Neural network based antenna analysis using genetically optimized Bézier parameterization

Athar Kharal*, Irfan Shahid, Muzammil Bashir

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review


Antenna design is a time consuming and tedious task which needs to be speeded up. This work discusses time efficient determination of antenna radiation pattern and return loss based on Artificial Neural Network. Return loss and radiation pattern data has been parameterized using Bézier parameterization and then optimized using genetic algorithm (GA) for better results. Finally, Feed-Forward Back-Propagation (FFBP) neural network has been trained based on normalized optimized Bézier parameters. Results show that neural network based antenna models are well suited for applications that require time efficient determination of antenna properties.

Original languageEnglish
Title of host publicationProceedings of 2016 13th International Bhurban Conference on Applied Sciences and Technology (IBCAST)
EditorsMuhammad Zafar-uz-Zaman, Naveed A. Siddiqui, Mazhar Iqbal, Abdul Mannan, Abdur Rauf, Saifullah Khan, Nadial Jamil, M. Anwar Mughal, Qaiser Ahsan, Mureed Hussian, Mehreen Afzal, Muhammad Rafique, Naveed Durrani, Shahid Ali, Syed Ali Abbas, Naveed Ahsan, Abdul Mueed
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)9781467391276, 9781467391252
ISBN (Print)9781467391269
Publication statusPublished - 2016
Externally publishedYes
Event13th International Bhurban Conference on Applied Sciences and Technology (IBCAST) - Islamabad, Pakistan
Duration: 12 Jan 201616 Jan 2016

Publication series

ISSN (Electronic)2151-1411


Conference13th International Bhurban Conference on Applied Sciences and Technology (IBCAST)


  • Antenna design
  • Neural Network
  • Genetic Algorithm
  • Bezier curves
  • Radiation pattern parameterization
  • Return loss parameterization

Cite this