A Robust Indoor/Outdoor Detection Method Based on Spatial and Temporal Features of Sparse GPS Measured Positions

Sae IWATA; Kazuaki ISHIKAWA; Toshinori TAKAYAMA; Masao YANAGISAWA; Nozomu TOGAWA

doi:10.1587/transfun.E102.A.860

A Robust Indoor/Outdoor Detection Method Based on Spatial and Temporal Features of Sparse GPS Measured Positions

Sae IWATA, Kazuaki ISHIKAWA, Toshinori TAKAYAMA, Masao YANAGISAWA, Nozomu TOGAWA

Full Text Views

0

Cite this

Summary :

Cell phones with GPS function as well as GPS loggers are widely used and we can easily obtain users' geographic information. Now classifying the measured GPS positions into indoor/outdoor positions is one of the major challenges. In this letter, we propose a robust indoor/outdoor detection method based on sparse GPS measured positions utilizing machine learning. Given a set of clusters of measured positions whose center position shows the user's estimated stayed position, we calculate the feature values composed of: positioning accuracy, spatial features, and temporal feature of measured positions included in every cluster. Then a random forest classifier learns these feature values of the known data set. Finally, we classify the unknown clusters of measured positions into indoor/outdoor clusters using the learned random forest classifier. The experiments demonstrate that our proposed method realizes the maximum F₁ measure of 1.000, which classifies measured positions into indoor/outdoor ones with almost no errors.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E102-A No.6 pp.860-865

Publication Date: 2019/06/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E102.A.860

Type of Manuscript: LETTER

Category: Intelligent Transport System

Authors

Sae IWATA
  Waseda University
Kazuaki ISHIKAWA
  Zenrin DataCom Co., LTD.
Toshinori TAKAYAMA
  Zenrin DataCom Co., LTD.
Masao YANAGISAWA
  Waseda University
Nozomu TOGAWA
  Waseda University

Keyword

indoor/outdoor detection, sparse GPS, random forest classifier

Cite this

Copy

Sae IWATA, Kazuaki ISHIKAWA, Toshinori TAKAYAMA, Masao YANAGISAWA, Nozomu TOGAWA, "A Robust Indoor/Outdoor Detection Method Based on Spatial and Temporal Features of Sparse GPS Measured Positions" in IEICE TRANSACTIONS on Fundamentals, vol. E102-A, no. 6, pp. 860-865, June 2019, doi: 10.1587/transfun.E102.A.860.
Abstract: Cell phones with GPS function as well as GPS loggers are widely used and we can easily obtain users' geographic information. Now classifying the measured GPS positions into indoor/outdoor positions is one of the major challenges. In this letter, we propose a robust indoor/outdoor detection method based on sparse GPS measured positions utilizing machine learning. Given a set of clusters of measured positions whose center position shows the user's estimated stayed position, we calculate the feature values composed of: positioning accuracy, spatial features, and temporal feature of measured positions included in every cluster. Then a random forest classifier learns these feature values of the known data set. Finally, we classify the unknown clusters of measured positions into indoor/outdoor clusters using the learned random forest classifier. The experiments demonstrate that our proposed method realizes the maximum F₁ measure of 1.000, which classifies measured positions into indoor/outdoor ones with almost no errors.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E102.A.860/_p

Copy

@ARTICLE{e102-a_6_860,
author={Sae IWATA, Kazuaki ISHIKAWA, Toshinori TAKAYAMA, Masao YANAGISAWA, Nozomu TOGAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Robust Indoor/Outdoor Detection Method Based on Spatial and Temporal Features of Sparse GPS Measured Positions},
year={2019},
volume={E102-A},
number={6},
pages={860-865},
abstract={Cell phones with GPS function as well as GPS loggers are widely used and we can easily obtain users' geographic information. Now classifying the measured GPS positions into indoor/outdoor positions is one of the major challenges. In this letter, we propose a robust indoor/outdoor detection method based on sparse GPS measured positions utilizing machine learning. Given a set of clusters of measured positions whose center position shows the user's estimated stayed position, we calculate the feature values composed of: positioning accuracy, spatial features, and temporal feature of measured positions included in every cluster. Then a random forest classifier learns these feature values of the known data set. Finally, we classify the unknown clusters of measured positions into indoor/outdoor clusters using the learned random forest classifier. The experiments demonstrate that our proposed method realizes the maximum F₁ measure of 1.000, which classifies measured positions into indoor/outdoor ones with almost no errors.},
keywords={},
doi={10.1587/transfun.E102.A.860},
ISSN={1745-1337},
month={June},}

Copy

TY - JOUR
TI - A Robust Indoor/Outdoor Detection Method Based on Spatial and Temporal Features of Sparse GPS Measured Positions
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 860
EP - 865
AU - Sae IWATA
AU - Kazuaki ISHIKAWA
AU - Toshinori TAKAYAMA
AU - Masao YANAGISAWA
AU - Nozomu TOGAWA
PY - 2019
DO - 10.1587/transfun.E102.A.860
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E102-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2019
AB - Cell phones with GPS function as well as GPS loggers are widely used and we can easily obtain users' geographic information. Now classifying the measured GPS positions into indoor/outdoor positions is one of the major challenges. In this letter, we propose a robust indoor/outdoor detection method based on sparse GPS measured positions utilizing machine learning. Given a set of clusters of measured positions whose center position shows the user's estimated stayed position, we calculate the feature values composed of: positioning accuracy, spatial features, and temporal feature of measured positions included in every cluster. Then a random forest classifier learns these feature values of the known data set. Finally, we classify the unknown clusters of measured positions into indoor/outdoor clusters using the learned random forest classifier. The experiments demonstrate that our proposed method realizes the maximum F₁ measure of 1.000, which classifies measured positions into indoor/outdoor ones with almost no errors.
ER -