talk: Topic Modeling for Analyzing Document Collection, 11am Mon 3/16

The UMBC CSEE Seminar Series Presents

Learning to Predict the Future from Unlabeled Data

Hamed Pirsiavash, CSEE Department, UMBC

1-2pm Friday, 28 October 2016, ITE 229

Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world that is difficult to write down. We believe that a promising resource for efficiently learning this knowledge is through readily available unlabeled video. I will talk about our framework that capitalizes on temporal structure in unlabeled video to learn to anticipate human actions and objects. The key idea behind our approach is that we can train deep networks to predict the visual representation of images in the future. I will also talk about our recent work on a Generative Adversarial learNing (GAN) architecture that generates a novel video given the first frame.

Hamed Pirsiavash is an assistant professor at the University of Maryland, Baltimore County (UMBC) since August 2015. Prior to that, he was a postdoctoral research associate at MIT working with Antonio Torralba. He earned his PhD at the University of California Irvine under the supervision of Deva Ramanan (now at CMU). He performs research in the intersection of computer vision and machine learning.

Organizers: Professors Tulay Adali () and Alan T. Sherman ()

About the CSEE Seminar Series: The UMBC Department of Computer Science and Electrical Engineering presents technical talks on current significant research projects of broad interest to the Department and the research community. Each talk is free and open to the public. We welcome your feedback and suggestions for future talks.

talk: Learning to Predict the Future from Unlabeled Data, 1pm Fri 10/28, ITE229, UMBC


2016 ADVANCE Distinguished Lecture Series

Against the Odds: How I Became a Computer Scientist

Dr. Claudia Pearce (UMBC MS ’89, PhD ’94)
National Security Agency

4:30-5:30 Tuesday, 11 October 2016
Library and Gallery, Albin O. Kuhn

Dr. Claudia Pearce, UMBC Alumna and Senior Computer Science Authority at NSA, shares a personal story of perseverance in her educational, research, and career journey as a computer scientist.

UMBC-ADVANCE is pleased to announce that alumna Dr. Claudia Pearce M.S., ’89 and Ph.D., ’94 and 2014 UMBC Alumna of the Year in COEIT is our 2016 ADVANCE Distinguished Speaker. Dr. Pearce is currently Senior Computer Science Authority at NSA, a member of UMBC’s COEIT advisory board, and involved in collaborative research with our CSEE faculty.

The event will take place on Tuesday, October 11th and we are proud to incorporate this event into UMBC’s 50th Anniversary celebrations. As part of this event, Dr. Pearce will deliver a campus-wide talk on her career trajectory at 4:30pm in the Library Gallery followed by a reception.


Claudia Pearce, UMBC Alumna (’89 M.S. in Computer Science and ’94 Ph.D. in Computer Science) and 2014 COEIT Alumna of the Year awardee, is currently the Senior Computer Science Authority at the NSA. In her time at the NSA, Pearce has created development programs for computer science and information technology new-hires to NSA, a short-course series on high-end topics in CS and IT, a summer intern program and organized a distinguished lecture series. In addition, she has created a computer science grants program with the National Science Foundation, for computer science education and outreach. She has also served on the Advisory Board of the Anita Borg Institute for Women in Technology and UMBC’s College of Engineering and Information Technology Advisory Board.

Prior to becoming the NSA’s Senior Computer Science Authority, Pearce served as the Chief of Knowledge Discovery Sciences, where she directed a research team that created Knowledge Discovery applications.

From 2000-2003, Pearce was part of the Senior Technical Development Program. While involved with this program, Pearce collaborated with organizations such as the Johns Hopkins Applied Physics Lab and Magnify Research, Inc., on topics such as “applications of data mining techniques to natural language processing.” As a Senior Computer Scientist from 1985-2000, Pearce conducted research in the area of databases and information retrieval systems.

Pearce received a B.S. in Mathematics from the University of Florida in 1973, graduating with High Honors and a Phi Beta Kappa distinction. She received an M.S. in Industrial and Systems Engineering from the University of Florida in 1974. In 1989 she received an M.S. in Computer Science from UMBC.  She also received a Ph.D. in Computer Science from UMBC in 1994.

