Predicting Demographics and Affects in Social Networks
Dr. Svitlana Volkova
Date/Time: May 13th (Friday), ITE 459, 11:00am
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.
Statistical Methods for Integration and Analysis of Opinionated Text Data
Dr. ChengXiang Zhai
Date/Time: April 21st (Thursday), ITE 459, 10:00am
Opinionated text data such as blogs, forum posts, product reviews and online comments are increasingly available on the Web. They are very useful sources for public opinions about virtually any topics. However, because the opinions are scattered and abundant, it is a significant challenge for users to collect all the opinions about a topic and digest them efficiently. In this talk, I will present a suite of general statistical text mining methods that can help users integrate, summarize and analyze scattered online opinions to obtain actionable knowledge for decision making. Specifically, I will first present approaches to integration of scattered opinions by aligning them to a well-structured article or relevant ontology. Second, I will discuss several techniques for generating a concise opinion summary that can reveal the major sentiments and opinion points buried in large amounts of opinionated text data. Finally, I will present probabilistic generative models for analyzing review data in depth to discover latent aspect ratings and relative weights placed by reviewers on different aspects. These methods are general and can thus potentially help users integrate and analyze large amounts of online opinionated text data on any topic in any natural language.
ChengXiang Zhai is a Professor of Computer Science and a Willett Faculty Scholar at the University of Illinois at Urbana-Champaign, where he is also affiliated with the Graduate School of Library and Information Science, Institute for Genomic Biology, and Department of Statistics. He received a Ph.D. in Computer Science from Nanjing University in 1990, and a Ph.D. in Language and Information Technologies from Carnegie Mellon University in 2002. He worked at Clairvoyance Corp. as a Research Scientist and a Senior Research Scientist from 1997 to 2000. His research interests include information retrieval, text mining, natural language processing, machine learning, biomedical informatics, and intelligent education systems, in which he published over 200 research papers. He is a former Associate Editor of ACM Transactions on Information Systems and Elsevier’s Information Processing and Management.
He is a conference program co-chair of ACM CIKM 2004, NAACL HLT 2007, ACM SIGIR 2009, ECIR 2014, ICTIR 2015, and WWW 2015, and conference general co-chair for ACM CIKM 2016. He is an ACM Distinguished Scientist and a recipient of multiple awards, including the ACM SIGIR 2004 Best Paper Award, the ACM SIGIR 2014 Test of Time Paper Award, Alfred P. Sloan Research Fellowship, IBM Faculty Award, HP Innovation Research Program Award, and the Presidential Early Career Award for Scientists and Engineers (PECASE).
The Effects of Page Transition on Mobile Shopping Behavior: Do Interruption and Distraction Matter?
Xue Yang, Ph.D.
Date/Time: March 28 (Monday), ITE 406, 12:00pm – 1:00pm
With the popularization of smart phone and mobile internet, e-commerce companies have launched mobile applications for consumers to do mobile shopping without the restriction of time and space. Each mobile application has its unique interface design characteristics and thus may have important effects on consumers’ mobile shopping behavior. In specific, this study examines the effect of different page transition and the presence of different interruption or distraction of the mobile shopping applications. This study focuses on two different types of page transition, which are vertical scroll and horizontal swipe. The interruption and distraction are related to the presence of incoming messages, pop-up advertisements, static advertisements or background music. We conducted four lab experiments to test the research hypotheses. The results showed significant effects of page transition and some of the interruptions or distractions. Theoretical and practical implications are discussed.
Xue Yang is an associate professor in the Department of Marketing and Electronic Business, School of Business (Management), Nanjing University (NJU), China. She received her Ph.D. on Information Systems from National University of Singapore (NUS). Her current research interests include e-commerce and m-commerce, free trial software, spontaneous virtual team and IT usage. Her research work has appeared in journals such as Journal of the Association for Information Systems, Information & Management, Decision Support Systems, IEEE Transaction on Engineering Management, Business Horizons, Journal of Global Information Management, Information Systems Frontiers, among others, as well as various conferences such as International Conference on Information Systems (ICIS). She has been a member of Association of Information Systems (AIS) since 2004. She has acted as the Program Committee member, Track Chair or Associate Editor for multiple international conferences such as ICIS, PACIS, and CSWIM. She is currently in the Executive Editorial board for Electronic Commerce Research and Journal of Global Information Management. She has been supported by National Natural Science Foundation China (NSFC) in 2011-2014 (Youth Program) and 2016-2019 (General Program).
SystemT: Declarative Information Extraction
Laura Chiticariu, Research Staff Member at IBM Research-Almaden
Date/Time: March 7 (Monday), ITE 406, 1:00pm
Information extraction (IE), the task of extracting structured information from unstructured or semi-structured data, is increasingly important to a wide array of enterprise applications, ranging from Business Intelligence to Data-as-a-Service. Such applications drive the following main requirements for IE systems: accuracy, scalability, expressivity, transparency, and customizability.
