Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories

2025-05-12

AI Summary

To address low vertical localization accuracy—specifically floor identification—in multi-level indoor environments, this paper proposes a trajectory-driven graph embedding method for Wi-Fi fingerprint-based floor separation. We construct a fingerprint graph where access points serve as nodes and weighted edges encode both signal similarity and trajectory-aware contextual transitions. Node2Vec is employed to learn discriminative node embeddings, followed by unsupervised floor clustering via K-means. This work is the first to integrate graph embedding with trajectory-aware Wi-Fi fingerprint modeling, significantly enhancing robustness against signal noise and complex building structures. Evaluated on the Huawei University Challenge 2021 dataset, our method achieves 68.97% floor identification accuracy, an F1-score of 61.99%, and an Adjusted Rand Index of 57.19%—all substantially outperforming baseline approaches. The source code and preprocessed data are publicly available.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Indoor positioning systems (IPSs) are increasingly vital for location-based services in complex multi-storey environments. This study proposes a novel graph-based approach for floor separation using Wi-Fi fingerprint trajectories, addressing the challenge of vertical localization in indoor settings. We construct a graph where nodes represent Wi-Fi fingerprints, and edges are weighted by signal similarity and contextual transitions. Node2Vec is employed to generate low-dimensional embeddings, which are subsequently clustered using K-means to identify distinct floors. Evaluated on the Huawei University Challenge 2021 dataset, our method outperforms traditional community detection algorithms, achieving an accuracy of 68.97%, an F1- score of 61.99%, and an Adjusted Rand Index of 57.19%. By publicly releasing the preprocessed dataset and implementation code, this work contributes to advancing research in indoor positioning. The proposed approach demonstrates robustness to signal noise and architectural complexities, offering a scalable solution for floor-level localization.

Problem

• Addresses vertical localization in multi-storey indoor environments
• Improves floor separation accuracy using WiFi trajectory clustering
• Enhances robustness to signal noise and architectural complexities

Innovation

• Graph-based floor separation using WiFi trajectories
• Node2Vec embeddings for low-dimensional representation
• K-means clustering to identify distinct floors