Pearce is currently involved in research at UMBC. She helped to organize a workshop sponsored by the NSF and the Department of Defense, titled “Beyond Watson: Predictive Analytics and Big Data.” The research that inspired the Beyond Watson workshop ties into questions that are relevant to information retrieval systems. Questions such as “how do you find the right documents out of very large collections of text?” and “what are the kinds of languages, tools, techniques, infrastructure [needed]…to build our own Watson?” Pearce notes that she’s “always been interested in databases, and in particular text and natural language databases, and this notion of answering questions.” Furthermore, information retrieval systems was the topic of her Ph.D. dissertation.

Claudia lives with her husband Jonathan Cohen in Glenwood, MD. She is “an avid snow skier, quilt maker and trumpet player.”

talk: Against the Odds: How I Became a Computer Scientist, 4:30pm Tue 10/11, UMBC


Credibility, Privacy and Policing on Online Social Media

Prof. Ponnurangam Kumaraguru (“PK”)
Indraprastha Institute of Information Technology, Delhi, India

1:00-2:00pm Friday, 14 October 2016, ITE 229, UMBC

With increase in usage of the Internet, there has been an exponential increase in the use of online social media on the Internet. Websites like Facebook, Google+, YouTube, Orkut, Twitter and Flickr have changed the way the Internet is being used. There is a dire need to investigate, measure, and understand privacy and security on online social media from various perspectives (computational, cultural, psychological). Real world scalable systems need to be built to detect and defend security and privacy issues on online social media. I will describe briefly some cool projects that we work on: TweetCred, OSM & Policing, OCEAN, and Call Me MayBe. Many of our research work is made available for public use through tools or online services. Our work derives techniques from Computational Social Science, Data Science, Statistics, Network Science, and Human Computer Interaction. In particular, in this talk, I will focus on the following:

  • TweetCred, a tool to extract intelligence from Twitter which can be useful to security analysts. TweetCred is backed by award-winning research publications in international and national venues.
  • How police in India are using online social media, how we can use computer science understanding to help police engage more with citizens and increase the safety in society.
  • OCEAN: Open source Collation of eGovernment data and Networks, how publicly available information on Government services can be used to profile citizens in India. This work obtained the Best Poster Award at Security and Privacy Symposium at IIT Kanpur, 2013 and it has gained a lot of traction in Indian media.
  • Given an identity in one online social media, we are interested in finding the digital foot print of the user in other social media services, this is also called digital identity stitching problem. This work is also backed by award-winning research publication.

Ponnurangam Kumaraguru (“PK”) is an Associate Professor, at the Indraprastha Institute of Information Technology (IIIT), Delhi, India from Aug 2009. He is currently the Hemant Bharat Ram Faculty Research Fellow, and the Founding Head of Cybersecurity Education and Research Centre. PK is an ACM Distinguished Speaker. He received his Ph.D. from the School of Computer Science at Carnegie Mellon University. He is primarily excited about and works with a bunch of smart students and collaborators around the world on the issues related to Privacy and Security in Online Social Media, Computational Social Science, and Data Science for Social Good. In the past seven years of his faculty life, he has managed projects close to a $800,000 USDs. PK has received research funds from multiple departments of the Government of India, National Science Foundation, Adobe, RSA, and International Development Research Centre. PK is part of multiple government initiatives / projects in the area of Cybersecurity in India. Technology that PK and his students have developed at IIIT Delhi is currently being used by 40+ different State and Central Government agencies in India. PK has spent his summer sabbaticals at IBM India Research Labs, Adobe Research Labs – India, and Universidade Federal de Minas Gerais. He is currently visiting Max Planck Institute for Software Systems for Summer 2016. PK regularly serves as a PC member at prestigious conferences like WWW, ICWSM, CSCW, AsiaCCS and he also serves as a reviewer for International Journal of Information Security and ACM’s Transactions on Internet Technology. PK’s Ph.D. thesis work on anti-phishing research at CMU has contributed in creating an award winning start-up Wombat Security Technologies, which recently raised Series C funding and also acquired a company. PK founded and manages the PreCog research group at IIIT-Delhi.

