ITng Services will provide the following: - Two storage systems and set of Intel-based blades. These devices will be connected via gigabit ethernet networking. - As-needed support during normal business hours (8a-5p Eastern Time, Monday-Friday). Response for any support request occurring within the above business hours will receive a response within one business day upon receipt of the request. Otherwise, support is best effort. - All systems will be monitored by the lab Cacti installation.

The following items will be completed by ITng Services: Support Stark Media in implementation of a enterprise level web application that requests sensor data from PDSS. Develop and refine filter health analytics framework in PDSS, Implement raw data read function in PDSS, Implement raw data write function in PDSS, Implement data verification on read function in PDSS, and Maintenance fixes in PDSS and Pentairweb

The following items will be completed by ITng Services: support Stark Media in implementation of a enterprise level web application that requests sensor data from PDSS; develop and refine filter health analytics framework in PDSS; monitor and adjust PDSS as necessary to support growing demand; rackspace VM monitoring; organize code base to make PDSS and PentairWeb repositories ?always-deployable?; create an issue tracker and defined feature development and fix process for PDSS and PentairWeb.

Since 1995, the Triangle Computer Science Distinguished Lecturer Series (TCSDLS) has been hosting influential university researchers and industry leaders from computer-related fields as speakers at the three universities within the Research Triangle Area. The lecturer series, sponsored by the Army Research Office (ARO), is organized and administered by the Computer Science departments at Duke University, NC State University, and the University of North Carolina at Chapel Hill. This proposal argues for continuation, for an additional 3 years, of this highly successful lecturer series

This research applies methods of dependency tracing and analysis and formal measures of entrenchment toward the identification of deception and deceivers in large scale activity graphs.

This project builds on the SILO project that started in 2006 to design a new architecture for the Internet. In this new project, we will collaborate with teams of researchers from the University of Kentucky, the University of Massachusetts, and RENCI, to design critical parts of a new architecture for the Internet that will support the flexible use of widely applicable information transport and transformation modules to create good solutions for specific communication applications. The key idea is to allow a network to offer information transformation services at the edge or in the core transparently to the application, and creating a framework in which application can issue a request not only for communication but for specific reusable services. We also propose research tasks that will enable network virtualization and isolation seamlessly at many levels, currently a difficult but highly relevant problem in practical networking.

The goal of this project is to develop and deploy a GENI instrumentation framework, integrate it into one of thecfive control framework prototypes, and develop a set of experimenter capabilities to enable cross-layer experimentation in the optical substrate.

Mobile browsers are beginning to serve as critical enablers of modern computing. With a combination of rich features that rival their desktop counterparts and strong security mechanisms such as TLS/SSL, these applications are becoming the basis of many other mobile apps. Unfortunately, the security guarantees provided by mobile browsers and the risks associated with today's mobile web have not been evaluated in great detail. In the proposed work, we will investigate the security of mobile browsers and the mobile specific websites they access. Characterizing and responding to the threats in this space is critical, especially given that cellular devices are used by more than five billion people around the world

Recent research shows that students are capable of writing a peer-reviewed textbook for their own course. The pedagogical advantages are numerous. Instead of being merely the consumers of knowledge, students become co-producers. This forces them to learn the material in greater depth, and to reflect upon it more frequently. The natural medium for creating such a textbook is a wiki, because it standardizes the format and makes it easy to edit parts of a larger work. This project is building a software system to manage creation and peer review of a wiki textbook, automating features such as rubric creation by students, double-blind feedback between author and reviewer, quality-control strategies for student peer reviews, and support for flow management to allow different chapters of the text to be written and reviewed at different times during the course. It promises to bring wiki textbook-writing to a much wider audience. The project addresses several high?profile needs in American education. Students hone composition skills writing for authentic purposes and audiences. Peer-reviewing fosters critical analysis and teaches them how to provide meaningful feedback. The project is socially relevant, as Wiki textbooks are freely available to a global audience, helping to combat the problem of rising textbook costs. The project has the potential to benefit at-risk students, since students receive feedback while they still have a chance to improve their work. This helps nontraditional students stay on task, and typically offers the most benefit to students who underperform as measured by exams and standardized tests

We propose to explore the new computing model of offering computation- and/or data-intensive cloud services on active nodes serving on-demand utility computing users. More specifically, we plan to (1) assess the efficacy of resource sharing between foreground interactive utility computing workloads and background high-throughput cloud computing workloads on multi-core servers, in terms of energy saving and performance interference; (2) develop a scheduling and load management middleware that performs dynamic background workload distribution considering the energy-performance tradeoff; and (3) exploits the use of GPGPUs for cloud services on active nodes running foreground workloads mainly on the CPUs.

Large-scale virtualized hosting infrastructures have become the fundamental platform for many real world systems such as cloud computing, enterprise data centers, and educational computing lab. However, due to their inherent complexity and sharing nature, hosting infrastructures are prone to various runtime problems such as performance anomalies and software/hardware failures. The overarching objective of this proposal is to systematically explore innovative runtime reliability management techniques for large-scale virtualized hosting infrastructures. Our research focuses on handling performance anomalies in distributed systems that are often very difficult to reproduce offline. Our approach combines the power of online learning, knowledge-driven first-response recovery, and in-situ diagnosis to handle unexpected system anomalies more efficiently and effectively. We aim at transforming the runtime system anomaly management from a trial-and-error guessing game into an efficient knowledge-driven self-healing process.

Large-scale virtualized computing infrastructures have become important platforms for many real-world systems such as cloud computing, virtual computing lab, and massive information processing. However, due to its inherent complexity and sharing nature, virtualized computing infrastructures are inevitably prone to various system anomaly problems such as software/hardware failures, performance anomalies, and malicious attacks. The goal of this project is to develop a new predictive anomaly management system to enhance the resilience of virtualized computing infrastructure. The major contributions will be an integrated framework consisting of four synergistic techniques: 1) scalable runtime virtual machine monitoring; 2) self-evolving online anomaly prediction; 3) speculative anomaly diagnosis; and 4) online anomaly correction.

