From Global to Local: Cluster-Aware Learning for Wi-Fi Fingerprinting Indoor Localisation

2026-01-09

arXiv.org

AI Summary

This work addresses the degradation in localization accuracy in large-scale multi-floor Wi-Fi fingerprinting caused by data heterogeneity, signal fluctuations, and the neglect of spatial structure. To mitigate these issues, the authors propose a cluster-aware learning framework that first partitions fingerprint data into building- or floor-level clusters based on spatial or radio-frequency features. During inference, a test sample is assigned to the most relevant cluster according to its strongest access point and localized only within that cluster. This approach explicitly leverages structural priors in the data, decomposing the global localization problem into manageable local subproblems, thereby enhancing model scalability and localization consistency. Experiments on three public datasets demonstrate that the proposed strategy significantly reduces positioning error—particularly when using building-level clustering—at the cost of only a minor reduction in floor identification accuracy.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Clustering
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Wi-Fi fingerprinting remains one of the most practical solutions for indoor positioning, however, its performance is often limited by the size and heterogeneity of fingerprint datasets, strong Received Signal Strength Indicator variability, and the ambiguity introduced in large and multi-floor environments. These factors significantly degrade localisation accuracy, particularly when global models are applied without considering structural constraints. This paper introduces a clustering-based method that structures the fingerprint dataset prior to localisation. Fingerprints are grouped using either spatial or radio features, and clustering can be applied at the building or floor level. In the localisation phase, a clustering estimation procedure based on the strongest access points assigns unseen fingerprints to the most relevant cluster. Localisation is then performed only within the selected clusters, allowing learning models to operate on reduced and more coherent subsets of data. The effectiveness of the method is evaluated on three public datasets and several machine learning models. Results show a consistent reduction in localisation errors, particularly under building-level strategies, but at the cost of reducing the floor detection accuracy. These results demonstrate that explicitly structuring datasets through clustering is an effective and flexible approach for scalable indoor positioning.

Problem

• Wi-Fi fingerprinting
• indoor localisation
• RSSI variability
• multi-floor environments
• dataset heterogeneity

Innovation

• clustering
• Wi-Fi fingerprinting
• indoor localisation
• spatial features
• radio features