Dr. Naren Ramakrishnan: Forecasting Significant Societal Events using Open Source Indicators
Professor of Engineering, Department of Computer Science, Virginia Tech
Bio: Naren Ramakrishnan is the Thomas L. Phillips Professor of Engineering at Virginia Tech. He directs the Discovery Analytics Center, a university-wide effort that brings together researchers from computer science, statistics, mathematics, and electrical and computer engineering to tackle knowledge discovery problems in important areas of national interest. His work has been featured in the Wall Street Journal, Newsweek, Smithsonian Magazine, PBS/NoVA Next, Chronicle of Higher Education, and Popular Science, among other venues. Ramakrishnan serves on the editorial boards of IEEE Computer, ACM Transactions on Knowledge Discovery from Data, Data Mining and Knowledge Discovery, IEEE Transactions on Knowledge and Data Engineering, and other journals. He received his PhD in Computer Sciences from Purdue University.
Abstract: We describe our experiences developing a system (EMBERS) to forecast significant societal events – such as protests, disease outbreaks, elections, domestic political crises – using a multitude of open source data feeds. Over the past three years, EMBERS has successfully forecast many international (and rare) events such as the "Brazilian Spring" (June 2013), Hantavirus outbreaks in Argentina and Chile (2013), student-led protests in Venezuela (Feb 2014), protests stemming from the kidnappings and killings of student-teachers in Mexico (Sep- Oct 2014), and protests in Paraguay (Feb 2015) against a new public-private partnership law. The system also correctly forecast the winners of presidential elections in Panama and Colombia, even as every major poll indicated other candidates would come out on top. In addition to these correct forecasts, we will cover missed forecasts, lessons learnt from participating in a forecasting tournament, and our perspectives on the limits of forecasting including ethical considerations.
Dr. Vijay Raghavan: Triangular Spatial relationships based Protein 3-D comparison
Professor, Computer Science, Center for Advanced Computer Studies, University of Louisiana at Lafayette
Bio: Dr. Vijay Raghavan is the Alfred and Helen Lamson Endowed Professor in Computer Science at the Center for Advanced Computer Studies. His research interests are in information retrieval and extraction, data and web mining, multimedia retrieval, data integration, and literature-based discovery (https://www.researchgate.net/profile/Vijay_Raghavan10). He has published around 270 peer-reviewed research papers. These and other research contributions cumulatively accord him an h-index of 33, based on citations to his publications. He has served as major adviser for 25 doctoral students and has garnered over $13 million in external funding. Dr. Raghavan brings substantial technical expertise, interdisciplinary collaboration experience, and management skills to his projects. Read More.
Abstract: After the success of human genome project, efforts have shifted towards the human proteome project. These international efforts have resulted in an explosion of protein data available for computation. The eventual aim here is to generate the protein-based molecular architecture of humans, taking a step forward towards personal proteome and personalized medicine. The greatest challenge in representing protein structures is the complexity of the protein macromolecule in addition to its size. On an average there are 300 amino acids in each protein and each protein has three structural levels-primary, secondary and tertiary. To add to the complexity is the fact that while calculating the physical coordinates for each atom, the reference frame is usually based on the most stable amino acid therefore varies greatly from protein to protein. The lack of reference frame makes comparison of two proteins computationally expensive and approximate. Popular 3-D structure comparison algorithms are computationally expensive, distance-based methods that require translation and rotation to achieve precise alignment before calculating similarity the root mean square distance between the two macromolecules.
In this invited talk, an algorithm for transforming each building block or structural unit of the 3-D structure of a protein into a unique integer that acts as a structural fingerprint is introduced. These fingerprints will not depend upon any standard reference frame. The resulting "bucket of fingerprints" representation of a protein can help identify similar local structure similarity among proteins having very different global structures -a feature that existing algorithms do not have- and can be used for classifying proteins into their different structural classes. The similarity measure obtained between pairs of proteins can also be used to generate a similarity graph, representing the relational structure among a set of proteins of interest.
The research described above, for comparative analysis of proteomics data, can have breakthrough contributions to understanding protein functions, drug design and in determining the cause of several diseases.
Dr. Marek Rusinkiewicz: Towards Smarter Cyber Security
Dean of the Ying Wu College of Computing Sciences, New Jersey Institute of Technology
Bio: Marek Rusinkiewicz is a computer scientist, an educator, and a former research executive. Currently he is the Dean of the Ying Wu College of Computing Sciences at the New Jersey Institute of Technology. He retired in 2013 from his position as a Senior Group Vice President and the General Manager of Applied Research Laboratories at Telcordia Technologies (formerly Bell Communication Research), which included R&D centers in New Jersey, Texas, Taiwan and Poland.
Before joining Telcordia, Rusinkiewicz was the Vice President for Information Technology Research at the Microelectronics and Computer Technology Corporation (MCC) in Austin, a leading industrial R&D consortium, where he led a number of initiatives aimed at the development of next generation information management technologies, including web search, semantic agents, and collaboration management.
Rusinkiewicz has held academic positions at the University of Glasgow, the University of Michigan, and the University of Houston, where he was a Professor of Computer Science until 1999. His research interests include heterogeneous database systems, workflow management, agent-based systems and cyber security. He has published extensively in these areas.
