Indoor localization has become a crucial area of research due to the increasing demand for location-aware applications and services within indoor environments. Bluetooth Low Energy (BLE) is a promising technology for indoor localization due to its advantages such as low power consumption and wide compatibility with various devices. However, BLE also faces limitations, including its limited range and susceptibility to interference from other wireless devices operating in the same frequency range. This paper presents a comprehensive comparative analysis of BLE-based indoor localization techniques using machine learning regression methods. Several models, including Boosted Tree, Bagged Tree, Gaussian Process Regression (GPR), and Support Vector Machine (SVM), are trained and tested using new datasets. The results highlight the superior performance of the Boosted Tree model, with a root mean squared error (RMSE) of 0.7 m. The study's findings provide valuable insights into the strengths and limitations of different machine learning regression techniques for BLE-based indoor localization.
A Comparative Analysis of BLE-Based Indoor Localization with Machine Learning Regression Techniques
Lect. Notes Electrical Eng.
International Conference on Robotics, Vision, Signal Processing and Power Applications ; 2021 April 05, 2021 - April 06, 2021
Proceedings of the 12th International Conference on Robotics, Vision, Signal Processing and Power Applications ; Chapter : 45 ; 357-362
2024-03-31
6 pages
Article/Chapter (Book)
Electronic Resource
English