With the increasing complexity of the electromagnetic environment, the recognition of electromagnetic signals faces significant challenges. Traditional methods of electromagnetic signal recognition rely on manually designed features, which are insufficient for handling complex signal classification tasks effectively. This paper proposes a novel approach that combines Convolutional Neural Networks (CNN) and Transformer models. The method involves constructing a signal transmission model to generate signals of four modulation types: QAM64, QAM16, 8PSK, and CPFSK. These signals are then demodulated and filtered to obtain I/Q signals, which are converted into two-dimensional grayscale images. A signal recognition model is employed for feature extraction and classification, achieving an accuracy of approximately 90% within a certain Signal-to-Noise Ratio (SNR) range.

Zhe Wang. Signal Recognition Model Based on Transformer. Academic Journal of Engineering and Technology Science (2024) Vol. 7, Issue 4: 187-195. https://doi.org/10.25236/AJETS.2024.070426.

[1] Cui M, Wu Z, Lu Y, et al. Near-field MIMO communications for 6G: Fundamentals, challenges, potentials, and future directions [J]. IEEE Communications Magazine, 2022, 61(1): 40-46.

[2] Li Q, Yang S, Chen H. Performance Evaluation System Based on Multi-Indicators for Signal Recognition [J]. IEEE Access, 2022, 11: 2820-2830.

[3] Li F Z, Liu Y, Wu P X, et al. A survey on recent advances in meta-learning[J]. Chinese Journal of Computers, 2021, 44(2): 422-446.

[4] Huang J, Wu B, Li P, et al. Few-shot learning for radar emitter signal recognition based on improved prototypical network[J]. Remote Sensing, 2022, 14(7): 1681.

[5] Shao P, Chen Z. Radio frequency fingerprint feature extraction based on I/Q data distribution features[C]//2022 Photonics & Electromagnetics Research Symposium (PIERS). IEEE, 2022: 161-165.

[6] Wang H, Li J, Guo L, et al. Fractal complexity-based feature extraction algorithm of communication signals [J]. Fractals, 2017, 25(04): 1740008.

[7] Xi H C, Li B, Mai W H, et al. Feature extraction for evaluating the complexity of electromagnetic environment based on adaptive multiscale morphological gradient and nonnegative matrix factorization [J]. Journal of Electrical and Computer Engineering, 2022, 2022.

[8] Yang B, Hong T, Ma L, et al. A Recognition Algorithm for Complex Spatial Electromagnetic Signal Perception Based on KNN[C]//2022 International Conference on Microwave and Millimeter Wave Technology (ICMMT). IEEE, 2022: 1-3.

[9] Wu J, Wu B, Niu H, et al. A Novel Support Vector Machine Based Radar Individual Recognition Algorithm Under Inconsistent Noise Condition[C]//IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2020: 2847-2850.

[10] Chirov D S, Kandaurova E O. Synthesis of informative features for recognition of the type of pulse repetition interval modulation of signals from radars[C]//2019 Systems of Signals Generating and Processing in the Field of on Board Communications. IEEE, 2019: 1-6.

[11] Malekian A, Chitsaz N. Concepts, procedures, and applications of artificial neural network models in streamflow forecasting[M]//Advances in streamflow forecasting. Elsevier, 2021: 115-147.

[12] Taherdoost H. Enhancing social media platforms with machine learning algorithms and neural networks [J]. Algorithms, 2023, 16(6): 271.

[13] Chen Z, Shi Y, Wang Y, et al. Unlocking signal processing with image detection: a frequency hopping detection scheme for complex EMI environments using STFT and CenterNet[J]. IEEE Access, 2023.

[14] Tu Y, Lin Y, Hou C, et al. Complex-valued networks for automatic modulation classification[J]. IEEE Transactions on Vehicular Technology, 2020, 69(9): 10085-10089.

[15] Hou C, Fu D, Hua L, et al. The recognition of multi-components signals based on semantic segmentation [J]. Wireless Networks, 2023, 29(1): 147-160.

[16] Liu Z, He T, Wu T, et al. Open‐set recognition of LPI radar signals based on a slightly convolutional neural network and support vector data description[J]. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 2024, 37(2): e3213.

[17] Tao Guanhong, Liao Kaisheng, Zhou Lin. A New Method for Electromagnetic Signal Modeling and Modulation Recognition Based on Deep Learning[J]. Electronic Information Countermeasure Technology, 2019, 34(5): 10-15.

[18] Ashish V. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30: I.