Ph.D. Dissertation Defense
Computer Science and Electrical Engineering
University of Maryland, Baltimore County

Human Sensor Networks for Disasters

Oleg Aulov

11:00am Thursday, 29 May 2014, ITE325b, UMBC

This dissertation, presents a novel approach that utilizes quantifiable social media data as a human aware near real-time observing system coupled with geophysical predictive models for improved response to disasters and extreme events. It shows that social media data has the potential to significantly improve disaster management beyond informing the public and emphasizes the importance of different roles that social media can play in management, monitoring, modeling and mitigation of natural and human-caused disasters.

In the proposed approach, social media sources are viewed as a Human Sensor Network, and Social Media users are viewed as “human sensors” that are “deployed” in the field, and their posts are considered to be “sensor observations”. I have utilized the “human sensor observations”, i.e. data acquired from social media, as boundary value forcings to show improved geophysical model forecasts of extreme disaster events when combined with other scientific data such as satellite observations and sensor measurements. In addition, I have developed a system called ASON maps that dynamically combines model forecast outputs with specified social media observations and physical measurements to define the regions of event impacts such as flood distributions and levels, beached tarballs, power outages etc. Real time large datasets were collected, archived and are available for following recent extreme disasters events as use case scenarios.

In the case of the Deepwater Horizon oil spill disaster of 2010 that devastated the Gulf of Mexico, the research demonstrates how social media data can be used as a boundary forcing condition of the oil spill plume forecast model, and results in an order of magnitude forecast improvement. In the case of Hurricane Sandy NY/NJ landfall impact of 2012, owing to inherent uncertainties in the weather forecasts, the NOAA operational surge model only forecasts the worst-case scenario for flooding from any given hurricane. This dissertation demonstrates how the model forecasts, when combined with social media data in a single framework, can be used for near-real time forecast validation, damage assessment and disaster management. Geolocated and time-stamped photos allow near real-time assessment of the surge levels at different locations, which can validate model forecasts give timely views of the actual levels of surge, as well as provide an upper bound regional street level maps beyond which the surge did not spread. In the case of the Tohoku Earthquake and Tsunami of 2011, social media aspects of handheld devices such as Geiger counters that can potentially detect radioactive debris are discussed as well.

Committee: Dr. Milton Halem (chair), Tim Finin, Anupam Joshi, James Smith, Yelena Yesha

 Ph.D.Dissertation Defense
Computer Science and Electrical Engineering
University of Maryland, Baltimore County

Schema Free Querying of Semantic Data

Lushan Han

10:00am Friday, 23 May 2014, ITE 325b

Developing interfaces to enable casual, non-expert users to query complex structured data has been the subject of much research over the past forty years. We refer to them as as schema-free query interfaces, since they allow users to freely query data without understanding its schema, knowing how to refer to objects, or mastering the appropriate formal query language. Schema-free query interfaces address fundamental problems in natural language processing, databases and AI to connect users’ conceptual models and machine representations.

However, schema-free query interface systems are faced with three hard problems. First, we still lack a practical interface. Natural Language Interfaces (NLIs) are easy for users but hard for machines. Current NLP techniques are still unreliable in extracting the relational structure from natural language questions. Keyword query interfaces, on the other hand, have limited expressiveness and inherit ambiguity from the natural language terms used as keywords. Second, people express or model the same meaning in many different ways, which can result in the vocabulary and structure mismatches between users’ queries and the machines’ representation. We still rely on ad hoc and labor-intensive approaches to deal with this ‘semantic heterogeneity problem’. Third, the Web has seen increasing amounts of open domain semantic data with heterogeneous or unknown schemas, which challenges traditional NLI systems that require a well-defined schema. Some modern systems gave up the approach of translating the user query into a formal query at the schema level and chose to directly search into the entity network (ABox) for the matchings of the user query. This approach, however, is computationally expensive and has an ad hoc nature.

In this thesis, we develop a novel approach to address the three hard problems. We introduce a new schema-free query interface, SFQ interface, in which users explicitly specify the relational structure of the query as a graphical “skeleton” and annotate it with freely chosen words, phrases and entity names. This circumvents the unreliable step of extracting complete relations from natural language queries.

We describe a framework for interpreting these SFQ queries over open domain semantic data that automatically translates them to formal queries. First, we learn a schema statistically from the entity network and represent as a graph, which we call the schema network. Our mapping algorithms run on the schema network rather than the entity network, enhancing scalability. We define the probability of “observing” a path on the schema network. Following it, we create two statistical association models that will be used to carry out disambiguation. Novel mapping algorithms are developed that exploit semantic similarity measures and association measures to address the structure and vocabulary mismatch problems. Our approach is fully computational and requires no special lexicons, mapping rules, domain-specific syntactic or semantic grammars, thesauri or hard-coded semantics.

