@article{darabseh_al-ayyoub_jararweh_benkhelifa_vouk_rindos_2017, title={A novel framework for software defined based secure storage systems}, volume={77}, ISSN={["1878-1462"]}, DOI={10.1016/j.simpat.2016.05.003}, abstractNote={The Software Defined Systems (SDSys) paradigm has been introduced recently as a solution to reduce the overhead in the control and management operations of complex computing systems and to maintain a high level of security and protection. The main concept behind this technology is around isolating the data plane from the control plane. Building a Software Defined System in a real life environment is considered an expensive solution and may have a lot of risks. Thus, there is a need to simulate such systems before the real-life implementation and deployment. In this paper we present a novel experimental framework as a virtualized testbed environment for software defined based secure storage systems. Its also covers some related issues for large scale data storage and sharing such as deduplication. This work builds on the Mininet simulator, where its core components, the host, switch and the controller, are customized to build the proposed experimental simulation framework. The developed emulator, will not only support the development and testing of SD-based secure storage solutions, it will also serve as an experimentation tool for researchers and for benchmarking purposes. The developed simulator/emulator could also be used as an educational tool to train students and novice researchers.}, journal={SIMULATION MODELLING PRACTICE AND THEORY}, author={Darabseh, Ala' and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Vouk, Mladen and Rindos, Andy}, year={2017}, month={Sep}, pages={407–423} }
 @inbook{dreher_nair_sills_vouk_2017, title={Cost Analysis Comparing HPC Public Versus Private Cloud Computing}, volume={740}, ISBN={9783319625935 9783319625942}, ISSN={1865-0929 1865-0937}, url={http://dx.doi.org/10.1007/978-3-319-62594-2_15}, DOI={10.1007/978-3-319-62594-2_15}, abstractNote={The past several years have seen a rapid increase in the number and type of public cloud computing hardware configurations and pricing options offered to customers. In addition public cloud providers have also expanded the number and type of storage options and established incremental price points for storage and network transmission of outbound data from the cloud facility. This has greatly complicated the analysis to determine the most economical option for moving general purpose applications to the cloud. This paper investigates whether this economic analysis for moving general purpose applications to the public cloud can be extended to more computationally intensive HPC type computations. Using an HPC baseline hardware configuration for comparison, the total cost of operations for several HPC private and public cloud providers are analyzed. The analysis shows under what operational conditions the public cloud option may be a more cost effective alternative for HPC type applications.}, booktitle={Communications in Computer and Information Science}, publisher={Springer International Publishing}, author={Dreher, Patrick and Nair, Deepak and Sills, Eric and Vouk, Mladen}, year={2017}, pages={294–316} }
 @article{kim_vouk_2016, title={Assessing Run-time Overhead of Securing Kepler}, volume={80}, ISSN={1877-0509}, url={http://dx.doi.org/10.1016/J.PROCS.2016.05.412}, DOI={10.1016/J.PROCS.2016.05.412}, abstractNote={Abstract We have developed a model for securing data-flow based application chains. We have imple- mented the model in the form of an add-on package for the scientific workflow system called Kepler. Our Security Analysis Package (SAP) leverages Kepler's Provenance Recorder (PR). SAP secures data flows from external input-based attacks, from access to unauthorized exter- nal sites, and from data integrity issues. It is not a surprise that cost of real-time security is a certain amount of run-time overhead. About half of the overhead appears to come from the use of the Kepler PR and the other half from security function added by SAP.}, journal={Procedia Computer Science}, publisher={Elsevier BV}, author={Kim, Donghoon and Vouk, Mladen A.}, year={2016}, pages={2281–2286} }
