WebApp-Based Digital Modulation Waveform Generator for Automatic Modulation Classification in Wireless Communication Systems

To alleviate the issue of data scarcity in the context of communication systems, a viable solution is the capacity to generate realistic wireless signal constellation diagrams with Generative Adversarial Networks (GANs). While it was possible to train stable GANs for multi-class (20 classes) image data for some time, the situation where it is launched with strict calculation resources such as only using the CPU and High Performance Storage(HPS) in a small amount, and is trained for a large number of classes (260 classes) has been difficult until recently. In this paper, we propose two lightweight GANs, an improved vanilla generator-dominant GAN (G:D ratio 3.28) and an improved vanilla GAN (G:D ratio 1.43), along with a novel hybrid GAN model with the incorporation of DCGAN components and class conditioning: a Conditional Least Squares GAN (LSGAN Hybrid, G:D ratio 2.0) is made. All models were trained on 52,000 constellation images with four successive epochs (5, 10, 15, 20) using a standard Intel Core i7 CPU. The LSGAN Hybrid achieved outstanding training stability with monotonically decreasing loss throughout training, and with the smallest epoch-to-epoch correlation variance (σ = 0.0073) with only 720K parameters, which is more than 55% reduction from its vanilla counterpart. All architectures had 100% discriminative accuracy (ACC) when tested against the test dataset; the vanilla models, however, were suffering from serious discriminator dominance, with the ratio reaching up to 18.57 for the 10th epoch, which reflects the occurrence of the gradient becoming saturated. SGD statistical distribution analyses (t-tests) showed that the LSGAN was the only algorithm to make significant distributional changes at subsequent epochs (p < 0.05 after 15 epochs and 20 epochs of generation), which validates its continuous improvement capacity for generation. These results paved the way for parameter-efficient constellation generation algorithm on a controlled constellation in an ideal back nook for LSGAN Hybrid for strict constellation generation requirements, especially under hardware constraints scenarios.

Communication Systems, Constellation, Generative Adversarial Networks

1. Akpinar, M. H., Sengur, A., Salvi, M., Seoni, S., Faust, O., Mir, H., ... & Acharya, U. R. (2024). Synthetic data generation via generative adversarial networks in healthcare: a systematic review of image-and signal-based studies. IEEE Open Journal of Engineering in Medicine and Biology, 6, 183-192. [Google Scholar] [Crossref]

2. Alnaseri, O., Alzubaidi, L., Himeur, Y., Ala’Anzy, M. A., Timmermann, J., Gismalla, M. S., ... & Mansoor, W. (2026). A review on deep learning autoencoder in the design of next-generation communication systems. IEEE Open Journal of the Communications Society. [Google Scholar] [Crossref]

3. Arjovsky, M., & Bottou, L. (2017). Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862. [Google Scholar] [Crossref]

4. Doha, S. R., & Abdelhadi, A. (2025). Deep learning in wireless communication receivers: A survey. IEEE Access. [Google Scholar] [Crossref]

5. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of wasserstein gans. Advances in neural information processing systems, 30. [Google Scholar] [Crossref]

6. Hu, C., Zhang, R., Li, B., Jiang, X., Zhao, N., Di Renzo, M., ... & Karagiannidis, G. K. (2025). Generative AI-Empowered Secure Communications in Space–Air–Ground Integrated Networks: A Survey and Tutorial. IEEE Communications Surveys & Tutorials, 28, 4156-4194. [Google Scholar] [Crossref]

7. Little, C., Elliot, M., Allmendinger, R., & Samani, S. S. (2021). Generative adversarial networks for synthetic data generation: a comparative study. arXiv preprint arXiv:2112.01925. [Google Scholar] [Crossref]

8. Liu, Y. (2024). The signal generator: A critical analysis of its basic principles, applications, and development. Applied and Computational Engineering, 42, 27-33. [Google Scholar] [Crossref]

9. Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017). A survey on mobile edge computing: The communication perspective. IEEE communications surveys & tutorials, 19(4), 2322-2358. [Google Scholar] [Crossref]

10. Metz, L., Poole, B., Pfau, D., & Sohl-Dickstein, J. (2016). Unrolled generative adversarial networks. arXiv preprint arXiv:1611.02163. [Google Scholar] [Crossref]

11. Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957. [Google Scholar] [Crossref]

12. Ndubuisi, C. N., Diyoke, G., & Oko, P. (2024). Design and construction of a signal generator. World Sci. News, 187, 93-111. [Google Scholar] [Crossref]

13. Ramzan, F., Sartori, C., Consoli, S., & Reforgiato Recupero, D. (2024). Generative adversarial networks for synthetic data generation in finance: Evaluating statistical similarities and quality assessment. Ai, 5(2), 667-685. [Google Scholar] [Crossref]

14. Sang, H., Zhang, L., Chen, T., Guo, W., & Zhang, Z. (2026). Onboard Deployment of Remote Sensing Foundation Models: A Comprehensive Review of Architecture, Optimization, and Hardware. Remote Sensing, 18(2), 298. [Google Scholar] [Crossref]

15. Xu, H., Liang, Y., Xie, R., & Kong, Y. (2026). The Deep Learning Evolution in Wireless Physical Layer Communications: Applications, Challenges, and Evolutionary Directions. Sensors, 26(11), 3609. [Google Scholar] [Crossref]