Prof. Vesna Zeljkovic , July 28, 13:40-14:30, FENS G032
Part I: Shape Recognition in ISAR Radar Images
Two different novel methods for classification of aircraft categories
of Inverse Synthetic Aperture Radar (ISAR) images are presented and
compared. The first method forms numerical equivalents to shape, size
and other aircraft features as critical criteria to constitute the
algorithm for their correct classification. The second method compares
each ISAR image to unions of images of the different aircraft
We computer simulated five different categories of ISAR images and
took two more from the internet. ISAR images are constructed based on
the Doppler shifts of various parts, caused by the rotation of the
aircraft and the radar reflection pulse shape which includes the size
or duration of the radar pulse.
The proposed classification algorithms were tested on these seven
categories. All seven different aircraft models are flying a holding
pattern. The aim of both algorithms is to quickly match and determine
the similarity of the captured aircraft to the seven different
categories where the aircraft is in any position of a prescribed
Our experimental results clearly indicate that in most parts of the
holding pattern the category of the aircraft can be successfully
identified with both proposed methods. The union method shows more
successful identification results and is superior to the results we
obtained in the first proposed method.
Part II: Simulation and Mathematical Modeling of Cancerous /Osteoporosis Bones
A model of ultrasonic waves propagating through a rectangular solid
model of bone is simulated with the purpose to develop an X-ray free
method of diagnosing diseases that manifest themselves as abnormal
ratios of solid to liquid substances in the bone; e.g. osteoporosis or
bone cancer. We use finite element analysis and apply equations of
motion and stress tensors to predict how application of ultrasound
will send waves through the solid part of the elastic bone tissue.
Zero surface stress for boundary conditions is used. We model the
evolution of velocities which, in finite element analysis, can easily
be converted into displacements by integrating over time elements.
Based on the discretized equations of motion and the stress strain the
simulation model is developed.
Dr Vesna Zeljkovic is Associate Professor at New York Institute of
Technology, Nanjing campus. She is a researcher in the field of signal
and image processing with more than ten years of experience,
developing mathematical models and novel algorithms for the analysis
of 2D images that have applications in video surveillance, analysis of
complex optical spectra, public health, industry application, homeland
security and national defense.
She has more than 50 scientific papers and one book published in these
fields and serves as a reviewer for peer reviewed journals and
During her residence in US she participated in obtaining highly ranked
grants. Dr Zeljkovic mentored and graduated two PhD students in 2009.
She was awarded by the US Government in 2007 an EB-1 status as the
Outstanding Professor and Researcher based on which she received her
Dr Zeljkovic's goal as a scientist and a researcher is to help in
improving the human quality of life in all aspects.