Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering

Emre Işcan; Vasil Tabatadze; Kamil Karaçuha; Ertuǧrul Karaçuha; Ömer Faruk Alperen

doi:10.1109/DIPED66951.2025.11194475

Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper introduces a novel artificial neural network (ANN) model designed to reconstruct the shape, permittivity, and rotation angle of dielectric elliptical objects. The model uses the Method of Auxiliary Sources (MAS) to solve scattering problem efficiently, eliminating field singularities and speeding up the solution process. Gaussian periodic pulse feedback is used to provide data for the ANN's estimations. The ANN can make real-time recognitions, with a typical 5% variation in intermediate parameters and a 0.1% average deviation on training data. Since it only requires a single measurement, the model is suitable for real-time applications like subsurface imaging and missile tracking. This work establishes a new framework for integrating machine learning with computational electromagnetics, enabling advancements in defence systems and imaging technologies.

Original language	English
Title of host publication	2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings
Publisher	IEEE Computer Society
Pages	111-116
Number of pages	6
ISBN (Electronic)	9798331588144
DOIs	https://doi.org/10.1109/DIPED66951.2025.11194475
Publication status	Published - 2025
Event	30th IEEE International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Tbilisi, Georgia Duration: 8 Sept 2025 → 10 Sept 2025

Publication series

Name	Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED
ISSN (Print)	2165-3585
ISSN (Electronic)	2165-3593

Conference

Conference	30th IEEE International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025
Country/Territory	Georgia
City	Tbilisi
Period	8/09/25 → 10/09/25

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Keywords

artificial neural networks
dielectric elliptical object
Gaussian pulse feedback
MAS
real-time detection

Access to Document

10.1109/DIPED66951.2025.11194475

Cite this

Işcan, E., Tabatadze, V., Karaçuha, K., Karaçuha, E., & Alperen, Ö. F. (2025). Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering. In 2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings (pp. 111-116). (Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED). IEEE Computer Society. https://doi.org/10.1109/DIPED66951.2025.11194475

Işcan, Emre ; Tabatadze, Vasil ; Karaçuha, Kamil et al. / Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering. 2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings. IEEE Computer Society, 2025. pp. 111-116 (Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED).

@inproceedings{2567963275d946f79e725143687c9148,

title = "Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering",

abstract = "This paper introduces a novel artificial neural network (ANN) model designed to reconstruct the shape, permittivity, and rotation angle of dielectric elliptical objects. The model uses the Method of Auxiliary Sources (MAS) to solve scattering problem efficiently, eliminating field singularities and speeding up the solution process. Gaussian periodic pulse feedback is used to provide data for the ANN's estimations. The ANN can make real-time recognitions, with a typical 5\% variation in intermediate parameters and a 0.1\% average deviation on training data. Since it only requires a single measurement, the model is suitable for real-time applications like subsurface imaging and missile tracking. This work establishes a new framework for integrating machine learning with computational electromagnetics, enabling advancements in defence systems and imaging technologies.",

keywords = "artificial neural networks, dielectric elliptical object, Gaussian pulse feedback, MAS, real-time detection",

author = "Emre I{\c s}can and Vasil Tabatadze and Kamil Kara{\c c}uha and Ertuǧrul Kara{\c c}uha and Alperen, \{{\"O}mer Faruk\}",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 30th IEEE International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 ; Conference date: 08-09-2025 Through 10-09-2025",

year = "2025",

doi = "10.1109/DIPED66951.2025.11194475",

language = "English",

series = "Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED",

publisher = "IEEE Computer Society",

pages = "111--116",

booktitle = "2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings",

address = "United States",

}

Işcan, E , Tabatadze, V , Karaçuha, K , Karaçuha, E & Alperen, ÖF 2025, Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering. in 2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings. Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED, IEEE Computer Society, pp. 111-116, 30th IEEE International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025, Tbilisi, Georgia, 8/09/25. https://doi.org/10.1109/DIPED66951.2025.11194475

Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering. / Işcan, Emre ; Tabatadze, Vasil ; Karaçuha, Kamil et al.
2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings. IEEE Computer Society, 2025. p. 111-116 (Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering

AU - Işcan, Emre

AU - Tabatadze, Vasil

AU - Karaçuha, Kamil

AU - Karaçuha, Ertuǧrul

AU - Alperen, Ömer Faruk

PY - 2025

Y1 - 2025

N2 - This paper introduces a novel artificial neural network (ANN) model designed to reconstruct the shape, permittivity, and rotation angle of dielectric elliptical objects. The model uses the Method of Auxiliary Sources (MAS) to solve scattering problem efficiently, eliminating field singularities and speeding up the solution process. Gaussian periodic pulse feedback is used to provide data for the ANN's estimations. The ANN can make real-time recognitions, with a typical 5% variation in intermediate parameters and a 0.1% average deviation on training data. Since it only requires a single measurement, the model is suitable for real-time applications like subsurface imaging and missile tracking. This work establishes a new framework for integrating machine learning with computational electromagnetics, enabling advancements in defence systems and imaging technologies.

AB - This paper introduces a novel artificial neural network (ANN) model designed to reconstruct the shape, permittivity, and rotation angle of dielectric elliptical objects. The model uses the Method of Auxiliary Sources (MAS) to solve scattering problem efficiently, eliminating field singularities and speeding up the solution process. Gaussian periodic pulse feedback is used to provide data for the ANN's estimations. The ANN can make real-time recognitions, with a typical 5% variation in intermediate parameters and a 0.1% average deviation on training data. Since it only requires a single measurement, the model is suitable for real-time applications like subsurface imaging and missile tracking. This work establishes a new framework for integrating machine learning with computational electromagnetics, enabling advancements in defence systems and imaging technologies.

KW - artificial neural networks

KW - dielectric elliptical object

KW - Gaussian pulse feedback

KW - MAS

KW - real-time detection

UR - https://www.scopus.com/pages/publications/105020834012

U2 - 10.1109/DIPED66951.2025.11194475

DO - 10.1109/DIPED66951.2025.11194475

M3 - Conference contribution

AN - SCOPUS:105020834012

T3 - Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED

SP - 111

EP - 116

BT - 2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings

PB - IEEE Computer Society

T2 - 30th IEEE International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025

Y2 - 8 September 2025 through 10 September 2025

ER -

Işcan E , Tabatadze V , Karaçuha K , Karaçuha E , Alperen ÖF. Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering. In 2025 IEEE 30th International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED 2025 - Proceedings. IEEE Computer Society. 2025. p. 111-116. (Proceedings of International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, DIPED). doi: 10.1109/DIPED66951.2025.11194475

Real-Time Recognition of Dielectric Elliptical Object Parameters Using an ANN Method Based on EM Pulse Scattering

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this