Authors : Muhammad Afzal Shah; Yang Tiemei; Muhammad Suleman Soomro; Kashif Bashir

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/5n6d8ffc

Scribd : https://tinyurl.com/3r54ncct

DOI : https://doi.org/10.38124/ijisrt/26jun260

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The proposed Uncertainty-Aware Multi-Modal Semantic Communication (UAMM-SC) architecture serves as a fundamental concept in 6G communications and beyond, in which the goal shifts from accurate information transfer at the bit level to the conservation of meaningful information. The limitations in the current state-of-the-art semantic communication frameworks can be summarized as follows: (i) AWGN channel models ignoring fading, phase noise, and hardware imperfections; (ii) reliance on text representations in the form of class labels instead of rich semantics of the natural language; and (iii) fixed error handling techniques without adaptability to channel changes. This paper proposes an UAMM-SC architecture that enables end-to-end transmission of multimodal data over realistic fading channels using adaptive latent correction. Specifically, our contributions include: (1) a cross-attention based encoder to fuse multimodal semantics in a common latent space, with pretrained ViT and DistilBERT as backbone models; (2) a hardware-aware channel model, including Rayleigh fading, Doppler frequency shift, phase noise, and IQ imbalance, simulated using native PyTorch functions;(3) a semantic uncertainty quantification layer based on Monte Carlo Dropout, which triggers gradient-based latent correction adaptively if the predictive entropy is higher than an SNR-adaptive threshold; and (4) an experimental evaluation of the effectiveness of UAMM-SC on CIFAR-10, where we show semantic preservation across SNR ranges (0–20 dB) with a remarkable 99.7% bandwidth reduction compared with JPEG + LDPC transmission.

Keywords : Semantic Communication; Multi-Modal Learning; 6G Networks; Uncertainty Estimation; Adaptive Correction; Rayleigh Fading; Deep Learning, IoT.

References :

