| Previous Research Projects |
| BioInformatics Research Center (BRC), UMBC |
Computation of Phylogenetic trees from protein
/ DNA sequences
This project was done at the Bioinformatics Research Center, under the
supervision of Dr Madhu Nayakkankuppam, Department of Mathematics and
Statistics, Univeristy of Maryland Baltimore County. View Abstract
It involved
- Study of existing methods for computation of
phylogenetic trees from DNA / protein sequences and relevant literature
review
- Parallelization of the problem of obtaining
phylogenetic trees to obtain better performance in determination of the
best tree
- Examination of optimization techniques
- Use of statistical methods to reduce search space of
trees generated to obtain best tree
- Comparison of results with existing software (PHYLIP)
- Extensive coding in C++ and MPI (message passing
interface)
|
| Temple University, Philadelphia |
| Analysis of performance of aircrafts using the
FltWinds software and a Neural Network based approach |
This project was done as part of a Neural Network
course under the supervision of Dr. Zoran Obradovic, in collaboration
with Lockheed Martin Inc, Valley ForgePhiladelphia.
It involved the following:
- Initial study of the FltWinds software that is at use
in Lockheed Martin for storing data for flights all over the world
- Extraction of the data dump for over a period of
three months (10GB) with the help of domain experts and importing them
into an Oracle Database
- Data Preprocessing with code written in Java and
MATLAB
- Development of a Neural Network to analyze the data
including the time of arrival and departure for the aircrafts.
Technical Report
Presentation
|
| Study of Isomorphism in Trees |
This project was aimed at studying various algorithms
to solve the problem of isomorphism in rooted trees and was done under
the supervision of Dr Igor Rivin, Department of Mathematics, Temple
University. It involved the following:
- Study of O(n 2 ) , O(n log n) and O(n) time
algorithms for solving the tree isomorphism problem
- Implementation of some of the above algorithms in
java, analysis of running time.
|
| Feature Extraction, Classification and
Searching in Medical Image Databases |
This independent study is being done under the
supervision of
Dr Vasilis Megaloikonomou, Department of Computer and Information
Science, Temple University. A research paper on the same has been
accepted at the International Conference on Image Processing,
Rochester, NY, 2002. The project deals with the following:
- An analysis of the existing content based image
retrieval
methods (including a review of literature on the same)
- An effort to modify some of the existing image
retrieval
methods
- Building a simulator for generating models of tumors
- Development of a novel method for the classification
of brain
tumors
- Using morphological operators for classification and
searching in large image databases
- Comparison of classification and searching efficiency
of the
new method with the traditional neural net and other classifiers
|
| Shape Representation and Matching in Medical
Tumor Databases (using
Morphology) |
This project was done as part of a Data Warehousing
course in Temple
University. It involved the following:
- Study of Mathematical Morphology
- Finding similar shapes of tumors in medical tumor
databases
|
| Design and Analysis of Feature Hidden Markov
Models for Protein
Classification |
This project was done as part of the course work in
Temple University
in Fall 2000 under the supervision of Dr Vasilis Megaloikonomou. It
involved the following:
- An extensive study of Statistical Models with stress
on
Hidden Markov Models and their application to analyze the structure of
proteins in real life
- Proposal of an improved method for detecting distant
homologs by taking into account three different properties of amino
acids flexibility, hydropathy and coordinate number
- Coding was done using MATLAB, C++ and Java.
|