Ambient Intelligence for Better Buildings

Humble sensors do not imply humble observations.

In the future buildings will be studded with sensors. Every movement will generate a few bits of data. Every fluctuation in temperature will be recorded. Every deviation in lighting will be noticed. These large and complex datasets will challenge the tools we use today. Are the tools we use to understand our data scalable to the tens of millions of records, huge spans of time, minute details of behavior, and large geographic extent that future sensor networks will generate?

These sensors will be installed to make our lives better: to make our buildings more comfortable, more efficient, and more enriching places to live and work. The sensors seem non-threatening, because they are so simple. Everyone understands that there is a danger to installing networks of cameras or microphones in buildings, but what of these simple sensors? It's important to explore these questions and understand how much we can learn about the people living under these sensors.

Our research shows that simple sensors can be used to make building systems more efficient. They can also be used to make camera networks far more powerful. They can be used to measure the work habits of people. They also expose the habitual patterns of the social web that connects us to co-workers and friends. We find that even simple sensors reach deeply into our lives when they become ubiquitous.

Researchers may be interested in the MERL Motion Sensor Dataset.

Please find more information on the MERL Project Page

Select Bibliography

Visualizing History of Living Spaces
Yuri A. Ivanov, Christopher R. Wren, Alexander Sorokin, Ishwinder Kaur. IEEE Transactions on Visualization and Computer Graphics, ISSN: 1077-2626, Volume 13, number 6. Nov-Dec 2007 IEEE Xplore, ( MERL TR2007-068)
SocialMotion: Measuring the Hidden Social Life of a Building
Christopher R. Wren, Yuri A. Ivanov, Ishwinder Kaur, Darren Leigh, Jonathan Westhues. Third International Symposium on Location- and Context-Awareness. September 2007. Oberpfaffenhofen, Germany. DOI () MERL TR2007-034)
Buzz: Measuring and Visualizing Conference Crowds
Christopher R. Wren, Yuri A. Ivanov, Darren Leigh, Jonathan Westhues, Mariela Buchin, Pavan Turaga. ACM SIGGRAPH 2007 Emerging Technologies, San Diego, CA, USA. August 2007. DOI ( MERL TR2007-035)
Toward Scalable Activity Recognition for Sensor Networks
Christopher R. Wren and Emmanuel Munguia Tapia. Second International Workshop on Location- and Context-Awareness. May 2006. Dublin, Ireland. DOI. ( MERL TR2006-011)
Worse is Better for Ambient Sensing
Carson J. Reynolds and Christopher R. Wren Pervasive 2006 Workshop on Privacy, Trust and Identity Issues for Ambient Intelligence. May 7th, 2006. Dublin, Ireland. ( MERL TR2006-005)
Functional Calibration for Pan-Tilt-Zoom Cameras in Hybrid Sensor Networks
Christopher R. Wren, U. Murat Erdem, Ali J. Azarbayejani. ACM Multimedia Systems Journal, Special Issue on Multimedia Surveillance Systems. Volume 12, number 3. December 2006. DOI ( MERL TR2005-084)
Similarity-based analysis for large networks of ultra-low resolution sensors
Christopher R. Wren, David Minnen, and Srinivas G. Rao. Pattern Recognition. Special Issue on Similarity-Based Pattern Recognition. Volume 39, number 10, October 2006. DOI ( MERL TR2005-003)

Christopher R. Wren, c@drwren.com
Last modified: Thu May 8 14:29:15 2008