Machine Learning-Based Multi-Room Indoor Localization Using Fingerprint Technique

Nowadays, developing Wi-Fi-based indoor localization systems has become an attractive research topic due to the growing need for pervasive location determination. The fingerprint technique offers higher positioning accuracy in indoor localization than the distance-based technique. Fingerprint-based techniques via machine learning have been proposed for many years to provide high-accuracy indoor localization services. These works attempt to establish the optimal correlation between the user fingerprint and a pre-defined set of grid points on a radio map. In this paper, a comparative analysis of selected machine learning algorithms is conducted within the context of online phase fingerprint techniques for localization, focusing on implementation in a multi-room case. The experiment involves measurements using a Wi-Fi module in a laboratory, an aisle, a lobby, and a typical classroom, resulting in a small-sized fingerprint database covering a total area of 573.71 m2. The results reveal that Naïve Bayes (NB) obtains the highest localization accuracy in the laboratory and classroom. Meanwhile, Support Vector Machine (SVM) outperforms other algorithms in the aisle, while K-Nearest Neighbor (KNN) delivers the best accuracy in the lobby. In summary, NB, KNN, and SVM are suitable pattern-matching algorithms for multi-room indoor localization and relatively small fingerprint databases.