Fast Graph - organic 3D graph for unsupervised location and mapping

التفاصيل البيبلوغرافية
العنوان: Fast Graph - organic 3D graph for unsupervised location and mapping
المؤلفون: Pendão, Cristiano Gonçalves, Moreira, Adriano
المساهمون: Universidade do Minho
بيانات النشر: Institute of Electrical and Electronics Engineers Inc., 2018.
سنة النشر: 2018
مصطلحات موضوعية: 3D-Graph, AP-Position Estimation, Force-Directed, Indoor Positioning, Unsupervised, Wi-Fi SLAM, Science & Technology
الوصف: It is well-known that fingerprinting-based positioning requires an exhaustive calibration phase to create a radio map, which often requires recalibration. Model-based and geometric approaches try to mitigate this effort at the expense of a lower accuracy or high computational cost. This paper introduces FastGraph, where a 3D graph is used to rapidly model the radio propagation environment. By means of unsupervised techniques, FastGraph is able to operate shortly after its deployment without previous knowledge about the environment. The proposed solution uses a novel algorithm to automatically provide location while simultaneously updating the radio map; and learn the position of the Access Points (APs) and location-specific radio propagation parameters. FastGraph has been evaluated in two real-world environments, a factory-plant and a regular university building, with results comparable to those obtained by conventional radio map-based solutions.
الوصف (مترجم): This work has been supported by COMPETE: POCI-01-0145-FEDER-007043 and FCT – Fundação para a Ciência eTecnologia within the Project Scope: UID/CEC/00319/2013 and the PhD fellowship PD/BD/105865/2014
وصف الملف: application/pdf
اللغة: English
العلاقة: 9781538656358; 2162-7347
DOI: 10.1109/IPIN.2018.8533746
الإتاحة: https://hdl.handle.net/1822/66222Test
حقوق: open access
رقم الانضمام: rcaap.com.repositorium.repositorium.sdum.uminho.pt.1822.66222
قاعدة البيانات: RCAAP