolutional neural network (CNN) are applied to SEI. A patent gets the frequency domain features to identify the individual in [26], and more features can be found in [27] which disclose an apparatus for identifying a specific emitter in the presence of noise and interference.…”

“…Meanwhile, CNN is widely applied in the image identification field for its strong capability on subtle feature extraction and classification, such as the existing LeNet‐5, AlexNet, ZFNet, VGG‐16, GoogleNet and ResNet [40–43]. In [23, 25, 41], CNN has been applied in SEI work with different input features, which indicates the effectiveness of the ability to extract features. Hence, we design a CNN architecture and combine it with the PWI feature in the SEI work.…”