A Scalable Deep Learning Model for Simultaneous Reconstruction and Transmitter Localization in Inverse Scattering

Karthik, GR and Ghosh, PK (2023) A Scalable Deep Learning Model for Simultaneous Reconstruction and Transmitter Localization in Inverse Scattering. In: 2023 Photonics and Electromagnetics Research Symposium, PIERS 2023, 03-06 July 2023, Prague, Czech Republic, pp. 1237-1242.

PDF PIERS2023_1237-1242_PIERS2023.pdf Restricted to Registered users only Download (759kB) | Request a copy

Abstract

There have been several methods for solving the problem of inverse scattering. Recently, Deep Learning methods have been able to provide state-of-the-art results in inverse scattering. However, both traditional and Deep Learning based methods require the knowledge of the locations of the transmitters and receivers. This requires a calibration stage which involves the careful placement of the transmitters and receivers at specific known locations or placing the transmitters and receivers at arbitrary locations and using a system to calculate their respective positions. This reduces the ease of usability of the system. Therefore, in this work, we propose a Deep Learning based approach which can be used to simultaneously reconstruct the contrast and localize the transmitters. © 2023 IEEE.

Item Type:	Conference Paper
Publication:	2023 Photonics and Electromagnetics Research Symposium, PIERS 2023 - Proceedings
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the Institute of Electrical and Electronics Engineers Inc.
Keywords:	Deep learning; Inverse problems; Learning systems; Transmitters, Inverse-scattering; Learning methods; Learning models; Learning-based approach; Learning-based methods; Localisation; Simultaneous reconstruction; State of the art; Transmitter and receiver, Location
Department/Centre:	Autonomous Societies / Centres > IISc Alumni Association
Date Deposited:	28 Feb 2024 06:01
Last Modified:	28 Feb 2024 06:01
URI:	https://eprints.iisc.ac.in/id/eprint/83565

Actions (login required)

View Item