Neural nets are a powerful method for the classification of radio signals in the electromagnetic spectrum. These neural nets are often trained with synthetically generated data due to the lack of diverse and plentiful real RF data. However, it is often unclear how neural nets trained on synthetic data perform in real-world applications. This paper investigates the impact of different RF signal impairments (such as phase, frequency and sample rate offsets, receiver filters, noise and channel models) modeled in synthetic training data with respect to the real-world performance. For that purpose, this paper trains neural nets with various synthetic training datasets with different signal impairments. After training, the neural nets are evaluated against real-world RF data collected by a software defined radio receiver in the field. This approach reveals which modeled signal impairments should be included in carefully designed synthetic datasets. The investigated showcase example can classify RF signals into one of 20 different radio signal types from the shortwave bands. It achieves an accuracy of up to 95 % in real-world operation by using carefully designed synthetic training data only.
In digital signal processing time-frequency transforms are used to analyze time-varying signals with respect to their spectral contents over time. Apart from the commonly used short-time Fourier transform, other methods exist in literature, such as the Wavelet, Stockwell or Wigner-Ville transform. Consequently, engineers working on digital signal processing tasks are often faced with the question which transform is appropriate for a specific application. To address this question, this paper first briefly introduces the different transforms. Then it compares them with respect to the achievable resolution in time and frequency and possible artifacts. Finally, the paper contains a gallery of time-frequency representations of numerous signals from different fields of applications to allow for visual comparison.
This paper investigates deep neural networks for radio signal classification. Instead of performing modulation recognition and combining it with further analysis methods, the classifier operates directly on the IQ data of the signals and outputs the transmission mode. A data set of radio signals of 18 different modes, that commonly occur in the HF radio band, is presented and used as a showcase example. The data set considers HF channel properties and is used to train four different deep neural network architectures. The results of the best networks show an excellent accuracy of up to 98%.