 @inproceedings{lenhardt_conway_scott_blanton_krishnamurthy_hadzikadic_vouk_wilson_2016, title={Cross-institutional research cyberinfrastructure for data intensive science}, DOI={10.1109/hpec.2016.7761597}, abstractNote={This paper describes a multi-institution effort to develop a “data science as a service” platform. This platform integrates advanced federated data management for small to large datasets, access to high performance computing, distributed computing and advanced networking. The goal is to develop a platform that is flexible and extensible while still supporting domain research and avoiding the walled garden problem. Some preliminary lessons learned and next steps will also be outlined.}, booktitle={2016 ieee high performance extreme computing conference (hpec)}, author={Lenhardt, W. C. and Conway, M. and Scott, E. and Blanton, B. and Krishnamurthy, A. and Hadzikadic, M. and Vouk, M. and Wilson, Alyson}, year={2016} }
 @article{dreher_vouk_2016, title={Embedding Cloud Computing inside Supercomputer Architectures}, DOI={10.5220/0005912302960301}, abstractNote={Recently there has been a surge of interest in several prototype software systems that can embed a cloud computing image with user applications into a supercomputer’s hardware architecture. This position paper will summarize these efforts and comment on the advantages of each design and will also discuss some of the challenges that one faces with such software systems. This paper takes the position that specific types of user applications may favor one type of design over another. Different designs may have potential advantages for specific user applications and each design also brings a considerable cost to assure operability and overall computer security. A “one size fits all design” for a cost effective and portable solution for Supercomputer/cloud delivery is far from being a solved problem. Additional research and development should continue exploring various design approaches. In the end several different types of supercomputer/cloud implementations may be needed to optimally satisfy the complexity and diversity of user needs, requirements and security concerns. The authors also recommend that the community recognize a distinction when discussing cluster-type HPC/Cloud versus Supercomputer/Cloud implementations because of the substantive differences between these systems.}, journal={PROCEEDINGS OF THE 6TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND SERVICES SCIENCE, VOL 2 (CLOSER)}, author={Dreher, Patrick and Vouk, Mladen}, year={2016}, pages={296–301} }
 @article{jararweh_al-ayyoub_darabseh_benkhelifa_vouk_rindos_2016, title={Software defined cloud: Survey, system and evaluation}, volume={58}, ISSN={["1872-7115"]}, DOI={10.1016/j.future.2015.10.015}, abstractNote={Next generation cloud systems will require a paradigm shift in how they are constructed and managed. Conventional control and management platforms are facing considerable challenges regarding flexibility, dependability and security that next generation systems must handle. The cloud computing technology has already contributed in alleviating a number of the problems associated with resource allocation, utilization and management. However, many of the elements of a well-designed cloud environment remain “stiff” and hard to modify and adapt in an integrated fashion. This includes the underlying networking topologies, many aspects of the user control over IaaS, PaaS or SaaS layers, construction of XaaS services, provenance and meta-data collection, to mention but few. In many situations the problem may be due to inadequacy of service abstraction. Software Defined Systems (SDSys) is a concept that help abstract the actual hardware at different layers with software components; one classical example of this abstractions are hypervisors. Such abstraction provides an opportunity for system administrators to construct and manage their systems, more easily, through flexible software layers. SDSys is an umbrella for different software defined subsystems including Software Defined Networking (SDN), Software Defined Storage (SDStorage), Software Defined Servers (Virtualization), Software Defined Data Centers (SDDC), Software Defined Security (SDSec) etc. and ultimately Software Defined Clouds (SDCloud). Individual solutions and seamless integration of these different abstractions remains in many respects a challenge. In this paper, the authors introduce Software Defined Cloud (SDCloud), a novel software defined cloud management framework that integrates different software defined cloud components to handle complexities associated with cloud computing systems. The first part of paper presents, for the first time, an extensive state of the art critical review of different components of software defined systems, constructing the proposed SDCloud. The second part of the paper proposes the novel concept of SDCloud, which is implemented and evaluated for its feasibility, flexibility and potential superiority.}, journal={FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE}, author={Jararweh, Yaser and Al-Ayyoub, Mahmoud and Darabseh, Ala' and Benkhelifa, Elhadj and Vouk, Mladen and Rindos, Andy}, year={2016}, month={May}, pages={56–74} }
