GLoc: GNN in Indoor Localization

Indoor positioning holds significant application value in fields, such as smart homes and industrial IoT. However, CNN-based positioning methods do not effectively utilize the topological structure of positional relationships between access points and smart devices. This limitation hampers their ability to accurately model and interpret the spatial dependencies inherent in indoor environments. This article proposes a GLoc algorithm, which is the first to introduce graph neural networks (GNNs) into Wi-Fi-based indoor positioning. The method models the positioning environment as a graph structure consisting of location nodes and signal feature edges, leveraging GNNs to capture spatial dependencies and signal distribution characteristics between different locations. On a 144-m2 dataset, GLoc demonstrates excellent positioning accuracy, with a median accuracy of 23 cm, and 90% of the estimates within a 97-cm range. Compared to existing techniques, GLoc also exhibits stronger robustness and higher positioning accuracy in dynamic environments. This method opens new possibilities for advancing indoor positioning technology and may spur progress in related fields.