Department of Computer Science and Electrical Engineering

PhD Dissertation Proposal

Design and Validation of Brain Network
Visualization Techniques: A Unified Approach

Guohao Zhang

Time and Place:
8:00-10:00am, 22 Jan 22 2015, ITE325

We propose a unified approach to understand why and how visualization works, motivated by scientists’ difficulties in obtaining insights from increasingly complex data that involves multi-modality brain networks from structural and functional magnetic resonance imaging (dMRI and fMRI). Brain scientists are in need of visualization approaches to effectively analysis brain MRI data from different modalities. We design a unified theory expanded upon the classical 2D semiotics for the design and evaluation of brain network visualization approaches. Our research is divided to three-steps. First, we define a taxonomy that includes three dimensions: retinal variable, data continuity, and plane. Second, we demonstrated that this theory carries descriptive power in that we can use it to describe existing visualization techniques for brain imaging visualizations. We then propose five empirical studies to understand and evaluate encoding approaches in structure and functional networks accordingly. The first three studies focus on single modality and the last two studies differences in dual-modality multiplex network comparison based on cohort analyses. Using the results derived from the empirical studies, we present a visual analytics approach for brain scientists to explore cohort and individual brain network to let them answer research questions. We use computational methods to derive relationships from two modalities in cohorts of two modalities, and then represent cohort with uncertainty as well as individual ones for brain scientists to study uncertainty in network analysis.

Committee: Drs. Jian Chen (Chair), Penny Rheingans, Konstantinos Kalpakis, Peter Kochunov (UMB), Niklas Elmqvist (UMCP) and Alexander Auchus (UMC)

UMBC CSEE alumni Don Miner and Brandon Wilson have started a Meetup group for Hadoop users in and around the Baltimore area to discuss Hadoop technology and use cases.

Apache Hadoop is one of the most popular open-source tools used to harness clusters of computers to process, analyze or learn from massive amounts of data. Whether you are new to Hadoop or an experienced user, this is a great opportunity to improve your knowledge and network with others in the Baltimore computing technology community.

The first meeting will be held from 7:00pm to 9:30pm on Thursday, 19 February 2015 at AOL/Advertising.com at 1020 Hull St #100, Baltimore, MD (map). Join the group here.

For the seventh year in a row, UMBC is the Baltimore-area host site for the Global Game Jam (GGJ).

In a game jam, people come together to make a video game — a hackathon for game development. Participants join small teams at the jam, and over a few days create new, unique and creative video games based on the jam’s theme and rules.

The GGJ is the world’s largest game jam event and takes place over 48 hours at 100s of physical locations worldwide. The 2015 GGJ will start at 5pm on Friday, January 23 and end at 5pm Sunday, January 25. For more information and to find out how you can register to participate at the UMBC site, visit the UMBC GAIM blog.

Two of UMBC’s regular hackathon participants took 3rd place at MHacks, a competitive 1000 student hackathon at the University of Michigan this past weekend!

CSEE students Michael Bishoff (President, HackUMBC) and Sekar Kulandaivel created a haptic feedback suit that makes virtual reality more immersive. To do this, the team created 12 vibrating modules that are placed on the user’s arms, legs, chest, and head. When various events occur in the virtual environment, the user will feel a vibration in the appropriate location on their body. For example, when a user falls in a virtual environment, they will feel a vibration in their legs, or when a user gets hit in their arm, they will experience a vibration on the appropriate arm.

For placing third, the duo won a trip to Seoul, South Korea in the summer to represent UMBC at the Global Hackathon, a 2000 person hackathon event backed by the mayor of Seoul. The event’s goal is to increase innovation and produce projects that make a global impact. Attendees of the event will include other brilliant students from around the world!

Mike and Sekar incorporated Oculus Rift technology, which they won at UMD’s 2014 Bitcamp hackathon.

Interested in maker-faires and participating in future hackathons? Join hackUMBC!