 @article{anderson_heckman_vouk_wright_carter_burge_gannod_2015, title={CS/SE Instructors Can Improve Student Writing without Reducing Class Time Devoted to Technical Content: Experimental Results}, DOI={10.1109/icse.2015.178}, abstractNote={The Computer Science and Software Engineering (CS/SE) profession reports that new college graduates lack the communication skills needed for personal and organizational success. Many CS/SE faculty may omit communication instruction from their courses because they do not want to reduce technical content. We experimented in a software-engineering-intensive second-semester programming course with strategies for improving students' writing of black box test plans that included no instruction on writing the plans beyond the standard lecture on testing. The treatment version of the course used 1) a modified assignment that focused on the plan's readers, 2) a model plan students could consult online, and 3) a modified grading rubric that identified the readers' needs. Three external raters found that students in the treatment sections outperformed students in the control sections on writing for five of nine criteria on rubrics for evaluating the plans and on the raters' holistic impression of the students' technical and communication abilities from the perspectives of a manager and a tester.}, journal={2015 IEEE/ACM 37TH IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, VOL 2}, author={Anderson, Paul V. and Heckman, Sarah and Vouk, Mladen and Wright, David and Carter, Michael and Burge, Janet E. and Gannod, Gerald C.}, year={2015}, pages={455–464} }
 @inproceedings{yu_ning_vouk_2015, title={Enhancing security of Hadoop in a public cloud}, DOI={10.1109/iacs.2015.7103198}, abstractNote={Hadoop has become increasingly popular as it rapidly processes data in parallel. Cloud computing gives reliability, flexibility, scalability, elasticity and cost saving to cloud users. Deploying Hadoop in cloud can benefit Hadoop users. Our evaluation exhibits that various internal cloud attacks can bypass current Hadoop security mechanisms, and compromised Hadoop components can be used to threaten overall Hadoop. It is urgent to improve compromise resilience, Hadoop can maintain a relative high security level when parts of Hadoop are compromised. Hadoop has two vulnerabilities that can dramatically impact its compromise resilience. The vulnerabilities are the overloaded authentication key, and the lack of fine-grained access control at the data access level. We developed a security enhancement for a public cloud-based Hadoop, named SEHadoop, to improve the compromise resilience through enhancing isolation among Hadoop components and enforcing least access privilege for Hadoop processes. We have implemented the SEHadoop model, and demonstrated that SEHadoop fixes the above vulnerabilities with minimal or no run-time overhead, and effectively resists related attacks.}, booktitle={2015 6th International Conference on Information and Communication Systems (ICICS)}, author={Yu, X. Q. and Ning, P. and Vouk, M. A.}, year={2015}, pages={38–43} }
 @article{darabseh_al-ayyoub_jararweh_benkhelifa_vouk_rindos_awan_younas_mecella_2015, title={SDDC: A Software Defined Datacenter Experimental Framework}, DOI={10.1109/ficloud.2015.127}, abstractNote={The rapid growth and the distributed sites of the datacenters increase the complexity of control and management processes. A new paradigm which is called Software Defined Systems (SDSys) comes as a solution to reduce the overhead of datacenters management by abstracting all the control functionalities from the hardware devices and setting it inside a software layer. These functionalities are responsible for organizing and controlling the main blocks of the datacenter; network, storage, compute and security. The Software Defined Datacenter (SDD) integrates the software defined concepts into all of these main blocks. Transferring these concepts into workable systems requires checking several performance aspects and testing its correctness before building real systems. In this paper we introduce a novel experimental framework (SDDC) to provide a novel virtualized testbed environment for SDD systems. This work builds on the Mininet simulator, where its core components, the host, the switch and the controller, are customized to build the proposed experimental simulation framework for SDD. This simulator lets the users develop and test their own SDD solutions, and at the same time gives the researchers an experimentation tool for benchmarking purposes. The developed simulator could also be used as an educational tool to train students and novice researchers.}, journal={2015 3RD INTERNATIONAL CONFERENCE ON FUTURE INTERNET OF THINGS AND CLOUD (FICLOUD) AND INTERNATIONAL CONFERENCE ON OPEN AND BIG (OBD)}, author={Darabseh, Ala' and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Vouk, Mladen and Rindos, Andy and Awan, I and Younas, M and Mecella, M}, year={2015}, pages={189–194} }
