9 March 2026 in Knowledge-Based Systems
11 March 2025 in IEEE Internet of Things Journal
This paper focuses on the accuracy and practicality of geomagnetic-based indoor localization in large-scale real-world sites. Previous studies often use continuous geomagnetic sequences for better discriminability but ignore that longer sequences, while more accurate, increase response times. Shorter sequences enhance practicality but sacrifice accuracy. Additionally, varying walking speeds can cause sequence variations along the same path, leading to ambiguity. To address these challenges, we propose a spatial-temporal constrained indoor localization model (STC-loc) that enables both accurate and practical localization using geomagnetic sequences collected at arbitrary walking speeds. Specifically, we first design a speed-oriented adaptive normalization module to tackle the walking speed heterogeneity problem. Then to balance accuracy and practicality, we initially employ shorter sequences as input and a self-attention hierarchical structure to efficiently extract the temporal features for initial location estimation. Subsequently, we further apply an Encoder-Decoder based refinement strategy, leveraging spatial contextual for continuous localization to ensure accuracy and robustness. Additionally, a slide-window based two-phase system architecture optimizes processing efficiency and scalability. Experiments on three large-scale real-world sites have demonstrated the superiority of the proposed STC-loc, reducing the localization error by more than 43% with shorter geomagnetic sequences.
16 March 2026 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Geomagnetic indoor localization has emerged as a promising direction, mainly because geomagnetism is ubiquitous indoors, relatively stable and does not require external infrastructure support. Prior approaches mainly leverage temporal correlations in geomagnetic sequences for location inference. However, geomagnetic sequences in practical trial sites could be ambiguous due to environmental (e.g., similar building structures) and user factors (e.g., directions, speeds), leading to degraded localization accuracy.; AB@To address the above challenges, we propose
GRETE
, which injects relative trajectory encoding to enhance the localization accuracy. Our key contributions are as follows. First, we design a rotary position-based relative trajectory encoding module. By taking relative directions and distances between user's positions during walking into consideration, GRETE effectively captures the latent spatial clues in trajectories. We enhance geomagnetic temporal features with trajectory encodings. Second, we propose a fine-grained contrastive learning method, where we divide the enhanced feature sequences into multiple subsequences. This guides the model to pay more attention to detailed differences in enhanced features, consequently improving their expressiveness and discriminability. We have conducted extensive experimental evaluations with two public datasets and one self-constructed dataset. Extensive experimental results show that GRETE consistently outperforms state-of-the-art competing schemes by a large margin (reducing mean localization error from 18.4% to 74.7%).
10 February 2026 in SSRN Electronic Journal
Indoor localization is a core technology for Internet of Things applications, but existing indoor positioning methods tend to suffer from poor positioning accuracy due to sensor noise and the short duration of signals collected during the cold-start phase. To address these issues, we propose CC-Loc, a cold-start multi-source collaborative localization framework that leverages geomagnetic signals and Bluetooth Low Energy (BLE) for infrastructure-free, high-precision positioning. Specifically, geomagnetic signals capture location-specific fingerprint features, while BLE RSSI models inter-device relative spatial relationships without precise distance conversion. However, the limited observation length at system startup inevitably introduces ambiguity in initial position estimation. To alleviate this issue, we design a cold start enhancement module that generates reliable predicted positions from short signal sequences. Building upon this initialization, we further enhance an encoder–decoder architecture with adjacency matrix–based spatial encoding and a Spatial Pyramid Pooling (SPP) layer to adapt to dynamic collaborative graphs and extract topological information. Additionally, we suppress BLE noise by a multi-task learning framework jointly optimizes the primary task, coordinate prediction and the auxiliary task, relative distance prediction. Experimental results show that our method achieves an error of only 2.93m in a trial site of 1750m^2, even when the length of the geomagnetic sequence at the initial startup phase is only one second. It effectively addresses cold-start challenges and adapts to dynamic multi-device collaboration, making it suitable for consumer-grade indoor localization applications.