1. Z. Qin, X. Tao, J. Lu, W. Zhang, and G. Y. Li, "Semantic communications: Principles and challenges," arXiv preprint arXiv:2201.01389, 2022.
2. X. Luo, H.-H. Chen, and Q. Guo, "Semantic communications: Overview, open issues, and future research directions," IEEE Wireless Commun., vol. 29, no. 1, pp. 210–219, Feb. 2022.
3. E. C. Strinati, S. Barbarossa, J. L. Gonzalez-Jimenez, D. Kténas, N. Cassiau, L. Maret, and C. Dehos, "6G AI-native communication networks: Extensions and advances towards goal-oriented and semantic communications," arXiv preprint arXiv:2402.07573, 2024.
4. J. Park, S. Samarakoon, A. B. Sediq, M. Debbah, and M. Bennis, "Joint source-channel coding for channel-adaptive digital semantic communications," IEEE Trans. Cogn. Com- mun. Netw., vol. 10, no. 3, pp. 892–907, Jun. 2024.
5. E. Bourtsoulatze, D. B. Kurka, and D. Gündüz, "Deep joint source-channel coding for wireless image transmission," IEEE Trans. Cogn. Commun. Netw., vol. 5, no. 3, pp. 567– 579, Sep. 2019.
6. H. Xie, Z. Qin, G. Y. Li, and B.-H. Juang, "Deep learning enabled semantic communica- tion systems," IEEE Trans. Signal Process., vol. 69, pp. 2663–2675, 2021.
7. Z. Wang, J. Rao, and M. D. Renzo, "Deep learning for physical-layer 6G wireless tech- niques: Opportunities, challenges, and future directions," IEEE Wireless Commun., vol. 28, no. 1, pp. 144–151, Feb. 2021.
8. Y. Shao, Q. Cao, and D. Gündüz, "Uncertainty-aware deep learning for robust semantic communications," IEEE Trans. Veh. Technol., vol. 73, no. 2, pp. 2156–2169, Feb. 2024.
9. D. Wen, K.-J. Kim, and M. Pan, "Multi-modal semantic communication for autonomous driving," IEEE Internet Things J., vol. 11, no. 5, pp. 8234–8247, Mar. 2024.
10. F. A. Aoudia and J. Hoydis, "End-to-end learning of communications systems without a channel model," arXiv preprint arXiv:2106.04927, 2021.
11. P. Jiang, C.-K. Wen, S. Jin, and G. Y. Li, "Deep semantic communication for image trans- mission," IEEE Trans. Wireless Commun., vol. 22, no. 8, pp. 5389–5403, Aug. 2023.
12. A. Goldsmith, Wireless Communications. Cambridge University Press, 2021.
13. M. B. Mashhadi, Q. Yang, and D. Gündüz, "Deep learning-based joint source-channel coding for wireless image transmission," IEEE Open J. Commun. Soc., vol. 2, pp. 539– 553, 2021.
14. T. Fujihashi, T. Koike-Akino, S. Koyama, and P. V. Orlik, "DeepJSCC-based semantic communications with attention mechanisms," IEEE Commun. Lett., vol. 27, no. 4, pp. 1185–1189, Apr. 2023.
15. R. Shafin, L. Liu, V. Chandrasekhar, H. Chen, J. Reed, and J. C. Zhang, "Artificial intelligence-enabled 6G cellular networks: A preliminary study," IEEE Wireless Com- mun., vol. 27, no. 6, pp. 124–131, Dec. 2020.
16. Y. Jiao, X. Fang, and L. Hao, "Rayleigh fading channel estimation using deep learning for 6G communications," IEEE Trans. Commun., vol. 70, no. 9, pp. 6123–6136, Sep. 2022.
17. S. D. Liyanaarachchi, T. Riihonen, C. B. Papadias, and R. Wichman, "Optimized wave- forms for 6G communications with sensing: A hybrid design approach," IEEE Wireless Commun. Lett., vol. 10, no. 10, pp. 2215–2219, Oct. 2021.
18. W. Saad, M. Bennis, and M. Chen, "A vision of 6G wireless systems: Applications, trends, technologies, and open research problems," IEEE Netw., vol. 34, no. 3, pp. 134–142, May/Jun. 2020.
19. K. B. Letaief, W. Chen, Y. Shi, J. Zhang, and Y.-J. A. Zhang, "The roadmap to 6G: AI empowered wireless networks," IEEE Commun. Mag., vol. 57, no. 8, pp. 84–90, Aug. 2019.
20. M. Chen, U. Challita, W. Saad, C. Yin, and M. Debbah, "Artificial neural networks-based machine learning for wireless networks: A tutorial," IEEE Commun. Surveys Tuts., vol. 21, no. 4, pp. 3039–3071, 4th Quart. 2019.
21. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, "Attention is all you need," in Adv. Neural Inf. Process. Syst., vol. 30, 2017.
22. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever, "Learning transferable visual models from natural language supervision," in Proc. 38th Int. Conf. Mach. Learn., 2021, pp. 8748– 8763.
23. V. Sanh, L. Debut, J. Chaumond, and T. Wolf, "DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter," in Proc. 5th Workshop Energy Efficient Mach. Learn. Cogn. Comput., 2019.
24. Y. Gal and Z. Ghahramani, "Dropout as a Bayesian approximation: Representing model uncertainty in deep learning," in Proc. 33rd Int. Conf. Mach. Learn., 2016, pp. 1050–1059.
25. T. Riihonen, S. Werner, and R. Wichman, "Mitigation of looping interference in OFDM relaying: Interference alignment or echo cancellation?" IEEE Trans. Wireless Commun., vol. 10, no. 12, pp. 4115–4125, Dec. 2011.
26. N. C. Luong, D. T. Hoang, S. Gong, D. Niyato, P. Wang, Y.-C. Liang, and D. I. Kim, "Ap- plications of deep reinforcement learning in communications and networking: A survey," IEEE Commun. Surveys Tuts., vol. 21, no. 4, pp. 3133–3174, 4th Quart. 2019.
27. C. Zhang, P. Patras, and H. Haddadi, "Deep learning in mobile and wireless networking: A survey," IEEE Commun. Surveys Tuts., vol. 21, no. 3, pp. 2224–2287, 3rd Quart. 2019.
28. H. Lee, S. Eom, and J. Park, "Deep reinforcement learning-based semantic communication systems," IEEE Access, vol. 10, pp. 124567–124578, 2022.
29. Z. Liu, X. Chen, C. Zhong, A. Liu, S. Shao, W. Tong, and Z. Zhang, "Deep learning-based joint source-channel coding for semantic communications," IEEE Wireless Commun., vol. 29, no. 6, pp. 102–109, Dec. 2022.
30. J. Xu, Y. Wang, K. Huang, and V. K. N. Lau, "Over-the-air computation for IoT networks: A multiple access perspective," IEEE Internet Things J., vol. 8, no. 13, pp. 10577–10590, Jul. 2021.
31. P. Liang, F. Liu, L. Zhang, and R. Zhang, "Deep learning-enabled semantic communica- tions for 6G IoT networks," IEEE Netw., vol. 37, no. 2, pp. 156–163, Mar./Apr. 2023.
32. S. C. Liew, S. Zhang, and L. Lu, "Physical-layer network coding: Tutorial and survey," IEEE Commun. Mag., vol. 54, no. 9, pp. 146–153, Sep. 2016.
33. M. Sana and E. C. Strinati, "Learning to communicate with deep multi-agent reinforce- ment learning in 6G networks," IEEE J. Sel. Areas Commun., vol. 41, no. 5, pp. 1423– 1438, May 2023.
34. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 770–778.
35. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of deep bidi- rectional transformers for language understanding," in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, 2019, pp. 4171–4186.
36. A. Krizhevsky, G. Hinton, and others, "Learning multiple layers of features from tiny images," University of Toronto, Tech. Rep., 2009.
37. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, "Microsoft COCO: Common objects in context," in Proc. Eur. Conf. Comput. Vis., 2014, pp. 740–755.
38. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, "Communication- efficient learning of deep networks from decentralized data," in Proc. 20th Int. Conf. Artif. Intell. Stat., 2017, pp. 1273–1282.
39. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proc. 3rd Int. Conf. Learn. Represent., 2015.
40. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, "PyTorch: An imperative style, high-performance deep learning library," in Adv. Neural Inf. Process. Syst., vol. 32, 2019.