Large-scale hosting infrastructures have become important platforms for many real-world systems such as cloud computing, virtual computing lab, enterprise data centers, and web hosting services. However, system administrators are often overwhelmed by the tasks of correcting various system anomalies such as performance bottlenecks, resource hotspots, and service level objective (SLO) violations. The goal of this project is to develop novel online anomaly prediction and diagnosis techniques to achieve robust continuous system operation. The major contributions will be an integrated framework consisting of three synergistic techniques: i) self-compressing information tracking to achieve low-cost continuous system monitoring; ii) online anomaly prediction that can raise advance alerts to impending anomalies; and iii) just-in-time anomaly diagnosis that can perform online anomaly diagnosis while the system approaches the anomaly state.

This proposal will study methods to visualize simulation ensembles, large sets of simulation results generated by repeatedly executing a simulation across a range of input parameter values. Ensembles will be provided by collaborators in astrophysics, meteorology, high energy physics, and statistics. The goal of our research is to identify effective techniques to visualize ensembles containing 100s or 1000s of simulation runs. We propose to combine techniques from perceptual and multidimensional visualization to build images that present some or all of the results to an end-user, in a manner that allows him to explore, validate, discover, and analyze individual values within the ensemble

We propose a project to explore collection and analysis of information available from Internet sources including, but not limited to, web pages, blogs, Twitter, and social media such as shared affinity group sites. We hypothesize that it is possible to process data obtained from these sources to identify new entities, situations, and events that are of interest because of their potential to enable activities or situations of interest. The objective of this effort is to create technology to perform and support such identification, either automatically or through human-machine collaboration. The technology developed would then be available for use in future work. To provide a grounded domain for research and development, this effort is focused on the cyber domain, and the goal is to detect newly identified system vulnerabilities, newly identified exploits against vulnerabilities, and attacks, which are applications of exploits against vulnerabilities.

For this project, we will explore the potential benefits of symptomatic and syndromic surveillance using existing NCB-Prepared data sources, including EMS, ED and poison control data, to improve surveillance capacity and outbreak response relating to the area of food safety. During the initial phase, we will examine two years of NCB-Prepared national poison control data to evaluate its utility related to evaluating trends in foodborne illness. This initial phase will produce preliminary statistics by working with the SAS analytics team of NCB-Prepared to incorporate poison control data into the system. Some possible analytical techniques employed may include descriptive statistics, Fourier analysis and cluster analysis. Results from this phase will provide a baseline for identifying potential foodborne illness outbreaks in the future as part of the NCB-Prepared system. This first phase will demonstrate basic functionality of the poison control data by July 30, 2012. During the second phase, we will continue to explore relationships between the poison control, EMS and ED data in relationship to their ability to improve early detection of potential foodborne illness outbreaks. After the first phase, project will have a national poison center data set relating to food safety issues available covering at least 10 year. For example, we will select key national outbreaks and determine if the historical data provided to NCB-Prepared could have been used to provide earlier signals that an outbreak was ongoing. A preliminary result will be produced for this second phase by September 30. Additional efforts will be made to help the team explore relationships between the poison control, EMS and ED data as they pertain to foodborne illness outbreaks.

Stealthy rootkit attacks are one of the most foundational threats to cyberspace. With the capability of subverting the software root of trust of a computer system, i.e., the operating system (OS) or the hypervisor, a rootkit can instantly take over the control of the system and stealthily inhabit the victim. To effectively mitigate and defeat them, researchers have explored various solutions. Unfortunately, the state-of-the-art defense is mainly reactive and in a fundamentally disadvantageous position in the arms-race against these stealthy attacks. The proposed research aims to fundamentally change the arms-race by proposing a systematic immunization approach to proactively prevent and exterminate rootkit attacks. Inspired by our human immune system and fundamental biological design principles, the proposed approach transforms system software (i.e., the OS and the hypervisor) so that the new one will tip the balance of favor toward the rootkit defense. To accomplish that, we will investigate a suite of innovative techniques to preserve kernel/hypervisor control flow integrity and evaluate their effectiveness with real-world malware and infrastructures. The proposed education components include the creation and dissemination of unique hands-on course materials with live demos, lab sessions, and tutorials.

Research in virtualization technologies has gained significant momentum in recent years. One of the basic yet powerful enabling function in many virtualization research efforts is virtual machine introspection or VMI: Observing a VM's states and events from outside the VM. The goal of this project is to develop OpenVMI: a software-based research infrastructure for VMI, which is expected to enable new research and education opportunities, including, but not limited to, safe malware experiments, intelligent virtual infrastructure management etc.

Kernel rootkit attacks are one of the most stealthy yet foundational threats to cyberspace. Unfortunately, current research and practice in kernel rootkit defense is mainly reactive and in a fundamentally disadvantageous position relative to the kernel attackers. In this work, we advocate the development of strategic kernel rootkit defense that is proactive with early kernel rootkit threat indication, automatic when performing rootkit attack avoidance and forensics, and integrated with all these capabilities enabled under the same architecture for production systems. Specifically, we envision a virtualization-based rootkit-prevention architecture that is capable of (1) indicating a kernel rootkit threat before it strikes, (2) avoiding the attack by ?steering? the targeted production system away from the threat, and (3) profiling the (possibly zero-day) kernel rootkit for future kernel protection. The architecture is deployable in a wide range of virtualization-based cyber infrastructures, such as data centers, enterprises, and cloud computing environments (e.g., VCL).

Botnets are recognized as one of the most serious threats to today's Internet. To combat them, one key step is to effectively understand how the botnet members communicate with each other. Unfortunately, the trend of adopting various obfuscation schemes (e.g., encryption) in recent bots greatly impedes our understanding. The main thrust of this research is the investigation of several interrelated key techniques to overcome the above challenges and significantly enrich the understanding of botnet command and control.

Our goal is to develop new automated program analyses capable of proving that the application programs have security properties of interest to the DoD and demonstrate those analyses in the form of tools designed specifically to keep malicious code out of DoD Android-based mobile application marketplaces.

This proposal proposes to build a hybrid computing testbed for detecting emerging mobile threats and improving research and education in information security at North Carolina State University (NCSU). The proposed computing testbed will be developed on the basis of the current Virtual Computing Lab (VCL) environment to provide a prototyping environment, which will be used for rapid development and evaluation of a variety of ongoing research projects funded by DoD and other government agencies. Also, it supports research-related education components in system oriented information security courses at NCSU. Moreover, we propose to equip the hybrid testbed with various mobile devices for detecting and experimenting with emerging mobile threats (e.g., Android malware). One key use of this hybrid testbed is to detect emerging or new threats against current mobile gadgets (e.g., smart phones and tablets), which is not available or possible yet based on current computing resources. The results and experience gained from operating and managing a real computing testbed will also provide practical insights into emerging threats on mobile Internet for students and researchers. The experience in managing and operating such a hybrid computing testbed will also be valuable to identify new security and performance problems and develop their practical solutions.

