Foundations of Cyber-Physical Networks

Abstract:

Cyber Physical Systems (CPSs) integrate physical devices (e.g., sensors, cameras) with cyber components to form a situation-aware analytical system. The overall research objective of the project is to reveal cross-cutting fundamental scientific and engineering principles that underpin the integration of cyber and physical elements across all application sectors. Here we provide an overview of our recent research achievements:

• Mining Event Periodicity from Incomplete Observations [KDD'12]
• Nokia Location Prediction Competition (received No. 2 in the Nokia Challenge International Competition)
• "Mining lines in sand" [KDD'13]: detection of moving intruders from untrustworthy sensors (One of the best papers in 2013 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, invited to submission to the KDD'13 special issue of journal ACM Trans. on KDD)
• Attraction and avoidance detection from Movements [VLDB'14] (accepted by VLDB'13 conference and PVLDB journal)
• The development of MoveMine system and integrated to the Movebank system (delivered to Moverbank.org, integrated with the MoveBank system, which has been the major research platform used by animal scientists internationally).
• The new findings have been published in the proceedings of multiple international conferences and scientific journals and also lead to multiple tutorials and invited speeches in international conferences.

The research has trained a good number of students: Two received Ph.Ds (Zhenhui Jessie Li: joined Penn State Univ. as assistant professor, and Lu An Tang joined NEC Lab as a research scientist). Currently, the group consists of Ph.D. students: Jingjing Wang, Chao Zhang, and MS students: Tobias Lei and Tanvi Jindal. The progress of the project and the research results are also disseminated via the project Web site: http://www.cs.uiuc.edu/homes/hanj/projs/cps.htm.