2026-05-28T17:40:37Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/399362026-02-03T11:08:57Zcom_10630_2254col_10630_37953

00925njm 22002777a 4500 dc Fernández-Rodríguez, Jose David author García Aguilar, Iván author Luque-Baena, Rafael Marcos author López-Rubio, Ezequiel author Baena-Molina, Marcos author Valenzuela-Valdés, Juan Francisco author 2025-10 The field of reconfigurable intelligent surfaces (RIS) has gained significant traction in recent years in the wireless communications domain, owing to the ability to dynamically reconfigure surfaces to change their electromagnetic radiance patterns in real-time. In this work, we propose utilizing a novel deep learning model that innovatively employs only the parameters of each signal or beam as input, eliminating the need for the entire one-dimensional signal or its diffusion map (two-dimensional information). This approach enhances efficiency and reduces the overall complexity of the model, drastically reducing network size and enabling its implementation on low-cost devices. Furthermore, to enhance training effectiveness, the learning model attempts to estimate the discrete cosine transform applied to the output matrix rather than the raw matrix, significantly improving the achieved accuracy. This scheme is validated on a 1-bit programmable metasurface of size 10 X 10, achieving an accuracy close to 95% using a K-fold methodology with K=10. Jose David Fernández-Rodríguez, Iván García-Aguilar, Rafael Marcos Luque-Baena, Ezequiel López-Rubio, Marcos Baena-Molina, Juan Francisco Valenzuela-Valdés, Learning to shape beams: Using a neural network to control a beamforming antenna, Computer Networks, Volume 270, 2025, 111544, ISSN 1389-1286, https://doi.org/10.1016/j.comnet.2025.111544. (https://www.sciencedirect.com/science/article/pii/S1389128625005110) https://hdl.handle.net/10630/39936 10.1016/j.comnet.2025.111544 Lenguajes de programación Telecomunicaciones Redes neuronales (Informática) Aprendizaje automático (Inteligencia artificial) Antenas Learning to shape beams: Using a neural network to control a beamforming antenna