This program will establish a national Secure Open Systems Institute (SOSI), located on North Carolina State’s premier Centennial Campus that will be a global center for Open Source security research and development. The goals are twofold. First, SOSI will significantly contribute to strengthening mission critical information technology infrastructures vital to the Department of Defense, state and nation. Second, SOSI will accelerate the creation and growth of high tech industries in North Carolina and beyond by providing a centralized repository of research results, testing tools and qualification services.

Contemporary research on multi-agent learning environments has focused on self-regulated learning (SRL) while relatively little effort has been made to use co-regulated learning as a guiding theoretical framework (Hadwin et al., 2011). This oversight needs to be addressed given the complex nature that self-and other-regulatory processes play when human learners and artificial pedagogical agents (APAs) interact to support learners? internalization of cognitive, affective, and metacognitive (CAM) SRL processes. We will use the Crystal Island learning environment to investigate these issues.

The goal of the ENGAGE project is to develop a game-based learning environment that will support middle grade computer fluency education. It will be conducted by an interdisciplinary research team drawn from computer science, computer science education, and education. In collaboration with North Carolina middle schools, the research team will design, develop, deploy, and evaluate a game-based learning environment that enables middle school students to acquire computer fluency knowledge and skills. The ENGAGE project will be evaluated in middle grade classrooms with respect to both learning effectiveness and engagement.

By leveraging intelligent cyberlearning technologies, rich media, and advanced digital storytelling, the Future Worlds demonstration project will enable children at a museum to take virtual journeys through time to explore the impact of social and economic decisions on the environment. Guided by a virtual environmentalist who will narrate their journeys and offer problem-solving advice, visitors will travel to the past, present, and future to explore the relationship between conservation decisions, energy use, and population growth on Earth's ecosystem.

The project will develop automated detectors that can infer the engagement and affect of trainees learning through the vMedic training system. This project will combine interaction-based methods for detecting these constructs (e.g., models making inference solely from the trainee?s performance history) with scalable sensor-based methods for detecting these constructs, towards developing models that can leverage sensor information when it is available, but which can still assess trainee engagement and affect effectively even when sensors are not available. The automated detectors will be developed, integrated together, and validated for accuracy when applied to new trainees.

Recent years have seen a growing recognition of the transformative potential of game-based learning technologies. Crystal Island is an intelligent game-based learning environment we have developed for middle grade students. To date, more than 1,000 students have used Crystal Island, and rigorous studies have demonstrated that it helps students achieve significant learning gains. In the proposed work, Crystal Island will be extended to provide literacy education for middle grade students. The project will focus on the deployment of Crystal Island in classrooms of low SES rural middle schools in eastern North Carolina.

The goal of the Leonardo project is to develop an intelligent cyberlearning system for interactive scientific modeling. Students will use Leonardo's intelligent virtual science notebooks to create and experiment with interactive models of physical phenomena. As students design and test their models, Leonardo's intelligent virtual tutors will engage them in problem-solving exchanges in which they will interactively annotate their models as they devise explanations and make predictions. During the project, the Leonardo virtual science notebook system will be rolled out to 60 classrooms in North Carolina, Texas, and California.

Despite the great promise offered by game-based learning environments for elementary science education, realizing its potential poses significant technological challenges. In this project we will develop a full suite of intelligent game-based learning environment technologies for elementary science education. To promote effective science learning, we will create intelligent game-based learning environment technologies that leverage the rich interactive 3D game environments provided by commercial game engines and the inferential capabilities of intelligent tutoring systems. We will also provide a comprehensive empirical account of the cognitive processes and results of elementary students interacting with intelligent game-based learning environments for science education.

Intelligent tutoring systems leverage artificial intelligence technologies to create effective learning experiences for students. The project targets the design, implementation, and empirical validation of an integrated model of cognitive and affective scaffolding for intelligent tutoring systems. Computational models of tutorial strategies will be automatically acquired through machine learning techniques from human-human tutorial dialogue traces. The resulting models of cognitive and affective scaffolding, which are based on hierarchical hidden Markov models, will be incorporated into an intelligent tutoring system, JavaTutor. JavaTutor will be evaluated with first year university computer science students to assess its impact on student learning gains and motivation.

This joint appointment will allow the PI to continue her long-term collaboration with ORNL researchers. Specifically for 2012-2013, the joint teams will focus on several HPC projects, including active storage on new memory media, automatic creation of parallel I/O benchmarks, and application I/O workload analysis based on server-side aggregate I/O load traces. The PI will supervise NCSU graduate students performing PhD research on these joint projects, who will also receive mentoring from ORNL collaborators.

While individual workstations in scientific research environments have become more powerful, they cannot meet the needs of today's interactive data processing tasks. Meanwhile, idle desktop resources are not efficiently utilized. This project aims at harnessing the collective idle resources within institutional boundaries to speed up computation- or data-intensive tasks routinely executed on desktop machines. We will build a novel desktop parallel computing framework, which will integrate distributed computing and storage resources to create an execution platform similar to that provided by a parallel computer, while maintaining the comfort and responsiveness of desktop sequential computing and the autonomy of resource donors.

Xioasong Ma's joint work with NCSU and Oak Ridge National Laboratories (ORNL) will bridge the gap between the two organizations in a practical manner to cooperatively research parallel I/O in conjunction with the Genomes to Life (GTL) and Scientific Data management projects within the Computer Science and Mathematics Division at ORNL.

We propose to explore the new computing model of offering computation- and/or data-intensive cloud services on active nodes serving on-demand utility computing users. More specifically, we plan to (1) assess the efficacy of resource sharing between foreground interactive utility computing workloads and background high-throughput cloud computing workloads on multi-core servers, in terms of energy saving and performance interference; (2) develop a scheduling and load management middleware that performs dynamic background workload distribution considering the energy-performance tradeoff; and (3) exploits the use of GPGPUs for cloud services on active nodes running foreground workloads mainly on the CPUs.

