Department of Computer Science and Electrical Engineering

MS Defense

Modeling Individual Nodes In Dynamic Link Prediction

Maksym Morawski

2:00pm Thursday, 25 April 2013, ITE325b, UMBC

The question of how to predict which links will form in a graph, given the graph’s history, is an open research problem in computer science. There are many different approaches to the link prediction problem, one of which involves building a set of features for pairs of nodes and using supervised learning to build a model that predicts when these pairs of nodes will link. Typically, this model is learned over the entire graph. In this thesis, I investigate building this model over each individual node in an attempt to learn the particular ways in which that node behaves before making predictions about it. In addition, research into link prediction to date lacks intelligent ways of utilizing the graph over large timespans. To address this, I introduce a variety of ways to include temporality into the link prediction process by introducing new ways of using existing features.

Committee: Dr. Marie desJardins (Chair), Dr. Tim Oates, Dr. Tim Finin

MS Thesis Defense

A Hybrid CPU/GPU Pipeline Workflow System

Tim Blattner

11:45am Thurday, 25 April 2013, ITE 325b, UMBC

Heterogeneous architectures can be problematic to program on, particularly when trying to schedule tasks on all available compute resources, overlapping PCI express transfers, and managing the limited memory available on the architectures. In this thesis we propose a workflow system that is capable of scheduling on all available compute resources, overlaps PCI express transfers, and manages the limited memory. A procedure for creating the workflow system is described and two case studies are analyzed.

• Image Stitching, which implements the workflow system and achieves two orders of magnitude speedup over an image stitching plugin found in the popular Fiji ImageJ application. Implementing the image stitching algorithm without the workflow system yielded only one order of magnitude speedup over the image stitching plugin.
• Out of Core LU Decomposition, which does not implement the workflow system. This case study demonstrates the impact of the PCI express on a problem with a large number of dependencies. A proposed workflow system for this algorithm is provided in Future Work.

Using the workflow system, programmers have a method for scheduling any algorithm on all available compute resources and is capable of hiding the I/O impact by overlapping computation with I/O.

Committee Members: Milton Halem, Yelena Yesha, Shujia Zhou, John Dorband, Walid Keyrouz

CSEE Colloquium

Queuing and Long Lines: How to run efficient elections

Dr. William A. Edelstein
Visiting Distinguished Professor of Radiology
Johns Hopkins School of Medicine

1:00pm Friday, 3 May 2013, ITE227, UMBC

Computerized touchscreen "Direct Recording Electronic" (DRE) voting systems have been used by over 1/3 of American voters in recent elections, including in Maryland. In many places, insufficient DRE numbers, in combination with lengthy ballots and high voter traffic, have caused long lines and disenfranchised voters who left without voting. We have applied computer queuing simulation to the voting process and conclude that far more DREs, at great expense, would be needed to keep waiting times low. Alternatively, paper ballot-optical scan systems can be easily and economically scaled to prevent long lines and meet unexpected contingencies. We have developed a heuristic "Queue Stop Rule" that can be applied to prevent long lines at voting stations. We have also carried out queuing simulations of other parts of the voting process, for example, voter check-in and ballot scanning. Our results can be used to help plan cost-effective election systems that will produce expeditious elections.

William Edelstein, physicist, received BS and PhD degrees in that subject from University of Illinois and Harvard, respectively. His career has principally focused on the development of MRI, starting in Scotland in 1977 and continuing from 1980 at the GE research lab in Schenectady, NY. He has been Visiting Distinguished Professor of Radiology at Johns Hopkins School of Medicine since 2007. His MRI work has been recognized with many honors, including the 2005 Industrial Applications of Physics Prize from the American Institute of Physics. His interest in election systems began several years ago in NY State during the debate to replace lever voting machines.

UMBC CSEE Colloquium

Large Data Transfer over the Wide Area Network

Jim Finlayson
Laboratory for Physical Sciences
Advanced Computing Systems Group

1:00pm Friday, 26 April 2013, ITE 227, UMBC

The Department of Defense has challenges related to the transfer of large data sets over distance. This talk will go over some of the investigations into potential solutions in this space.

Jim Finlayson is a File Systems and I/O researcher for the Laboratory for Physical Sciences' Advanced Computing Systems Group. Mr. Finlayson has a long history in data storage infrastructure. He graduated from the University of Maryland, College Park with a BS in Computer Science and later received his MS in Computer Science from The Johns Hopkins University's Whiting School of Engineering.

Center for Hybrid Multicore Productivity Research
Distinguished Computational Science Lecture Series

Quantum Computer Compilers

Professor Alfred V. Aho

Department of Computer Science, Columbia University

3:00pm Thursday, 25 April 2013, ITE 456, UMBC

Quantum computing is an exciting emerging field that offers great potential for next generation information processing but also presents great scientific and engineering challenges. Assuming that someday we will be able to build scalable and reliable quantum computers, we will need to create programming languages and compilers that will allow programmers to harness quantum phenomena. In this talk, Alfred Aho will look at quantum computing from a compiler writer's perspective and discuss some of the formidable challenges that face quantum computer compilers.

