Department of Computer Science and Electrical Engineering

EE Graduate Seminar

Unsupervised Multispectral Image Classification

Shih-Yu Chen
PhD (EE) Student, CSEE Dept/UMBC

11:30am-12:45pm, Friday, 6 April 2012, ITE 237

This seminar presents a new approach to unsupervised classification for multispectral imagery. It first uses a Gaussian pyramid multi- resolution technique to reduce image size from which the pixel purity index (PPI) is implemented to find regions of interest (ROIs) with PPI counts greater than zero. These PPI-found samples are further used as support vectors for a support vector machine (SVM) to classify data. The resulting SVM-classified data samples are further processed by a newly designed iterative Fishers linear discriminant analysis (IFLDA), which implements FLDA in an iterative manner to refine classification results. The experimental results show the proposed approach has great promise in unsupervised classification.

Shih-Yu Chen received the BSEE degree from Da-Yeh University in 2005, and the MSEE degree from National Chung Hsing University in 2010. He is currently a PhD (EE) student at UMBC. Mr. Chen's research interest includes medical image, remote sensing image, and vital-sign signal processing.

Host: Prof. Joel M. Morris

Ph.D. Defense

Multivariate Time Series Analysis
of Physiological and Clinical Data

Patti Ordóñez Rozo

1:00pm Thursday, 29 March 29 2012, ITE 325b UMBC

The complexity and volume of collected medical data is greater now than at any point in the history of medicine. Medical providers are expected to examine large volumes of data and identify correlations among parameters based on their own clinical experience to detect significant medical events or conditions. The information overload that providers may face may hinder the diagnostic process. Most existing visualizations of the data to assist the provider in analyzing the information consist of a table or plot of values for a particular parameter as a function of time. Automated techniques for discovering these correlations not only may assist the provider in making a diagnosis but may help to identify hidden patterns within the data associated with specific medical conditions or events. Current visualization and machine learning techniques show promise for extracting this information.

This dissertation presents three novel representations and two visualizations to assist in the analysis of multivariate time series data. It focuses on physiological and clinical data, in particular, because this type of data captures the complexity of a human being, and thus, the multivariate time series in this type of data are more interdependent and synchronized than most. The three representations are the Multivariate Time Series Amalgam (MTSA), the Stacked Bags-of-Patterns (Stacked BoP), and the Multivariate Bag-of-Patterns (Multivariate BoP). Each provides an integrated, multivariate approach for representing multivariate time series data. An evaluation of the latter two techniques against two techniques that use univariate techniques of multiple variables, Ensemble Voting with Bag-of-Patterns and Multivariate Piecewise Dynamic Time Warping in five diverse datasets yields interesting insights into the classification of multivariate time series.

The MTSA representation is the foundation for two visualizations – the MTSA Visualization and the Fixed Dual MTSA Visualization. These animated visualizations capture the rate of change of provider-selected parameters and the relationships among them. While both visualizations were created for the medical domain, they generalize to domains where multiple variables measure the state of an entity as a function of time. An evaluation of the Fixed Dual MTSA Visualization was carried out with 23 pediatric residents at Johns Hopkins University School of Medicine. The results indicate that the visualization merits further investigation for use as a diagnostic tool.

Committee

• Dr. Tim Oates (co-chair)
• Dr. Marie desJardins (co-chair)
• Dr. Anupam Joshi
• Dr. Jim Fackler, JHMI
• Dr. Christoph U. Lehmann, JHMI

EE Graduate Seminar

High Power Mid-Infrared Quantum Cascade Laser
Arrays for Standoff Photoacoustic Chemical Detection

Xing Chen, PhD (EE) Student
Computer Science and Electrical Engineering, UMBC

11:30am-12:45pm, Friday, 30 March 2012, ITE 237

Quantum cascade lasers (QCLs) are compact, powerful, mid-infrared, Semiconductor laser sources. High power QCLs are very important to infrared counter measures (IRCM) and standoff chemical detection applications, as well as others. The performance of such systems critically depend on the amount of power that QCLs can produce. One way to achieve high power operation is to use multi-emitter phase-locked laser arrays.

