Vikram Singh
Publications Conference

A Hybrid CNN-Transformer Framework for Precise Indoor Positioning in 6G Networks

Shubham Kukadiya, Vikram Singh, Abhishek Jindal, Manish Kumar

IEEE International Mediterranean Conference on Communications and Networking (MeditCom) · 09/07/2026

DOI

Abstract

Precise indoor localization in dense industrial environments remains a formidable challenge due to severe Non-Line-of-Sight (NLoS) propagation, which degrades traditional geometric estimation methods. This paper presents a hybrid CNN-Transformer framework for accurate indoor positioning in 6G networks. By combining convolutional neural networks for local feature extraction with Transformer-based architectures for capturing long-range dependencies, the proposed framework enables robust and precise localization in challenging indoor environments.

BibTeX 
@inproceedings{11641129,
author={Kukadiya, Shubham K. and Singh, Vikram and Jindal, Abhishek and Kumar, Manish},
booktitle={2026 IEEE International Mediterranean Conference on Communications and Networking (MeditCom)}, 
title={A Hybrid CNN-Transformer Framework for Precise Indoor Positioning in 6G Networks}, 
year={2026},
volume={},
number={},
pages={1-7},
keywords={Modeling;Channel impulse response;Transformers;Tail;Training;3GPP;Encoding;Printing;Convolutional neural networks;Geometry;Indoor Positioning;6G;Deep Learning;Transformer;Channel State Information (CSI);Non-Line-of-Sight (NLoS);Industry 4.0},
doi={10.1109/MeditCom67211.2026.11641129}}