He is Editor-in-Chief of the World Wide Web Journal and serves on advisory boards of several Universities and Research Centers. He has consulted for numerous industry and government organizations in the USA, Japan, Taiwan and Europe.
Abstract: Cyberspace, the ubiquitous collection of interconnected IP networks and hosts, has become the nervous system of the country. Healthy functioning of Cyberspace is essential for the proper operation of numerous critical infrastructures, including telecommunication, energy distribution, and transportation. It is also necessary to support the ever expanding business infrastructure for commerce and banking. The increasing reliance on Cyberspace has been paralleled by a corresponding increase in the variety, frequency and impact of attacks from a range of assailants. Both commercial companies and government agencies face continuous and increasingly more sophisticated cyber-attacks ranging from data exfiltration and spear phishing to sophisticated worms and logic bombs. The targets include not only computer information systems, but also the network communication infrastructure and power grids.
In this talk, I will discuss protecting cyber-physical systems from attacks and argue that cyber security can significantly benefit from multidisciplinary research including Web Intelligence, Data Analytics and Network Science.
Dr. Daniel Siewiorek: Converting Mobile Sensing into Data and Data into Action
Buhl University Professor of Electrical and Computer Engineering and Computer Science, Carnegie Mellon University
Bio: Professor Siewiorek has designed or been involved with the design of nine multiprocessor systems and has been a key contributor to the dependability design of over two dozen commercial computing systems. Dr. Siewiorek leads an interdisciplinary team that has designed and constructed over 20 generations of mobile computing systems. Dr. Siewiorek has written nine textbooks in the areas of parallel processing, computer architecture, reliable computing, and design automation in addition to over 475 papers. Dr. Siewiorek has served as Associate Editor of the Computer System Department of the Communications of the Association for Computing Machinery, as Chairman of the IEEE Technical Committee on Fault-Tolerant Computing and as founding Chairman of the IEEE Technical Committee on Wearable Information Systems. He is a thrust director for the Quality of Life Technology NSF Engineering Research Center. He is also a thrust leader in the Future of Work Center and the Smart Grid Center. His previous positions included Director of the Human Computer Interaction Institute, Director of the Engineering Design Research Center and co-founder of it's successor organization, the Institute for Complex Engineered Systems, where he served as Associate Director. He has been the recipient of the American Association of Engineering Education Frederick Emmons Terman Award, the IEEE/ACM Eckert-Mauchly Award, and the ACM SIGMOBILE Outstanding Contributions Award. He is a Fellow of IEEE, ACM, and AAAS and is a member of the National Academy of Engineering. Read More.
Abstract: The proliferation of wearable sensor platforms (Jawbone, FitBit, Smart Watches), sensor rich Smart Phones, and stationary sensors have produced a torrent of real time sensed signals that is interpreted to produce data (e.g. sleep quality, step count). Often the volume of this data overwhelms users. Visualization is an effective way to summarize data and observe trends. This is especially valuable when someone, such as a doctor, has to monitor a large number of people. When a human expert is not available, a Virtual Coach can provide feedback and guidance. Virtual coaches can recognize actions, correct errors, recognize emotions, and provide motivation. We will illustrate how these two technologies can effectively convert data into action in dozens of real applications. Examples include monitoring physiological parameters, identifying trends, providing guidance, correcting errors, and motivating. We will conclude with a projection of future Virtual Coaches.
Dr. Chris Welty: Towards an Embedded Theory of Truth
Sr. Research Scientist, Google
Bio: Dr. Chris Welty is a Sr. Research Scientist at Google in New York, and an Endowed Professor of Cognitive Systems at the VU University, Amsterdam. His main area of interest is using structured semantic information to improve semantic processing of unstructured information, such as using freebase to help improve web search. His latest work is on using crowdsourcing to form a new theory of truth based on diversity of perspectives. Before Google, Dr. Welty was a member of the technical leadership team for IBM's Watson - the question answering computer that destroyed the all-time best Jeopardy! champions in a widely televised contest. He appeared on the broadcast, discussing the technology behind Watson, as well as many articles in the popular and scientific press. His proudest moment was being interviewed for StarTrek.com about the project. He is a recipient of the AAAI Feigenbaum Prize for his work. Welty was one of the first to call attention to the new paradigm of Cognitive Computing that is emerging in computation, and previously has played a seminal role in the development of the Semantic Web and Ontologies, and co-developed OntoClean, the first formal methodology for evaluating ontologies. He is on the editorial board of AI Magazine, the Journal of Applied Ontology, the Journal of Web Semantics, and the Semantic Web Journal. Read More.
Abstract: Since the early days of Computer Science and AI, the Tarskian theory of truth being a discrete and binary valued function that maps from symbols to objects in the world has been accepted and rarely questioned. Even in today's deep learning world, measurements of performance are taken against a simple binary division of data into positive and negative examples. But we don't live in a discrete world, and human intelligence is anything but discrete - is Michael Jordan the best basketball player of all time? Is Beethoven's Fifth Symphony "festive"? Is the statement "Google is located-in NY" true? As it turns out, nothing outside of the artificial realm of mathematics can be viewed as discretely true or false. In this talk, I will present a new, spatial, view of semantics that allows for a richer set of possibilities and far more closely aligns with human intelligence and the universe we live in, with examples of how this makes artificial intelligence a bit less ... artificial.