This decade is projected to usher in the period of exascale computing with the advent of systems with more than 500 million concurrent tasks. Harnessing such hardware with coordinated computing in software poses significant challenges. Production codes tend to face scalability problems, but current performance analysis tools seldom operate effectively beyond 10,000 cores. We propose to combine trace analysis and in-situ data analysis techniques at runtime. Application developers thus create ultra low-overhead measurement and analysis facilities on-the-fly, customized for the performance problems of particular application. We propose an analysis generator called ScalaJack for this purpose. Results of this work will be contributed as open-source code to the research community and beyond as done in past projects. Pluggable, customization analysis not only allows other groups to build tools on top of our approach but to also contribute components to our framework that will be shared in a repository hosted by us.

In High-End Computing (HEC), faults have become the norm rather than the exception for parallel computation on clusters with 10s/100s of thousands of cores. As the core count increases, so does the overhead for fault-tolerant techniques that rely on checkpoint/restart (C/R) mechanisms. At 50% overheads, redundancy is a viable alternative to fault recovery and actually scales, which makes the approach attractive for HEC. The objective of this work to the develop a synergistic approach by combining C/R-based fault tolerance with redundancy in computer to achieve high levels of resilience. This work alleviates scalability limitations of current fault tolerant practices. It contributes to fault modeling as well as fault detection and recovery in significantly advancing existing techniques by controlling levels of redundancy and checkpointing intervals in the presence of faults. It is transformative in providing a model where users select a target failure probability at the price of using additional resources.

This proposal provides subcontractor support to Virginia Tech for a proposal submitted under the Air Force's Basic Research Initiative. The proposal will focus on development of reconfigurable mapping strategies for porting multi-block structured and unstructured-mesh CFD codes to computing clusters containing CPU/GPU processing units.

Assuring deadlines of embedded tasks for contemporary multicore architectures is becoming increasingly difficult. Real-time scheduling relies on task migration to exploit multicores, yet migration actually reduces timing predictability due to cache warm-up overheads and increased interconnect traffic. We propose a fundamentally new approach to increase the timing predictability of multicore architectures aimed at task migration in embedded environments making three major contributions. 1. We develop novel strategies to guide migration based on cost/benefit tradeoffs exploiting both static and dynamic analyses. 2. We devise mechanisms to increase timing predictability under task migration providing explicit support for proactive and reactive real-time data movement across cores and their caches. 3. We propose rate- and bandwidth-adaptive mechanisms as well as monitoring capabilities to increase predictability under task migration. Our work aims at initiating a novel research direction investigating the benefits of interactions between hardware and software for embedded multicores with respect to timing predictability.

For large-scale high-performance computing (HPC) systems with 10s/100s of thousands of cores, faults have become the norm rather than the exception. To address this problem, we propose to develop and evaluate advanced mechanisms to protect the operating and runtime systems and thereby increase resilience to failures.

The objective of this work is to design and evaluate novel system and program abstractions for combined performance and scalability paving the path into a future of operating system supporting a massive number of cores on a single chip.

The objective of this work is to provide functionality for the Berkeley Lab Checkpoint/Restart (BLCR) Linux module to support advanced fault-tolerant capabilities, which are of specific value in the context of large-scale computational science codes running on high-end clusters. We have developed a set of techniques to reduce this checkpoint/restart overhead. We propose to integrate a job pause mechanism, live migration support and an incremental checkpoiting mechanism into the latest BLCR version.

Scalability is one of the key challenges to computing with hundreds if not thousands of processor. Yet, testing software at scale with hundreds of processing cores is impossible if system software with privileged access rights needs to be modified. The inability to change system software at will in large-scale computing installations thus impedes progress in system software. This project creates a mid-size computational infrastructure, called ARC (A Root Cluster), that directly supports research into scalability for system-level software solutions. ARC empowers users temporarily with administrator (root) rights and allows them to replace arbitrary components of the software stack. Such replacements range from entire operating systems over drivers, kernel modules to runtime libraries, middleware and system tools. ARC ultimately enables a multitude of systems research directions to be assessed under scalability that could otherwise not be conducted. Through ARC, methodologies for scalability of experimental system software in various institutional projects and beyond can be explored and systematically improved. ARC is positioned to benefit the software systems community and indirectly science in general by this assessment of system software requirements at scale.

Parallel I/O benchmarks are crucial for application developers, I/O software/hardware designers, and center administrators. However, currently there lack portable and comprehensive I/O benchmarks for high-end storage systems. We address this gap by proposing automatic generation of parallel I/O benchmarks. More specifically, we target the automated creation of application I/O benchmarks.

Recent advances in computing have led to continually deeper integration between computers and human society. Yet as socio-technical systems have grown in complexity, their underlying computation has become increasingly difficult for people to express, manipulate, and understand. This proposal aims to advance knowledge and understanding of solutions to these problems by supporting a Doctoral Consortium (DC) at the IEEE Conference on Visual Languages and Human-Centric Computing (VL/HCC).

A wide variety of program analysis tools have been created to help software developers do their jobs, yet the output of these tools are often difficult to understand and vary significantly from tool to tool. As a result, software developers may waste time trying to interpret the output of these tools, instead of making their software more capable and reliable. This proposal suggests a broad investigation of several types of program analysis tools, with the end goal being an improved understanding of how program analysis tools can inform developers in the most expressive and uniform way possible. Once this goal is reached, we can create program analysis tools that enable developers to make tremendous strides towards more correct, more reliable, and more on-time software systems.

This is a pilot internship program between NCSU and Cisco for 4 undergraduate students to learn through working part-time on real life problems for Cisco with the hope that this pilot program can grow and develop into a long term working relationship. Specifically, NCSU students will participate in Cisco Software Application Support plus Upgrades (SASU) projects and/or conduct research for SASU. This will be done with an understanding that the interns are students, and as such are learning and being trained with the training coming from both the Cisco (for SASU-specific skills), and NCSU (through the undergraduate program they are enrolled in) in general relevant skills.

This project consists of three technical thrusts: (1) Thrust 1 -- new security architecture and services that better isolate different customers' workloads and enhance their trustworthiness; (2) Thrust 2 -- protection of management infrastructure against malicious workloads; and (3) Thrust 3 -- protection of hosted workloads from potentially malicious management infrastructure. The first thrust explores new opportunities to enhance the trustworthiness of virtual cloud computing against mutual threats between workloads as well as external security threats, while the last two address the service providers' security concerns for customers' workloads and customers' security concerns for the service providers, respectively.

