Machine Learning and Intelligent Communications. Third International Conference, MLICOM 2018, Hangzhou, China, July 6-8, 2018, Proceedings

Research Article

Highly-Available Localization Techniques in Indoor Wi-Fi Environment: A Comprehensive Survey

  • @INPROCEEDINGS{10.1007/978-3-030-00557-3_45,
        author={Mu Zhou and Oyungerel Bulgantamir and Yanmeng Wang},
        title={Highly-Available Localization Techniques in Indoor Wi-Fi Environment: A Comprehensive Survey},
        proceedings={Machine Learning and Intelligent Communications. Third International Conference, MLICOM 2018, Hangzhou, China, July 6-8, 2018, Proceedings},
        proceedings_a={MLICOM},
        year={2018},
        month={10},
        keywords={Wi-Fi localization RSS correlation Smooth filtering Neighbor matching Bayesian estimation},
        doi={10.1007/978-3-030-00557-3_45}
    }
    
  • Mu Zhou
    Oyungerel Bulgantamir
    Yanmeng Wang
    Year: 2018
    Highly-Available Localization Techniques in Indoor Wi-Fi Environment: A Comprehensive Survey
    MLICOM
    Springer
    DOI: 10.1007/978-3-030-00557-3_45
Mu Zhou1,*, Oyungerel Bulgantamir1,*, Yanmeng Wang1,*
  • 1: Chongqing University of Posts and Telecommunications
*Contact email: zhoumu@cqupt.edu.cn, oyukagerele@gmail.com, hiwangym@gmail.com

Abstract

With the increasing interests on received signal strength (RSS) fingerprint-based Wi-Fi localization, the requirement of recording reliable and accurate RSS fingerprints for radio map construction becomes a significant concern. The neighbor matching and Bayesian estimation is recognized as the two most representative algorithms for RSS fingerprint-based indoor Wi-Fi localization. To guarantee the accuracy performance of neighbor matching and Bayesian estimation algorithms, we introduce several method to eliminate RSS sample noise for the sake of improving the distance dependency of Wi-Fi RSS fingerprints.