Accurate and efficient floor localization with scalable spiking graph neural networks  

作　　者：Fuqiang Gu Fangming Guo Fangwen Yu Xianlei Long Chao Chen Kai Liu Xuke Hu Jianga Shang Songtao Guo 

机构地区：[1]College of Computer Science,Chongqing University,Chongqing,China [2]Department of Precision Instrument,Tsinghua University,Beijing,China [3]Institute of Data Science,German Aerospace Center(DLR),Jena,Germany [4]School of Computer Science,China University of Geosciences,Wuhan,China

出　　处：《Satellite Navigation》2024年第1期191-206,共16页卫星导航（英文）

基　　金：supported by the National Natural Science Foundation of China(No.42174050,62172066,62172064,62322601);National Science Foundation for Excellent Young Scholars(No.62322601);Open Research Projects of Zhejiang Lab(No.K2022NB0AB07);Venture&Innovation Support Program for Chongqing Overseas Returnees(No.cx2021047);Chongqing Startup Project for Doctorate Scholars(No.CSTB2022BSXM-JSX005);Excellent Youth Foundation of Chongqing(No.CSTB2023NSCQJQX0025);China Postdoctoral Science Foundation(No.2023M740402);Fundamental Research Funds for the Central Universities(No.2023CDJXY-038,2023CDJXY-039).

摘　　要：Floor localization is crucial for various applications such as emergency response and rescue,indoor positioning,and recommender systems.The existing floor localization systems have many drawbacks,like low accuracy,poor scalability,and high computational costs.In this paper,we first frame the problem of floor localization as one of learning node embeddings to predict the floor label of a subgraph.Then,we introduce FloorLocator,a deep learning-based method for floor localization that integrates efficient spiking neural networks with powerful graph neural networks.This approach offers high accuracy,easy scalability to new buildings,and computational efficiency.Experimental results on using several public datasets demonstrate that FloorLocator outperforms state-of-the-art methods.Notably,in building B0,FloorLocator achieved recognition accuracy of 95.9%,exceeding state-of-the-art methods by at least 10%.In building B1,it reached an accuracy of 82.1%,surpassing the latest methods by at least 4%.These results indicate FloorLocator’s superiority in multi-floor building environment localization.

关 键 词：Indoor positioning Deep learning Floor localization Spiking neural networks Graph neural networks 

分 类 号：O15[理学—数学]