Using Information about Experimental Conditions to Predict Properties of Metamaterials
In this work, a method of increasing the amount of data for training neural networks is proposed using the possibility of using information about the experimental conditions of measuring the properties of metamaterials. It is shown that the method is flexible and effective. The results of predictin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Igor Sikorsky Kyiv Polytechnic Institute
2023-12-01
|
| Series: | Mìkrosistemi, Elektronìka ta Akustika |
| Subjects: | |
| Online Access: | http://elc.kpi.ua/article/view/287808 |
| _version_ | 1797374875318353920 |
|---|---|
| author | Pavlo I. Krysenko Maksym Olehovych Zoziuk |
| author_facet | Pavlo I. Krysenko Maksym Olehovych Zoziuk |
| author_sort | Pavlo I. Krysenko |
| collection | DOAJ |
| description |
In this work, a method of increasing the amount of data for training neural networks is proposed using the possibility of using information about the experimental conditions of measuring the properties of metamaterials. It is shown that the method is flexible and effective. The results of predicting the transmission coefficient of the metamaterial for different angles of incidence of radiation and type of polarization are presented. Using the architecture presented in the work, a high rate of learning and generation of new data was obtained with an error that does not exceed 12% for experiments in one frequency range and does not exceed 31% if all experiments are used for training. The architecture of the neural network and the method by which it is possible to easily change the number and types of experimental conditions are presented.
|
| first_indexed | 2024-03-08T19:11:07Z |
| format | Article |
| id | doaj.art-e6ffd52d5a6f4e398b911fb6da00ff18 |
| institution | Directory Open Access Journal |
| issn | 2523-4447 2523-4455 |
| language | English |
| last_indexed | 2024-03-08T19:11:07Z |
| publishDate | 2023-12-01 |
| publisher | Igor Sikorsky Kyiv Polytechnic Institute |
| record_format | Article |
| series | Mìkrosistemi, Elektronìka ta Akustika |
| spelling | doaj.art-e6ffd52d5a6f4e398b911fb6da00ff182023-12-27T13:22:00ZengIgor Sikorsky Kyiv Polytechnic InstituteMìkrosistemi, Elektronìka ta Akustika2523-44472523-44552023-12-0128310.20535/2523-4455.mea.287808Using Information about Experimental Conditions to Predict Properties of MetamaterialsPavlo I. Krysenko0Maksym Olehovych Zoziuk1National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” In this work, a method of increasing the amount of data for training neural networks is proposed using the possibility of using information about the experimental conditions of measuring the properties of metamaterials. It is shown that the method is flexible and effective. The results of predicting the transmission coefficient of the metamaterial for different angles of incidence of radiation and type of polarization are presented. Using the architecture presented in the work, a high rate of learning and generation of new data was obtained with an error that does not exceed 12% for experiments in one frequency range and does not exceed 31% if all experiments are used for training. The architecture of the neural network and the method by which it is possible to easily change the number and types of experimental conditions are presented. http://elc.kpi.ua/article/view/287808metamaterials3D convolutional neural networkexperimental conditions |
| spellingShingle | Pavlo I. Krysenko Maksym Olehovych Zoziuk Using Information about Experimental Conditions to Predict Properties of Metamaterials Mìkrosistemi, Elektronìka ta Akustika metamaterials 3D convolutional neural network experimental conditions |
| title | Using Information about Experimental Conditions to Predict Properties of Metamaterials |
| title_full | Using Information about Experimental Conditions to Predict Properties of Metamaterials |
| title_fullStr | Using Information about Experimental Conditions to Predict Properties of Metamaterials |
| title_full_unstemmed | Using Information about Experimental Conditions to Predict Properties of Metamaterials |
| title_short | Using Information about Experimental Conditions to Predict Properties of Metamaterials |
| title_sort | using information about experimental conditions to predict properties of metamaterials |
| topic | metamaterials 3D convolutional neural network experimental conditions |
| url | http://elc.kpi.ua/article/view/287808 |
| work_keys_str_mv | AT pavloikrysenko usinginformationaboutexperimentalconditionstopredictpropertiesofmetamaterials AT maksymolehovychzoziuk usinginformationaboutexperimentalconditionstopredictpropertiesofmetamaterials |