 @article{jararweh_al-ayyoub_darabseh_benkhelifa_vouk_rindos_2015, title={SDIoT: a software defined based internet of things framework}, volume={6}, ISSN={1868-5137 1868-5145}, url={http://dx.doi.org/10.1007/S12652-015-0290-Y}, DOI={10.1007/S12652-015-0290-Y}, number={4}, journal={Journal of Ambient Intelligence and Humanized Computing}, publisher={Springer Science and Business Media LLC}, author={Jararweh, Yaser and Al-Ayyoub, Mahmoud and Darabseh, Ala’ and Benkhelifa, Elhadj and Vouk, Mladen and Rindos, Andy}, year={2015}, month={Jun}, pages={453–461} }
 @inproceedings{darabseh_al-ayyoub_jararweh_benkhelifa_vouk_rindos_2015, title={SDSecurity: A software defined security experimental framework}, DOI={10.1109/iccw.2015.7247453}, abstractNote={The emerging Software Defined Systems (SDSys) is a recent paradigm, which has been introduced to reduce the overhead in the control and management operations of complex computing systems. The main concept behind this technology is around isolating the data plane from the control plane. Traditional security mechanisms are facing more challenges in providing sufficient levels of protection and efficiency. SDSys for security has been proposed to address these challenges. Software Defined Security (SDSec) provides a flexible and centralized security solution by abstracting the security mechanisms from the hardware layer to a software layer. In this paper we present a novel experimental framework to provide a novel virtualized testbed environment for SDSec systems. This work builds on the Mininet simulator, where its core components, the host, switch and the controller, are customized to build the proposed experimental simulation framework for SDSec. To the best of the authors' knowledge, this is the first experimental framework and simulator for SDSec solutions. The developed simulator, will not only support the development and testing of SDSecurity solutions, it will also serve as an experimentation tool for researchers and for benchmarking purposes. The developed simulator could also be used as an educational tool to train students and novice researchers.}, booktitle={2015 IEEE International Conference on Communication Workshop}, author={Darabseh, A. and Al-Ayyoub, M. and Jararweh, Y. and Benkhelifa, E. and Vouk, M. and Rindos, A.}, year={2015}, pages={1871–1876} }
 @article{darabseh_al-ayyoub_jararweh_benkhelifa_vouk_rindos_2015, title={SDStorage: A Software Defined Storage Experimental Framework}, DOI={10.1109/ic2e.2015.60}, abstractNote={With the rapid growth of data centers and the unprecedented increase in storage demands, the traditional storage control techniques are considered unsuitable to deal with this large volume of data in an efficient manner. The Software Defined Storage (SDStore) comes as a solution for this issue by abstracting the storage control operations from the storage devices and set it inside a centralized controller in the software layer. Building a real SDStore system without any simulation and emulation is considered an expensive solution and may have a lot of risks. Thus, there is a need to simulate such systems before the real-life implementation and deployment. In this paper we present SDStorage, an experimental framework to provide a novel virtualized test bed environment for SDStore systems. The main idea of SDStorage is based on the Mininet Software Defined Network (SDN) Open Flow simulator and is built over of it. The main components of Mininet, which are the host, the switch and the controller, are customized to serve the needs of SDStore simulation environments.}, journal={2015 IEEE INTERNATIONAL CONFERENCE ON CLOUD ENGINEERING (IC2E 2015)}, author={Darabseh, Ala' and Al-Ayyoub, Mahmoud and Jararweh, Yaser and Benkhelifa, Elhadj and Vouk, Mladen and Rindos, Andy}, year={2015}, pages={341–346} }