SystemT, a declarative IE system, has been designed and developed to address these requirements. It is based on the basic principle underlying relational database technology: complete separation of specification from execution. SystemT uses a declarative language for expressing NLP algorithms called AQL, and an optimizer that generates high-performance algebraic execution plans for AQL rules. It makes IE orders of magnitude more scalable and easy to use, maintain and customize.
SystemT ships today with multiple products across 4 IBM Software Brands. Furthermore, SystemT is used in multiple ongoing research projects and being taught in universities. Our ongoing research and development efforts focus on making SystemT more usable for both technical and business users, and continuing enhancing its core functionalities based on natural language processing, machine learning, and database technology.
Laura Chiticariu is a Research Staff Member in the Scalable Natural Language Processing group at IBM Research-Almaden in CA. Her primary research is in Database Systems and Natural Language Processing. Laura joined IBM Research after obtaining her Ph.D. in Computer Science from University of California, Santa Cruz in 2008. Her current work focuses on building development support for information extraction systems, utilizing a range of techniques including data provenance, information integration and machine learning.
Big Data/Data Science Programs at NSF
Chaitan Baru, Senior Advisor for Data Science, CISE Directorate, NSF
Date/Time: February 12 (Friday), ITE 459, 10:00am – 11:00am
This talk will provide an overview of current programs and activities related to Big Data and Data Science at NSF, and also highlight NSF’s inter-agency engagements in this topic area. The talk will also discuss future directions for Data Science research, education, and infrastructure. Considering that Data Science is a rapidly emerging, evolving field and discipline, ample time will be provided for Q&A and discussions about where the field ought to be going, given what we know today.
Is Bigger Better? Comparing User Generated Passwords on 3×3 vs. 4×4 Grid Sizes for Android’s Pattern Unlock
Dr. Adam J. Aviv, Assistant Professor of Computer Science at the United States Naval Academy
Date/Time: Tuesday, December 1st, ITE 459, 1pm – 2pm
Android’s graphical authentication mechanism requires users to unlock their devices by “drawing” a pattern that connects a sequence of contact points arranged in a 3×3 grid. Prior studies have shown that human-generated patterns are far less complex than one would desire; large portions can be trivially guessed with sufficient training. Custom modifications to Android, such as CyanogenMod, offer ways to increase the grid size beyond 3×3, and in this paper we ask the question: Does increasing the grid size increase the security of human-generated patterns? To answer this question, we conducted two large studies, one in-lab and one online, collecting 934 total 3×3 patterns and 504 4×4 patterns. Analysis shows that for both 3×3 and 4×4 patterns, there is a high incidence of repeated patterns and symmetric pairs (patterns that derive from others based on a sequence of flips and rotations). Further, many of the 4×4 patterns are similar versions of 3×3 patterns distributed over the larger grid space. Leveraging this information, we developed the most advanced guessing algorithm in this space, and we find that guessing the first 20% (0.2) of patterns for both 3×3 and 4×4 can be done as efficiently as guessing a random 2-digit PIN. Guessing larger portions of 4×4 patterns (0.5), however, requires 2-bits more entropy than guessing the same ratio of 3×3 patterns, but the entropy is still on the order of cracking random 3-digit PINs. These results suggest that while there may be some benefit to expanding the grid size to 4×4, the majority of patterns will remain trivially guessable and insecure against broad guessing attacks.
Adam J. Aviv is an Assistant Professor of Computer Science at the United States Naval Academy, receiving his Ph.D. from the University of Pennsylvania under the advisement of Jonathan Smith and Matt Blaze. He has varied research interests including in system and network security, applied cryptography, smartphone security, and more recently in the area of usable security with a focus on mobile devices.
An Extension of Self: The Present and Future of Wearable Computing
Dr. Thad Starner Ph.D., Professor of Computing at Georgia Institute of Technology, Director of the Contextual Computing Group
Date/Time: Nov. 16, 12-1pm, ITE 459
Google’s Glass captured the world’s imagination, perhaps more than any other head-up display. Yet, why would people want a wearable computer in their everyday lives? For over 20 years, Professor Thad Starner and his teams of researchers have been creating living laboratories to discover the most compelling reasons to integrate humans and
computers. They have created “wearables” that augment human memory and the senses, focus attention, and assist communication. Is it possible that computers and wearable devices will transform humans for the better, enhancing key abilities and leaving more time and space for deeper connections? In this talk, Starner will discuss why wearables, more than any class of computing to date, have the potential to extend us beyond ourselves.