Achieving scalable processing of the increasing amount of publicly-available Semantic Web data will hinge on parallelization. The Map-Reduce programming paradigm recently emerged as a de-facto parallel data processing standard and has demonstrated effectiveness with respect to structured and unstructured data. However, Semantic Web data presents challenges not adequately addressed by existing techniques due to its flexible, fine-grained data model and the need to reason beyond explicitly represented data. This project will investigate optimization techniques that address these unique challenges based on rethinking Semantic Web data processing on Map-Reduce platforms from the ground, up - from query algebra to query execution.

The Web is evolving from a resource for finding/verifying facts, to one used to support complex problem solving and exploratory tasks in a variety of domains. Thus, the traditional search paradigm targeted primarily at fact-finding, and is predicated on users knowing what they want and how to search for it, is unsuitable for such situations. This project focuses on developing support for advanced query models that capture the iterative process typical of problem solving and exploratory tasks where at each step users may only be able to formulate vague queries. It proposes to develop semantic techniques for integrating information created across the multiple steps of such tasks as and also predict and recommend other potentially relevant and informative data that the user may have missed.

The grant money will be used to turn the Master of Science in Computer Networks to a Professional Science Master (PSM).

There are many ways that computers attached to the Internet can be infected by malicious software. Virus and computer worm writers go to great pains to make their software difficult to detect. We have developed a method for identifying infectious software, before it succeeds, that is fast and very general. This method has been tested on a wide variety of software and shown to be effective. We propose now to automate this method to a greater degree. Essentially every method of detection relies upon human intelligence to guide the search for uniquely identifying properties of infectious software. We propose to instead use techniques of data mining that will automatically search for and evaluate such properties. A key characteristic that is exploited is that there are few true innovations in the design of infectious software, but many imitations or variations. Our method looks for the unvarying, common properties of such software. The benefit will be automated defenses that adapt rapidly to changing threats, including previously-unknown, or "zero-day", threats.

In this collaborate research between NCSU and ETRI, both institutions investigate the application service architectures for future internet testbeds. The collaboration includes surveys, architecture designs and validation of the application service architectures for various types of future internet services

This project develops a high-level notion of context that exploits the capabilities of next genera-tion networks to enable applications that deliver better user experiences. In particular, it exploits mobile devices always with a user to capture key elements of context: the user's location and, through localization, characteristics of the user's environment.

Optical networking forms the foundation of the global network infrastructure, hence the planning and design of optical networks is crucial to the operation and economics of the Internet and its ability to support critical and reliable communication services. With this research project we aim to make contributions that will lead to a quantum leap in the ability to solve optimally a range of optical design problems. In particular, we will develop compact formulations and solution approaches that can be applied efficiently to instances encountered in Internet-scale environments. Our goal is to lower the barrier to entry in fully exploring the solution space and in implementing and deploying innovative designs. The solutions we will develop are "future-proof" with respect to advances in DWDM transmission technology, as the size of the corresponding problem formulations is independent of the number of wavelengths.

Dr. Nagiza Samatova's joint work with NC State University and Oak Ridge National Laboratory (ORNL) will provide the interface between the two organizations aiming to collaboratively address computational challenges in the Scientific Data Management, and the Large-Scale Analysis of DOE-mission applications. (Supplement)

Accelerating the rate of insight and scientific productivity demands new solutions to managing the avalanche of data expected in extreme-scale. Our approach is to use tools that can reduce, analyze, and index the data while it is still in memory (referred to as "in-situ" processing of data). ). In order to deal with the large amount of data generated by the simulations, our team has partnered with many application teams to deliver proven technology that can accelerate their knowledge discovery process. These technologies include ADIOS, FastBit, and Parallel R. In this proposal we wish to integrate these technologies together, and create a runtime system that will allow scientist to create an easy-to-use scientific workflow system, that will run in situ, in extra nodes on the system, which is used to not only accelerate their I/O speeds, but also to pre-analyze, index, visualize, and reduce the overall amount of information from these solutions.

Dr. Nagiza Samatova's joint work with NC State University and Oak Ridge National Laboratory (ORNL) will provide the interface between the two organizations aiming to collaboratively address computational challenges in the Scientific Data Management, Data-Intensive Computing for Understanding Complex Biologicial Systems, Knowledge Integration for the Shewanella Federation, and the Large-Scale Analysis of Biologicial Networks with Applications to Bioenergy Production.

The specific objectives of the proposal are as follows: 1. Design and develop data mining kernels and algorithms for acceleration on hybrid architectures which include many-core systems, GPUs, and other accelerators. 2. Design and develop approximate scalable algorithms for data mining and analysis kernels enabling faster exploration, more efficient resource usage, reduced memory footprint, and more power efficient computations. 3. Design and develop index-based data analysis and mining kernels and algorithms for performance and power optimizations including index-based perturbation analysis kernels for noisy and uncertain data. 4. Demonstrate the results of our project by enabling analytics at scale for selected applications on large-scale HPC systems.

One of the most significant advances for large-scale scientific simulations has been the advent of Adaptive Mesh Refinement, or AMR. By using dynamic gridding, AMR can achieve substantial savings in memory, computation, and disk resources while maintaining or even increasing simulation accuracy, relative to static, uniform gridding. However, the resultant non-uniform structure of the simulation mesh produced by AMR methods cause inefficient post-simulation access patterns during AMR data analytics that is becoming a substantial bottleneck given the exponential increase in simulation output. Toward bridging this gap in efficient analytics support for AMR data, we propose an integrated, three-prong approach that aims: (a) To devise an AMR query model; (b) To explore effective indexing methods for AMR data analytics; and (c) To investigate data storage layout strategies for AMR data retrieval optimized for analytics-induced heterogeneous data access patterns.

Computational science applications have been described as having one of seven motifs (the ?seven dwarfs?), a particular pattern of computation and communication. While the exercise has not been performed, one can imagine that these applications can also be grouped into a number of data model motifs, describing the way data is organized and accessed during simulation and analysis. The goal of this project is to determine the data model motifs present in computational science applications, to identify where current I/O software falls short in usability and performance for each of these motifs, and to construct a software toolkit for developing optimized I/O support for computational science data models at exascale.

