Doctoral theses of the School of Electrical Engineering at Aaltodoc (external link)
Doctoral theses of the School of Electrical Engineering are available in the open access repository maintained by Aalto, Aaltodoc.
Public defence, Communications Engineering and Networking Technology, MSc Xinze Li
Machine Learning-Enhanced Localization based on 5G System.
Public defence from the Aalto University School of Electrical Engineering, Department of Information and Communications Engineering.
Public defence from the Aalto University School of Electrical Engineering, Department of Information and Communications Engineering.
In our events, we are committed to Aalto University’s principles for a safer space.
Title of the thesis: Machine Learning-Enhanced Localization based on 5G System
Thesis defender: Xinze Li
Opponent: Prof. Fredrik Tufvesson, Lund University, Sweden
Custos: Prof. Olav Tirkkonen, Aalto University School of Electrical Engineering
This thesis studied machine learning algorithms for indoor positioning using 5G radio signals. Its purpose was to improve positioning accuracy while reducing measurement effort and device reporting overhead. The study explored feature engineering using channel state information, improved positioning algorithms, and developed adaptive sampling methods for efficiently constructing radio maps. It contributes to wireless localization research by showing how signal information and spatial relationships can support accurate positioning with limited offline data samples. The findings can help the development of indoor positioning systems for industrial automation and mobile robots.
Key words: Indoor localization, 5G positioning, non line-of-sight, machine learning, channel state information, fingerprint localization, channel covariance, radio map construction
Thesis available for public display 7 days prior to the defence at Aalto University's public display page.
Doctoral theses of the School of Electrical Engineering
Zoom Quick Guide