CSEE’s Dr. Rick Forno was a panelist for Schmoocon 2015’s closing plenary session on January 18 in Washington, DC. The session, entitled “Get Off My Lawn: Examining Change through the Eyes of The Old Guard” brought together four longtime security practitioners to discuss in a free-flowing (if not somewhat curmudgeonly) manner the state of Internet security over the years while fielding audience questions and avoiding Schmooballs tossed their way.

Joining Rick on the panel were Carole Fennelly (independent New York area security consultant), Ben Laurie (Google), and Space Rogue (L0pht). Schmoocon founder Bruce Potter moderated the session.

ShmooCon is an annual east coast hacker convention held in Washington, DC offering three days of demonstrating technology exploitation, inventive software and hardware solutions, and hosting open, unfiltered discussions of critical information security issues. Tickets to the conference routinely sell out within seconds, and the acceptance rate for proposals traditionally hovers around 20%.

Top 10 highest rated passwords for most “Highly Usable” and “Highly Secure.” The highest rated is in the top left, and moving left-to-right by row, the tenth, highest rated is the lower right.

UMBC Information Systems

Measuring Visual Perceptions of Security

Professor Adam J. Aviv
United States Naval Academy

10:00am – 11:00am Friday, 16 January 2015, ITE 459

This talk presents the results of a user study of the Android graphical password system to measure visual perceptions of security. The survey methodology asked participants to select between carefully selected pairs of patterns indicating either a security or usability preference. By selecting password pairs that isolate a visual feature, a perception of usability and security of different features can be quantified in relatively. We conducted a large IRB-approved survey using pairwise preferences which attracted 384 participants on Amazon Mechanical Turk. Analyzing the results, we find that visual features that can be attributed to complexity indicated a stronger perception of security, while spatial features, such as shifts up/down or left/right are not strong indicators for security or usability.

We extended and applied the survey data by building logistic models to predict perception preferences by training on features used in the survey and other features proposed in related work. The logistic model accurately predicted preferences above 70%, twice the rate of random guessing, and the strongest feature in classification is password distance, the total length of all lines in the pattern, a feature not used in the online survey. This result provides insight into the internal visual calculus of users when comparing choices and selecting visual passwords, and the ultimate goal of this work is to leverage the visual calculus to design systems where inherent perceptions for usability coincides with a known metric of security.

Adam J. Aviv is an Assistant Professor of Computer Science at the United States Naval Academy, receiving his Ph.D. from the University of Pennsylvania under the advisement of Jonathan Smith and Matt Blaze. He has varied research interests including in system and network security, applied cryptography, smartphone security, and more recently in the area of usable security with a focus on mobile devices.

Dissertation Defense

TABEL — A Domain Independent and Extensible
Framework for Inferring the Semantics of Tables

Varish Vyankatesh Mulwad

8:00am Thursday, 8 January 2015, ITE325b

Tables are an integral part of documents, reports and Web pages in many scientific and technical domains, compactly encoding important information that can be difficult to express in text. Table-like structures outside documents, such as spreadsheets, CSV files, log files and databases, are widely used to represent and share information. However, tables remain beyond the scope of regular text processing systems which often treat them like free text.

This dissertation presents TABEL — a domain independent and extensible framework to infer the semantics of tables and represent them as RDF Linked Data. TABEL captures the intended meaning of a table by mapping header cells to classes, data cell values to existing entities and pair of columns to relations from an given ontology and knowledge base. The core of the framework consists of a module that represents a table as a graphical model to jointly infer the semantics of headers, data cells and relation between headers. We also introduce a novel Semantic Message Passing scheme, which incorporates semantics into message passing, to perform joint inference over the probabilistic graphical model. We also develop and explore a “human-in-the-loop” paradigm, presenting plausible models of user interaction with our framework and its impact on the quality of inferred semantics.

We present techniques that are both extensible and domain agnostic. Our framework supports the addition of preprocessing modules without affecting existing ones, making TABEL extensible. It also allows background knowledge bases to be adapted and changed based on the domains of the tables, thus making it domain independent. We demonstrate the extensibility and domain independence of our techniques by developing an application of TABEL in the healthcare domain. We develop a proof of concept for an application to generate meta-analysis reports automatically, which is built on top of the semantics inferred from tables found in medical literature.

