Search
Unsupervised specification-driven design of antenna structures using artificial intelligence and machine learning
This project aims at the development of techniques for unsupervised design of antennas for emerging applications. The major tasks include the development of geometry parameterization (flexible yet featuring a limited number of dimensions to be manageable by modeling and optimization procedures), machine-learning-enabled algorithms for automated generation of antenna topology and geometric dimensions, and artificial-intelligence tools (including deep learning classifiers and regression models) to expedite the design process. These techniques will allow antenna development solely based on performance specifications, without engaging human experts. They will go beyond the capabilities of the state-of-the-art approaches in terms of rendering high-performance structures for demanding applications under reasonable computational budgets. Methodological advancements will be complemented by design of antennas for specific devices, e.g., smart glasses. The accomplishment of the goals will push forward the state of the art in EM-driven antenna development and design automation.
Details
- Project's acronym:
- brak
- Financial Program Name:
- OPUS
- Organization:
- Narodowe Centrum Nauki (NCN) (National Science Centre)
- Agreement:
- UMO-2022/47/B/ST7/00072 z dnia 2023-06-14
- Realisation period:
- 2023-06-14 - 2027-06-13
- Project manager:
- prof. dr inż. Sławomir Kozieł
- Team members:
-
- Co-Investigator dr hab. inż. Anna Pietrenko-Dąbrowska
- Co-Investigator prof. dr inż. Sławomir Kozieł
- Co-Investigator prof. dr hab. inż. Stanisław Szczepański
- Realised in:
- Department of Microelectronic Systems
- Project's value:
- 1 251 440.00 PLN
- Request type:
- National Research Programmes
- Domestic:
- Domestic project
- Verified by:
- Gdańsk University of Technology
seen 155 times