RT Journal Article
T1 Scenario-Agnostic Localization System for Cellular Network Based on Feature Engineering
A1 Luo Chen, Hao Qiang
A1 Khatib, Emil Jatib
A1 Sethi, Deepak
A1 Cruz, Eduardo
A1 Arostegui, Asier
A1 Martín, Raúl
A1 Barco-Moreno, Raquel
K1 Sistemas de comunicaciones móviles
AB In the last few years, location-aware services and network management have driven the demand for user location estimation in mobile networks. Nevertheless, the location obtained from user terminals is not usually accessible to mobile operators. In addition, available cell Key Performance Indicators (KPI) vary highly from network to network, and only a few of them are always enabled widely. Currently prevalent Machine Learning (ML) based solutions have achieved high precision, but they are bound to a trained scenario, restricting their application to new areas. We propose a method for creating scenario-agnostic prediction models which solves these problems through applying feature engineering, over a small set of easily obtainable KPIs, applicable for any ML method. Finally, the performance of the proposed method is demonstrated using real network datasets.
PB IEEE
YR 2024
FD 2024-08
LK https://hdl.handle.net/10630/37538
UL https://hdl.handle.net/10630/37538
LA eng
NO H. Q. Luo-Chen et al., "Scenario-Agnostic Localization System for Cellular Network Based on Feature Engineering," in IEEE Open Journal of the Communications Society, vol. 5, pp. 4999-5012, 2024, doi: 10.1109/OJCOMS.2024.3440186.
NO This work was supported in part by the European Union-NextGenerationEU within the Framework of the Project “Massive AI for the Open RadIo b5G/6G Network (MAORI)” under Grant Real Decreto 1040/2021, and in part by the Ericsson España S.A.U. within the Project “Desarrollo de casos de uso para el diseño, optimización y dimensionado de redes móviles – Líneas B1 y D1” under Grant 8.06/5.59.5705-3 IDEA.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026