 @article{kim_vouk_2015, title={Securing Scientific Workflows}, ISBN={["978-1-4673-9598-4"]}, DOI={10.1109/qrs-c.2015.25}, abstractNote={This paper investigates security of Kepler scientific workflow engine. We are especially interested in Kepler-based scientific workflows that may operate in cloud environments. We find that (1) three security properties (i.e., input validation, remote access validation, and data integrity) are essential for making Kepler-based workflows more secure, and (2) that use of the Kepler provenance module may help secure Kepler based workflows. We implemented a prototype security enhanced Kepler engine to demonstrate viability of use of the Kepler provenance module in provision and management of the desired security properties.}, journal={2015 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY AND SECURITY - COMPANION (QRS-C 2015)}, author={Kim, Donghoon and Vouk, Mladen A.}, year={2015}, pages={95–104} }
 @inproceedings{kim_vouk_2015, title={Securing software application chains in a cloud}, booktitle={2015 2nd International Conference on Information Science and Security (ICISS)}, author={Kim, D. and Vouk, M. A.}, year={2015}, pages={50–53} }
 @article{rivers_vouk_williams_2014, title={On Coverage-Based Attack Profiles}, DOI={10.1109/sere-c.2014.15}, abstractNote={Automated cyber attacks tend to be schedule and resource limited. The primary progress metric is often "coverage" of pre-determined "known" vulnerabilities that may not have been patched, along with possible zero-day exploits (if such exist). We present and discuss a hypergeometric process model that describes such attack patterns. We used web request signatures from the logs of a production web server to assess the applicability of the model.}, journal={2014 IEEE EIGHTH INTERNATIONAL CONFERENCE ON SOFTWARE SECURITY AND RELIABILITY - COMPANION (SERE-C 2014)}, author={Rivers, Anthony T. and Vouk, Mladen A. and Williams, Laurie}, year={2014}, pages={5–6} }
 @article{vouk_averitt_dreher_kekas_kurth_hoit_mugge_peeler_schaffer_sills_et al._2013, title={Constructing next generation academic cloud services}, volume={2}, DOI={10.1504/ijcc.2013.055290}, abstractNote={NC State University (NCSU) is embarked on an ambitious vision to change the paradigm for higher education and research by ‘virtualising’ its award-winning Centennial Campus (creating so called vCentennial). Centennial Campus is a small city made up of NCSU research, teaching and outreach facilities, entrepreneurs, academic entities, private firms, and government agencies. NCSU wants the ability to replicate services and functionality of this physical environment and its virtual avatars ‘anywhere, anytime’ in the world using a cloud of clouds computing platform. The initial operating system for this platform is NCSU’s open source Virtual Computing Laboratory (VCL) technology. This paper provides an overview of the vision and discusses several vCentennial pilot projects.}, number={2/3}, journal={International Journal of Cloud Computing}, author={Vouk, M. A. and Averitt, S. F. and Dreher, P. and Kekas, D. H. and Kurth, A. and Hoit, Marc and Mugge, P. and Peeler, A. and Schaffer, H. E. and Sills, Eric and et al.}, year={2013}, pages={104–122} }
 @inproceedings{subramani_vouk_williams_2013, title={Non-operational testing of software for security issues}, DOI={10.1109/issrew.2013.6688857}, abstractNote={We are studying extension of the classical Software Reliability Engineering (SRE) methodology into the security space. We combine “classical” reliability modeling, when applied to reported vulnerabilities found under “normal” operational profile conditions, with safety oriented fault management processes. We illustrate with open source Fedora software.}, booktitle={2013 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW)}, author={Subramani, S. and Vouk, M. and Williams, L.}, year={2013}, pages={21–22} }
 @inbook{vouk_2012, place={Berlin Heidelberg}, series={FIP Advances in Information and Communication Technology}, title={A Note on Uncertainty in Real-Time Analytics}, ISBN={9783642326769 9783642326776}, ISSN={1868-4238 1861-2288}, url={http://dx.doi.org/10.1007/978-3-642-32677-6_20}, DOI={10.1007/978-3-642-32677-6_20}, abstractNote={Today real-time analytics of large data sets is invariably computer-assisted and often includes a “human-in-the-loop”. Humans differ from each other and all have a very limited innate capacity to process new information in real-time. This introduces statistical and systematic uncertainties into observations, analyses and decisions humans make when they are “in the loop”. Humans also have unconscious and conscious biases, and these can introduce (major) systematic errors into human assisted or human driven analytics. This note briefly discusses the issues and the (considerable) implications they can have on real-time analytics that involves humans, including software interfaces, learning, and reaction of humans in emergencies.}, booktitle={Uncertainty Quantification in Scientific Computing. WoCoUQ 2011}, publisher={Springer}, author={Vouk, Mladen A.}, editor={Dienstfrey, A.M. and Boisvert, R.F.Editors}, year={2012}, pages={312–318}, collection={FIP Advances in Information and Communication Technology} }
