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

TL;DR

SimDeep is a federated learning framework for 3D indoor localization that uses similarity-aware aggregation to handle non-IID data and device heterogeneity, achieving high accuracy in complex environments.

Contribution

The paper introduces SimDeep, a novel federated learning approach with similarity-based aggregation to improve indoor localization under challenging data conditions.

Findings

Achieves 92.89% localization accuracy.

Outperforms traditional federated and centralized methods.

Effectively manages non-IID data and device heterogeneity.

Abstract

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.