UAV-Facilitated 3D Signal Mapping via Temporal-Spatial Features and Neural Networks

Mead, Fin ORCID: https://orcid.org/0009-0004-5758-9765, Wu, Taoyang ORCID: https://orcid.org/0000-0002-2663-2001 and Ren, Edwin ORCID: https://orcid.org/0000-0001-7423-6719 (2026) UAV-Facilitated 3D Signal Mapping via Temporal-Spatial Features and Neural Networks. In: UNSPECIFIED.

Preview

PDF (a92-mead final-1) - Accepted Version Available under License Creative Commons Attribution Non-commercial. Download (779kB) | Preview

Abstract

The rise of complex robotics systems for 6G infrastructure is generating demand for greater environmental mapping and monitoring, with increasing scale, complexity, and precision. A key area of development is within 3D signal estimation for cellular and robotic infrastructure. We present a method for predicting cellular network properties in 3D by combining sparse real-world collection methods with feature engineering and neural networks. We show this model applied to our experimental drone-based dataset, consisting of network, environment, time-series and positional fields. Through this approach, we show 3D predictions for cellular network conditions across a range of test sizes and formats including vertical and non-uniform subsets. Our approach shows promise in applications such as cellular map generation, drone networks, fleet management, mobile 6G infrastructure and comprehensive environmental mapping.

Item Type:	Conference or Workshop Item (Paper)
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Health Computing Faculty of Science > Research Groups > Data Science and AI Faculty of Science > Research Groups > Computational Biology Faculty of Science > Research Centres > Centre for Ecology, Evolution and Conservation Faculty of Science > Research Groups > Cyber Intelligence and Networks
Depositing User:	LivePure Connector
Date Deposited:	10 Nov 2026 15:59
Last Modified:	10 Nov 2026 15:59
URI:	https://ueaeprints.uea.ac.uk/id/eprint/105045
DOI:	10.1109/ISCC70364.2026.11740085

Downloads

Actions (login required)

View Item