Department of Computer Science and Electrical Engineering

Photo: The Retriever Weekly

This August, UMBC welcomed its inagural batch of Transfer Scholars in Information Technology and Engineering (T-SITE) Scholars (pictured above).

The brainchild of a team of seven women sprinkled throughout IT and Engineering departments in the College of Engineering and Information Technology at UMBC, the T-SITE scholarship program offers support–financial and otherwise–to help transfer students succeed in careers in Computer Science, Computer Engineering, Mechanical Engineering, Chemical and Biochemical Engineering, and Information Systems.

The scholars took part in the Center for Women in Technology's (CWIT) New Scholars Retreat, held August 10-12. The Olympics-themed retreat included a trust-building activity at College Park's ropes course, a traditional business dinner with faculty members, industry representatives, and CWIT alumni, and a discussion of women in STEM fields.

You can read more about CWIT's New Scholars Retreat in a Retriever Weekly article: " CWIT summer retreat welcomes the T-SITE scholars."

Photo: Gracehopper.org

Facebook has announced that it will award scholarships to 25 women who wish to attend the upcoming Grace Hopper Celebration of Women in Computing Conference that will take place at the Baltimore Convention center October 3-6. This year's theme is "Are We There Yet?"

Applicants must be women studying Computer Science, Computer Engineering, or a related technical field. Both full-time students and full-time working professionals within the same fields are eligible.

Scholarship recipients will receive free registration to the conference, free travel and lodgings, and a $200 food stipend. The lucky winners will also be treated to an all-expenses-paid visit to Facebook's New York City office from September 30 through October 2 that includes tech talks, mentoring sessions, and optional sightseeing. During the conference, the 25 recipients will be invited to a private reception with Jocelyn Goldfein, the director of engineering at Facebook.

If interested, you can apply for the scholarship through the Facebook Grace Hopper Scholarship application page by next Wednesday, September 5, 2012. Winners will be notified by September 14, 2012.

An initial 20 event calendar for the first-ever Baltimore Innovation Week has just been released. Organized by local tech news site Technically Baltimore, the annual event, held from September 20-30, is a celebration of technology and innovation in Baltimore. Its goal is to encourage local innovation through programming focused on technology, collaboration, and improving the city, says the website.

Highlights include:

Startup Weekend (Sep. 28), a worldwide three-day frenzy where aspiring entrepreneurs gather to  pitch business proposals, create business models, and gather feedback from local entrepreneurial leaders. The Baltimore chapter takes place at Betamore, an urban campus for technology and entrepreneurship that opens in September.

DiversiTech #7 (Sep. 26), a meetup geared towards the needs of the minority tech entrepreneur. "The Meetups allow for unmatched networking opportunities and access to resources relevant to building diversity in the regional tech entrepreneurship space," explains the website. 

Open Source Hack Night (Sep. 25), a chance to break into groups to work on the hack project of your choice. Hackers of all skill levels are welcome.

Check out the full calendar of events.

Anupam Joshi and Tim Finin have received a $200,000 research award from the NSF Division of Information and Intelligent Systems for a two-year project focused on extracting information from tables. The project, T2K: From Tables to Knowledge, will explore the feasibility of automatically extracting new knowledge directly from data found in spreadsheets, database relations, and document tables and representing it as highly interoperable linked open data (LOD) in the Semantic Web language RDF. The extraction is guided by probabilistic graphical models that use statistical information mined from current LOD knowledge resources. To demonstrate the potential payoff of the research, the system is used to extract knowledge from tables collected from medical journals and tables from web sites like data.gov.

While the W3C semantic web languages RDF and OWL are used to represent the knowledge, the results are applicable to other semantic data frameworks such as Microdata (Search Consortium), Freebase (Google), Probase (Microsoft) and the Open Graph (Facebook). The open sourced prototype software allows other researchers to experiment with automatically producing semantically enriched data from tables for their domains.

If successful, such software extraction systems are expected to become part of a new online knowledge ecology — both consuming existing LOD knowledge to understand the intended meaning implicit in a table and producing new facts and knowledge that will become part of Web. This represents a dramatic increase in the breadth and depth of public semantic data that can make “big data'' analytics more effective.

MS Thesis Defense

Calculating Representativeness of
Geographic Sites Across the World

Ashwinkumar Ganesan

11:00am Friday, 31 August 2012, ITE 325b, UMBC

GLOBE is a global correlation engine, a project to study the effects of human activity on land change based on a set of parameters that include temperature, forest cover, human population, atmospheric parameters, and many other variables. The aim of this research is to understand how a land change study or set of studies of specific geographic areas generalizes to other areas of the world. The generic form of the question is – given a set of data points with a set of variables, how can we determine how much a selected subset of points represents the rest of the distribution. The research aims to answer a set of questions which include the definition of representativeness of a geographical site and how the representativeness can be computed. Land change researchers will dynamically select a subset of variables which they would like to study. Hence the method developed not only computes representativeness, but must do so in an efficient manner. For this purpose, we apply dimension reduction techniques to reduce the size of computation and analyze the effectiveness of using these techniques to calculate representativeness.

Committee: Drs. Tim Oates (chair), Tim Finin and Dr. Matt Schmill

This Friday, August 31, new and returning students are invited to the Office of Undergraduate Education's Open House.

Held from Noon to 2 p.m. in the Academic IV Building (Room 114), the event is a chance to talk about First Year Seminars, The New Student Book Experience, Undergraduate Research, and an Introduction to an Honors University.

MS Thesis Defense

Predicting the Activities of Mobile Phone Users
with Hidden Markov Models

Amey Sane

9:00am Tuesday, 28 August 2012, ITE 325b, UMBC

Mobile phones are ubiquitous and increasingly capable, with sophisticated sensors, network access, significant storage and processing power and access to a wide range of application data. They can improve the range and quality of their services by acquiring and using models of their context, including the activities in which their users are engaged. This thesis explores the use of supervised machine learning techniques for predicting a smartphone user's activities from available sensor data. We have specifically concentrated on applying classifiers and ensembles using hidden markov models for activity recognition. Our classifiers predict a user's current activity from among a set of conceptual activity classes such as sleeping, traveling, playing, working, and chatting/watching TV. We have experimented with and evaluated the effectiveness of different approaches on data collected on Android smartphones by university faculty and students.

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

If, in getting to this post, you navigated straight to myUMBC and bypassed UMBC's home page, you probably haven't seen its new look.

The update is part of a long term project to improve UMBC's web presence. "Our marketing and recruitment efforts demand a cutting edge homepage, and the innovation and expertise of our faculty in the computer science, information technology and visual design fields further raise the bar," said a UMBC press release. "In the constantly evolving environment of the web, we simply can’t stand still."

The goal is to make the site more user friendly. To that effect, the update includes tabs targeted toward different members of the UMBC community (current students, prospective students, faculty and staff, etc.) that provide the most relevant information for their audience.

Plus, the new page is designed to work well with mobile devices like smartphones, and tablets.

You can send feedback about the new design to . What do you think makes a website user friendly? Does UMBC's new homepage meet your criteria?

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

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