Deep Learning for Over-the-Air Non-Orthogonal Signal Classification

Non-cooperative communications, where a receiver can automatically distinguish and classify transmitted signal formats prior to detection, are desirable for low-cost and low-latency systems. This work focuses on the deep learning enabled blind classification of multi-carrier signals covering their orthogonal and non-orthogonal varieties. We define Type-I signals with large feature diversity and Type-II signals with strong feature similarity. We evaluate time-domain and frequency-domain convolutional neural network (CNN) models with wireless channel/hardware impairments. Experimental systems are designed and tested, using software defined radio (SDR) devices, operated for different signal formats in line-of-sight and non-line-of-sight communication link scenarios. Testing, using four different time-domain CNN models, showed the pre-trained CNN models to have limited efficiency and utility due to the mismatch between the analytical/simulation and practical/real-world environments. Transfer learning, which is an approach to fine-tune learnt signal features, is applied based on measured over-the-air time-domain signal samples. Experimental results indicate that transfer learning based CNN can efficiently distinguish different signal formats for Type-I in both line-of-sight and non-line-of-sight scenarios relative to the non-transfer-learning approaches. Type-II signals are not identified correctly in the experiment even with the transfer learning assistance leading to potential applications in secure communications.