Thad Starner is a wearable computing pioneer; he has been wearing a head-up display based computer as part of his daily life since 1993 – perhaps the longest such experience known. Starner is a Professor in the School of Interactive Computing at the Georgia Institute of Technology and a Technical Lead on Google’s Glass. In 1990 he coined the term “augmented reality” to describe the types of interfaces he envisioned at the time. He is a founder of the annual ACM/IEEE International Symposium on Wearable Computers, now in its 19th year, and has produced over 450 papers and presentations on his work. Starner is an inventor on over 80 United States patents awarded or in process. In addition to Google’s Glass, he has worked on a wireless glove that teaches the wearer to play piano melodies without active attention; a game for deaf children that helps them acquire language skills using sign language recognition; wearable computers that enable two-way communication experiments with wild dolphins; and wearable computers for working dogs to better communicate with their handlers.
Motivating Group Donation: Evidence from a Large Field Experiment
Date/Time: Oct. 23, 12-1pm, ITE 459
Recent literature has established that people donate more when donating in a group. However, less is known about how to motivate donors to form a group in the first place. Using a randomized field experiment involving 80,000 participants, we test the effect of behavioral intervention and economic reward on group donation. Our experiment generates three
findings: 1) blood banks can motivate group formation to increase blood donation, but only with appropriate economic reward; 2) reward conditional on group donation works through a sorting mechanism and attracts donors different from those under individual reward; 3) participants donate a greater amount of blood when donating in group, regardless of whether their friends donate or not. Our structural estimation suggests that rewarding group donors is four times cost effective than rewarding individual donors in motivating blood donation. We also perform policy simulations and provide additional insights on the optimal design of economic rewards and targeting strategy.
Professor Ginger Zhe Jin received her PhD from UCLA in 2000 and is currently Professor of Economics at the University of Maryland College Park, Research Associate of NBER, co-editor of the Journal of Economics & Management Strategy, and Chief Data Scientist at Hazel Analytics. Most of her research focuses on information asymmetry among
economic agents and how to provide information to overcome the information problem. The applications she has studied include restaurant food safety, health insurance, prescription drugs, online trading, online reviews, regulatory inspection, scientific innovation, air quality, blood donation, and the intrafamilial interaction between parents and children. Her research has been published in economics, management and marketing journals, with support from the National Science Foundation, the Net Institute, and the Sloan Foundation. In October 2014, she co-founded Hazel Analytics, an advanced analytics company that promotes the use of open government data. The company provides public access to a national database of retail food safety inspection results via InspectionRepo.com, and it also develops proprietary technology to standardize and analyze food
safety inspection data nationwide. In addition, Professor Jin holds a special-term visiting professorship at the Guanghua School of Management in Peking University and conducts research on development issues in China.
Measuring Visual Perceptions of Security
Dr. Adam Aviv, Assistant Professor of Computer Science at the United States Naval Academy
Date/Time: Friday, January 16th, ITE 459, 10am-11.15am
Location: ITE 459
This talk presents the results of a user study of the Android graphical password system to measure visual perceptions of security. The survey methodology asked participants to select between carefully selected pairs of patterns indicating either a security or usability preference. By selecting password pairs that isolate a visual feature, a perception of usability and security of different features can be quantified in relatively. We conducted a large IRB-approved survey using pairwise preferences which attracted 384 participants on Amazon Mechanical Turk. Analyzing the results, we find that visual features that can be attributed to complexity indicated a stronger perception of security, while spatial features, such as shifts up/down or left/right are not strong indicators for security or usability. We extended and applied the survey data by building logistic models to predict perception preferences by training on features used in the survey and other features proposed in related work. The logistic model accurately predicted preferences above 70%, twice the rate of random guessing, and the strongest feature in classification is password distance, the total length of all lines in the pattern, a feature not used in the online survey. This result provides insight into the internal visual calculus of users when comparing choices and selecting visual passwords, and the ultimate goal of this work is to leverage the visual calculus to design systems where inherent perceptions for usability coincides with a known metric of security.
Adam J. Aviv is an Assistant Professor of Computer Science at the United States Naval Academy, receiving his Ph.D. from the University of Pennsylvania under the advisement of Jonathan Smith and Matt Blaze. He has varied research interests including in system and network security, applied cryptography, smartphone security, and more recently in the area of usable security with a focus on mobile devices
Understanding and Supporting Patients as Health Experts
Dr. Wanda Pratt, Professor in the Information School, adjunct appointment in Biomedical & Health Informatics in the Medical School, University of Washington
Date/Time: November 20, 2014 10:00AM-11:00AM
Many online tools such as PatientsLikeMe, CureTogether, as well as thousands of online health communities, blogs, and video blogs help patients to develop and share their own health expertise. This patient expertise focuses on strategies for coping with day-to-day personal health issues gained through their experience of living with their health issues. In this talk, I will describe our studies of what patient expertise is and how it plays a unique role in our increasingly overburdened health-care system. I will include details of our latest research on how technology can further support patients in developing and sharing their expertise and how that support can enhance patients’ overall health and well-being.