Alfred Aho is the Lawrence Gussman Professor of Computer Science at Columbia University. He received a B.A.Sc. in Engineering Physics from the University of Toronto and a Ph.D. in Electrical Engineering/ Computer Science from Princeton University. Prior to his current position, he served as vice president of the Computing Sciences Research Center at Bell Labs, the lab that invented UNIX, C and C++. He is the "A" in AWK, a widely used pattern-matching language. His current research interests include programming languages, compilers, algorithms, software engineering and quantum computing. He has won the IEEE John von Neumann Medal and is a Member of the National Academy of Engineering and of the American Academy of Arts and Sciences. He is a Fellow of the AAAS, ACM, Bell Labs and IEEE. In 2003 he received the Great Teacher Award from the Society of Columbia Graduates.

Host: Professor Milton Halem

We are now offering the UMBC Cybersecurity MPS program at Shady Grove in Montgomery County, MD.

The Cybersecurity Master’s in Professional Studies degree provides students the essential knowledge required to serve in leadership and operational roles throughout the industry. Through the program, students will learn how to analyze cybersecurity risks and assess available countermeasures. The program will expose students to practical managerial and operational considerations needed to conduct cybersecurity activities for large organizations.

Puzzle Perfect

What do crosswords and Computer Science have in common? For starters there’s CSEE professor Marie desJardins. When she’s not furthering the field of Artificial Intelligence, Dr. desJardins has a crossword puzzle in hand. It’s no accident that she’s the top ranking female crossword solver in the Mid-Atlantic.

This March Dr. desJardins joined hundreds of puzzle pros at the 36^th annual American Crossword Puzzle Tournament. Directed by New York Times crossword editor Will Shortz, it’s the nation’s oldest and   largest competition of its kind. Hundreds of competitors spend two days solving seven puzzles. It’s a race against the clock to prove their mental mettle.

“It’s a very unforgiving sport,” she says. “It’s like gymnastics. One little foot slipping off the balance beam and you’re not going to be on that podium.”

You need both speed and accuracy to succeed. Dr. desJardins can breeze through smaller puzzles in fifteen minutes; forty-five for the larger, Sunday-New-York-Times-sized puzzles. Though speed isn’t as important as accuracy in these competitions. One mistake can hurt as much as seven minutes of stalling. 

This year Dr. desJardins handed in seven perfect puzzles. That means getting every single word right—even those baffling clues pointing at pop-culture references or words all but erased from the English language. She placed 24^th out of 570 solvers, finishing 5^th in the “B” division.

Years ago Dr. desJardins discovered the tournament from the documentary Wordplay, which follows the personal and competitive lives of a band of crossword enthusiasts. One year she realized that the competition was during UMBC’s Spring Break. So she signed up and hit the road for Connecticut.  

“I wasn’t at all expecting to do well,” she says. It was a pleasant surprise when she placed in the top quarter of competitors. The success got her hooked. Since then, she’s been engaged in a personal battle to beat her own time. She has competed five times, and each year, her speed increases.  

Her secret to success? Practice is part of it. Dr.desJardins completes a lot of puzzles. She does them on Sunday morning with a cup of coffee. She does them to relax before bed. She’s adopted a policy of leaving no puzzle unfinished. Keeping a positive mindset is half the battle, she says.

Being a Computer Scientist may have something to do with it as well. Both require a knack for pattern recognition and problem solving. “It’s just the way my brain is wired,” she says.  

Had Dr. desJardins solved a mere two minutes quicker this year, she would have qualified for the finals in her division. Being a finalist would mean solving an oversized puzzle on a whiteboard against two fellow division “B” finalists. It’s a daunting and high-pressure test made tougher by the gaze of six hundred spectators. It’s no surprise that this is Dr. desJardins’ goal when she competes again next year.  

Photos: Top Right, courtesy UMBC Magazine Left, courtesty crosswordtournament.com

Information Systems Council of Majors Speaker Series

Technology, Diversity and Lifelong Learning

Dr. Freeman Hrabowski
President, University of Maryland, Baltimore County

3:00-4:30pm Friday, 26 April 2013, ITE102

As an ongoing service to UMBC our student group, the Information Systems Council of Majors (ISCOM), has developed a speaker series to bring industry professionals, academic luminaries, and prominent regional figures to discuss topics relating to technology, education, or topics of the speakers choosing.

This month our very special guest is Dr. Freeman Hrabowski. He will meet with members of ISCOM and UMBC students who are interested in hearing him speak about diversity, lifelong learning and of course technology. There will be interactive sessions prior to his remarks and our President Tabitha Haverkamp will provide closing remarks.