Terascale computing and high-throughput experiments enable studies of complex natural phenomena, on a scale not possible just a few years ago. With this opportunity, comes a new problem - the massive quantities of complex so data produced. However, answers to fundamental science questions remain largely hidden in these data. The goal of this work is to provide a scalable high performance data analytics technologies to help application scientists extract knowledge from these raw data. Towards this goal, this project will research and develop methodologies for addressing key bottlenecks, and provide proof-of-principle demonstrations on the DOE applications.

The SDAV is a unique and comprehensive combination of scientific data management, analysis, and visualization expertise and technologies aimed at enabling scientific knowledge discovery for applications running on state-of-the-art computational platforms located at DOE's primary computing facilities. This integrated institute focuses on tackling key challenges facing applications in our three focus areas through a well-coordinated team and management organization that can respond to changing technical and programmatic objectives. The proposed work portfolio is a blend of applied research and development, aimed at having key software services operate effectively on large distributed memory multi-core, and many-core platforms and especially DOE's open high performance computing facilities. Our goal is to create an integrated, open source, sustainable framework and software tools for the science community.

Physical science applications such as nanoscience, fusion science, climate and biology generate large-scale data sets from their simulations and high throughput technologies. This necessitates scalable technologies for processing and analyzing this data. We plan to research and develop advanced data mining algorithms for knowledge discovery from this complex, high-dimensional, and noisy data. We will apply these technologies to DOE-mission scientific applications related to fusion energy, bioenergy, understanding the impacts of climate extremes, and insider threat detection and mitigation.

Physical science applications such as nanoscience, fusion science, climate and biology generate large-scale data sets from their simulations and high throughput technologies. This necessitates scalable technologies for processing and analyzing this data. We plan to research and develop advanced data mining algorithms for knowledge discovery from this complex, high-dimensional, and noisy data. We will apply these technologies to DOE-mission scientific applications related to fusion energy, bioenergy, understanding the impacts of climate extremes, and insider threat detection and mitigation.

The goal is to provide a computational capability for effective and efficient exploration of high-resolution climate networks derived from multivariate, uncertain, noisy and spatio-temporal climate data. We plan to increase the efficiency and climatologically relevancy of the network patterns identification through integrated research activities focused on: (a) supporting comparative analysis of multiple climate networks; (b) constraining the search space via exploiting the inherent structure (e.g., multi-partite) of climate networks; (c) establishing the foundation to efficiently update solutions for perturbed (changing) graphs; and (d) designing and implementing parallel algorithms scalable to thousands of processors on multi-node multi-core supercomputer architectures.

Over the past ten years, lecture hall partitions have emerged as fundamental structures in combinatorics and number theory, leading to new generalizations and new interpretations of several classical theorems. This project takes a geometric view of lecture hall partitions and uses polyhedral geometry to investigate their remarkable properties.

This project will develop policy-based service governance modules for the Oceanographic Observatories Initiative (OOI) Cyberinfrastructure. The main objectives of the proposed project include (1) formulating the key conceptual model underlying the patterns of governance; (2) formalizing "best practices" patterns familiar to the scientific community and seeding the cyberinfrastructure with them; (3) understanding user requirements for tools that support creating and editing patterns of governance

This project will develop a computational approach to trust geared toward enhancing the quality of information in tactical networks. In particular, this project will develop a trust model that takes into account various objective and subjective qualities of service as well as the social relationships among the parties involved in a network who originate, propagate, or consume information. The proposed approach will build an ontology for quality of information and its constituent qualities, and will expand existing probabilistic techniques to multivalued settings. The project will develop a prototype software module that realize the techniques for producing trust assessments regarding the information exchanged.

We propose to investigate the challenges of understanding social computing applied in the enterprise in the context of facilitating engagements among communities of service providers, requesters, and partners in enterprise service marketplace. Specifically, we will study the problems of (1) detecting and recommending relevant communities based on an analysis of interactions and transactions in the service marketplace to improve the engagement, and (2) building an intelligent model for recommending services and workflows to maximize value in the marketplace.

This project will develop policy-based service governance modules for the Oceanographic Observatories Initiative (OOI) Cyberinfrastructure. The main objectives of the proposed project include (1) formulating the key conceptual model underlying the patterns of governance; (2) formalizing "best practices" patterns familiar to the scientific community and seeding the cyberinfrastructure with them; (3) understanding user requirements for tools that support creating and editing patterns of governance.

The primary objective of the project is to help NCDES assess automatability of its workflows. This will lead into facilitation of NCDES?s successful participation in the Southeast Consortium for Unemployment Benefits Integration (SCUBI), and eventually into assisting NCDES in successfully implementing a new Primary Information System.

NCSU graduate student will develop a machine learning approach to linking extreme atmospheric ridging events with extreme surface temperatures, employing a Gaussian Process (GP)-based predictive analysis tool that leverages the predictive value of spatial and temporal correlations and builds on ORNL’s past success in spatial classification, temporal change prediction, and parallelizing GP for large spatiotemporal extents.

With the increasing volume and complexity of data produced by ultra-scale simulations and high-throughput experiments, understanding the science is largely hampered by the lack of comprehensive, end-to-end data management solutions ranging from initial data acquisition to final analysis and visualization. The SciDAC-1 Scientific Data Management (SDM) Center succeeded in bringing an initial set of advanced data management technologies to DOE application scientists in astrophysics, climate, fusion, and biology. Building on our early successes, we will improve the SDM framework to address the needs of ultra-scale science.

In partnership with industry and faculty from across the country, this project will develop a transformative approach to developing the communication abilities (writing, speaking, teaming, and reading) of Computer Science and Software Engineering students. We will integrate communication instruction and activities throughout the curriculum in ways that enhance rather than replace their learning technical content and that supports development of computational thinking abilities of the students. We will implement the approach at two institutions. By creating concepts and resources that can be adapted by all CS and SE programs, this project also has the potential to increase higher education's ability nationwide to meet industry need for CS and SE graduates with much better communication abilities than, on average, is the case today. In addition, by using the concepts and resources developed in this project, CS and SE programs will be able to increase their graduates' mastery of technical content and computational thinking.

