Performance Comparison and Evaluation of Indoor Positioning Technology Based on Machine Learning Algorithms

Abstract

Precise location of things in indoor environments is the essential information for future wireless networks and services. Wi-Fi fingerprinting positioning has recently attracted great attention due to its high applicability in the complex indoor environments, although it still needs to improve positioning accuracy. In this paper, we introduce machine learning algorithms combined with filtering techniques to improve positioning accuracy. We compare and evaluate several positioning accuracies based on machine learning algorithms. The experimental results show that the performance of the GBDT algorithm is better than that of KNN, SVM and RF, and the performance of the regression method is better than the classification method for the same machine learning algorithm. In addition, we introduce filtering methods in the online phase. The simulation results indicate that the Kalman filtering method can further improve the positioning accuracy.