A thorough evaluation with experiments over dataset of tables from the Web and medical research reports presents promising results.

Committee: Drs. Tim Finin (chair), Tim Oates, Anupam Joshi, Yun Peng, Indrajit Bhattacharya (IBM Research) and L. V. Subramaniam (IBM Research)

UMBC GM Niclas “The Dark Knight” Huschenbeth plays GM Nadezhda Kosintseva from UT Dallas in the fifth round of the Pan-Am chess tournament.

Congratulations to the UMBC chess team for placing third in the 2014 Pan American Intercollegiate Team Chess Championship and qualifying to advance to the President’s Cup on April 5-6 at the New York Athletic Club.  This tournament, known as the Final Four of College Chess, will determine the 2015 U.S. college team chess champion.

The UMBC team in this year’s Pan-Am consists of GM Niclas Huschenbeth, IM Levan Bregadze, IM Tanguy Ringoir, GM Akshayraj Kore and WGM Nazi Paikidze (alternate).

The final standings were: Webster University A (5.5 points), the University of Texas at Dallas A (5 points), the University of Maryland, Baltimore County (5 points) and Texas Tech University A (4.5 points). UTD placed ahead of UMBC by virtue of winning their match.

You can view the final results on the tournament website and review selected games on Monroi.

Photo by Marlayna Demond. Sitting (left to right): Joel DeWyer, Business Manager; Dr. Alan T. Sherman, Director and GM Sam Palatnik, Coach. Standing (left to right): GM Akshayraj “The Indian Knight” Kore; IM Levan “The Georgian Gangster” Bregadze; GM Niclas “The Dark Knight” Huschenbeth, Captain; IM and WGM Nazi “The Black Widow” Paikidze and IM Tanguy “The Belgium Butcher” Ringoir.

The UMBC chess team won its match (4-0) against Lindenwood University in the first round of the 2014 Pan American Intercollegiate Team Chess Championship being held this week in South Padre Island, Texas. Five more rounds will be played over the next three days to determine winner and the top four USA schools, which will compete in the President’s Cup championship April 5-6 at the New York Athletic Club to determine the U.S. college team chess champion.

UMBC’s chess team has won or tied for first place a record ten times at the Pan-Am and a record six times at the President’s Cup. The UMBC team in this year’s Pan-Am consists of GM Niclas Huschenbeth, IM Levan Bregadze, IM Tanguy Ringoir, GM Akshayraj Kore and WGM Nazi Paikidze (alternate).

CSEE professor Alan Sherman, director of UMBC’s chess program, reports that the field is especially strong this year with 22 International Grandmasters (GM) or International Woman Grandmaster (WGM) and notes that “At least one strong school will not make the Final Four”.

You can view the latest results on the tournament website and watch selected games live on Monroi.

MS Thesis Defense

distratto: Real-time Impaired Driving Detection Using Multiple Textile and Inertial Sensors

Tsu An Chen

1:00-3:00pm Tuesday, 23 December 2014, ITE 341

Statistical data shows that driving-related accidents and human casualties caused by vehicles are on the rise in the US and globally. Most of these accidents are cause by impaired or distracted driving. Existing systems that detect impaired driving use cameras that perform eye and head tracking and do not capture full-body movements that are indicative of dangerous driving. To address this problem, in this thesis we present a system, distratto, that uses capacitive textile sensors embedded into car seats, headrests, and arm rests to capture whole body motion, and inertial and GPS sensors for determining vehicle speed and turns. Using a combination of these sensors and a tiered signal processing algorithm, we infer attributes that are indicative of impaired driving. We have developed a fully functional prototype of distratto that we evaluate in a real vehicle setting. We show that our system can detect impaired driving instances and driver movements with high accuracy.

Committee: Drs. Nilanjan Banerjee (chair), Ryan Robucci, Chintan Patel