UDC 004.891.2
IMPROVING POSITIONING METHODS IN WIRELESS NETWORKS
USING MACHINE LEARNING
M. V. Filippov, Ph.D. (in technical sciences), associate professor, Informatics and Control Systems Department,
Bauman Moscow State Technical University, Moscow, Russia;
spin 3781-5276, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
D. Y. Pudov, post-graduate student, Informatics and control systems Department, Bauman Moscow
State Technical University, Moscow, Russia;
orcid.org/0000-0003-0980-1317, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
D. A. Kalachev, student, Radio-electronic systems and devices Department, Bauman Moscow State
Technical University, Moscow, Russia;
orcid.org/ 0009-0001-7187-6128, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
This paper examines the problem of estimating the distance between devices in wireless networks based
on RSSI metric, using BLE as an example. The aim of the study is to develop and validate an effective distance
estimation method using mathematical filtering models and machine learning. A comparative analysis
of various approaches to solving the problem is conducted, including Kalman filter, LSTM networks, polynomial
regression, and random forest method. Experimental studies using real-world data showed that a
combined model with Kalman pre-filtering and random forest demonstrates accuracy with a root-meansquare
error (RMS) of less than 0.5 m. The practical significance of this study lies in the potential application
of the developed method for creating effective positioning systems in enclosed spaces.
Key words: RSSI, Bluetooth Low Energy, distance estimation, machine learning, Kalman filter, Random
Forest, positioning, wireless networks, LSTM.