Host: Anupam Joshi,

talk: Credibility, Privacy and Policing on Online Social Media, 1pm Fri 10/14, UMBC

The UMBC Cyber Defense Lab presents

An Introduction to the Security of Software Defined Networks

Enis Golaszewski
CSEE Department, UMBC

11:15am-12:30pm, Friday, 7 October, UMBC, ITE 229

We introduce the concept of Software Defined Networks (SDNs) and the security challenges facing them. SDNs are a promising new network architecture that separates the data and control planes. By providing a central point of control and visibility over the network, SDNs allows a network to handle traffic with unprecedented flexibility, while simultaneously introducing potentially vulnerable lines of communication between a centralized controller and its constituent switches. To highlight the security challenges facing SDNs, we introduce and discuss several existing attacks. Anyone interested in networks and network security will want to know about the emerging trend of SDNs.

About the Speaker. Enis Golaszewski () is a first-semester PhD student and SFS scholar at UMBC working with Dr. Sherman on the security of software defined networks.

Host: Alan T. Sherman,

The UMBC Cyber Defense Lab meets biweekly Fridays

Security of Software Defined Networks, 11:15 Fri 10/7, UMBC

Department of Information Systems

Challenges of Implementing Personalized (Precision) Medicine

Dr. Eddy Karnieli, Rambam Medical Center, Israel
11:00-12:00 Friday, 7 October 2016, ITE 459, UMBC

The concept of personalized (precision) medicine (PM) emphasizes the scientific and technological innovations that enable the physician to tailor disease prediction, diagnosis and treatment to the individual patient, based on a personalized data-driven approach. The major challenge for the medical systems is to translate the molecular and genomic advances into clinical available means.

For example, type 2 diabetes (T2D) is a major health problem. T2D is a very heterogeneous disease with at least three subgroups that exhibit distinct phenotypic and biological characteristics and susceptibilities to diabetes-related complications and comorbidities and specific genetic markers. Genomic analysis has already revealed about 80 gene loci variations. However, only few clinical and biochemical factors are taken into account in identifying diabetes type and advising therapy.

Among the main challenges to implementation of personalized (precision) medicine into current medical practice are knowledge gap of professionals; lack of approved and readily available genomic, phramcogenomics and other –omics tests; the lack of decision support systems integrated with EMRs clinical data, as well as updated genetic and molecular information at the clinical point of care and ethical and regulatory challenges. Currently, expensive cost of the new molecular targeting drugs like those used in treating cancers and rare genetic diseases patients results in major economic burden on the health system. Further, the question whether PM will reduce major causes of chronic morbidity and mortality still waits for an answer. During the lecture I will also outline programs currently being implemented to overcome these challenges.

Professor Eddy Karnieli is a graduate of the Rappaport Faculty of Medicine at the Technion– Israel Institute of Technology in Haifa.He obtained clinical training in Internal Medicine and Endocrinology at the Rambam Medical Center and did his Post-Doctoral Fellowship in Diabetes, Obesity and Endocrinology at the National Institutes of Health in Bethesda, Maryland. He was a visiting scholar at the University of California at San Diego and at the National Institutes of Health. He is currently the Director of the Institute of Endocrinology, Diabetes and Metabolism at the Rambam Medical Center. …

talk: Challenges of Implementing Personalized (Precision) Medicine, 11am Fri 10/7

UMBC CSEE Seminar Series

Analytic approaches to study the chronnectome
(time-varying brain connectivity)

Dr. Vince D. Calhoun
Executive Science Officer and Director, Image Analysis and MR Research
The Mind Research Network
Distinguished Professor, Electrical and Computer Engineering
The University of New Mexico

1:00-2:00pm Friday, 7 October 2016, ITE 229 UMBC

Recent years have witnessed a rapid growth in moving functional magnetic resonance imaging (fMRI) connectivity beyond simple scan-length averages into approaches that capture time-varying properties of connectivity. In this perspective we use the term “chronnectome” to describe such metrics that allow a dynamic view of coupling. We discuss the potential of these to improve characterization and understanding of brain function, which is inherently dynamic, not-well understood, and thus poorly suited to conventional scan-averaged connectivity measurements.

Prof. Vince Calhoun (EE Ph.D.’02, UMBC) is this year’s distinguished alum in the Engineering and Information Technology category and is the first speaker in our departmental seminar series.

