MS Thesis Defense

A Specialist Approach for Classification of Column Data

Nikhil Puranik

1:30pm Friday 24 August, 2012, 325b ITE, UMBC

Much information is encoded in spreadsheets, databases, and tables on the Web and in documents. Interpreting this content and making its meaning explicit in a representation language like RDF enables many applications. This thesis addresses the problem of identifying the semantic type of the information represented in a table column containing conventionally encoded data such as phone numbers or stock ticker symbols. We describe a ‘specialist’ approach for classification in which different specialists work together to come up with a ranked list for the given input column. We use three types of specialists: those based on regular expressions, dictionaries and classifiers. We discuss a serial and parallel framework for the specialists. We evaluate our system in two ways: by testing individual specialist for accuracy and by testing the performance of the overall system in terms of generation of ranked list. We also discuss the scalability of the system in terms of addition of new specialists and performance impact for systems with hundreds of specialists.

Committee: Drs. Tim Finin (chair), Anupam Joshi, Tim Oates and Yelena Yesha

I played cricket for the UMBC 22-Yards team last year, but due to time constraints this year I haven’t been able to play in any matches.

Read more about Zulqarnain's research by visiting the link below...

Ph.D. Dissertation Defense

Joint Inference for Extracting Soft Biometric
Text Descriptorsfrom Patient Triage Images

Niyati Chhaya

10:00am Friday, 24 August 2012, ITE 325b, UMBC

Disaster events can result in mass casualties and missing persons, giving rise to a need to provide information about victims to the public. This can be achieved by digitally documenting information available at emergency medical care centers in the form of pictures. The images and other identifying information, such as fingerprints, cannot be broadcast due to privacy concerns, leading to a need to extract appearance-related non-unique features from this data to facilitate locating missing persons. Using humans and machines to compare images is not feasible due to the scale of the situation and the nature (presence of blood and debris) of the images. Extracting a soft biometric text descriptor (text labels describing different soft biometric features) makes it possible to organize information about individuals from these images in a searchable format without revealing the person's identity. The main aim of this thesis is to extract soft biometric features from person images to label appearance-related information and make it available as a text descriptor.

We begin by presenting soft biometric feature detectors for patient images that include an ensemble-based face detection algorithm, template-based eye detection, and eyeglasses, hair color, and skin color detection. We also present a facial hair detector that uses a combination of face and hair information. The feature detection results indicate a need to combine and exploit feature relationships for better performance. We propose a novel probabilistic graphical model that consists of different feature detectors and exploits relationships between these features using a message-passing inference algorithm to build a coherent text descriptor. Further, to understand the utility and the nature of the text descriptors, we present a study based on human descriptions that aims at extracting order and structure information about the features.

We evaluate the performance of individual feature detectors for standard and triage images and establish the challenges posed by the latter. Further, our text analysis shows extreme variability in human descriptions. However, we succeed in extracting some insights about the order of a natural text description. Through our evaluations of the graphical model, we show that for different feature detectors, datasets, and graph sizes the graphical model helps improve the accuracy of the text output. We also show that the performance of the graphical model depends on the individual nodes (feature detectors) and that the model can be used to improve the performance of the individual feature detectors. This thesis illustrates the whole process from images to text descriptors while evaluating components as we proceed. This work presents an approach to extract text labels from images using computer vision, a probabilistic graphical model, and natural language processing techniques.

Committee: Drs. Dr. Tim Oates (Chair), Marie desJardins, Tim Finin, Glenn Pearson and Jesus Caban

CSEE Professor Dr. Alan Sherman (PI) and Dr. Rick Forno (Co-PI), Graduate Program Director, Cybersecurity have received an NSF grant of $2.5 million over five years to fund 22 students studying Information Assurance (IA) and Cybersecurity. The scholarships are part of the Federal Cyber Scholarship for Service (SFS) program.