Jamming resistance is crucial for applications where reliable wireless communication is required, such as rescue missions and military applications. Spread spectrum techniques such as Frequency Hopping (FH) and Direct Sequence Spread Spectrum (DSSS) have been used as countermeasures against jamming attacks. However, these anti-jamming techniques require that senders and receivers share a secret key to communicate with each other, and thus are vulnerable to insider attacks where the adversary has access to the secret key. The objective of this project is to develop a suite of techniques to defend against insider jammers in DSSS and FH based wireless communication systems. We will develop novel and efficient insider-jamming-resistant techniques for both DSSS- and FH-based wireless communication systems. Our proposed research consists of two thrusts. The first thrust is to develop novel spreading/despreading techniques, called DSD-DSSS (which stands for DSSS based on Delayed Seed Disclosure), to enhance DSSS-based wireless communication to defend against insider jamming threats, while the second thrust is to develop a new approach, called USD-FH (which stands for FH based on Uncoordinated Seed Disclosure), to enable sender and receivers using FH to communicate without pre-establishing any common secret hopping pattern. A key property of our new approaches is that they do not depend on any secret shared by the sender and receivers. Our solution has the potential to significantly enhance the anti-jamming capability of today?s wireless communication systems.

In this project, we aim at developing a new indoor localization technique relying on low-frequency radio that can penetrate indoor obstacles (or detour obstacles by diffraction in the shortest path) by its long wave characteristics. The smartphone running this system would be able to identify its position by measuring straight-line distances from a few radio transmission towers deployed in a city scale (or in a district scale). Straight-line distances that have not been affected by indoor obstacles would be able to provide a three-dimensional position including floor information and position information in the floor (e.g., store information in a shopping complex).

In this project, a system providing intelligence to WiFi AP scan operations will be studied and developed for Android-operated smart devices, to reduce energy consumption in using WiFi chipsets. We ultimately aim at eliminating WiFi scans when users are mainly moving around their living boundaries by predicting which WiFi AP to connect without scanning. The prediction will be performed based on matching algorithms that find the similarity between a short term observation of cellular signal information measured in a smart device and a database of WiFi APs containing cellular base station IDs and their signal strength information per WiFi AP accumulated whenever the device is connected to a specific WiFi AP. Given our small scale measurement of energy consumption showing that WiFi scan operations drain about 10~15% of battery capacity of smartphones in their daily usages, our proposed algorithm is expected to be able to save substantial amount of energy in smart devices.

As smart devices like smartphones and tablet computers become prevalent, TCP performance over cellular networks is of growing importance. However, various measurement studies reveal that TCP suffers from excessively long delay as well as throughput degradation in cellular networks. In this project we will conduct extensive experiments over the 3G/4G networks of various cellular network carriers and investigate several under-developed issues: the current 3G/4G networks are over-buffered (termed as bufferbloat) and the excessive buffers void TCP congestion control who relies on packet loss to detect network congestion. Since all the overshot packets are absorbed by the buffers, no packet is lost and TCP will keep increasing its congestion window even if it is already much larger than the underlying bandwidth-delay product. To mitigate such problems, smartphones set the maximum receive buffer size to a relatively small value. Although this simple provisional scheme alleviates the aforementioned problem, it is losing performance in a number of scenarios due to its static nature. Through this project, we aim at proposing an adaptive receive window adjustment algorithm that requires changes only in receiver-side and implement it in Android phones and tablets.

In the proposed work, we will investigate innovative techniques to enable efficient I/O staging at a variety of locations in the HEC storage stack. The proposed work will improve the application-visible I/O performance in Peta-scale applications and explore the scalable incorporation of solid state drives (SSDs) into the HEC I/O hierarchy.

The damage and loss caused by attacks and security breaches have drawn Compared to their desktop counterparts, embedded devices are facing more security challenges, such as the more possible physical access to a target device and more constrained computing environment (e.g., limited RAM and CPU power). Together, these challenges lead to a favorable hardware/software co-design approach to deal with security issues for embedded systems. This proposal presents a trustful computing framework based on hypervisor for embedded systems. Our framework is a hybrid approach consisted of both hardware and software components. The trustworthiness of our approach roots from a hardware-based root-of-trust device. The root-of-trust device provides key security capabilities, such as the secure system initialization and physically isolated code execution, which cannot be achieved by a pure software-based solution. On top of the root-of-trust device, our approach provides a trustful boot-loader, which measures and attests the static integrity of the software and hardware components of the target embedded systems. The trustful boot-loader executes a trustful hypervisor which provides a virtual environment for Commercial Off The Shelf (COTS) Operating Systems (OS) and applications. The trustful hypervisor provides many security features, such as the high flexibility and dynamic attestation, which cannot be achieved by a pure hardware-based solution. In particular, the trustful hypervisor leverages the HIMA technology, a previous effort from North Carolina State University, which dynamically checks the security integrity of running OS and applications. Based on the trustworthy components, our trustful computing framework will provide an efficient, flexible and secure computing environment for embedded systems.

Simulating realistic mobility patterns of mobile devices is important for the performance study of mobile networks because deploying a real testbed of mobile networks is extremely difficult, and furthermore, even with such a testbed, constructing repeatable performance experiments using mobile devices is not trivial. Humans are a big factor in simulating mobile networks as most mobile nodes or devices (cell phones, PDAs and cars) are attached to or driven by humans. Emulating the realistic mobility patterns of humans can enhance the realism of simulation-based performance evaluation of human-driven mobile networks. Our NSF-funded research that ends this year has studied the patterns of human mobility using GPS traces of over 100 volunteers from five different sites including university campuses, New York City, Disney World, and State Fair. This research has revealed many important fundamental statistical properties of human mobility, namely heavy-tail flight distributions, self-similar dispersion of visit points, and least-action principle for trip planning. Most of all, it finds that people tend to optimize their trips in a way to minimize their discomfort or cost of trips (e.g., distance). No existing mobility models explicitly represent all of these properties. Our results are very encouraging and the proposed research will extend the work well beyond what has been accomplished so far. . We will perform a measurement study tracking the mobility of 100 or 200 students in a campus simultaneously, and analyze the mobility patterns associated with geo-physical and social contexts of participants including social networks, interactions, spatio-temporal correlations, and meetings. . We will cast the problem of mobility modeling as an optimization problem borrowing techniques from AI and Robotics which will make it easy to incorporate the statistical properties of mobility patterns commonly arising from group mobility traces. The realism of our models in expressing human mobility will surpass any existing human mobility models. . We will develop new routing protocols leveraging the researched statistical properties found in real traces to optimize delivery performance. The end products of the proposed research is (a) a new human mobility model that is capable of realistically expressing mobility patterns arising from reaction to social and geo-physical contexts, (b) their implementation in network simulators such as NS-2/3 and GloMoSim, (c) mobility traces that contain both trajectories of people in a university campus and contact times, (d) new efficient routing protocols for mobile networks

As medical device technology evolves, so too does the software upon which the technology often relies. Changes in device software, after it has been approved or cleared, may compromise the safety of that device. Assessing the safety of such changes presents special challenges to regulators at the FDA. This project explores differential analysis techniques to assess the effects of software changes on device safety.

