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

研究成果: Article

1 引用 (Scopus)

抄録

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.

元の言語English
ページ(範囲)860-865
ページ数6
ジャーナルIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
E102A
発行部数6
DOI
出版物ステータスPublished - 2019 1 1

Fingerprint

Global positioning system
Classifiers
Random Forest
Learning systems
Classify
Classifier
Positioning
Experiments
Machine Learning
Calculate
Unknown
Cell
Demonstrate
Experiment

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

これを引用

@article{f7a47a37004a4365b5b9cb84cfe3a148,
title = "A robust indoor/outdoor detection method based on spatial and temporal features of sparse GPS measured positions",
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 = "Indoor/outdoor detection, Random forest classifier, Sparse GPS",
author = "Sae Iwata and Kazuaki Ishikawa and Toshinori Takayama and Masao Yanagisawa and Nozomu Togawa",
year = "2019",
month = "1",
day = "1",
doi = "10.1587/transfun.E102.A.860",
language = "English",
volume = "E102A",
pages = "860--865",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "6",

}

TY - JOUR

T1 - A robust indoor/outdoor detection method based on spatial and temporal features of sparse GPS measured positions

AU - Iwata, Sae

AU - Ishikawa, Kazuaki

AU - Takayama, Toshinori

AU - Yanagisawa, Masao

AU - Togawa, Nozomu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

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.

KW - Indoor/outdoor detection

KW - Random forest classifier

KW - Sparse GPS

UR - http://www.scopus.com/inward/record.url?scp=85069560046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069560046&partnerID=8YFLogxK

U2 - 10.1587/transfun.E102.A.860

DO - 10.1587/transfun.E102.A.860

M3 - Article

AN - SCOPUS:85069560046

VL - E102A

SP - 860

EP - 865

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 6

ER -