Wanda Pratt is a Professor in the Information School with an adjunct appointment in Biomedical & Health Informatics in the Medical School at the University of Washington. She received her Ph.D. in Medical Informatics from Stanford University, and her M.S. in Computer Science from the University of Texas. Her research focuses on understanding patients’ needs and designing new technologies to address those needs. She has worked with people coping with a variety of chronic diseases, such as cancer, diabetes, asthma, and heart disease. Dr. Pratt has received best paper awards from the American Medical Informatics Association (AMIA), the ACM CHI Conference on Human Factors in Computing Systems, and the Journal of the American Society of Information Science & Technology (JASIS&T). Her research has been funded by the National Science Foundation, the National Library of Medicine, the Agency for Healthcare Research & Quality, the Robert Woods Johnson Foundation, Intel, and Microsoft. Dr. Pratt is a fellow of the American College of Medical Informatics.
Data Science Platforms: Integral to Help Drive Molecularly Targeted Therapy Development and Personalized Medicine Research
Dr. Subha Madhavan, Director, Biomedical Informatics, Innovation Center for Biomedical Informatics, Georgetown University, Washington D.C
Date/Time: October 17, 2014 12:00PM-1:00PM
Location: ITE 459
The advent of the microarray technology in 2000 has paved the way for advanced translational research methods that use molecular markers such as microRNA, proteins, metabolites and copy number data. Our flagship web platform, the Georgetown Database of Cancer (G-DOC), was deployed in April 2011 to enable the practice of an integrative translational and systems-based approach to research and medicine in cancer. G-DOC is a feature-rich shareable research infrastructure that allows physician scientists and translational researchers to mine and analyze a variety of “omics” data in the context of consistently defined clinical outcomes data for cancer patients.
The popularity of next generation sequencing (NGS) grew exponentially in 2007 when a faster, more accurate and affordable sequencing throughput became a reality. Since then, the size and complexity of genomic data has increased many fold, making its analysis, management and integration increasingly challenging. Scientists today are using not only a combination of clinical, NGS and omics data for analysis, but also medical and pathology images for validation of analysis results. To drive hypothesis generation and validation of molecular markers for biologists and researchers, it would be convenient to have a “one–stop” system that can handle all these data types, including NGS and medical images, in one location. For this purpose, we expanded the G-DOC system to support NGS and medical images. Moreover, the success of G-DOC in the cancer realm has helped us realize the importance of such systems in the non-cancer world for complex diseases such as Alzheimer’s, Duchene Muscular dystrophy, etc.
With the goal of improving overall health outcomes through advanced genomics research, we present G-DOC Plus, our web platform that enables the integrative analysis of multiple data types to understand mechanisms of cancer and non-cancer diseases for precision medicine. G-DOC Plus allows researchers to explore data one sample at a time, as a sub-cohort of samples; or as a population as a whole, providing the user with a comprehensive view of the data.
Dr. Madhavan is the Director of Biomedical Informatics and Center Director. She leads several informatics efforts including the Georgetown Database of Cancer a tool for both researchers and clinicians to realize the goals of personalized medicine at GU, and the NIH caBIG In Silico Research Center for Excellence. She also directs the Informatics cores for NIH funded translational efforts. She is the PI on the Breast and Colon Cancer Family Registries data center that coordinates public health and epidemiology data across 12 sites in the US, Australia, and Canada. More recently, she has partnered with the FDA on the Center for Excellence in Regulatory Science program to develop evidence bases for pharmacogenomics and vaccine adverse event detection. She is also involved in a whole genome data analysis project with the Inova Translational Medicine Institute. Prior to joining Georgetown, Dr. Madhavan served as the Associate Director of Product and Program Management in the Life sciences informatics area at NCI’s Center for Biomedical Informatics and Information technology. Her work at NCI involved bridging the gap between bench and bedside by enabling researchers and physician scientists to use cutting edge biomedical informatics solutions to identify better therapies for cancer. At NCI she led a group of scientists, physicians and software engineers in building REMBRANDT (REpository for Molecular BRAin Neoplasia DaTa) – a database that hosts and interconnects clinical data points with various genomics datasets from large brain tumor clinical trials. This effort won the Service to America Award. While at NCI she also established the data coordination center for The Cancer Genome Atlas (TCGA), which managed and analyzed high dimensional genomic data of approximately 100 TB over a period of 3 years. At Georgetown, she leads various informatics efforts including the caBIG In Silico Research Center for Excellence, and the Georgetown Database of Cancer. She also directs the Informatics cores for NIH funded translational efforts such as the Center for Cancer Systems Biology at Georgetown; and the Clinical Translational Science Award at Georgetown along with Howard University, the Washington Veteran’s Affairs Medical Center, and MedStar Health Research Institute. She is the PI on the Breast and Colon Cancer Family Registries data center that coordinates public health and epidemiology data across 12 sites in the US, Australia, and Canada. More recently, she has partnered with the FDA on the Center for Excellence in Regulatory Science program to develop evidence bases for pharmacogenomics and vaccine adverse event detection. She is also involved in a whole genome data analysis project with the Inova Translational Medicine Institute. Dr. Madhavan has a master of science in Information Technology from University of Maryland and a Ph.D. in Molecular Biology and Biological Sciences from the Uniformed Services University for the Health Sciences (Indo-US Collaborative program). – See more at: http://icbi.georgetown.edu/Madhavan#sthash.5Jzxjsnj.dpuf