We evaluate our approach on two large datasets, DBLP+ and DBpedia. We developed DBLP+ by augmenting the DBLP dataset with additional data from CiteSeerX and ArnetMiner. We created 220 SFQ queries on the DBLP+ dataset. For DBpedia, we had three human subjects (who were unfamiliar with DBpedia) translate 33 natural language questions from the 2011 QALD workshop into SFQ queries. We carried out cross-validation on the 220 DBLP+ queries and cross-domain validation on the 99 DBpedia queries in which the parameters tuned for the DBLP+ queries are applied to the DBpedia queries. The evaluation results on the two datasets show that our system has very good efficacy and efficiency.

Committee: Drs. Li Ding (Memect), Tim Finin (chair), Anupam Joshi, Paul McNamee (JHU), Yelena Yesha

UMBC Center for Hybrid Multicore Productivity Research
Distinguished Computational Science Lecture Series

Tales of Scientific Computation at Ames and in NASA

Dr. Hans Mark

University of Texas Cockrell School of Engineering, Austin, TX

4:00pm Thursday, 22 May 2014, ITE 456, UMBC

This is personal story about how high performance computing was developed at the NASA-Ames Research Center and elsewhere in NASA. There were people at Ames who were first class aerodynamic scientists and who could use computers. Thus, it was decided that some procurement short cuts were justified. We acquired computers in three quantum steps. First, in 1969, there was an IBM duplex 360/67 which was captured by a “midnight supply operation” from the Air Force. Next, in 1972, the ILLIAC IV at the University of Illinois became available because of an act of domestic terrorism and financial help from DARPA. Finally in 1975, there was one of Seymour Cray’s CDC 7600s, also from an Air Force source. In 1981, by which time Seymour Cray had his own company, a Cray 1S appeared at Ames, followed in 1984 by CDC Cyber 205 and a Cray X-MP/22. The last named machines were made available because of shameless earmarking by NASA Headquarters. However, confession being good for the soul, the NASA-Goddard Space Flight Center also benefited from the earmarking with twenty million dollar fund to develop a truly massively parallel computer, the Goodyear MPP with 16,000 processors, which was delivered in 1984. Now we are working with people at Ames on a quantum computer manufactured by D‐Wave Systems, Inc. The machine was installed at Ames last year and we are now working on various “benchmark” tests and developing operating systems for the machine. We believe that there is great promise for much more capable computing machines in this new quantum technology.

Dr. Hans Mark is a leading expert in the fields of both aerospace design an national defense policy. For fourteen years Dr. Mark was associated with the University of California’s Nuclear Weapons Laboratory at Livermore, serving as Physics Division Leader from 1960 to 1964. He was named Under Secretary of the Air Force an Director of the National Reconnaissance Office in 1977. While Director of the National Reconnaissance Office, he initiated the development of a new reconnaissance satellite system an the upgrade of two others. As Secretary of the Air Force (1979 to 1981), Dr. Mark initiated the establishment of the U.S. Air Force Space Command. During his tenure as Deputy Administrator of NASA from 1981 to 1984, Dr. Mark oversaw the first fourteen Space Shuttle flights and was a leading contributor to the establishment of the U.S. Space Station Program. Over the past twenty years, Dr. Mark has served as Chancellor of the University of Texas System (1984 to 1992) and is still actively involved in research and teaching at the University of Texas Cockrell School of Engineering in Austin, TX. From 1998 to 2001, Dr. Mark was on leave from the University to serve in the Pentagon as Director of Defense Research and Engineering. Dr. Mark received an A.B. Degree in physics from the University of California, Berkeley and a Ph.D. in physics from the Massachusetts Institute of Technology (MIT). He has been member of the National Academy of Engineering for three years an holds six honorary doctorates.

Host: Prof. Milton Halem, Sorry, you need javascript to view this email address.

Computer Science and Electrical Engineering
University of Maryland, Baltimore County

Data Analytics for Sustainability

Professor Katharina Morik
TU Dortmund University, Germany

11:00am-12:30pm, Thursday 22 May 2014, ITE 456, UMBC

Sustainability has many facets and researchers from many disciplines are working on them. Particularly knowledge discovery always considered sustainability an important topic (e.g., special issue on data mining for sustainability in Data Mining and Knowledge Discovery Journal, March 2012).

