The ubiquity of WiFi infrastructure has motivated significant research into WiFi-based indoor positioning systems as practical alternatives to GNSS. While deep learning approaches show promise, existing models face three critical limitations: (1) inadequate modeling of long-range feature dependencies, (2) difficulty in correcting time-of-flight (ToF) offsets induced by device clock asynchrony, and (3) prohibitive computational costs for environmental adaptation through model retraining. This paper introduces SwinULoc, a novel U-shaped indoor positioning framework that synergizes Swin Transformer blocks with 2D CSI heatmap processing. Our architecture uniquely addresses these challenges through three key innovations: First, the integration of shifted window attention mechanisms enables effective learning of long-range signal correlations. Second, a multi-access-point fusion strategy enhanced with skip connections achieves precise ToF offset correction through cross-device pattern analysis and multi-scale feature integration. Third, a transfer learning paradigm reduces retraining costs by 75% compared to conventional approaches. Extensive evaluations demonstrate SwinULoc's superiority, achieving 70% higher positioning accuracy than state-of-the-art baselines while requiring only 1/4 of the training resources for new environments.

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.