Future scholars will come from UMBC’s undergraduate, graduate, and professional studies programs. In addition to a generous full-ride scholarship, scholars are granted an annual stipend during their last two or three years.  The yearly stipends are $20,000 for underdergraduate, $25,000 for M.S. and $30,000 for PhD students.  Students will also engage in paid summer internships with federal government agencies and have opportunities to carry out mentored research projects at UMBC and its cyber partners from government and industry.

“Our goal is to encourage students to pursue cybersecurity education at UMBC and then move into careers that can build upon their education,” explains Dr. Forno. “The SFS program is one way to do that, with the outcome being to provide educated, qualified and highly competent cybersecurity practitioners to the federal government.”

The scholarships will be coordinated through UMBC’s Center for Information Security and Assurance (CISA), and both CISA and UMBC’s Cyber Defense Lab (CDL) will play a key role in the overall academic experience of the SFS scholars.

Along with the monetary award come a few scholarship program requirements. During their scholarship period (typically two years), students are required to intern at a federal organization. After graduation, scholars must serve at a Federal agency in an information assurance position for one to two years, depending on their level of support.

During the upcoming 2012-2013 school year, the program will support two Masters students and two Master in Professional Studies students, though in the future, one B.S., two M.S., two M.P.S., and one Ph.D. students will be supported annually.

Degree-seeking students in Computer Science, Computer Engineering, or any related field, including Electrical Engineering, Math, Physics, Information Systems, Public Policy, or Education, are eligible. “We are interested in fostering a diverse group of SFS scholars,” says Forno. “To that end, we intend to work closely with groups like CWIT and the Meyerhoff Scholars (among others) to help in our outreach and recruiting efforts in this critical academic discipline.” To learn more about applying for the scholarship, visit the CISA scholarship oppotunities page.

The grant will also fund a new one-day annual regional workshop that will focus on innovations for K-12, undergraduate, and graduate cybersecurity education. The goal is to develop "innovative, relevant, meaningful, and real-world oriented pedagogical materials that can be applied across the academic spectrum in conducting cybersecurity education."

The scholarship program, coupled with UMBC’s location at the “epicenter of cybersecurity,” will further mark UMBC as a pioneer in the field. “We all know that cybersecurity is a hot field and of critical national interest," says Forno. "UMBC’s strength in Computer Science, Cybersecurity, and related STEM fields, combined with our reputation for producing qualified technologitsts makes our participation in SFS very attractive both to the school and our current and future students.”

Tim Finin and Anupam Joshi have received a $400,000 research award from the NSF Secure and Trustworthy Cyberspace (SaTC) program for a three year project to investigate how to better manage security and privacy constraints while querying semantically annotated linked data sources. The project, Policy Compliant Integration of Linked Data, is a collaboration with researchers at M.I.T. and the University of Texas at Dallas.

The ubiquity of computing technology and the Internet have created an age of big data that has the potential to greatly enhance the efficiency of our societies and the well-being of all people. The trend comes with problems that threaten to prevent or undermine the benefits. An immediate concern is how to fuse, integrate and analyze data while respecting privacy, security and usage concerns. A second issue is allowing data to remain distributed, enabling its owners to maintain and control quality as well as to enforce security and privacy policies. A final underlying challenge is helping to produce sound and useful results by assuring that systems understand the meaning of the data being integrated and analyzing access and usage policies. For some domains, like health informatics and clinical research, solving these problems will have a significant impact on society.

This project explores an approach to solving these problems by developing a policy-compliant integration system for linked healthcare data. The system models data, schemas and policies using open Web standards such as Semantic Web languages, federates queries to independent Linked Data stores based on content, provides policy enforcement by modifying incompliant queries, and uses formal methods to guarantee correctness of key components.

This project provides new approaches to solving one of the most significant problems our society faces in the 21st century: benefiting from the integration of distributed linked data while respecting security, privacy, and usage requirements. The prototype tools and systems are incorporated into our educational activities and made available to others via appropriate open source licenses.