Ninja optimization algorithm based ultra wideband antenna electromagnetic band gap modeling via a generative...

Area of Science:

• Electromagnetic engineering
• Antenna theory
• Wireless communication systems

Background:

• Ultra-wideband (UWB) antennas with electromagnetic band-gap (EBG) structures are vital for next-generation wireless and energy-efficient communication.
• These antennas offer broad spectral coverage, high gain, and reduced interference, crucial for advanced systems.
• Accurate modeling and prediction of UWB antenna-EBG performance are essential for design and optimization.

Purpose of the Study:

• To develop an intelligent prediction framework for modeling and predicting the electromagnetic performance of UWB antenna-EBG configurations.
• To enhance surrogate modeling accuracy and robustness by coupling adversarial learning with the Ninja Optimization Algorithm (NOA).
• To establish an efficient, scalable, and high-precision modeling pathway for UWB antenna-EBG design and optimization.

Main Methods:

• Integration of a Generative Adversarial Network (GAN) with the Ninja Optimization Algorithm (NOA) for performance prediction.
• Comparison of the proposed NOA-GAN framework with other deep learning models like LSTM, GRU, RNN, and ANN.
• Benchmarking the framework's robustness against hybrid optimization strategies such as PSO-GAN, BA-GAN, and DE-GAN.

Main Results:

• The NOA-tuned GAN achieved superior predictive accuracy with a mean squared error of [Formula: see text], root mean squared error of [Formula: see text], and a coefficient of determination of [Formula: see text].
• The Ninja Optimization Algorithm significantly improved learning stability, convergence rate, and generalization performance.
• The framework demonstrated competitive robustness compared to other hybrid optimization strategies.

Conclusions:

• The proposed NOA-enhanced GAN provides an efficient, scalable, and high-precision modeling pathway for UWB antenna-EBG structures.
• This framework contributes to the advancement of intelligent communication and renewable energy systems through improved antenna design.
• The intelligent prediction framework offers a significant step forward in optimizing complex electromagnetic systems.