研究概要

研究テーマ

• 自律学習型環境知能CPS
• 地震発生予測モデル
• 地震動モデル

主要論文

「*」は、理研外のみでの成果です。

• 1.*Ueda, N.
  "Proactive People-flow Navigation Based on Spatio-temporal Prediction"
  Japanese Journal Applied Statistics, Vol.45, No.3, pp.89-104, 2016, (invited).
• 2.*Iwata, T., Shimizu, H., Naya, F., and Ueda, N.:
  "Estimating people flow from spatio-temporal population data via collective graphical mixture models"
  ACM Transactions on Spatial Algorithms and Systems, Vol. 3, Issue 1, Article 39. 2017.
• 3.*Ueda, N., Naya, F., Shimizu, H., Iwata, T., Okawa, M., and Sawada, H.:
  "Real-time and proactive navigation via spario-temporal prediction"
  Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers(UbiComp 2015), pp. 1559-1566, 2015.
• 4.*Takeuchi, K., and Ueda, N.:
  "Graph regularized non-negative tensor completion for spatio-temporal data analysis"
  The Second International Workshop on Smart Cities, 2016.
• 5.*Saito, K. Ohara, K. Kimura, M. and Motoda, H.:
  "An Accurate and Efficient method to Detect Critical Links to Maintain Information Flow in Network"
  Proc. of the 23th International Symposium on Methodologies for Intelligent Systems (ISMIS2017), pp.116--126, 2017.
• 6.*Saito, K, Kimura, M. Ohara, K. and Motoda, H.:
  "Detecting Critical Links in Complex Network to Maintain Information Flow/Reachability"
  Proc. of the 14th Pacific Rim International Conference on Artificial Intelligence (PRICAI2016), pp.419-432, 2016.
• 7.*Toda, R., Inuue, S., and Ueda, N.:
  "Mobile Activity Recognition from Training Labels with Inaccurate Activity Segments (Best paper candidate)"
  International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous) (Acceptance Rate: 30%), pp. 57-64, 2016

研究成果（プレスリリース）

• 

  2022年12月1日
  物理と深層学習による地殻変動解析

関連リンク

メンバーリスト

お問い合わせ先