The first part of the seminar presents the issues and challenges to design, fabricate, and characterize multi-emitter phase-locked QCL arrays for achieving high power operation. The second part of the seminar discusses using high power mid-infrared QCLs to perform standoff photoacoustic (PA) chemical detection. The PA effect is a photo-matter effect involving generation and detection of an acoustic signal when a gas sample absorbs electromagnetic energy (particularly of light).

In recent years, with the help of the development of mid-infrared QCLs, significant progress has been made in their use for PA chemical detection, and sensitivity has been improved significantly. Our theoretical and experimental studies of standoff photoacoustic chemical detection, using QCLs as the laser source, will be presented.

Xing Chen received the BS degree in Opto-Electronics Engineering from Huazhong University of Science and Technology in 2007, and the MSEE degree from UMBC in 2009. He is currently a PhD (EE) candidate at UMBC. Mr. Chen's research interest includes design and fabrication of high power mid-infrared phase-locked QCL arrays and application to standoff photoacoustic chemical detection.

Host: Prof. Joel M. Morris

Still looking for a summer internship? The 2012 Google Summer of Code (GSoC) starts accepting application from students on Monday March 26.

GSoC is a global program funded by Google that pays undergraduate or graduate students a $5000 stipend to write code for open source projects. GSoC has worked with the open source community to identify and fund exciting projects for the upcoming summer. Last year over 1,100 students were funded by the program. The FAQ is a good place to find out more.

A set of open source projects (aka mentoring organizations) has been selected. Students apply to work on one of more of these and each mentoring organization ranks the students interested in working with them. Google facilitates the final selection and pairing. The mentoring organization works closely with the student to define tasks, check progress, help solve problems, etc. Typically the student works remotely, interacting with his or her mentor via email, chat, skype, etc.

Students can submit applications via the Google Summer of Code 2012 site from March 26 to April 6. Google says that that the best applications they receive are from students who took the time to interact with one of the participating mentoring organizations and discuss their ideas before submitting an application. So your first step should be to look at the list of 2012 GSoC Mentoring Organizations and contact some that have projects that interest you and for which you have the right skills and background.

See the GSoC 2012 Program Timeline for a complete schedule. You might also check out the information on the Advice for GSoC Students Page and the GSoC forum.

Ph.D. Dissertation Defense

Clustering and Visualization Techniques
for Aggregate Trajectory Analysis

David Trimm

1:00pm Thursday 15 March 15th 2012, ITE 365

Analyzing large trajectory sets enables deeper insights into multiple real-world problems. For example, animal migration data, multi-agent analysis, and virtual entertainment can all benefit from deriving conclusions from large sets of trajectory data. However, the analysis is complicated by several factors when using traditional analytic techniques. For example, directly visualizing the trajectory set results in a multitude of lines that cannot be easily understood. Statistical analysis methods and non-direct visualization techniques (e.g., parallel coordinates) produce conclusions that are non-intuitive and difficult to understand. By using two complementary processes—clustering and visualization—a new approach is developed to analyzing large trajectory sets. First, clustering techniques are developed and refined to group related trajectories together. From these similar sets, a trajectory composition visualization is created and implemented that clearly depicts the cluster characteristics including application-specific attributes. The effectiveness of the approach is demonstrated on two separate and unique data sets resulting in actionable conclusions. The first application, multi-agent analysis, represents a rich, spatial data that, when analyzed using this approach, shows ways to improve the underlying artificial intelligence algorithms. Student course-grade history analysis, the second application, requires tailoring the approach for a non-spatial data set. However, the results enable a clear understanding of which courses are most critical in a student's career and which student groups require assistance to succeed. In summary, this research contributes to methods for trajectory clustering, techniques for large-scale visualization of trajectory data, and processes for analyzing student data.

