Robotics Institute
Seminar, September 8, 2006
Time and Place | Seminar Abstract | Speaker Biography | Speaker Appointments
Data Mining to Support Food Safety
Artur Dubrawski
Systems Scientist/Adj Professor Mism Prg
Carnegie Mellon
University
Mauldin
Auditorium (NSH 1305)
Refreshments 3:15 pm
Talk 3:30 pm
Unsafe
food can be blamed as the ultimate cause in several million instances of
illnesses and injuries occurring every year in the US. Vigilant monitoring and rapid
resolution of detected problems are crucial in effective mitigation of those
adverse effects. This talk presents one and very briefly reviews a few more
ongoing attempts to use statistical data mining in support of detection of
emerging patterns of safety problems in food supply. The analytical component
of the Consumer Complaint Monitoring System II is designed to help the USDA
Food Safety Inspection Service officials to efficiently and effectively monitor
incoming reports of adverse effects of food on its consumers. These reports,
collected in a passive surveillance mode, contain multi-dimensional,
heterogeneous and sparse pieces of specific information about the consumers’
demographics, the kinds, brands and sources of the implicated food, symptoms of
possible sickness, characteristics of foreign objects which could have been
found in food, involved locations and times of occurrences, etc. The statistical data mining component of the
system supports surveillance of naturally occurring problems as well as
potential acts of agro-terrorism. The system is being envisioned as one of the
key components of the nationwide bio-security protection infrastructure, it has
been accepted for use and it is currently going through the final stages of
deployment. We explain the motivation, key design concepts and report the
system’s utility and performance observed so far.
Artur Dubrawski received
a Ph.D. in robotics and automation from the Institute
of Fundamental Technological Research,
Polish Academy of Sciences, and a M.Sc. in
aircraft engineering from Warsaw University of Technology. Artur considers
himself a scientist and a practitioner; he has been tainted with some real
world entrepreneurial experiences. He had started up a small company which
turned out successful in integration and deployment of advanced computerized control
systems and novel technological devices. He had also been affiliated with
startups incorporated by others: Schenley Park Research, a data mining
consultancy and a CMU spin-off, where he was a scientist; and (more recently)
with Aethon, a company building robots to automate transportation in hospitals,
where he served as a Chief Technical Officer. Artur returned to CMU in 2003 to
join the Robotics Institute's Auton Lab. He works on a range of applied data
mining endeavors and teaches data mining to graduate students at the CMU Heinz
School (in fact, he has been doing that since 2000). In his previous academic
life, he worked mainly on machine learning approaches to mobile robot
navigation and control, as well as on other applications of adaptive autonomous
systems. In 1995/96 Artur spent a year at CMU (obviously, with the Auton Lab)
as a visiting Fulbright scholar. In January 2006 Artur Dubrawski was named the
director of the Auton Lab.
For
appointments, please contact Virginia Arrington (va2@andrew.cmu.edu)
The
Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