Real-time systems often exhibit some level of non-determinism with regard to defect observability. Testers frequently must run tests multiple times in order to have some assurance that the test actually passes. This costs industry significant time and effort. No one has yet studied these defects to understand why they exhibit non- determinism and what techniques or tools can be used to better observe the software and control the non-determinism.

North Carolina State University (NCSU), led by the Department of Computer Science and the Institute of Advanced Analytics in conjunction with the Institute for Next Generation IT Systems (ITng), will create and manage a Science of Security Lablet (SOSL) research organization on behalf of the National Security Agency (NSA). The SOSL research organization will conduct and coordinate basic science research projects focused on the Science of Security. SOSL will coordinate with related Lablet activities sponsored by NSA at Carnegie Mellon University and at University of Illinois at Urbana Champaign (UIUC). SOSL will also coordinate with the Security Science Virtual Organization at Vanderbilt University. The coordination will be in the form of workshops and technical exchanges.

Developer testing has been widely recognized as an important, valuable means of improving software reliability. However, manual developer testing is often tedious and not sufficient. Automated testing tools can be used to reduce manual testing efforts. This project develops a systematic framework for cooperative developer testing to enable effective, synergetic cooperation between developers and testing tools. This framework centers around test intentions (i.e., what testing goals to satisfy) and consists of four components: intention specification, test generation, test abstraction, and intention inference. The project also includes integrated research and educational plans.

Testing is essential for database applications to function correctly and with acceptable performance when deployed. In practice, it is often necessary for a database software vendor to test their software completely before selling or integrating their package to the database owner. In this proposal, we focus on two bottlenecks in database application testing: functional testing, which is to test whether the applications can perform a set of predefined functions correctly, and performance testing, which is to test whether the applications can function with acceptable performance when deployed.

The objective of this project is to enhance the Software-artifact Infrastructure Repository in order to enable the evaluation of various new research projects on software testing such as unit test generation.

The objective of this project is to write parameterized mock objects for the database API to facilitate the application of Pex on database applications written in the Microsoft .NET platforms.

Testing and fault localization are two essential activities performed in virtually every engineering project. These activities can be very laborious and time-consuming. How to improve the effectiveness and efficiency of these two activities has been a major focus in many areas of engineering research. This project will develop effective and efficient fault localization techniques based on combinatorial testing, and adapt these techniques to produce domain-specific techniques applicable to different domains.

This project enhances the Access Control Policy Testing (ACPT) tool to support information sharing between affiliated organizations. The sharing of information should comply with security and privacy policies from federal, state, local or tribal security and privacy status. ACPT allows policy authors to compose and combine policies based on predefined templates of practical policy models. ACPT converts resulting models with user-provided attributes to machine-readable XACML representation, which can be directly enforced by information sharing entities.

Improving software quality is becoming an important yet challenging task in software development, especially for those mission-critical or safety-critical software systems. Many software defects related to correctness, security, and robustness are caused by the incorrect usage of system or application programming interfaces (APIs). We propose to develop new approaches for mining API properties for static verification from the API client call sites in existing code repositories, and then detect violations of these mined API properties to find defects in code repositories.

An increasing number of applications are set within narrative-oriented 3D virtual worlds. Current research on the generation of activities within these worlds holds the promise of tailored experiences customized to individual users? needs. The work described in this project seeks to expand the computational models of narrative being used to AI researchers, specifically to explore formal, plan-based models of actions to create stories that demonstrate complex conflict, rising action, dynamism and intentionality. The work will proceed both formally and empirically, with models being developed motivated by work from narrative theory and cognitive psychology and evaluated using experimental methods.

Through innovative application of computational thinking, this project will build the necessary cyber infrastructure to provide the next generation platform for multi-disciplinary and multi-agency collaboration in crime scene investigation (CSI). Since Daubert v. Merrell Dow Pharmaceuticals, CSI is both a highly visual and quantitative analysis characterized by a time-sensitive need to gather, organize, analyze, model, and visualize large, multi-scale, heterogeneous and context-rich data. CSI is also characterized by a fundamental need for rapid coordination and data translation across disciplines, agencies and levels of expertise as crime scenes are processed, reconstructed, solved and ultimately prosecuted over time, often critically in front of lay-people comprising a jury. Current methods of CSI are hindered by a lack of cyber infrastructure and protocols for virtual access to expertise and inadequate repositories of key data. From a computational e-Science perspective, forensic science is ripe for revolution through the development of a cyber infrastructure that will provide both new core data resources and collaboration capabilities in CSI for analysis and communication. Through remote access to data, tools and experts, as well as holistic integration of diverse data streams to virtually reconstruct and preserve actual crime scenes, the application of computational thinking to CSI will enable meta-analysis of evidentiary data and transform research and education for CSI professionals, legal professionals, forensic scientists, and K-20 students. The transformative research goal of this project is to develop a pioneering platform for interdisciplinary, cyber-enabled crime reconstruction through innovative methodology and engagement (IC-CRIME). The IC-CRIME platform will enable collaborative engagement in a 3D virtual reconstructed crime scene that incorporates multi-layer, scale-variant data and objects, including new critical data resources. The proposed cyber infrastructure will allow novice users to embed, interact with and analyze multi-layered data and objects within reconstructed crime scene in such a way that provides lucid spatial insight for users while simultaneously preserving quantitative geospatial relationships among evidentiary components as meaning is gleaned from data. The transformative educational goal of this project is to develop a team-based inter-disciplinary educational tool for professionals and K-20 that provides experiential, problem-based learning opportunities in a data-intensive virtual environment.

Online social networks not only greatly expand the scale of people's social connections, but also have the potential to become an open computing platform, where new types of services can be quickly offered and propagated through existing social structures. Mechanisms for trust management of privacy protection are integral to the future success of online social networks. In this project, we develop theoretical and practical techniques for the management of trust and privacy for social networks. Some of the innovative expected results include a formal trust model and trust policy languages for social networks, privacy preserving feedback management, and graph anonymization techniques for the sharing of social network data.