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.
| Original language | English |
|---|---|
| Pages (from-to) | 860-865 |
| Number of pages | 6 |
| Journal | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences |
| Volume | E102A |
| Issue number | 6 |
| DOIs | |
| Publication status | Published - 2019 Jan 1 |
Fingerprint
Keywords
- Indoor/outdoor detection
- Random forest classifier
- Sparse GPS
ASJC Scopus subject areas
- Signal Processing
- Computer Graphics and Computer-Aided Design
- Electrical and Electronic Engineering
- Applied Mathematics
Cite this
A robust indoor/outdoor detection method based on spatial and temporal features of sparse GPS measured positions. / Iwata, Sae; Ishikawa, Kazuaki; Takayama, Toshinori; Yanagisawa, Masao; Togawa, Nozomu.
In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E102A, No. 6, 01.01.2019, p. 860-865.Research output: Contribution to journal › Article
}
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 -