PhD Dissertation Defense

Analysis of brain network connectivity
using spatial information

Sai Ma

1:00pm Thursday, 18 April 2013, ITE 325b

In current functional magnetic resonance imaging (fMRI) research, one of the most active areas involves exploring statistical dependencies among brain regions, known as functional connectivity analysis. Data-driven methods, especially independent component analysis (ICA), have been successfully applied to fMRI data to extract distributed brain networks and offer an opportunity to investigate functional connectivity on a network level, thus at a multivariate level. However, the independence assumption in ICA is neither necessarily nor typically satisfied in real applications and an extension is desirable. Furthermore, most current ICA-based studies focus on the use of temporal information and second-order statistics for functional connectivity analysis. Taking spatial information and higher-order statistics in fMRI data into account is expected to lead to better understanding of the overall brain network connectivity in healthy controls and also in patients with mental disorders, such as schizophrenia.

We develop a dependent component analysis (DCA) framework to generalize the ICA-based connectivity analysis methods by grouping components into maximally independent clusters. First, we define functional network connectivity as the statistical dependence among spatial components, instead of the typically used temporal correlation. Based on this definition, we use a hypothesis test to automatically generate functional connectivity structure for a large number of brain networks. After that, we separate dependent components within a given cluster using prior information, such as sparsity and experimental paradigm information, to achieve a better decomposition. We also combine this DCA-based clustering analysis with graph-theoretical analysis to discover significant group differences in topological properties of functional connectivity structure. To extend the methodologies currently available for functional connectivity, we propose an independent vector analysis (IVA) based scheme to extract and analyze dynamic functional connectivity.

The methods we develop offer advantages for effective and efficient examination of not only static, but also dynamic functional connectivity among different brain networks. We identify significant differences in functional connectivity structure between healthy controls and patients with schizophrenia, which may prove useful to serve as potential biomarkers for diagnosis. We also find task-induced modulations in functional connectivity when comparing different active states in the brain. Furthermore, we observe temporal variability in functional connectivity structure and physiologically meaningful group differences in dynamic connectivity among several brain networks. Our methods can provide insights to understanding of functional characteristics of the brain network organization in healthy individuals and patients with schizophrenia.

Committee: Dr. Adali (Chair), Dr. Morris, Dr. Rutledge, Dr. LaBerge, Dr. Phlypo, Dr. Calhoun, and Dr. Westlake

PhD Dissertation Defense

Data-driven group analysis of complex-valued fMRI data

Pedro A. Rodriguez

11:00am Tuesday, 16 April 2013, ITE 346, UMBC

Analysis of functional magnetic resonance imaging (fMRI) data in its native, complex form has been shown to increase the sensitivity of the analysis both for data-driven techniques such as independent component analysis (ICA) and for model-driven techniques. The promise of an increase in sensitivity and specificity in clinical studies provides a powerful motivation for utilizing both the phase and magnitude data; however, the unknown and noisy nature of the phase poses a challenge for successful study of the fMRI data. In addition, complex-valued analysis algorithms, such as ICA, suffer from an inherent phase ambiguity, which introduces additional difficulty for group analysis and visualization of the results. We present solutions for these issues, which have been among the main reasons phase information has been traditionally discarded, and show their effectiveness when used as part of a complex-valued group ICA algorithm application. The developed methods become key components of a framework that allows the development of new fully complex data-driven and semi-blind methods to process, analyze, and visualize fMRI data.

In this dissertation, we first introduce the methods developed as part of the fully complex framework for ICA of fMRI data. We introduce a physiologically motivated de-noising method that uses phase quality maps to successfully identify and eliminate noisy voxels—3D pixels—in the fMRI complex images so they can be used in individual and group studies. We also introduce a phase correction scheme that can be either applied sub-sequent to ICA of fMRI data or can be incorporated into the ICA algorithm in the form of prior information to eliminate the need for further processing for phase correction. Finally, we present two visualization methods that are used to augment the sensitivity and specificity in the detection of activated voxels. We show the benefits of using the developed methods on actual complex-valued fMRI data.

In the remainder of the dissertation, we focus on developing constrained ICA (C-ICA) algorithms for complex-valued fMRI data. C-ICA uses prior information, hence providing a balance between model-based and data-driven approaches such as ICA to improve the source estimation performance and robustness to noise. C-ICA algorithms have been used to improve the estimation performance in real-valued fMRI data, but—to our knowledge—have not been applied to complex-valued fMRI data. We develop the first C-ICA algorithm that uses complex-valued references to constrain either the sources or the mixing coefficients. The designed algorithm is not restricted to having a unitary demixing matrix, which is a major assumption in existing C-ICA algorithms. We show, on both simulated and actual fMRI data, how the performance of ICA improves by using prior information about the fMRI paradigm.

Committee: Dr. Adali (Chair), Dr. Morris, Dr. Rutledge, Dr. Laberge, Dr. Phlypo, and Dr. Calhoun