Fall 2014 IS Distinguished Lecturer: Opinion Mining, Machine Learning and Big Data
Dr. Bing Liu, Professor of Computer Science at the University of Illinois at Chicago (UIC)
Date/Time: October 20, 2014 12:00PM-1:00PM
Opinion mining (OM) or sentiment analysis is the computational study of people’s opinions, sentiments, and emotions expressed in written language. It is one of the most active research areas in natural language processing (NLP) and text mining due to almost unlimited applications and numerous research challenges. OM can be seen as a semantic analysis problem in NLP, but it is also highly targeted and bounded because an OM system does not need to fully “understand” each sentence or document. It only needs to comprehend some aspects of it, e.g., positive/negative opinions and emotions. Due to this targeted and bounded nature of OM, it allows us to perform deeper text analyses to gain better insights into NLP than in the general setting because the complexity of the general setting of NLP is too overwhelming. Thus, although general natural language understanding is still far from us, we may be able to solve the OM problem satisfactorily. OM also offers an excellent platform for NLP and text mining researchers to potentially make major breakthroughs on many fronts of text analysis. In this talk, I will first introduce OM and then discuss a recent study that uses OM as a platform to explore an important idea of intelligent top discovery involving continuous machine learning and big data.
Bing Liu is a professor of Computer Science at the University of Illinois at Chicago (UIC). He received his PhD in Artificial Intelligence from the University of Edinburgh. Before joining UIC, he was a faculty member at the National University of Singapore. His current research interests include sentiment analysis and opinion mining, data mining, machine learning, and natural language processing (NLP). He has published extensively in top conferences and journals. He is also the author of two books: “Sentiment Analysis and Opinion Mining” (Morgan and Claypool) and “Web Data Mining: Exploring Hyperlinks, Contents and Usage Data” (Springer). In addition to research impacts, his work has also made important social impacts. Some of his work has been widely reported in the press, including a front-page article in The New York Times. On professional services, Liu has served as program chairs of many leading data mining related conferences of ACM, IEEE, and SIAM: KDD, ICDM, CIKM, WSDM, SDM, and PAKDD, as associate editors of several leading data mining journals, e.g., TKDE, TWEB, DMKD, and as area/track chairs or senior technical committee members of numerous NLP, data mining, and Web technology conferences. He currently also serves as the Chair of ACM SIGKDD, and is an IEEE Fellow.
Data Science: Current and Future R&D Opportunities and Challenges
Dr. Ashit Talukder, Program Director, National Institute of Standards and Technology (NIST)
Date/Time: September 15, 2014 12:00PM-1:00PM
Location: ITE 459
This presentation will cover the latest research and development activities, federal initiatives, and future opportunities, challenges, and trends in Big Data and Data Science, and its impact across various fields. Data Science is the science of extraction of actionable knowledge directly from data, which are increasingly larger in volume, variety and velocity (i.e. Big Data). Adoption of Big Data Science technologies can be accelerated by creation of reference datasets and challenge problems to drive improvements in Big Data R&D and tools. Advances in Big Data Science can be fostered by formulating new measurement methods and benchmarks, and metrics and models to measure performance of Big Data Science solutions, and creation of reference architectures and guidelines for interoperability. The talk will present details of the Data Science Initiative and interagency coordination to improve reliability, robustness, accuracy, generalizability, usability & performance of solutions for data-driven discovery and decisions through measurements, evaluations, and reference data. The initiative brings together a broad multi-sector community of interest including researchers, end-users, other federal agencies, and solution providers focused on advancing data science and Big Data technologies across all components of analytics, visualization, interaction, and data lifecycle management.
Dr. Ashit Talukder leads and manages the Information Access Division in the Information Technology Laboratory at the National Institute of Standards and Technology (NIST). At NIST he leads and directs a division of over 100 researchers and staff in the areas of information access, data processing, and information search and retrieval for multimedia, biometrics, Big Data, visualization, image processing, computer vision, video analytics, speech processing, speech recognition, machine translation, human-computer interaction, human-factors and usability, and multimodal data for science, defense and other applications. The programs that he leads at IAD involves collaborations within NIST, and with many federal agencies including DARPA, IARPA, NSA, FBI, DoD, DoJ, DHS and others. He initiates and leads new research efforts in the above areas, and facilitates collaborations and partnerships between research labs, academia and industry.He received his Ph.D. in computer science from Carnegie Mellon University and a MS from Iowa State University. He was previously at the Jet Propulsion Laboratory, California Institute of Technology, a federally funded research and development center at NASA. He has served as a research faculty member at the University of Southern California (USC). His research background and expertise covers machine learning, search and retrieval, human language technologies, NLP, pattern recognition, image / signal processing, multimedia processing, video understanding, computer vision, data mining and analytics of massive datasets, Big Data, distributed control, biometrics, robotics, sensor networks and cyber-physical systems. He has led several projects and programs funded by DARPA, NSF, NIH, DHS, and other agencies. He has more than 65 journal and conference publications, and has served as a reviewer on numerous conferences and journals. He was a recipient of the Premium Award for Academic Excellence (1992), and several NASA Space Act Awards. He is an inventor of 2 patents. He is a member of the ACM and the IEEE Computer Society.
