.png){kind=icon}
.png){kind=icon}
Return
Enhanced Gaussian Process-Based Localization Using a Low Power Wide Area Network
.png){kind=icon}
PRE
AI
DOI：10.1109/LCOMM.2018.2878704.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
With the recent advances of technology innovation in the Internet-of-Things (IoT) era, radio chips are able to transmit over long distances with extremely low energy consumption. While extending the range of communication links, the ability to provide large scale location-based services (LBS) solutions using native physical layer parameters from IoT networks will dramatically widen the availability of IoT applications. This letter proposes an enhanced Gaussian process-based localization solution for such a low power wide area network (LPWAN). It effectively deals with intermittent signals over a large area caused by low communication throughput, interference or packet collisions in LPWAN. Furthermore, a parametric model enhancement combining indoor and outdoor hypotheses and signal propagation statistics is proposed and evaluated. Field tests over a 37,500 square meter area have been conducted. Results show that the proposed method can provide LBS-quality positioning with a 2-D root mean square error of 20 to 30 meters, with an accuracy improvement of 29.8% outdoors and 40.6% indoors, respectively, compared to the traditional fingerprinting method.
Keywords:
Gaussian process
navigation
maximum likelihood estimation
multipath interference
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.4
Papers:
1.3W
Citations:
2.2W