TY - GEN
T1 - Robust indoor/outdoor detection method based on sparse GPS positioning information
AU - Iwata, Sae
AU - Ishikawa, Kazuaki
AU - Takayama, Toshinori
AU - Yanagisawa, Masao
AU - Togawa, Nozomu
N1 - Funding Information:
ACKNOWLEDGEMENTS This research is supported in part by Waseda University Grant for Special Research Projects (Nos. 2018K-189 and 2018B-088).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/13
Y1 - 2018/12/13
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 paper, we propose a robust indoor/outdoor detection method based on sparse GPS positioning information 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 sequence of measured positions into indoor/outdoor positions using the learned random forest classifier. The experiments demonstrate that our proposed method realizes the $F-{1}$ measure of 0.9836, 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 paper, we propose a robust indoor/outdoor detection method based on sparse GPS positioning information 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 sequence of measured positions into indoor/outdoor positions using the learned random forest classifier. The experiments demonstrate that our proposed method realizes the $F-{1}$ measure of 0.9836, 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=85060275710&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060275710&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Berlin.2018.8576188
DO - 10.1109/ICCE-Berlin.2018.8576188
M3 - Conference contribution
AN - SCOPUS:85060275710
T3 - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
BT - 2018 IEEE 8th International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018
PB - IEEE Computer Society
T2 - 8th IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin 2018
Y2 - 2 September 2018 through 5 September 2018
ER -