Mobile Analytics: An Enabler for Urban Lifestyle Applications
Dr. Archan Misra, School of Information Systems, Singapore Management University
Date/Time: June 24, 2014 10:00AM-11:00AM
Location: ITE 459
This talk will describe various research initiatives related to the theme of “urban mobile analytics and applications”, which utilizes smartphone sensor data from multiple individuals to extract near-real time insights about individual and collective behavior in urban public spaces. A major part of this research is being conducted under the auspices of the LiveLabs Experimentation Platform, a unique urban behavioral testbed effort that enables an ecosystem of industry partners to test advanced context-based applications on a pool of approx. 30,000 real-world users in
multiple real-world public spaces in Singapore. Besides describing LiveLabs-related research in areas related to a) energy-efficient mobile sensing and b) large-scale mobile analytics (e.g., queuing analytics, group detection and adaptive indoor localization), I will describe the role of such analytics for a couple of novel industry-driven applications: (a) in-store shopper intent monitoring and (b) large-scale mobile crowd-tasking.
Archan Misra is an Associate Professor of Information Systems at Singapore Management University (SMU), and a Director of the Live Labsresearch center at SMU. Over the past 14 years (as part of his previousjobs with IBM Research and Telcordia Technologies), he has worked extensively in the areas of mobile systems, wireless networking and pervasive computing, and is a co-author on papers that received the Best Paper awards in EUC 2008, ACM WOWMOM 2002 and IEEE MILCOM 2001. Archan’s broad research interests lie in the areas of pervasive computing & mobile systems, with specific current focus on applying mobile sensing and real-time analytics to understand human lifestyle-driven activities in urban spaces. He is presently an Editor of the IEEE Transactions on Mobile Computing and the Elsevier Journal of Pervasive and Mobile Computing and chaired the IEEE Computer Society’s Technical Committee on Computer Communications (TCCC) from 2005-2007. Archan holds a Ph.D. in Electrical and Computer Engineering from the University of Maryland at College Park.
Modeling and Simulation of Human Behavior in Aircraft Evacuations using Multi-Agent System and Virtual Reality Environment
Dr. Sharad Sharma, Director of Virtual Reality Laboratory, Department of Computer Science, Bowie State University
April 18th 2014, 12:00pm-1:00pm
UMBC ITE 459
Crowd simulations are powerful tools for visualizing, analyzing, and communicating how a venue will work or testing evacuations scenarios in emergencies. Human behavior is difficult to model and simulate due to the high level of uncertainty involved because human behavior is unpredictable. Computer simulation is an invaluable tool for modeling emergency evacuations because it is cost effective, saves time, and ensures that no lives are put at risk. Crowd simulation can be used to observe the influence different behaviors such as calm, panic, and cooperation have on evacuation models. Automated systems are useful tools for aiding situation assessment in complex environment such as emergency evacuations. These environments include large amount of information which includes integration of judgment decisions, assessments and human behavior characteristics. This talk will describe the modeling capabilities within AvatarSim evacuation model to simulate human behavior characteristics and judgment decisions for an airplane evacuation. AvatarSim model is a goal oriented agent based model based on intelligent AI agent based technology. Its applications range from building evacuation behavior scenarios to battle field scenarios to aircraft scenarios.
Also, this talk will show a multi-user environment in Virtual Reality for airplane evacuation scenarios. Collaborative virtual environment for studying aircraft evacuations in virtual reality environment can be used as an education and training tool. The implemented multi-user interface allows multiple user controlled agents to navigate in a virtual environment. Our hypothesis is that the “sense of presence” provided by the virtual environment will allow running simulations and conducting evacuation drills without the cost and risk of injury to live actors. We present two approaches for controlling crowd behavior. First by defining rules for computer simulated agents, second by providing controls to the users to navigate in the environment as autonomous agents and guiding other agents. Our contribution lies in our approach to combining these two approaches of behavior in order to simulate the crowd behavior in emergencies. Given the existing models and methods available, the research questions are as follows: What are the most effective approaches for training and testing evacuations scenarios in emergencies for unexpected events? How can we evaluate and validate the results of crowd simulations for these given applications? We have conducted user studies to explore crowd simulation in aircraft evacuation using Virtual Reality to achieve high levels of presence. The use of collaborative virtual environments to run virtual evacuation drills for an emergency evacuation eliminates risk of injury to participants and allows for the testing of scenarios that could not be tested in real life due to legal issues and possible health risks to participants.
