home


010101000111110101011101010101     
010010101011001010101010101010
000101101111101101110101101010
111011111011011101010101110110
001101101100101011110101101011
011010001011011010101001011011
011111110101101010101011111101
Workshop on

Hybrid Pervasive/Digital Inference

(HPDI 2011)


San Francisco, CA


Colocated with Pervasive 2011

June 12, 2011
010101000111110101011101010101     
010010101011001010101010101010
000101101111101101110101101010
111011111011011101010101110110
001101101100101011110101101011
011010001011011010101001011011
011111110101101010101011111101


CALL FOR PAPERS
Two different lines of research have developed around the topic of making inferences from data. One line arises from the analysis of physical data captured directly by sensors of real-world behaviors. These data include streams of GPS and WiFi sensors, accelerometers, compasses, gyroscopes, audio, and video, which are often processed to infer location, motion, co-presence, and identity. Another line arises from data captured about online behaviors. These include email messages, web browsing histories, application traces, keystroke loggers, online calendars, document repositories, tagging databases, and social networks. Analysis of online data sources is performed to infer topics of interest, retrieve information, and enhance collaboration.

Will these two types of data streams remain separate? Or will they come together in the near future? Smartphones have made it easy to collect physical data about people. Web 2.0 technologies have encouraged users to create and curate more information online. Together, these techniques could make inferences more accurate, more detailed, more "24-7" than ever before, and make completely new kinds of inferences possible.

However, there are challenges. It is not clear how to combine the different data sources. Because of the differences in types, and large amount of data involved, it may not be obvious how to combine data and inferences together into a useful application. The workshop has the following goals:

  • Discuss and understand how physical inference techniques can benefit applications that typically use only digital data. An example might be how location sensing can improve information retrieval.
  • Discuss and understand how digital inference techniques can benefit applications that typically use only physical data. An example might be how topic modeling can assist activity inference.
  • Discuss and understand how both data types can be blended in a single system, either to support a well-established application or a completely new one.
  • Discuss and understand how methods in one domain can assist the evaluation of an approach in the other.
Submissions should be prepared in LNCS format as PDF. The page limit is 4 pages. Samples and templates can be found at the Springer web site.  Submissions should be made
before 11:59pm EST (American East Coast Time) on Feb 4th, 2011 Feb 11th, 2011 at the HDPI EasyChair Submission Site.

DATES

Deadline for paper submission: February 4, 2011 February 11th, 2011
Notification of acceptance: March 11, 2011 March 18th, 2011


WORKSHOP ORGANIZERS

Kurt Partridge, Palo Alto Research Center
Oliver Brdiczka, Palo Alto Research Center
Judy Kay, University of Sydney
Bob Kummerfeld, University of Sydney
Paul Lukowicz, Universität Passau
Kai Kunze, Universität Passau

Partially sponsored by the ALLOW project.