Deep Learning-Based Automatic Modulation Recognition in OTFS and OFDM systems
Jinggan Zhou, Xuewen Liao, Zhenzhen Gao
Abstract
Automatic modulation recognition (AMR) is one of the most essential techniques in non-cooperative orthogonal time frequency space (OTFS) and orthogonal frequency division multiplexing (OFDM) communication systems. Since coexistence of OTFS and OFDM is a potential and practical solution in the future wireless communication scenarios, classification of the OTFS scheme and the OFDM scheme will be a challenging and meaningful task. In this paper, we propose a deep learning-based method, including multi-layer convolution neural networks (CNNs) and an attention-based residual Squeeze-and-Excitation Module (SE), to extract effective characteristics of OTFS and OFDM signals in multi-path Doppler spread fading channel. To obtain comparable and convincing results, the design of OTFS transmitters is on the basis of OFDM systems and contains six different sub-carrier modulation modes (BPSK, QPSK, 8PSK, 16QAM, 64QAM and 256QAM). Meanwhile, data structures of the signals are all well-deigned for fair comparisons. In addition, datasets include five modulation modes (OTFS, OFDM and other commonly-used modulation modes) and different Doppler spread values to verify our proposed method. The simulations show that our proposed SE-CNN model performs better than other baseline methods. Moreover, extensive experiment results demonstrate the robustness of our proposed method.