RT-DETR-Based Signal Modulation Recognition with AIFI-Dattention

Minghao Cao; Peng Chu; Hongjie Guo; Wei Xing

doi:10.54097/bxrhhn78

Authors

Minghao Cao
Peng Chu
Hongjie Guo
Wei Xing

DOI:

https://doi.org/10.54097/bxrhhn78

Keywords:

Feature extraction networks. Signal modulation recognition. Deep learning.

Abstract

In response to the issues of high computational complexity, low accuracy, and cumbersome manual feature extraction steps in traditional machine learning algorithms for communication signal modulation recognition, a communication signal modulation recognition model based on deep learning is proposed. This model can directly recognize the category of communication signals after sampling and is characterized by high recognition accuracy, strong generalization capability, good noise resistance, and a simplified processing flow. It effectively addresses the limitations of traditional algorithms in automatic feature extraction. Through extensive experiments and accurate analysis of communication signal features, an end-to-end model based on the Transformer RT-Detr model is adopted, achieving high recognition accuracy.

Downloads

Download data is not yet available.

References

[1] Maganioti, A.E., Chrissanthi, H.D., Charalabos, P.C., Andreas, R.D., George, P.N. and Christos, C.N. Cointegration of Event-Related Potential (ERP) Signals in Experiments with Different Electromagnetic Field (EMF) Conditions. Health, (2010) 2, 400-406.

[2] Bootorabi, F., Haapasalo, J., Smith, E., Haapasalo, H. and Parkkila, S. Carbonic Anhydrase VII—A Potential Prognostic Marker in Gliomas. Health, (2011) 3, 6-12.

[3] Shafik, R. A., Rahman, S., & Supangkat, S. H. Automatic Modulation Classification for Cognitive Radios using Cyclostationary Features. IEEE Communications Surveys & Tutorials, (2012) 14(1), 105-117.

[4] O'Shea, T. J., & West, N. Radio Machine Learning Dataset Generation with GNU Radio. Proceedings of the GNU Radio Conference, (2017) 1(1), 1-9.

[5] Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. End-to-End Object Detection with Transformers. Proceedings of the European Conference on Computer Vision, (2020) 213-229.

[6] Hu, J., Shen, L., & Sun, G. Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2018) 7132-7141.

[7] Amini, A., Shirani-Mehr, H., & Karbasi, A. Digital Modulation Classification: A Deep Learning Approach. IEEE Transactions on Communications, (2017) 65(11), 4658-4668.

[8] He, K., Zhang, X., Ren, S., & Sun, J. Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016) 770-778.

[9] Kingma, D. P., & Ba, J. Adam: A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations(2015) (ICLR).

[10] Powers, D. M. W. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation. Journal of Machine Learning Technologies, (2011) 2(1), 37-63.

[11] Hochreiter, S., & Schmidhuber, J. Long Short-Term Memory. Neural Computation, (1997) 9(8), 1735-1780.

[12] LeCun, Y., Bottou, L., Orr, G. B., & Müller, K.-R. (2012). Efficient BackProp. In G. Montavon, G. B. Orr, & K.-R. Müller (Eds.), Neural Networks: Tricks of the Trade (pp. 9-48). Springer.

[13] Shorten, C., & Khoshgoftaar, T. M. A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(60), (2019). 1-48.

[14] Prechelt, L. (1998). Early Stopping - But When? In G. B. Orr & K.-R. Müller (Eds.), Neural Networks: Tricks of the Trade (pp. 55-69). Springer.

[15] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., et al. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations (ICLR).

[16] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15(1), (2014). 1929-1958.