Postdoctoral Research Opportunity - University of Manitoba

[Pizzi, Nicolino]

POSTDOCTORAL RESEARCH OPPORTUNITY - COMPUTER ENGINEERING
HYBRID KNOWLEDGE-BASED CLASSIFICATION OF VOLUMETRIC PATTERNS

Pending final approval, a postdoctoral position is available within the
Electrical and Computer Engineering Department to participate in an
NSERC-funded strategic research project investigating hybrid
knowledge-based classification of volumetric patterns. The position is
for a one-year term with a possible one year renewal. The research
project will be conducted in close collaboration with Prof. W. Pedrycz
and Dr. N. Pizzi.

Volumetric (three-dimensional) data are found in many application areas
such as radar scans of meteorological formations. These data normally
contain a number of three-dimensional regions of interest (ROI's) that
belong to several classes. The classification of an ROI is determined by
some well-established reference test. In the case of meteorological
radar scans, the ROI's may be cloud formations that cause severe
weather, the classes may be hail, heavy rain, wind, or tornadic events,
and the reference test might be eye-witness accounts of the storm
events.

The intent of this project is to develop a comprehensive pattern
recognition methodology aimed at such data and propose a suite of
classification algorithms that can take a ROI and produce a
classification outcome that matches the class to which it was assigned
by the corresponding reference test.

A number of factors can confound the classification process. It may
become difficult to glean any discriminating features from volumetric
data if it contains noise due to limitations of sensors,
instrumentation, or the data acquisition process. Moreover, the ROI's
may be extremely complex in nature. Several preprocessing methods are
proposed in order to transform the original ROI in order to eliminate or
diminish the effects of noise and/or reduce the dimensionality of the
input space as well as focus the classification effort on the most
significant features. The problem of identifying discriminating features
is further aggravated by the fact that the accepted reference test
itself may be imprecise or even unreliable. Finally, the volumetric data
may be incomplete and sophisticated interpolation methods will be
required to deal with missing values.

Required background:
-	Recent Ph.D. graduate
-	Experience in C++ programming on UNIX systems
-	Knowledge of pattern recognition techniques

	Desired background:
-	Working knowledge of fuzzy systems, artificial neural networks,
and data mining

Please send a curriculum vitae, expression of interest (including
earliest start date), and the names and e-mail addresses (or telephone
numbers) of two references to N. Pizzi at pizzi at ibd.nrc.ca. Your
curriculum vitae should include a list of recent publications. Please
outline your interest in this project, how it is related to work that
you have done, and what special expertise you would bring to the
project.

Nicolino Pizzi, Ph.D.
Associate Research Officer
Institute for Biodiagnostics
National Research Council
435 Ellice Avenue
Winnipeg MB  R3B 1Y6
CANADA