Improving GPS-based Indoor-Outdoor Detection with Moving Direction Information from Smartphone
Publication/Creation DateSeptember 9 2015
DescriptionThis paper presents an improvement for GPS-based indoor-outdoor detection with moving direction information. First, we considered several features based on raw GPS satellite information as the baseline. From the evaluation with GPS data from 19 persons, the SVM-based classifier using a combination of elevation and S/N ratio achieved over 96% accuracy for the simple ‘clear’ situation. Then we introduced direction information from a compass sensor to increase the detection robustness in the canyon of buildings. The second experimentation result showed the proposed method considering direction information kept almost the same accuracy of indoor-outdoor detection in a ‘canyon’ situation, whereas the baseline classifier worsened accuracy by 10%.
Date archivedOctober 31 2015
Last editedSeptember 26 2018
How to cite this entry
Masayuki Okamoto, Cheng Chen. (September 9 2015). "Improving GPS-based Indoor-Outdoor Detection with Moving Direction Information from Smartphone
". 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing Adjunct Publication (UbiComp/ISWC 2015 Adjunct). International Joint Conference On Pervasive And Ubiquitous Computing Adjunct Publication. Fabric of Digital Life. https://fabricofdigitallife.com/index.php/Detail/objects/1334