Committee

• Dr. Penny Rheingans (chair)
• Dr. Marie desJardins
• Dr. Anupam Joshi
• Dr. Marc Olano
• Dr. Sreedevi Sampath

The Grace Hopper Celebration of Women in Computing (GHC) is the world’s largest gathering of women in computing. The 2012 Grace Hopper Celebration will take place 3-6 October 2012 at the Baltimore Convention Center. This year’s theme “Are We There Yet?” recognizes that technology and the culture of technology are continuously evolving but there are also concrete goals we are striving to achieve. Since UMBC is a Gold Academic Sponsor, UMBC students will receive a 20% registration discount.

At the conference, leading researchers will present their current work, while special sessions focus on the role of women in today’s technology fields, including computer science, information technology, research and engineering. The technical conference features well known keynote speakers and invited technical speakers, panels, workshops, new investigator technical papers, PhD forums, technical posters, birds of a feather sessions, the ACM Student Research Competition and an Awards Celebration.

If you would like to submit a paper or poster abstract on your work, the deadline is this coming Friday, March 16th. See the 2012 GHC call for participation for details.

Ph.D. Dissertation Defense

Mining Commonsense Knowledge from the Web:
Towards Inducing Script-like Structures From Large-scale Text Sources

Niels Kasch

10:00am Friday, March 9th, 2012, ITE 325B

Knowing the sequences of events in situations such as eating at a restaurant is an example of commonsense knowledge needed for a broad range of cognitive tasks (e.g., language understanding). This thesis outlines an approach to mine information about sequential, every day situations in a topic-driven fashion to produce declarative, script-like representations (c.f., Schank's scripts). Given a topic such as eating at a restaurant, we produce graphs of temporally ordered events involved with the activity referenced by the topic. Our work utilizes large-scale data sources (e.g., the Web) to avoid data sparseness issues of narrow corpora.

We describe steps that address the scale and noisiness of the Web to make it accessible for script extraction. Boilerplate elements (e.g., navigation bars and advertising) on web pages skew distributional statistics of words and obstruct information retrieval tasks. To make the web usable as a corpus, we introduce a machine learning technique to separate boilerplate elements from content in arbitrary web pages.

A key element for commonsense knowledge extraction is the generation of a topic-specific corpus that facilitates script extraction in a topic-driven manner. We introduce Concept Modeling for Scripts as an efficient method to induce concepts containing script elements (e.g., events, people, and objects) from topic-specific corpora. Our experiments and user studies conducted on the 2011 ICWSM Spinn3r dataset show that our method outperforms state of the art topic-modeling approaches such as Latent Dirichlet Allocation (LDA) on this task when applied to unbalanced (topic-specific) corpora.

Concept Modeling serves as a starting point for automated methods to discover events relevant to a script. We demonstrate event detection methods in topic-specific corpora based on (1) learned dependency paths indicative of individual event structures, (2) semantic cohesiveness of event pairs, and (3) surface structures indicative of golden sentences containing sequential information. Events extracted for a given topic can be arranged in a graph. The detection methods exploit graph analysis methods to identify strongly connected components to prune the event set such that related and central events are predominant in the structure. User studies demonstrate that (1) the Web is suitable for mining script-like knowledge and (2) the resulting graph structures portray events strongly related to a given topic.

Script-like structures, by definition, impose temporal ordering on the events contained within the structure. This work also presents a novel method to induce ordering information from topic-specific corpora based on a counting framework to judge the presence and strength of a temporal happens-before relation. The framework is extensible to several counting methods, where a counting method provides co-occurrence and ordering statistics. We present, among others, a novel naive counting methods that uses a simple sentence position assumption for temporal order. Comparisons to existing temporal resources show that our naive method, in conjunction with connected components analysis, induces temporal relationship with similar accuracy than more sophisticated methods, yet with a smaller computational footprint.

Committee

• Dr. Tim Oates (chair)
• Dr. Ronnie W. Smith
• Dr. Matt Schmill
• Dr. Tim Finin
• Dr. Charles Nicholas

Meet Max, a Teaching Assistant who loves climbing mountains, swing dancing, and Artificial Intelligence.

“I’ve never been bored in my life,” says Maksym Morawski (call him Max), a Computer Science graduate student who spends most of his free time scaling mountains.

