This demo presents the Panda system for efficient support of a wide variety of predictive spatio-temporal queries. These queries are widely used in several applications including traffic management, location-based advertising, and store finders. Panda targets long-term query prediction as it relies on adapting a long-term prediction function to: (a) scale up to large number of moving objects, and (b) support predictive queries. Panda does not only aim to predict the query answer, but, it also aims to predict the incoming queries such that parts of the query answer can be precomputed before the query arrival. Panda maintains a tunable threshold that achieves a trade-off between the predictive query response time and the system overhead in precomputing the query answer. Equipped with a Graphical User Interface (GUI), audience can explore the Panda demo through issuing predictive queries over a moving set of objects on a map. In addition, they are able to follow the execution of such queries through an eye on the Panda execution engine.
|Original language||English (US)|
|Title of host publication||Proceedings - 2015 IEEE 16th International Conference on Mobile Data Management, MDM 2015|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||4|
|State||Published - Sep 11 2015|
|Event||16th IEEE International Conference on Mobile Data Management, MDM 2015 - Pittsburgh, United States|
Duration: Jun 15 2015 → Jun 18 2015
|Name||Proceedings - IEEE International Conference on Mobile Data Management|
|Other||16th IEEE International Conference on Mobile Data Management, MDM 2015|
|Period||6/15/15 → 6/18/15|
Bibliographical noteFunding Information:
This work is partially supported by the National Science Foundation, USA, under Grants IIS-0952977 and IIS-1218168.