SpiWasp-CNTM: A Hybrid Optimization–Deep Learning Framework with Hierarchical SpiWasp and CNN–BiLSTM Modeling
DOI:
https://doi.org/10.31838/NJAP/07.03.23Keywords:
Hybrid Optimization, CNN–BiLSTM Modeling, SpiWasp Algorithm, Deep Learning Framework, Spatial–Temporal Learning, Adaptive optimization, Intelligent systemsAbstract
The rapid pace of the development of smart communication systems has placed more pressure on high-quality optimization frameworks, which can help to settle complicated spatial and temporal learning issues. The proposed paper presents SpiWasp-CNTM, a deep learning – based metaheuristic optimization framework that combines a hierarchical SpiWasp computed with a CNN Bi-LSTM neural network. The model aims to improve pattern learning of adaptive parameters, nonlinear learning, and dynamic optimization in next-generation networks. The CNN module is used to obtain spatial correlations of input signals and the BiLSTM to obtain temporal dependencies, which allows strong sequence prediction. SpiWasp optimizer improves the exploration–exploitation balance by increasing the learning stability and convergence by withholding probabilistic hierarchical updates. The use of the extraction of statistical features also enhances model performance, which makes them useful in pre-processing and representation learning. Several experiments have shown that SpiWasp-CNTM is more accurate, quicker to converge, and has a high computational efficiency than standard algorithms. The essential metrics are used to determine performance; the measures used are MSE, MAE, RMSE, and convergence behavior. The experimental findings prove the ability of the model to facilitate smart decision-making and autonomous optimization in novel wireless and computer architecture. Having a hybrid learning topology and a high level of optimization behavior, SpiWasp-CNTM offers a potent basis of further research in the field of adaptive systems, such as intelligent beamforming, RIS control, and resource-sensitive automation.
References
1. Elhoushy, S., Samir, M., & Yacoub, M. (2023). CNN LSTM hybrid models for wireless channel prediction in next-generation systems. IEEE Access, 11, 12154–12167. https://doi.org/10.1109/ACCESS.2023.3237005
2. Surendar, A. (2025). Lightweight CNN architecture for real-time image super-resolution in edge devices. National Journal of Signal and Image Processing, 1(1), 1–8.
3. Ye, H., Li, G. Y., & Juang, B. H. F. (2018). Power of deep learning for channel estimation and signal detection in OFDM systems. IEEE Wireless Communications Letters, 7(1), 114–117. https://doi.org/10.1109/LWC.2017.2757490
4. Abdelghany, M., Ayanoglu, E., & Alouini, M. S. (2022). Reconfigurable intelligent surfaces for 6G wireless networks: A survey of applications, challenges, and future directions. IEEE Open Journal of the Communications Society, 3, 2124–2152. https://doi.org/10.1109/OJCOMS.2022.3209214
5. Basar, E. (2020). Reconfigurable intelligent surface-based index modulation: A new paradigm for 6G wireless communications. IEEE Transactions on Communications, 68(5), 3187–3196. https://doi.org/10.1109/TCOMM.2020.2971486
6. Di Renzo, M., Debbah, M., Phan-Huy, D. T., Zappone, A., Alouini, M. S., Hoydis, J., De Rosny, J., Tretyakov, S., & Zhang, R. (2020). Smart radio environments empowered by reconfigurable intelligent surfaces: How it works, what it is good for, and what it can do. IEEE Journal on Selected Areas in Communications, 38(11), 2450–2525. https://doi.org/10.1109/JSAC.2020.3007211
7. Surendheran, A. R., & Prashanth, K. (2015). A survey of energy-efficient communication protocol for wireless sensor networks. International Journal of Communicationand Computer Technologies, 3(2), 50–57. https://doi.org/10.31838/IJCCTS/03.02.01
8. Xiao, S., Tang, M., & Tian, Y. (2022). LSTM-based adaptive optimization for RIS-assisted wireless networks. IEEE Access, 10, 33412–33422. https://doi.org/10.1109/ACCESS.2022.3162058
9.Long, R., Chen, Y., Wu, W., & Yang, H. (2021). Deep learning–based hybrid beamforming for 6G massive MIMO systems. IEEE Transactions on Vehicular Technology, 70(5), 4561–4576. https://doi.org/10.1109/TVT.2021.3070692
10. Rahim, R. (2024). Optimizing reconfigurable architectures for enhanced performance in computing. SCCTS Transactions on Reconfigurable Computing, 1(1), 11–15. https://doi.org/10.31838/RCC/01.01.03
11. Alkhateeb, A. (2019). Deep learning for mmWave beam and blockage prediction using sub-6 GHz channels. IEEE Wireless Communications Letters, 8(5), 1410–1413. https://doi.org/10.1109/LWC.2019.2926141
12. Reginald, P. J. (2025). RF performance evaluation of integrated terahertz communication systems for 6G. National Journal of RF Circuits and Wireless Systems, 2(1), 9–20.
13. Wu, Q., & Zhang, R. (2019). Towards smart and reconfigurable environment: Intelligent reflecting surface aided wireless network. IEEE Communications Magazine, 57(8), 106–112. https://doi.org/10.1109/MCOM.001.1900107
14. Huang, C., Zappone, A., Alexandropoulos, G. C., Debbah, M., & Yuen, C. (2019). Reconfigurable intelligent surfaces for energy efficiency in wireless communication. IEEE Transactions on Wireless Communications, 18(8), 4157–4170. https://doi.org/10.1109/TWC.2019.2922609
15. Muralidharan, J. (2024). Advancements in 5G technology: Challenges and opportunities in communication networks. 1 Progress in Electronics and Communication Engineering, (1), 1–6. https://doi.org/10.31838/PECE/01.01.01
16. Tandi, M. R., & Shrirao, N. M. (2025). Optimizing sustainable energy microgrids in smart cities using IoT and renewable energy integration. Journal of Smart Infrastructure and Environmental Sustainability, 2(1), 45–50.
17. Uvarajan, K. P. (2024). Advanced modulation schemes for enhancing data throughput in 5G RF communication networks. SCCTS Journal of Embedded Systems Design and Applications, 1(1), 7–12. https://doi.org/10.31838/ESA/01.01.02
18. Uvarajan, K. P. (2024). Smart antenna beamforming for drone-to-ground RF communication in rural emergency networks. National Journal of RF Circuits and Wireless Systems, 1(2), 37–46.
19. Zappone, A., Shariatpanahi, S. P., & Bennis, M. (2021). Model-aided wireless artificial intelligence: Embedding expert knowledge in deep neural networks towards robust and interpretable learning. IEEE Transactions on Communications, 69(11), 7479–7495. https://doi.org/10.1109/TCOMM.2021.3098531
20. Zhang, S., Di, B., Han, C., & Song, L. (2020). Reconfigurable intelligent surfaces: A signal processing perspective. IEEE Transactions on Signal Processing, 68, 7275–7298. https://doi.org/10.1109/TSP.2020.3041385
