Much of data contained in large databases has explicit or implicit temporal information. Over the past decade, many powerful data mining techniques have been developed to analyze temporal and sequential data. TDM'06 will continue in the tradition of previous temporal data mining workshops at KDD but will focus on a specific topic: What can we infer about the structure of a complex dynamical system from observed temporal data? Properties that may be inferred include hierarchy, topology, sign (+/-), order, lag, lead, and strength of influences. The aim of this workshop is to critically evaluate the need in this area and identify promising technologies and methodologies for doing the same. We plan to bring together leading researchers from industry and academia for in-depth discussion. As a direct result of this workshop, we plan to come up with a position paper defining this topic.

• Functional genomics from time series
• Functional connectivity in neuronal systems from multi-electrode data
• Chemical process reconstruction from concentration measurements
• Disease spread from people movement data
• Root-cause diagnostics from plant-floor data
• Automotive prognostics from vehicle data

The purpose of this workshop hence is to bring together researchers from areas of temporal data mining, network reconstruction, and applications, and provide a forum for exchanging ideas, fostering collaborations, and gaining momentum.

• K. P. Unnikrishnan (Primary contact)
  General Motors R&D Center
  Warren, MI
  k.unnikrishnan@gm.com
  
  
• Naren Ramakrishnan
  Department of Computer Science
  Virginia Tech, Blacksburg, VA
  naren@cs.vt.edu
  
  
• P. S. Sastry
  Dept. of Electrical Engineering
  Indian Institute of Science
  Bangalore, India
  sastry@ee.iisc.ernet.in
  
  
• Ramasamy Uthurusamy
  General Motors IS&S
  Detroit, MI
  samy@gm.com