Transient response optimization of ultra wideband antennas (using particle swarm optimization)

2006 ◽  
Author(s):  
Petr Cerny ◽  
Milos Mazanek ◽  
Petr Piksa ◽  
Vratislav Sokol ◽  
Tomas Korinek
Keyword(s):  
Particle Swarm Optimization ◽  
Transient Response ◽  
Particle Swarm ◽  
Ultra Wideband ◽  
Wideband Antennas ◽  
Swarm Optimization ◽  
Response Optimization

scholarly journals Correction of Load Cell Output using Particle Swarm Optimization

2019 ◽  
Vol 9 (2) ◽  
pp. 4451-4453
Keyword(s):  
Particle Swarm Optimization ◽  
Transient Response ◽  
Optimization Technique ◽  
Particle Swarm ◽  
Search Space ◽  
Electrical Signal ◽  
Current Approach ◽  
Load Cell ◽  
Swarm Optimization ◽  
Force Transducers

A load cell is a type of force transducers that transform force and mechanical stress into electrical signal. But the output becomes distorted due to the presence of transient response. Particle Swarm Optimization (PSO) based correction of load cell output is presented this paper. PSO is a robust stochastic optimization technique that considers a swarm of particle (data) as its search space and looks for the best solution. The current approach optimizes a load cell output based on the median value of the signal. The optimization algorithm tries to bring the output response near to the median value.

scholarly journals Joint Optimization of Microstrip Patch Antennas Using Particle Swarm Optimization for UWB Systems

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Muhammad Zubair ◽  
Muhammad Moinuddin
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Monopole Antenna ◽  
Ultra Wideband ◽  
Joint Optimization ◽  
Geometrical Parameters ◽  
Swarm Optimization ◽  
Physical Constraints ◽  
High Data

Ultra wideband (UWB) systems are the most appropriate for high data rate wireless transmission with low power consumption. However, the antenna design for UWB has been a challenging task. Moreover, it is always desirable to have more freedom by designing different shape antennas with identical characteristics so that they can be used in either transmitter or receiver depending on other physical constraints such as area. To tackle these issues, in this paper, we have investigated a joint optimization of three different shape-printed monopole antennas, namely, printed square monopole antenna, printed circular monopole antenna and printed hexagonal monopole antenna, for UWB applications. More specifically, we have obtained the optimized geometrical parameters of these antennas by minimizing the mean-square-error for desired lower band edge frequency, quality factor, and bandwidth. The objective of joint optimization is to have identical frequency characteristics for the aforementioned three types of PMA which will give a freedom to interchangeably use them at either side, transmitting or receiving. Moreover, we employ particle swarm optimization (PSO) algorithm for our problem as it is well known in the literature that PSO performs well in electromagnetic and antenna applications. Simulation results are presented to show the performance of the proposed design.

Hyperparameters optimization of neural network using improved particle swarm optimization for modeling of electromagnetic inverse problems

2021 ◽  
pp. 1-12
Author(s):  
Debanjali Sarkar ◽  
Taimoor Khan ◽  
Fazal Ahmed Talukdar
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Evolutionary Algorithms ◽  
Particle Swarm ◽  
Ultra Wideband ◽  
Coefficient Of Determination ◽  
Ann Model ◽  
Swarm Optimization ◽  
Improved Particle Swarm Optimization ◽  
Ann Models

Abstract 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.

Sign in / Sign up

Export Citation Format

Share Document