Dr. Calhoun is currently Executive Science Officer at the Mind Research Network and a Distinguished Professor in the Department of Electrical and Computer Engineering at the University of New Mexico. He is the author of more than 450 full journal articles and over 550 technical reports, abstracts and conference proceedings. His work includes the development of flexible methods to analyze functional magnetic resonance imaging such as independent component analysis (ICA), data fusion of multimodal imaging and genetics data, and the identification of biomarkers for disease. Among other things, he leads an NIH P20 COBRE center grant on multimodal imaging of schizophrenia, bipolar disorder, and major depression as well as an NSF EPSCoR grant focused on brain imaging and epigenetics of adolescent development. Dr. Calhoun is a fellow of the Institute of Electrical and Electronic Engineers (IEEE), The Association for the Advancement of Science, The American Institute of Biomedical and Medical Engineers, The American College of Neuropsychopharmacology, and the International Society of Magnetic Resonance in Medicine. He is currently chair of the IEEE Machine Learning for Signal Processing (MLSP) technical committee.

Host: Tulay Adali

About the CSEE Seminar Series: The UMBC Department of Computer Science and Electrical Engineering presents technical talks on current significant research projects of broad interest to the Department and the research community. Each talk is free and open to the public. We welcome your feedback and suggestions for future talks.

Organizers: Tulay Adali and Alan Sherman

talk: Analytic approaches to study the chronnectome, 1pm Fri 10/7, ITE 229

The UMBC Cyber Defense Lab presents

Categorizing Misconceptions of Cybersecurity Reasoning

 Travis Scheponik
Computer Science and Electronical Engineering
University of Maryland, Baltimore County

11:15am-12:30pm Friday, 9 September 2016, ITE 237

We present preliminary analysis of student responses to cybersecurity interview prompts.

During spring 2016, we interviewed twenty-six students at three diverse colleges and universities (UMBC, Prince George’s Community College, Bowie State University) to understand how they reason about cybersecurity.  Each interview lasted approximately one hour during which we asked the subject to solve four cybersecurity problems.  For this purpose, we developed twelve engaging interview prompts organized in three protocols each comprising four prompts.  Using a paired expert-novice methodology, we are analyzing transcriptions of the interviews produced from audio and video recordings.  The twelve prompts focused on five difficult and important concepts identified from a Delphi method with thirty-six experts, which we carried out in fall 2014.

Preliminary analysis of student responses reveals common misconceptions and problematic reasoning, including conflating concepts, biased reasoning, unsound logic, and factual errors.  For example, students commonly conflate authentication and authorization, as well as encryption and hashing.   Examples of biased reasoning include seeing the situation only from the user’s perspective, placing inappropriately high trust in physical objects, and underestimating potential vulnerabilities from insider threats.  Initially, we marked student statements as “correct’’ or “incorrect.’’  From the “incorrect’’ responses, we identified misconceptions about cybersecurity.  Then, we categorized why responses were incorrect and we identified a variety of biases and problematic reasonings.

Our motivation is to produce educational assessment tools that will measure how well students understand cybersecurity concepts, for the purpose of identifying effective ways to teach cybersecurity.  Results of our work will also be useful in developing curricula, learning exercises, and other educational materials and policies.

Joint work with David Delatte, Geoffrey Herman, Michael Neary, Linda Oliva, Alan Sherman, and Julia Thompson.  Support for this research is provided in part by the U.S. Department of Defense under CAE-R grants H98230-15-1-0294 and H98230-15-1-0273, and by the National Science Foundation under SFS grant 1241576.  We will present our results at the Frontiers in Education Conference, October 12-15, 2016, in Erie, PA.

 About the Speaker:  Travis Scheponik is a PhD student in computer science at UMBC, working with Dr. Alan T. Sherman.  His research interests include cybersecurity education.

Host: Alan T. Sherman,

talk: Categorizing Misconceptions of Cybersecurity Reasoning, 11:15 Fri 9/9


Cognitive Computing and Visualization at IBM Research/RPI CISL

Dr. Hui Su, IBM Research

10:00-11:00am, Thursday, 19 May 2016, ITE 325b

Dr. Hui Su will talk about Cognitive and Immersive Systems Lab, a research initiative to develop the new frontier of immersive cognitive systems that explore and advance natural, collaborative problem-solving among groups of humans and machines. This lab is a collaboration between IBM Research and Rensselaer Polytechnic Institute. Dr. Su will talk about why the research for human computer interaction is extended to build a symbiotic relationship between human beings and smart machines, what research is going to be important to build immersive cognitive systems in order to transform the way professionals work in the future.