Originally from Silver Spring, Max moved to Baltimore in 2006 to study Computer Science as an undergraduate. In the 4th grade, while others kids were busy building volcanoes for their science projects, Max and his computer scientist dad were putting together a computer that compared different algorithms for computing prime numbers. So choosing his major in college, explains Max, was a no-brainer.

Now a second year graduate student pursuing a Master’s in Computer Science, Max is working on a thesis that looks at predicting connections in social networks, like Facebook. A computer scientist with a sociological streak, Max’s project uses computers to understand how people interact with one another based on e-mail data sets taken from corporations.

Max’s foray into teaching began in 2010 when he became a Teaching Assistant for CMSC 202. He says his favorite part about being a TA are the discussions—where he actually gets to get up and teach and get his students excited about Computer Science. His dose of teacherly advice is as follows: “Program for fun.” If you don’t practice and enjoy programming, he explains, you will never be as good as someone who lives and breathes it.

Throughout his years at UMBC, Max’s on-campus involvement has extended past teaching. An avid dancer (he frequents Mobtown Ballroom in Baltimore City), he founded UMBC’s Swing Dancing club. He also helped conceive Project X, the club that sponsored a campus-wide scavenger hunt in 2008 and 2009 that included tasks like jumping into the Inner Harbor and high-fiving Freeman Hrabowski (which prompted a not-so-enthusiastic e-mail from the UMBC president). The prize for the hunt was an amalgamation of candy that was procured from the “Spot” using late-night meals over a series of weeks, explains Max.

But, Max’s favorite thing to do is the hobby he took up in high school: exploring mountains. A frequenter of Earth Treks—a climbing center in Columbia–Max had plans to climb frozen waterfalls in New York State this winter. His dream job, he says half-jokingly, is to be a mountaineering guide. Though, he may also consider a job in academia: “I would love to be a teacher,” he says.

EE Graduate Seminar

Spectrum Wars: LightSquared vs. GPS

Professor Chuck LaBerge
Professor of the Practice, CSEE Dept/UMBC

11:30am-12:45pm Friday, 2 March 2012, ITE 231

The radio-frequency spectrum is a limited resource. Within the US, commercial use of the spectrum is administered by the Federal Communications Commission (FCC), while government use of the spectrum is administered by the National Telecommunications and Information Administration. Currently, the regulatory community is locked in a battle about spectrum utilization in the vicinity of 1.5 GHz. This struggle pits millions of users of GPS technology for position and time information against technical innovators desiring to bring 4G wireless communications to millions of users in underserved populations. So who wins the spectrum wars?

The talk will outline the technologies involved, and provide a time-line of the regulatory actions to date. There are some innovative things going on here, and some simple analysis will show why there are points of contention. A final resolution cannot be provided at this time, because the issue is currently an open discussion in FCC. And, as might expected, there are financial and political ramifications as well.

This talk will provide an interesting insight into how the 'real world' works.

Dr. LaBerge is Professor of the Practice of Electrical and Computer Engineering in the CSEE at UMBC, where he teaches a wide variety of courses ranging from Introductory Circuits to Error Correcting Codes. From 1975-2008, he was employed by Bendix, which became AlliedSignal, which became Honeywell through a series of corporate mergers. He retired in July 2008 as the Senior Fellow for Communications, Navigation, and Surveillance in Honeywell's Aerospace Research and Technology Center.

Dr. LaBerge has worked on precision landing systems and a wide variety of aeronautical radios and applications. He's recognized as an expert in issues involving interference to aeronautical systems. His technical, writing, and editorial contributions have received numerous citations from regulatory bodies, and he was the winner of the Best Paper of Conference at the 2000 IEEE/AIAA Digital Avionics Systems Conference.

Dr. LaBerge is a Senior Member of IEEE, a member of Tau Beta Pi, and an inductee in the Order of the Engineer. He received his BES-EE and MSE-EE, degrees, both with Honors, from The Johns Hopkins University and the PhD. in Electrical Engineering from UMBC. His three kids are older than his students. He's been married to his patient wife for almost 38 years.

Host: Prof. Joel M. Morris