Recently, researchers were interested in neural algorithms for optimization problems for several communication systems. This paper shows a novel algorithm based on neural technique presented to enhance the performance analysis of beam-forming in smart antenna technology using N elements for Uniform Circular Array (UCA) and Concentric Circular Array (CCA) geometries. To demonstrate the effectiveness and reliability of the proposed approach, simulation results are carried out in MATLAB. The radiators are considered isotropic, and hence mutual coupling effects are ignored. The proposed array shows a considerable improvement against the existing structures in terms of 3-D scanning, size, directivity, HPBW and SLL reduction. The results show that multilayer feed-forward neural networks are robust and can solve complex antenna problems. However, artificial neural network (ANN) is able to generate very fast the results of synthesis by using generalization with early stopping method. Important gain in the running time and memory used is obtained using this latter method for improving generalization (called early stopping). To validate this work, several examples are shown.

This paper proposes radiation pattern synthesis of almost periodic antenna arrays including mutual coupling effects (extracted by Floquet analysis according to our previous work), which in principal has high directivity and a large bandwidth. For modeling the given structures, the moment method combined with the generalized equivalent circuit (MoM-GEC) is proposed. The artificial neural network (ANN), as a powerful computational model, has been successfully applied to antenna array pattern synthesis. Our results showed that multilayer feedforward neural networks are rugged and can successfully and efficiently resolve various distinctive, complex almost periodic antenna patterns (with different source amplitudes) (in particular, both periodic and randomly aperiodic structures are taken into account). An ANN is capable of quickly producing the synthesis results using generalization with the early stopping (ES) method. Significant advantages in speed and memory consumption are achieved by using this method to improve the generalization (called early stopping). To justify this work, several examples are shown and discussed.

In this study, we introduce a new formulation based on Floquet (Fourier) spectral analysis combined with a spectral modulation technique (and its spatial form) to study strongly coupled sublattices predefined in the infinite and large finite extent of almost-periodic antenna arrays (e.g., metasurfaces). This analysis is very relevant for dense-massive-MIMO, intelligent-surfaces, 5G, and 6G applications (used for very small areas with a large number of elements such as millimeter and terahertz waves applications). The numerical method that is adopted to model the structure is the method of moments simplified by equivalent circuits MoM GEC. Other numerical methods (such as the ASM-array scanning method and the windowing Fourier method) used this analysis in their kernel to treat periodic and pseudo-periodic (or quasi-periodic) arrays.

Symmetries play an essential role in the field of physics. In this paper, we examine the relationship between the eigen-amplitudes of four (2 × 2) symmetrical antennas and the symmetry of the amplitudes of their sources (excitations) using mirroring effects. In our case, we find that changing mirrors using symmetry is identical to the point group theory. By exploiting the symmetry problem, we can show the advantage of reducing the size of the analysis domain, at least by a factor of two or more (2, 4, and 8…etc.) (depending on the problem). Several simulation examples have been developed by the MoM-GEC and HFSS to validate this approach.

This paper presents a compact, low-cost dual-band antenna design with low specific absorption rate (SAR) for Wireless Body Area Networks (WBAN) and Industrial, Scientific, and Medical (ISM) applications. The proposed antenna operates at 2.4 GHz with linear polarization and 5.8 GHz with circular polarization, fabricated on a 1.52 mm thick RF35 dielectric substrate (28 $$\times $$ 40 mm). The design features a coplanar waveguide (CPW) feed integrated with substrate-integrated waveguide (SIW) technology to enhance bandwidth and return loss characteristics. The antenna has broad bandwidths of 0.5 GHz with a 2.4 GHz center and 1 GHz with a 5.8 GHz center. To mitigate back radiation and reduce SAR, a 4 $$\times $$ 4 electromagnetic bandgap (EBG) structure was incorporated, resulting in significant performance improvements. The EBG implementation increased the maximum gain from 3.66 to 8.56 dB at 2.4 GHz and from 3.97 to 10 dB at 5.8 GHz. Additionally, SAR values decreased from 7.34 to 1.62 W/kg for 1 g of tissue at 2.4 GHz and from 2.18 to 0.91 W/kg at 5.8 GHz. Prototype measurements confirm simulation results, demonstrating the antenna’s suitability for WBAN and wearable ISM applications, including sensor networks and Wi-Fi devices. The design offers advantages of independent band tuning, circular polarization at the higher frequencies, and compliance with safety standards for human exposure to electromagnetic fields.

This paper proposes a radiation pattern synthesis of the almost periodic antenna arrays including mutual coupling effects (that extracted by the Floquet analysis according to our previous work), which principally has a high directivity and large bandwidth. For modeling the given structures, the moment method combined with the Generalized Equivalent Circuit (MoM-GEC) is proposed. The artificial neural network (ANN) as a powerful computational model has been successfully applied to the antenna array pattern synthesis. The results showed that the multilayer feedforward neural networks are rugged and can successfully and efficiently resolve various distinctive complex almost periodic antenna patterns (with different source amplitudes) (in particular, both periodic and randomly aperiodic structures are taken into account). However, the artificial neural network (ANN) is capable of quickly producing the synthesis results using generalization with the early stopping (ES) method. A significant time gain and memory consumption are achieved by using this given method to improve the generalization (called early stopping). To justify this work, several examples are developed and discussed.