STELLAR: Siamese Multi-Headed Attention Neural Networks for Overcoming Temporal Variations and Device Heterogeneity with Indoor Localization
This addresses accuracy and adoption issues in indoor localization for mobile and IoT devices, though it appears incremental as it builds on existing contrastive learning and attention mechanisms.
The authors tackled the challenges of device heterogeneity and temporal variations in smartphone-based indoor localization by proposing STELLAR, a contrastive learning framework using Siamese multi-headed attention neural networks. Their evaluations showed accuracy improvements of 8-75% for device heterogeneity and 18-165% for temporal variations over 2 years compared to state-of-the-art methods.
Smartphone-based indoor localization has emerged as a cost-effective and accurate solution to localize mobile and IoT devices indoors. However, the challenges of device heterogeneity and temporal variations have hindered its widespread adoption and accuracy. Towards jointly addressing these challenges comprehensively, we propose STELLAR, a novel framework implementing a contrastive learning approach that leverages a Siamese multi-headed attention neural network. STELLAR is the first solution that simultaneously tackles device heterogeneity and temporal variations in indoor localization, without the need for retraining the model (re-calibration-free). Our evaluations across diverse indoor environments show 8-75% improvements in accuracy compared to state-of-the-art techniques, to effectively address the device heterogeneity challenge. Moreover, STELLAR outperforms existing methods by 18-165% over 2 years of temporal variations, showcasing its robustness and adaptability.