论文信息 - A population model for predicting human mobility

A population model for predicting human mobility

We present a population model for predicting users' next relevant place. Our findings demonstrate the robustness of our population model in terms of the difference in accuracy with respect to users' individual models, which is for more than 90% of the users less than 3.5 percentage points.

Silvia Santini | Anind K. Dey | Paul Baumann | Christian Koehler

[1] Philip S. Yu,et al. Top 10 algorithms in data mining , 2007, Knowledge and Information Systems.

[2] Silvia Santini,et al. The influence of temporal and spatial features on the performance of next-place prediction algorithms , 2013, UbiComp.

[3] Anna Monreale,et al. WhereNext: a location predictor on trajectory pattern mining , 2009, KDD.

[4] Cecilia Mascolo,et al. NextPlace: A Spatio-temporal Prediction Framework for Pervasive Systems , 2011, Pervasive.

[5] Josef Kittler,et al. Floating search methods for feature selection with nonmonotonic criterion functions , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[6] Christopher M. Bishop,et al. Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[7] Imad Aad,et al. The Mobile Data Challenge: Big Data for Mobile Computing Research , 2012 .

[8] Eric Horvitz,et al. Predestination: Inferring Destinations from Partial Trajectories , 2006, UbiComp.