Skip to main navigation Skip to search Skip to main content

Indoor Localization with Data-Driven Prediction using Spatio-Temporal Fusion Transformer

  • Hellenic Mediterranean University
  • Department of Management Science and Technology
  • Warsaw University of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Our previous work combined Wi-Fi FTM and PDR for indoor localization, but lacked prediction. We introduce a Spatio-Temporal Fusion Transformer (STFT) that, in simulation, matches LSTM in accuracy and mean error, while providing robust early-epoch performance in low-data regimes.

Original languageEnglish
Title of host publication2025 IEEE Conference on Network Function Virtualization and Software-Defined Networking, NFV-SDN 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665465779
DOIs
Publication statusPublished - 2025
Event2025 IEEE Conference on Network Function Virtualization and Software-Defined Networking, NFV-SDN 2025 - Athens, Greece
Duration: 10 Nov 202512 Nov 2025

Publication series

Name2025 IEEE Conference on Network Function Virtualization and Software-Defined Networking, NFV-SDN 2025

Conference

Conference2025 IEEE Conference on Network Function Virtualization and Software-Defined Networking, NFV-SDN 2025
Country/TerritoryGreece
CityAthens
Period10/11/2512/11/25

Fingerprint

Dive into the research topics of 'Indoor Localization with Data-Driven Prediction using Spatio-Temporal Fusion Transformer'. Together they form a unique fingerprint.

Cite this