Modeling of circular fractal antenna using BFO‐PSO–based selective ANN ensemble

Abstract

Accurate design of miniaturized antenna is constrained by the limited wellformulated exact mathematical expressions. Demands for smart devices with features like portability, implantability, and configurability have further placed bigger challenges in front of the antenna design engineers or scientists. As a part of the search for various solutions, many innovative approaches have been proposed by various authors in different literatures. Application of soft computing is also another design approach to accurate design of fractal antenna. Here, the authors have attempted to propose a better solution to miniaturized antenna and its design. A fractal antenna based on circular outer geometry has been proposed as a solution to the search of miniaturized antennas, and a particle swarm optimization-based selective artificial neural networks ensemble is developed, which is employed as the objective function of a bacterial foraging optimization algorithm leading to a hybridized algorithm. The developed hybrid algorithm is utilized to develop the proposed antenna at 2.45 GHz. A good agreement of the simulated, desired, and experimental results validates the proposed design approach.KEYWORDS ANN ensemble, BFO, fractal antenna, ISM band, PSO | INTRODUCTIONFractal geometry is employed by many researchers to design the miniaturized antennas suitable for compact handheld wireless devices, MIMO applications, rectennas, and implantable devices. 1-5 The requirement for smart and intelligent systems made it imperative to look forward to design methods capable of high precision antenna and antenna systems. The system integration approach further demands for miniaturization of antenna with enhanced parameter capability to meet the demands of bandwidth, gain, directivity, pattern shape, front to back lobe ratio, main to side lobe ratio, noise rejection, and many others. In the present context, fractal antenna due to its properties like self-similar design to maximize the electrical length appears to be a candid choice. The fractal geometry has often features like fine structure at arbitrarily small scale, too irregular to be easily described in Euclidean geometry, self-similar, and has a Hausdorff dimension that is greater than the topological dimension which leads to space filling curves such as Hilbert curve, has a simple and recursive definition, etc; therefore, in the last few years, many researchers are working on fractal antenna to provide many innovative solution.Complex fractal shapes are used for the design of fractal patch antennas. Due to nonexistence of the closed-form exact mathematical formulas for fractal antennas, the design and analysis of these antennas are a challenging task. The analytical methods are suitable for simple microstrip antennas, but derivation of analytical methods is very difficult for fractal

An Optimized Ensemble Model for Prediction the Bandwidth of Metamaterial Antenna

“…Their model could reduce the size of the fractal antenna by 41.64% and has been used to design a 3.8 GHz WLAN antenna. In [37], an ensemble of neural networks has been used to minimize the design of the circular fractal antenna. Their model has been used to develop an antenna at 2.45 GHz.…”

Artificial bee colony algorithm based modified circular‐shaped compact hybrid fractal antenna for industrial, scientific, and medical band applications

“…The hybrid fractal approach utilizes the appropriate amalgamation of multiple fractals with unique properties. 12,13 Several forms of hybrid or compounded fractal shapes have been illustrated in ref. [14][15][16][17].…”

Analysis of a hybrid fractal curve antenna using the segmentation method

“…In addition to analytical and numerical methods, there are reports on the calculation of Fractal antenna parameters using soft computing techniques such as artificial neural networks. 18,19 The parameters, crucial to making an antenna resonant at the desired frequency, are predicted and then simulated to determine the complete antenna behavior. Although the soft computing techniques could be useful in reliably calculating design parameters, such methods do not provide an insight into the behavior of complex-shaped Fractal antennas.…”

“…Besides, an analysis method based on the inductor circuit model in Reference 17 is also not ideal for the microstrip Fractal curve antennas because its application is confined to the wire dipole antennas. In addition to analytical and numerical methods, there are reports on the calculation of Fractal antenna parameters using soft computing techniques such as artificial neural networks 18,19 . The parameters, crucial to making an antenna resonant at the desired frequency, are predicted and then simulated to determine the complete antenna behavior.…”