Dr. Sharad Sharma is an Associate Professor and Director of the Virtual Reality Laboratory in the Department of Computer Science at the Bowie State University. He has received PhD in Computer Engineering from Wayne State University, Detroit, MI in 2006, M.S. from University of Michigan, Ann Arbor, MI in 2003. He has won the “Outstanding Researcher Award” in year 2013 and 2011, “Outstanding Faculty Award” in year 2012, “Outstanding Publication Award” in year 2010, and “Outstanding Young Faculty Award” in year 2009 at College of Arts and Science in the Bowie State University.Dr. Sharma’s research focus is on modeling and simulation of multi-agent systems for emergency response and decision making strategies. The current projects in the Virtual Reality Laboratory include: multi‐user airplane evacuation using gaming metaphor, game-theme instructional modules, multi‐user virtual reality classroom, use of ARTtoolkit and mobile devices to create an emergency response system for evacuation.
Improving EHR Usability in an Integrated Healthcare Delivery Organization
Dr. Yan Xiao
UMBC ITE 459
Electronic health record (EHR) is an integral part of work in growing number of healthcare organizations. Quality of care received by patients and quality of working life of frontline professionals are increasingly tied to EHR. This presentation will share the experience of improving EHR usability in an integrated healthcare delivery organization, the largest in Texas. Usability as experienced by frontline clinicians is an evolving property of a complex socio-technical system, with leveraging points in hardware infrastructure, user training, technical support services, on-going system integration, optimization, and organizational policies. Case studies will be used to illustrate the role of human factors in understanding usability challenges, in defining approaches to improve EHR related safety and quality, and in identifying research opportunities. On-going projects sponsored both internally and by federal Office of National Coordinator for Health Information technology will be presented as well.
Yan Xiao leads the human factors program at Baylor Heath Care System, Dallas, Texas, and conducts patient safety research sponsored by the federal government. He is adjunct professor at University of Texas at Arlington, and previously adjunct professor at UMBC. His education includes a PhD in human factors from University of Toronto in 1994 and a Masters degree in systems engineering from Beijing Institute of Technology in 1985. He published more than 60 peer reviewed journal articles in the past 20 years in key aspects of human factors, including collaborative work, team leadership, and information systems. He left academia as a tenured full professor of anesthesiology at University of Maryland School of Medicine in 2009. As principal investigators his work has been sponsored by such federal agencies as National Science Foundation, National Institutes of Health, Department of Defense, NASA, and Agency for Healthcare Research and Quality (AHRQ). Industry support for his work came from top telecommunication, medical devices, and defense companies. He has two patents related to technology support for team performance. He is on editorial board for Human Factors & Journal of Cognitive Engineering and Decision Making. He serves in a standing panel of AHRQ to advise federal government on sponsored research.
November 13th 2013, 12:00pm-1:00pm
UMBC ITE 456
Collective Intelligence is group intelligence generated by the collaboration of many individuals. However, such intelligence is only as powerful as one’s ability to digest it. Thus, after describing two recent efforts, the first focusing on early disease detection using microblogs and the second focusing on collaborative tag labeling. Potentially, I will likewise describe an older effort that effectively integrates information and comment on its potential for the future.
Ophir Frieder holds the Robert L. McDevitt, K.S.G., K.C.H.S. and Catherine H. McDevitt L.C.H.S. Chair in Computer Science and Information Processing and is Chair of the Department of Computer Science at Georgetown University. He is also Professor of Biostatistics, Bioinformatics and Biomathematics in the Georgetown University Medical Center. He is a Fellow of the AAAS, ACM, and IEEE.
Topical Search in Twitter
Tuesday, November 5th at 1:00PM
UMBC ITE 459
Twitter is now a popular platform for discovering real-time news on various topics. We are developing methodologies to improve topical search in Twitter, specifically search for topical experts and popular content on specific topics. Utilizing social annotations provided by the Twitter population through the Lists feature, we have developed the following:
(i) A novel who-is-who system for Twitter, which gives the topical attributes of a specified user. The List-based methodology gives accurate and comprehensive topical attributes for millions of Twitter users.
(ii) A search system for topical experts in Twitter. Comparison of our system with the expert search service offered by Twitter shows that the List-based method provide better results for a large number of topical queries.
(iii) A novel topical search system which, given a topic, identifies and clusters the content (tweets, hashtags) being discussed by the community of experts on that topic. Our methodology gives relevant and trustworthy content for a wide range of topics. To the best our knowledge, this is the first systematic attempt to utilize social annotations to provide topical search in Twitter.
