Department of Computer Science and Electrical Engineering

MS Defense
Computer Science and Electrical Engineering

Social Media Data Analytics Applied to Hurricane Sandy

Han Dong

12:30-2:30 Monday, 29 July 2013, ITE 325b

Social media websites are an integral part of many people’s lives in delivering news and other emergency information. This is especially true during natural disasters. Furthermore, the role of social media websites is becoming more important due to the cost of recent natural disasters. These online platforms are usually the first to deliver emergency news to a wide variety of people due to the significantly large number of users registered. During disasters, extracting useful information from this pool of social media data can be useful in understanding the sentiment of the public; this information can then be used to improve decision making. In this work, I am presenting a system that automates the process of collecting and analyzing social media data from Twitter. I also explore a variety of visualizations that can be generated by the system in order to understand the public sentiment. I demonstrate an example of utilizing this system on the Hurricane Sandy disaster from October 26, 2012 to October 30, 2012. Finally, a statistical analysis is performed to explore the causality correlation between an approaching hurricane and the sentiment of the public.

As a result of the large amount of data collected by this system; scalable machine learning algorithms are needed for analysis. Boosting is a popular and powerful ensemble method in the area of supervised machine learning algorithms due to its theoretical convergence guarantees, simple implementation and ability to use different learning algorithms to produce a classifier with high accuracy. A novel parallel implementation of the multiclass version of Boosting (AdaBoost.MH) is proposed and our experimental results show that the parallel implementation achieves classification error percentages similar to serial implementation with fewer execution iterations. By distributing the tasks, the number of Boosting iterations decreased linearly at least up to 16 computational threads.

Committee: Professors Milton Halem (chair), Yelena Yesha, John Dorband and Shujia Zhou

Computer Science and Electrical Engineering
MS Thesis Defense

Sentiment Analysis on Tweets and their
Relationship with Stock Market Trends

Jay Sharma

10:00 AM – 12:00 PM Monday, July 29, 2013, ITE 325

We investigate whether sentiment derived from micro-blogging site Twitter can be used to identify important events (product launch, quarter results etc.) and help to infer the future movement of the stock. We used the volume and key performance index of Apple Company’s financial tweets to identify important events and infer the future movement. We present the results of machine learning algorithms (Naïve Bayes, Maximum Entropy, and SVM) for classifying the sentiment of Apple Company’s financial tweets. Statistical analysis using Granger causality test showed that we were able to infer the movement of Apple Company’s stock close price in advance.

Committee: Professors Yelena Yesha (chair), Shujia Zhou, and Tim Finin

MS Defense
Computer Science and Electrical Engineering

Detection Performance and Computational Complexity of
Radar Compressive Sensing for Noisy Signals

Asmita Korde

2:00-4:00 Wednesday, 24 July 2013, ITE 325

In recent years, compressive sensing has received a lot of attention due to its ability to reducethe sampling bandwidth, yet reproduce a good reconstructed signal back. Compressivesensing is a new theory of sampling which allows the reconstruction of a sparse signal bysampling at a much lower rate than the Nyquist rate. This concept can be applied to severalimaging and detection techniques. In this thesis, we explore the use of compressive sensing for radar applications. By using this technique in radar, the use of matched filter can be eliminated and high rate sampling can be replaced with low rate sampling. We analyze compressive sensing in the context of radar by applying varying factors such as noise and different measurement matrices. Different reconstruction algorithms are compared by generating ROC curves to determine their detection performance, which in turn are also compared against a traditional radar system. Computational complexity and MATLAB run time are also measured for the different algorithms. We also propose an algorithm called simplified OMP, which works well in noisy environments and has a very low computational complexity.

Committee: Professors Tinoosh Mohsenin (Chair), Joel Morris, Tulay Adali, and Mohamed Younis

Computer Science and Electrical Engineering
MS Thesis Defense

Multicast Routing with Byzantine Robustness

Debdatta Mukherjee

2:30-4:30 Tuesday, july 23, 2013, ITE 346

Network problems arise when nodes behave in arbitrary ways such as sending malformed messages, sending incorrect messages or not forwarding messages at all to other nodes in the network. These faults are called Byzantine failures. In a real network, these faults can be a result of hardware failure, cyber-attacks or network congestion. Due to the serious problems these faults can cause, it becomes important to make the network robust against them, so that the network continues to operate properly or degrades in an acceptable way in the presence of such faults. In this thesis, we propose methods that include multiple node disjoint path calculations and robust flooding to find byzantine-free multicast trees. By finding such trees, we can guarantee the delivery of the messages from a source to a particular multicast group.

Committee: Professors Deepinder Sidhu (chair), Kostas Kalpakis and Sergei Nirenburg

MS Defense
Computer Science and Electrical Engineering

Linked Data for Cybersecurity Vulnerability Descriptions

Arnav Joshi

9:00-11:00 Monday, 22 July 2013, 325b ITE

The Web is typically our first source of information about new software vulnerabilities, exploits and cyber-attacks. Information is found in semi-structured vulnerability databases as well as in text from security bulletins, news reports, cybersecurity blogs and Internet chat rooms. It can be useful to cybersecurity systems if there is a way to recognize and extract relevant information and represent it as easily shared and integrated semantic data. We describe such an automatic framework that generates and publishes a RDF linked data representation of cybersecurity concepts and vulnerability descriptions extracted from the National Vulnerability Database and other text sources. Entities, relations and concepts are represented using custom ontologies for the cybersecurity domain and also mapped to objects in the DBpedia knowledge base, producing a rich resource of machine-understandable linked data. The resulting cybersecurity linked data collection can be used for many purposes, including automating early vulnerability identification, mitigation and prevention efforts.