• Environmental tasks include risk analysis concerning floods, earthquakes, fires, and other disasters as well as the ability to react to them in order to guarantee resilience. The climate is certainly of influence and the debate on climate change received quite some attention.
• Energy efficiency demands energy-aware algorithms, operating systems, green computing. System operations are to be adapted to a predicted user behavior such that the required processing is optimized with respect to minimal energy consumption.
• Engineering tasks in manufacturing, assembly, material processing, and waste removal or recycling offer opportunities to save resources to a large degree. Adding the prediction precision of learning algorithms to the general knowledge of the engineers allows for surprisingly large savings.

Global reports on the millennium goals and open government data regarding sustainability are publicly available. For the investigation of influence factors, however, data analytics is necessary. Big data challenges the analysis to create data summaries. Moreover, the prediction of states is necessary in order to plan accordingly. In this talk, two case studies will be presented. Disaster management in case of a flood combines diverse sensor data streams for a better traffic administration. A novel spatiotemporal random field approach is used for smart routing based on traffic predictions. The other case study is in engineering and saves energy in the steel production based on the multivariate prediction of the processing end-point by the regression support vector machine.

Further reading:

• Katharina Morik, Kanishka Bhaduri, Hillol Kargupta “Introduction to Data Mining for Sustainability”, Data Mining and Knowledge Discovery Journal, Vol. 24, No.2, pp. 311 – 324, 2012.
• Nico Piatkowski, Sangkyun Lee, Katharina Morik “Spatio-Temporal Random Fields: Compressible Representation and Distributed Estimation”, Machine Learning Journal Vol.93, No. 1, pp: 115-139, 2013.
• Jochen Streicher, Nico Piatkowski, Katharina Morik, Olaf Spinczyk “Open Smartphone Data for Mobility and Utilization Analysis in Ubiquitous Environments” In: Mining Ubiquitous and Social Environments (MUSE) workshop at ECML PKDD, 2013.
• Norbert Uebbe, Hans Jürgen Odenthal, Jochen Schlüter, Hendrik Blom, Katharina MorikA novel data-driven prediction model for BOF endpoint. In: The Iron and Steel Technology Conference and Exposition in Pittsburgh (AIST), 2013.
• Alexander Artikis, Matthias Weidlich, Francois Schnitzler, Ioannis Boutsis, Thomas Liebig, Nico Piatkowski, Christian Bockermann, Katharina Morik, Vana Kalogeraki, Avigdor Gal, Shie Mannor, Dimitrios Gunopulos, Dermot Kinane, “Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic Management” Procs. 17th International Conference on Extending Database Technology, 2014.

Katharina Morik is full professor for computer science at the TU Dortmund University, Germany. She earned her Ph.D. (1981) at the University of Hamburg and her habilitation (1988) at the TU Berlin. Starting with natural language processing, her interest moved to machine learning ranging from inductive logic programming to statistical learning, then to the analysis of very large data collections, high-dimensional data, and resource awareness.

Her aim to share scientific results strongly supports open source developments. For instance, RapidMiner started out at her lab, which continues to contribute to it. She was one of those starting the IEEE International Conference on Data Mining together with Xindong Wu, and was chairing the program of this conference in 2004. She was the program chair of the European Conference on Machine Learning (ECML) in 1989 and one of the program chairs of ECML PKDD 2008. She is in the editorial boards of the international journals “Knowledge and Information Systems” and “Data Mining and Knowledge Discovery”. Since 2011 she is leading the collaborative research center SFB876 on resource-constrained data analysis, an interdisciplinary center comprising 12 projects, 19 professors, and about 50 Ph. D students or Postdocs.

Host: Hillol Kargupta, Sorry, you need javascript to view this email address.

PhD Dissertation Proposal

Learning and Executing Energy Efficient, Context-Dependent
Rules for Privacy and Security Management on Mobile Devices

Prajit Kumar Das

8:00am Friday, 16 May 2014, ITE325b

There are ongoing security and privacy concerns around mobile platforms that are increasingly being used by citizens. For example a newly discovered security flaw in WhatsApp that allows hackers using a malicious app to read chat messages stored on the SD card. The Brightest Flashlight application was reported to have logged precise location and a unique user identifier, which have nothing to with its intended functionality. Current mobile platform privacy and security mechanisms are limited to an initial installation phase permission acquisition method. In addition to that, the permissions are of the all or none form. This means that either the users accept all the permissions requested by the mobile app or they cannot use the app in question. Even if permissions were not structured as such, typically, users do not understand the permissions being requested or are too eager to use the application to even care to read them. These issues are present in all major mobile operating systems. Given the penetration of mobile devices into our lives, a fine-grained context-dependent security and privacy control approach needs to be created.

