arXiv：cs.LG· Rabia Yasa Kostas, Kahraman Kostas·· 4 小时前AI 评分27
基于图与 Node2Vec 节点嵌入的 WiFi 轨迹楼层分离方法
Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories
AI 导读
一项新研究提出基于图的楼层分离方法，将 WiFi 指纹作为节点、信号相似度与上下文转移作为边权构建图，再用 Node2Vec 生成低维嵌入并经 K-means 聚类识别楼层。在华为 University Challenge 2021 数据集上，该方法取得 68.97% 准确率、61.99% F1 分数和 57.19% 调整兰德指数，优于传统社区发现算法。作者公开了预处理数据集与实现代码。
正文
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.
| Comments: | Version 2 is re-uploaded to replace the withdrawn Version 3 and to appear as the active version of the paper |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG); Robotics (cs.RO) |
| Cite as: | arXiv:2505.08088 [cs.NI] |
| (or arXiv:2505.08088v5 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2505.08088 arXiv-issued DOI via DataCite |
Submission history
From: Kahraman Kostas Dr [view email]
[v1]
Mon, 12 May 2025 21:46:36 UTC (627 KB)
[v2]
Fri, 13 Jun 2025 15:48:03 UTC (853 KB)
[v3]
Sun, 1 Feb 2026 20:05:26 UTC (1,238 KB)
[v4]
Mon, 5 Oct 2026 08:09:01 UTC (1 KB) (withdrawn)
[v5]
Wed, 7 Oct 2026 08:19:55 UTC (849 KB)
来源：arXiv：cs.LG · arxiv.org