Committee: Professors Tim Finin (chair), Anupam Joshi and Tim Oates

UMBC Professor Helen J. Burgess was recognized has for creating "the first truly digital dissertation in the United States" by the Networked Digital Library of Theses and Dissertations. Dr. Burgess is an Associate Professor of English in the Communication and Technology track and specializes in digital humanities.

Her 2003 doctoral dissertation, Highways of the mind: the haunting of the superhighway from the World's Fair to the World Wide Web, was completed at West Virginia University.

In addition to the recognition, Dr. Burgess received an Innovative ETD Award from NDLTD for her work.

“In Helen J. Burgess’ doctoral dissertation ‘Highways of the mind: the haunting of the superhighway from the World's Fair to the World Wide Web’ she produced the first truly digital dissertation in the United States which took full advantage of a Web-based format — incorporating an HTML and multimedia environment. Her dissertation consists of well-organized Web pages, persistence index links, photographs as well as video and audio clips linked throughout the document. This allows the reader to completely immerse into the digital environment and provide immediately accessible examples indicated in textual format. As a true testament to time and durability, Burgess’ ETD is still as functional today as the day it was posted online a decade ago. The bundle of dissertation files contain the Web page version as well as a "linear" book format version in PDF format, along with copies of all multimedia objects preserved in their original format, for preservation purposes.”

First-year Cybersecurity MPS student Andrew Shiffer placed third in Microsoft's "Cybersecurity 2020" student essay contest.  The contest allows Microsoft to solicit original research about cybersecurity policy challenges from university students at any stage in their educational careers.  Andrew's paper is entitled "A Cybersecurity Triumvirate: Policies, Outcomes, and Emerging Trends."

Andrew will receive $2,000 prize (which he is applying toward his studies at UMBC) and the opportunity for his work to be published by Microsoft at a later date. According to a follow-up note from Microsoft, it appears that Andrew is the only American finalist — the first and second place students both came from Canadian universities.

Well done, Andrew!

Two UMBC students were among the 18 fellows selected by Code 2040 for a unique fellowship program that places high performing Black and Latino/a software engineering students in internships with top technology companies and startups in the San Francisco Bay area and supports them with mentorship, leadership training, and network development.

Perry Ogwuche, a rising senior majoring in computer science and mathematics, will spend the summer working at Redbeacon, a startup in Foster City, CA that connects qualified home-service professionals with exclusive job requests from homeowners. Perry is a member of the Phi Mu Epsilon National Mathematics Honorary Society, and has served as a Resident Assistant, Student Government Association member and as a math tutor to student athletes.

Randi Williams, a rising sophomore majoring in computer engineering, will spend her summer as an intern at Jawbone, a San Francisco company known for its noise eliminating Bluetooth headsets and portable speakers. Randi is a Meyerhoff scholar and Center for Women In Technology (CWIT) affiliate and coach in UMBC's Math Gym.

CODE2040 is a non-profit organization that aims to close the achievement, wealth, and skills gaps for Blacks and Latinos in the United States by creating access, awareness, and opportunities in technology and engineering. Its summer fellowship program brings high performing Black and Latino undergraduate and graduate coders and software engineering students to Silicon Valley for a comprehensive summer internship program that includes a paid internship with a top startup, mentoring, a speaker series, company visits, interactive workshops, executive coaching, and more. The program began last year with five students and has expanded to 18 this summer.

Students who are interested in the program can get more information on it and find out how to apply for the 2014 CODE 2040 fellows program at their web site.

CSEE Colloquium

Personalized Medicine – the future is already here

Professor Eddy Karnieli, MD

Director, Institute of Endocrinology, Diabetes and Metabolism
Rambam Health Care Campus, Israel
Director, Galil Center for Medical Informatics, Telemedicine
and Personalized Medicine
Technion, Israel

2:30pm June 20, 2013, ITE 325b, UMBC

Professor Eddy Karnieli will talk about applications of personalized medicine in healthcare. Personalized medicine allows us to determine an individual's unique genetic and molecular characteristics and use this to better diagnose and treat diseases and reduce possible adverse reactions. Personalized medicine can also be used to predict an individual's susceptibility to diseases, enabling steps to help avoid or reduce the extent to which an individual will experience a disease.

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.
Recently, he was a visiting professor at MSSM in New York.

He is currently the Director of the Institute of Endocrinology, Diabetes and Metabolism at the Rambam Medical Center and the Director of Galil Center for Medical informatics, Telemedicine and personalized Medicine at the Faculty of Medicine – Technion. Professor Karnieli's main research interests are the molecular mechanisms for regulating cellular glucose uptake and transporters and their implications in diabetes and obesity; Medical informatics, telemedicine and personalized medicine. He is also the current President of the Israel Endocrine Society.

He has published over 70 peer reviewed papers and reviews. Professor Karnieli serves on the editorial board of several scientific journals and review boards.
Professor Karnieli is a retired Colonel from the Israel Defense Forces Medical Corps.