November 20, 2009, Natallia Katenka, University of Michigan
Friday, November 20, 2009 at 2 PM
Photonics Center, 8 St. Mary’s Street, Room 211
Natallia Katenka, Ph.D. Student
Department of Statistics, University of Michigan
webpage
Tracking Multiple Targets Using Binary Decisions from Wireless Sensor Networks
Wireless sensor networks (WSN) are a new technology with many applications, including environmental monitoring, surveillance, and health care. This work introduces a novel framework for tracking multiple targets over time using binary decisions collected by a wireless sensor network, and applies the methodology to two case studies ? an experiment involving tracking people and a project tracking zebras. Unlike most existing methods, proposed tracking approach is based on a penalized maximum likelihood framework, and allows for sensor failures, targets appearing and disappearing over time, and complex intersecting target trajectories. The results show that binary decisions first corrected locally by a previously developed method known as local vote decision fusion provide the most robust performance in noisy environments and high accuracy in tracking applications.
Natallia Katenka is a postdoctoral Fellow at the Boston University Department of Mathematics and Statistics working with Professor Eric Kolaczyk. Her current research interests lie in the statistical analysis of network data including theoretical methodology for multivariate and functional data analysis with applications to sensor networks, social networks, biological networks, internet networks, and also to related problems in neuroscience, bioinformatics, and signal processing. Natallia received the B.S. and M.S. degrees with honors in Applied Mathematics and Computer Science from the Belarusian State University, Minsk, Belarus, in 2003 and 2004, respectively; and recently graduated with the PhD in Statistics from the University of Michigan, Ann Arbor. The major contributions of her PhD research are the design and application of wireless sensor networks to target detection, localization, and tracking.
Hosted by Professor Eric Kolaczyk.