Dr. Hui Su is the Director of Cognitive and Immersive Systems Lab, a collaboration between IBM Research and Rensselaer Polytechnic Institute. He has been a technical leader and an executive at IBM Research. Most recently, he was the Director of IBM Cambridge Research Lab in Cambridge, MA and was responsible for a broad scope of global missions in IBM Research, including Cognitive User Experience, Center for Innovation in Visual Analytics and Center for Social Business. As a technical leader and a researcher for 19 years at IBM Research, Dr. Su has been an expert in multiple areas ranging from Human Computer Interaction, Cloud Computing, Visual Analytics, and Neural Network Algorithms for Image Recognition etc. As an executive, he has been leading research labs and research teams in the US and China. He is passionate about game-changing ideas and fundamental research, passionate in speeding up the impact generation process for technical innovations, discovering and developing new linkages between innovative research work and business needs.

Host: Jian Chen ()

talk: Cognitive Computing & Visualization at IBM Research/RPI, 10am Thur 5/19, UMBC

UMBC Information Systems Department

Predicting Demographics and Affects in Social Networks

Dr. Svitlana Volkova
Pacific Northwest National Laboratory

11am Friday, 13 May 2016, ITE 459

Social media predictive analytics bring unique opportunities to study people and their behaviors in real time, at an unprecedented scale: who they are, what they like and what they think and feel. Such large-scale real-time social media predictive analytics provide a novel set of conditions for the construction of predictive models. This talk focuses on various approaches to handling this dynamic data for predicting latent user demographics, from constrained-resource batch classification, to incremental bootstrapping, and then iterative learning via interactive rationale (feature) crowdsourcing. In addition, we present the relationships between a variety of perceived user properties e.g., income, education etc. and opinions, emotions and interests in a social network.

Svitlana Volkova received her PhD in Computer Science from Johns Hopkins University. She was affiliated with the Center for Language and Speech Processing and the Human Language Technology Center of Excellence. Her PhD research focused on building predictive models for sociolinguistic content analysis in social media. She built online models for streaming social media analytics, fine-grained emotion detection and multilingual sentiment analysis, and effective annotation techniques via crowdsourcing incorporated into the active learning framework. She interned at Microsoft Research in 2011, 2012 and 2014 at the Natural Language Processing and Machine Learning and Perception teams. She was awarded the Google Anita Borg Memorial Scholarship in 2010 and the Fulbright Scholarship in 2008.

talk: Predicting Demographics and Affects in Social Networks, 11am Fri 5/13, UMBC


CHMPR Lecture Series

  • Topic Modeling for Analyzing Document Collection

Mitsunori Ogihara
Department of Computer Science, University of Miami

11:00am Monday, 16 May 2016, ITE 325b, UMBC

Topic modeling (in particular, Latent Dirichlet Analysis) is a technique for analyzing a large collection of documents. In topic modeling we view each document as a frequency vector over a vocabulary and each topic as a static distribution over the vocabulary. Given a desired number, K, of document classes, a topic modeling algorithm attempts to estimate concurrently K static distributions and for each document how much each K class contributes. Mathematically, this is the problem of approximating the matrix generated by stacking the frequency vectors into the product of two non-negative matrices, where both the column dimension of the first matrix and the row dimension of the second matrix are equal to K. Topic modeling is gaining popularity recently, for analyzing large collections of documents.

In this talk I will present some examples of applying topic modeling: (1) a small sentiment analysis of a small collection of short patient surveys, (2) exploratory content analysis of a large collection of letters, (3) document classification based upon topics and other linguistic features, and (4) exploratory analysis of a large collection of literally works. I will speak not only the exact topic modeling steps but also all the preprocessing steps for preparing the documents for topic modeling.

Mitsunori Ogihara is a Professor of Computer Science at the University of Miami, Coral Gables, Florida. There he directs the Data Mining Group in the Center for Computational Science, a university-wide organization for providing resources and consultation for large-scale computation. He has published three books and approximately 190 papers in conferences and journals. He is on the editorial board for Theory of Computing Systems and International Journal of Foundations of Computer Science. Ogihara received a Ph.D. in Information Sciences from Tokyo Institute of Technology in 1993 and was a tenure-track/tenured faculty member in the Department of Computer Science at the University of Rochester from 1994 to 2007.

1 2 3 42