log in  |  register  |  feedback?  |  help
Information Fusion and Sensemaking at Scale
Wednesday, October 25, 2017, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)

Information fusion deals with reconstructing objects from multiple observations. Such observations can be partial and inconsistent. The concept of information fusion has been used in different contexts including multi-sensor data fusion, human-centered information fusion, and information fusion for data integration. As an example consider the challenge of historical information fusion, where researchers need to recover numbers of historical events from aggregated, possibly overlapping reports. For instance, given the monthly and weekly sums, how can we find the daily counts of people infected with flu? What is the best way to recover such historical counts in the presence of missing values and how much should we trust this reconstruction?

The task of scalable information fusion is critical for interdisciplinary research where a comprehensive picture of the subject requires large amounts of data from disparate data sources. In this talk I will introduce an efficient framework that enables systematic information fusion in different application domains. In particular, I will consider how concepts of information fusion and crowdsourcing complement each other and accelerate novel research directions in scalable information sensemaking. I will explore each of those concepts and their synergy under scenarios of large-scale historical data integration and situation assessment in multi-robot search and rescue


Vladimir Zadorozhny (www.pitt.edu/~viz) is an Associate Professor at the University of Pittsburgh School of Computing and Information. He received his Ph.D. in 1993 from the Institute for Problems of Informatics, Russian Academy of Sciences in Moscow. Before coming to USA he was a Principal Research Scientist in the Institute of System Programming, Russian Academy of Sciences. Since 1998 he worked as a Research Associate in the University of Maryland Institute for Advanced Computer Studies at College Park. He joined University of Pittsburgh in 2001. His research interests include information integration and fusion, complex adaptive systems and crowdsourcing, query optimization in resource-constrained distributed environments, sensor data management, and scalable architectures for wide-area environments with heterogeneous information servers. His research has been supported by NSF, EU and Norwegian Research Council. Vladimir is a recipient of Fulbright Scholarship for 2014-2015.  He has received several best paper awards and has chaired and served on program committees of multiple Database and Distributed Computing Conferences and Workshops.


This talk is organized by Marine Carpuat