We propose a framework that will allow us to learn the privacy and security rules for a particular user, on their mobile devices. We do this by employing a simple user feedback mechanism. The rule learning framework consists of a “learning mode” where it observes and learns from user behavior and a “working mode” where it implements the learned rules to protect user privacy and provide security. The rules are represented to the user in plain English using an easily understandable construct. The rules are internally written in a logic based language and using Semantic Web technologies. The antecedents of the rules are context elements that are derived from an ontology using a query engine and an inference mechanism. The main contributions of our work include learning modifications to current rules and learning new rules to control the data flow between the various data providers on the user’s mobile device, including sensors and services and the consumer of such data. The privacy and security rule execution consumes significant energy due to the context detection. We create an energy model that allows us to make energy cost optimizations with regards to rule execution. We use a three-fold solution for achieving the said energy cost optimizations.

Committee: Drs. Anupam Joshi (chair), Nilanjan Banerjee, Dipanjan Chakraborty (IBM), Tim Finin, Tim Oates, Arkady Zaslavsky (CSIRO)

PhD Proposal

Distributed protocols for connectivity restoration
in damaged wireless sensor networks

Yatish K. Joshi

1:00pm Monday, 12 May 2014, ITE325b, UMBC

Decreasing costs and increasing functionality of embedded computation and communication devices have made Wireless Sensor Networks (WSNs) attractive for applications that serve in inhospitable environments like battlefields, planetary exploration or environmental monitoring. WSNs employed in these environments are expected to work autonomously and extend network lifespan for as long as possible while carrying out their designated tasks. The harsh environment exposes the individual nodes to q high risk of failure, which can potentially partition the network into disjoint segments. Therefore, a network must be able to self-heal and restore lost connectivity using available resources. The ad-hoc nature of deployment, harsh operating environment and lack of resources makes distributed approaches the most suitable choice for recovery.

Most solution strategies for tolerating the failure of multiple collocated nodes are based on centralized approaches that pursue the placement of additional relays to form a connected inter-segment topology. While they are the ideal solution for dealing with simultaneous multi-node failures, they need to utilize the entire network state to determine where and how recovery should occur. In addition to the scalability concern of these approaches, controlled placement of stationary relays in remote and inhospitable deployment area may not be logistically feasible due to resource unavailability and would not be responsive due to the delay in transporting the resources to the area. Space exploration is an example of those WSN applications in which placement of stationary relays is not practical.

In this proposal, we tackle the problem of connectivity restoration in a partitioned WSN in a distributed manner. We consider multiple variants of the problem based on the available resources and present novel recovery schemes that suit the capabilities and count of existing nodes.

Committee: Drs. Mohamed Younis (Chair), Dr. Charles Nicholas, Dr. Chintan Patel, Dr. Kemal Akkaya (SIU-Carbondale)Dr. Waleed Youssef (IBM)

UMBC Information Systems Security Association Seminar

Framework for Improving Critical
Infrastructure in Cybersecurity

Dr. Ron Ross, NIST

6:00-8:00pm Wednesday, 30 April 20014
Meyerhoff 030 Building Lecture Hall 2

RSVP
Schedule:
6:00-6:30pm Introductions to UMBC ISSA, Networking & Pizza
6:30-7:30pm Cyber Security Lecture From Dr. Ron Ross
7:30-8:00pm Networking

Host: Monique Jeffrey, UMBC ISSA President, Sorry, you need javascript to view this email address.

Ron Ross is a Fellow at the National Institute of Standards and Technology (NIST). His current areas of specialization include information security and risk management. Dr. Ross leads the Federal Information Security Management Act (FISMA) Implementation Project, which includes the development of security standards and guidelines for the federal government, contractors, and the United States critical information infrastructure.

A graduate of the United States Military Academy at West Point, Dr. Ross served in a variety of leadership and technical positions during his over twenty-year career in the United States Army. While assigned to the National Security Agency, he received the Scientific Achievement Award for his work on an inter-agency national security project and was awarded the Defense Superior Service Medal upon his departure from the agency. Dr. Ross is a three-time recipient of the Federal 100 award for his leadership and technical contributions to critical information security projects affecting the federal government and is a recipient of the Department of Commerce Gold and Silver Medal Awards.

