Optimization of hyperparameters of artificial neural network (ANN) usually involves a trial and error approach which is not only computationally expensive but also fails to predict a near-optimal solution most of the time. To design a better optimized ANN model, evolutionary algorithms are widely utilized to determine hyperparameters. This work proposes hyperparameters optimization of the ANN model using an improved particle swarm optimization (IPSO) algorithm. The different ANN hyperparameters considered are a number of hidden layers, neurons in each hidden layer, activation function, and training function. The proposed technique is validated using inverse modeling of two meander line electromagnetic bandgap unit cells and a slotted ultra-wideband antenna loaded with EBG structures. Three other evolutionary algorithms viz. hybrid PSO, conventional PSO, and genetic algorithm are also adopted for the hyperparameter optimization of the ANN models for comparative analysis. Performances of all the models are evaluated using quantitative assessment parameters viz. mean square error, mean absolute percentage deviation, and coefficient of determination (R2). The comparative investigation establishes the accurate and efficient prediction capability of the ANN models tuned using IPSO compared to other evolutionary algorithms.

In this paper, a small ultra-wideband (UWB) antenna with two stop bands by a compact electromagnetic bandgap (EBG) cell loaded with two new open meander slots is presented. With the coupling of the EBG cell to the feedline, the stop bands are formed. The designed EBG cell is a mushroom type that has the advantages of being able to independently control the stop bands, high responsiveness selectivity of stop bands, easy switching, the need for fewer EBG cells, and low impact on the working characteristics of the antenna. To have a better understanding of the proposed EBG mechanism, characteristic mode analysis is used. The size reduction of the suggested antenna is obtained by halving the reference antenna relative to the axis of symmetry. The measurement results for −10 dB adaptation are from 2.73 to 13 GHz with stop bands at 3.51 GHz (12.9%) and 5.34 GHz (14.1%). The radiation behavior of the minimized antenna is similar to that of a reference antenna. Minimized UWB antenna with transmission function and group delay with small variations in the operating frequency range is suitable for small multiple-input and multiple-output (MIMO) and diversity systems.

In this paper, a backfire suppressed aperture coupled circularly polarized (CP) stacked patch antenna for universal ultra-high frequency (UHF) radio frequency identification applications is presented. Cross-polarized backfire radiation patterns were successfully suppressed by a planar high impedance surface (HIS) reflector. The size of the fabricated antenna is 250 × 250 × 26.9 mm3 (0.71λ0 × 0.71λ0 × 0.076λ0) and its peak gain value of 7.1 dBi is measured. The distance between the antenna and the HIS reflector is only 4.8 mm (0.014 λ0). The HIS reflector suppressed cross-pol backfire radiations by about 10 dB. Detailed antenna and HIS reflector design are discussed thoroughly in this paper. The presented backfire suppression technique using the HIS reflector is scalable to other applications and frequency bands. This paper demonstrates the feasibility of the HIS structure at UHF band.