Johannes Gehrke

Affiliation

Cornell University

Research Interest

My research spans both data mining and distributed query processing. In data mining, we are building a distributed data-mining infrastructure that permits continuous monitoring of remote data sources, and we are working on improving the performance of existing data mining tools towards interactivity. My research in distributed query processing spans data management for sensor networks, processing queries over data streams, and peer-to-peer systems.

Foresight

The widespread distribution and availability of small-scale sensors, actuators, and embedded processors is transforming the physical world into a computing platform. Sensor networks consisting of a large number of sensor nodes that combine physical sensing capabilities with networking and computation capabilities will be deployed widely in the near future. We need a data management infrastructure to respond to the data tsunami, a system that scales with the growth of interconnectivity and computational power over the next decades, and provides scalable, fault-tolerant, flexible data access and intelligent data reduction, and its design will require novel research in database systems, data mining, networking, and fault-tolerance.