SimDeep: Federated 3D Indoor Localization via Similarity-Aware Aggregation

--Indoor localization plays a pivotal role in supporting a wide array of location-based services, including navigation, security, and context-aware computing within intricate indoor environments. Despite considerable advancements, deploying indoor localization systems in real-world scenarios remains challenging, largely because of non-independent and identically distributed (non-IID) data and device heterogeneity. In response, we propose SimDeep, a novel Federated Learning (FL) framework explicitly crafted to overcome these obstacles and effectively manage device heterogeneity. SimDeep incorporates a Similarity Aggregation Strategy, which aggregates client model updates based on data similarity, significantly alleviating the issues posed by non-IID data. Our experimental evaluations indicate that SimDeep achieves an impressive accuracy of 92.89%, surpassing traditional federated and centralized techniques, thus underscoring its viability for real-world deployment. While Global Positioning Systems (GPS) dominate outdoor positioning, indoor environments poses significant challenges for such systems. That is due to several factors that exist in such environments such as signal degradation and limited satellite visibility. These factors are seen as limitations in complex infrastructures such as multi-floor buildings, where accurate floor-level and room-level localization is essential. To overcome these challenges, alternative technologies--such as Bluetooth, Ultra-Wideband, inertial sensors, and cellular-based solutions--have been explored [1], [2], [3].