Niloy Ganguly is an associate professor in the department of computer science and engineering, Indian Institute of Technology Kharagpur. He has received his PhD from Bengal Engineering and Science University, Calcutta, India and his Bachelors in Computer Science and Engineering from IIT Kharagpur. He has been a post doctoral fellow in Technical University of Dresden, Germany. He focuses on investigating several different aspects on online-social networks (OSN) etc. He has worked on designing recommendation system based on community structures on various web-social networks like Twitter and Delicious. He has also simultaneously worked on various theoretical issues related to dynamical large networks often termed as complex networks. Specifically he has looked into problems related to percolation, evolution of networks as well as flow of information over these networks. He has been collaborating with various national and international universities and research lab including Duke University, TU Dresden, Germany, MPI PKS and MPI SWS, Germany, Microsoft Lab, India etc. He currently publishes in various top ranking international journals and conferences including CCS, PODC, ICDM, ACL, WWW, INFOCOM, SIGIR, Euro Physics Letters, Pysical Review E, ACM and IEEE Transactions, etc. For further information visit his webpage http://www.facweb.iitkgp.ernet.in/~niloy/
Development and Testing of a Social Networking Site (SNS)-Based Obesity Prevention Program for Korean American Adolescents
Bu Kyung Park
Friday, November 1, 12 pm-1pm
UMBC ITE 459
Abstract: In this presentation, Ms. Park will introduce her dissertation project entitled “Healthy Teens,” which is supported by the Sigma Theta Tau International, Pi Chapter.
The prevalence of adolescent obesity has more than tripled during the past three decades. Adolescent obesity increases risk for a number of comorbidities and creates economic burden for families and the nation. Given that using social networking sites (SNSs) has become ingrained in adolescents‘ daily life, obesity prevention education via SNSs for lifestyle modification can be an innovative and promising approach. Although current obesity prevalence among Korean American (KA) adolescents is relatively lower than the national average, acculturation to American lifestyle increases the risk of obesity for the second and the third generations of KA immigrants compared to the first generation immigrants. Therefore, obesity prevention education tailored for KA adolescent lifestyle is important. The purposes of this proposed study are to (1) develop a social cognitive theory-based “Healthy Teens” program on Facebook for KA adolescent obesity prevention, which includes physical activity and healthy eating modules, and (2) conduct usability testing of the “Healthy Teens” program for a future randomized controlled trial. Usability testing will be conducted using two usability assessment methods: (1) heuristic evaluation by three experts, which will identify usability problems based on Nielsen’s heuristics; and (2) user testing, which aims to assess usual users’ performance on the Healthy Teens program using observation, a think-aloud method, and a questionnaire by 20 KA adolescents (13–17 years old). Using a convenience sampling method, participants will be recruited from two Korean language schools in Maryland. Both qualitative and quantitative data will be collected and analyzed. The expected impact of this proposed study is two-fold. First, this proposed study will develop an innovative Facebook-based KA adolescent obesity prevention program that will be used for a future larger scale study. Second, the findings will provide important ground work on how to use an SNS to develop a structured, theory-based health education program for adolescents and contribute to other investigators’ research that uses similar technologies.
Brief Bio: Ms. Bu Kyung Park is a PhD student in School of Nursing at the University of Maryland. Her research focuses on the use of Web-based interventions to prevent obesity among children and adolescent. She has participated in various studies (conducted by her advisor, Dr. Eun-Shim Nahm) as a research assistant including mHealth, qualitative, and usability studies as well as randomized controlled trials. During her years in the PhD program, she has found advantages to adapting SNSs for adolescent health research. She recently published “A systematic review of social networking sites: innovative platforms for health research targeting adolescents and young adults” in the Journal of Nursing Scholarship based on extensive review of the literature.
Effect of Inventor Status on Intra-organizational Innovation Evolution
Friday 25 October 2013, 12:00 -1:00pm
UMBC ITE 459
Abstract: Innovation is one of the primary characteristics that separates successful from unsuccessful organizations. Organizations have a choice in selecting knowledge that is recombined to produce new innovations. The selection of knowledge is influenced by the status of inventors in an organization’s internal knowledge network. In this study, we model knowledge flow within an organization and contend that it exhibits unique characteristics not incorporated in most social network measures. Using the model, we also propose a new measure based on random walks and team identification and use it to examine innovation selection in a large organization. Using empirical methods, we find that inventor
status determined by the new measure had a significant positive relationship with the likelihood that his/her knowledge would be selected for recombination. We believe that the new measure in addition to modeling knowledge flow in a scientific collaboration network helps better understand how innovation evolves within organizations. The speaker will also present other projects in Information Assurance Education and Mobile Development that he is involved in.
Bio: Dr. Siddharth Kaza is an Assistant Professor in the Computer and Information Sciences department at Towson University. He received his Ph.D. degree in Management Information Systems from the University of Arizona. His research interests lie in information assurance education, data mining, social network analysis, and security informatics. Dr. Kaza’s work has been published in top-tier journals like Decision Support Systems, IEEE Transactions, ACM Transactions, Journal of the American Society for Information Science and Technology and various international conferences and has been funded by the National Science Foundation, Department of Defense, and the Maryland Higher Education Commission.