@inproceedings{f5ce731def954d44b4c613fd36e0d748,
title = "AI-enabled CSI fingerprinting for indoor localisation towards context-aware networking in 6G",
abstract = "The spatial distribution of cellular networks has made them very promising to use for localization. By knowing the location of a user, cellular networks can provide context-aware services customized to that user. Objects and the dynamic nature of indoor locations result in lots of multipath and non-line-of-sight (NLOS) propagations. In this work, we carry out a novel experimental investigation to improve indoor localization using a grid approach with channel state information (CSI) fingerprinting and artificial intelligence (AI)/ machine learning (ML) methods for determining the location of a mobile device. Experiments are conducted in a standard indoor setting. This paper compares a method for indoor positioning based on received signal strength identifier (RSSI), phase, and CSI using ML to show how the accuracy of indoor localization can be improved. Compared to heuristic approaches like DOA estimation, the precision of ML is superior.",
keywords = "CSI, Indoor positioning, Machine Learning",
author = "Jaspreet Kaur and Mahmoud Shawky and Mollel, \{Michael S.\} and Popoola, \{Olaoluwa R.\} and Imran, \{Muhammad Ali\} and Abbasi, \{Qammer H.\} and Abbas, \{Hasan T.\}",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Wireless Communications and Networking Conference, WCNC 2023 ; Conference date: 26-03-2023 Through 29-03-2023",
year = "2023",
doi = "10.1109/WCNC55385.2023.10118652",
language = "English",
series = "IEEE Wireless Communications and Networking Conference, WCNC",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2023 IEEE Wireless Communications and Networking Conference, WCNC 2023 - Proceedings",
address = "United States",
}