English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Wi-Fi fingerprinting becomes a dominant solution for large-scale indoorlocalization due to its major advantage of not requiring new infrastructure anddedicated devices. The number and the distribution of Reference Points (RPs)for the measurement of localization fingerprints like RSSI during the offlinephase, however, greatly affects the localization accuracy; for instance, theUJIIndoorLoc is known to have the issue of uneven spatial distribution of RPsover buildings and floors. Data augmentation has been proposed as a feasiblesolution to not only improve the smaller number and the uneven distribution ofRPs in the existing fingerprint databases but also reduce the labor and timecosts of constructing new fingerprint databases. In this paper, we propose themultidimensional augmentation of fingerprint data for indoor localization in alarge-scale building complex based on Multi-Output Gaussian Process (MOGP) andsystematically investigate the impact of augmentation ratio as well as MOGPkernel functions and models with their hyperparameters on the performance ofindoor localization using the UJIIndoorLoc database and the state-of-the-artneural network indoor localization model based on a hierarchical RNN. Theinvestigation based on experimental results suggests that we can generatesynthetic RSSI fingerprint data up to ten times the original data -- i.e., theaugmentation ratio of 10 -- through the proposed multidimensional MOGP-baseddata augmentation without significantly affecting the indoor localizationperformance compared to that of the original data alone, which extends thespatial coverage of the combined RPs and thereby could improve the localizationperformance at the locations that are not part of the test dataset.

On the Multidimensional Augmentation of Fingerprint Data for Indoor  Localization in A Large-Scale Building Complex Based on Multi-Output Gaussian  Process