Dr. Ross has been inducted into the Information Systems Security Association (ISSA) Hall of Fame and given its highest honor of ISSA Distinguished Fellow. Dr. Ross has also received several private sector cyber security awards and recognition including the Vanguard ChairmanÕs Award, the Symantec Cyber 7 Award, InformationWeek’s Government CIO 50 Award, Best of GTRA Award, and the ISACA National Capital Area Conyers Award. During his military career, Dr. Ross served as a White House aide and as a senior technical advisor to the Department of the Army. Dr. Ross is a graduate of the Defense Systems Management College and holds Masters and Ph.D. degrees in Computer Science from the U.S. Naval Postgraduate School specializing in artificial intelligence and robotics.

Center for Hybrid Multicore Productivity Research
Distinguished Computational Science Lecture Series

The White House Climate Data Initiative

Eric Letvin
Director, Disaster and Failure Studies
National Security Council

3:00pm Tuesday, 29 April 2014, ITE 456, UMBC

Delivering on the commitment in the President’s Climate Action Plan, the White House recently launched the Climate Data Initiative — a broad effort to leverage the Federal Government’s extensive, freely- available climate-relevant data resources to advance awareness of and preparedness for climate change impacts. This effort will help give communities across America the information and tools they need to plan for current and future climate impacts. Data from NOAA, NASA, the U.S. Geological Survey, the Department of Defense, and other Federal agencies was recently launched on climate.data.gov. Data and innovation challenges issued by public, private, nonprofit, and other organizations can help catalyze new, data-driven solutions that help communities understand and build resilience to climate change. NOAA and NASA recently announced an innovation challenge calling on researchers and developers to create data-driven simulations to help plan for the future and to educate the public about the vulnerability of their own communities to sea level rise and flood events.

Mr. Eric Letvin PE, Esq, is the Director of Hazard Mitigation and Risk Reduction Policy within the National Security Council in the Executive Office of the President. He coordinates the development and effective delivery of mitigation capabilities identified in the National Preparedness Goal, such as threat and hazard identification, risk and disaster resilience assessment, planning, and long-term vulnerability reduction.

When at NIST, Mr. Letvin is the Disaster and Failure Studies Program Director within NIST’s Engineering Laboratory. Mr. Letvin provides national coordination for conducting field data collection studies. He is also responsible for creating and maintaining a repository related to hazard events (earthquakes, hurricanes, tornadoes, windstorms, community-scale fires in the wildland-urban interface, structural fires, storm surge, flood, tsunami) and human-made hazards (accidental, criminal, or terrorist), the performance of the built environment during hazard events, associated emergency response and evacuation procedures.

Before coming to NIST, Mr. Letvin was Leader of Infrastructure Research and Resiliency in the Homeland Security Group of URS. He has participated in numerous post-disaster studies including the bombing of the Murrah Building in Oklahoma City, and Hurricanes Opal, Ike and Katrina. He has assessed over 200 buildings for risk from terrorist threats and natural disasters.

Mr. Letvin holds a bachelor’s and master’s degree in environmental engineering from Syracuse University and received his Juris Doctor from the University of Maryland. He has taught many courses on risk assessments and protection of infrastructure for FEMA/DHS and made related presentations throughout the world over the last ten years.

MS Thesis Defense

Learning Hierarchical Workflows Using Community Detection

Akshay Peshave

1:00pm Friday, 18 April 2014, ITE 325b

Workflows identified from user event logs and click-stream data are useful as knowledge bases for behavioral analysis and recommendation systems. In this study we identify abstractions or summaries of event logs modeled as user activity flow networks. The abstractions are identified based on structural properties as well as user activity flow dynamics over the network using community detection methods. We apply a fast modularity optimization and multi-level resolution approach to detect hierarchical community structure in user activity flow networks. The detected communities are compared to those detected by the information-theoretic map equation minimization approach to weigh pros and cons of the fast modularity optimization approach in the workflows context. We further attempt to identify the most probable sources and sinks of user activity in individual communities and trim the network accordingly to reduce entropy of the workflow abstractions.

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

MS Thesis Defense

Learning Hierarchical Workflows Using Community Detection

Akshay Peshave

1:00pm Friday, 18 April 2014, ITE 325b

Workflows identified from user event logs and click-stream data are useful as knowledge bases for behavioral analysis and recommendation systems. In this study we identify abstractions or summaries of event logs modeled as user activity flow networks. The abstractions are identified based on structural properties as well as user activity flow dynamics over the network using community detection methods. We apply a fast modularity optimization and multi-level resolution approach to detect hierarchical community structure in user activity flow networks. The detected communities are compared to those detected by the information-theoretic map equation minimization approach to weigh pros and cons of the fast modularity optimization approach in the workflows context. We further attempt to identify the most probable sources and sinks of user activity in individual communities and trim the network accordingly to reduce entropy of the workflow abstractions.

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