Using GPS to learn significant locations and predict movement across multiple users
Personal and Ubiquitous Computing
Reality mining: sensing complex social systems
Personal and Ubiquitous Computing
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Extraction of social context and application to personal multimedia exploration
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Learning and inferring transportation routines
Artificial Intelligence
Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Mining interesting locations and travel sequences from GPS trajectories
Proceedings of the 18th international conference on World wide web
A Hybrid Prediction Model for Moving Objects
ICDE '08 Proceedings of the 2008 IEEE 24th International Conference on Data Engineering
WhereNext: a location predictor on trajectory pattern mining
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Learning and predicting multimodal daily life patterns from cell phones
Proceedings of the 2009 international conference on Multimodal interfaces
IEEE Transactions on Multimedia
Now let me see where i was: understanding how lifelogs mediate memory
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Predestination: inferring destinations from partial trajectories
UbiComp'06 Proceedings of the 8th international conference on Ubiquitous Computing
The geography of taste: analyzing cell-phone mobility and social events
Pervasive'10 Proceedings of the 8th international conference on Pervasive Computing
Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication
Hi-index | 0.00 |
In this paper, we propose a method for predicting future locations of a person by exploiting the person's past lifelog data. To predict the future location of a person has many applications such as the delivery of information related to the predicted locations: information with limited lifetimes (sales in a supermarket), weather reports, and traffic reports. Most existing methods for prediction only use historical location data, thus they can only handle regular movements; irregular movements are not considered. Our method predicts future locations by using personal calendar entries in addition to GPS(Global positioning system) data. Using calendar entries makes it possible to predict the locations associated with the irregular events indicated by the entries. We make Dynamic Bayesian Networks models for integrating these different kinds of lifelog data so as to yield better predictions. In experiments on real data, our methods can predict irregular movements successfully even with long lead-times, while matching the accuracy of existing schemes in predicting usual movements.