 @article{lobo_bitzer_vouk_2012, title={Locally Invertible Multidimensional Convolutional Encoders}, volume={58}, ISSN={["1557-9654"]}, DOI={10.1109/tit.2011.2178129}, abstractNote={A polynomial matrix is said to be locally invertible if it has an invertible subsequence map of equal size between its input and output sequence spaces. This paper examines the use of these matrices, which we call locally invertible encoders, for generating multidimensional convolutional codes. We discuss a novel method of encoding and inverting multidimensional sequences using the subsequence map. We also show that the overlapping symbols between consecutive input subsequences obtained during the sequence inversion can be used to determine if the received sequence is the same as the transmitted codeword.}, number={3}, journal={IEEE TRANSACTIONS ON INFORMATION THEORY}, author={Lobo, Ruben and Bitzer, Donald L. and Vouk, Mladen A.}, year={2012}, month={Mar}, pages={1774–1782} }
 @inproceedings{carter_vouk_gannod_burge_anderson_hoffman_2011, title={Communication genres: Integrating communication into the software engineering curriculum}, DOI={10.1109/cseet.2011.5876091}, abstractNote={One way to improve the communication abilities of new software engineering graduates in the workplace is to integrate communication more effectively in the software engineering curriculum. But faculty typically conceive of communication as outside their realm of expertise. Based on the results of an NSF-funded project, we use theories of situated learning and genre to make the case that communication is integral to software engineering and that faculty are in the best position to guide students in becoming better communicators in the field. We identify software engineering genres and show how those genres may be used to integrate communication in the classroom and throughout the curriculum.}, booktitle={2011 24th IEEE-CS Conference on Software Engineering Education and Training (CSEET)}, author={Carter, M. and Vouk, M. and Gannod, G. C. and Burge, J. E. and Anderson, P. V. and Hoffman, M. E.}, year={2011}, pages={21–30} }
 @inbook{mouallem_crawl_altintas_vouk_yildiz_2010, title={A Fault-Tolerance Architecture for Kepler-Based Distributed Scientific Workflows}, ISBN={9783642138171 9783642138188}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-642-13818-8_31}, DOI={10.1007/978-3-642-13818-8_31}, abstractNote={Fault-tolerance and failure recovery in scientific workflows is still a relatively young topic. The work done in the domain so far mostly applies classic fault-tolerance mechanisms, such as "alternative versions" and "checkpointing", to scientific workflows. Often scientific workflow systems simply rely on the fault-tolerance capabilities provided by their third party subcomponents such as schedulers, Grid resources, or the underlying operating systems. When failures occur at the underlying layers, a workflow system typically sees them only as failed steps in the process without additional detail and the ability of the system to recover from those failures may be limited. In this paper, we present an architecture that tries to address this for Kepler-based scientific workflows by providing more information about failures and faults we have observed, and through a supporting implementation of more comprehensive failure coverage and recovery options. We discuss our framework in the context of the failures observed in two production-level Kepler-based workflows, specifically XGC and S3D. The framework is divided into three major components: (i) a general contingency Kepler actor that provides a recovery block functionality at the workflow level, (ii) an external monitoring module that tracks the underlying workflow components, and monitors the overall health of the workflow execution, and (iii) a checkpointing mechanism that provides smart resume capabilities for cases in which an unrecoverable error occurs. This framework takes advantage of the provenance data collected by the Kepler-based workflows to detect failures and help in fault-tolerance decision making.}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Berlin Heidelberg}, author={Mouallem, Pierre and Crawl, Daniel and Altintas, Ilkay and Vouk, Mladen and Yildiz, Ustun}, year={2010}, pages={452–460} }
 @inproceedings{mouallem_crawl_altintas_vouk_yildiz_2010, title={A fault-tolerance architecture for kepler-based distributed scientific workflows}, volume={6187}, booktitle={Scientific and statistical database management}, author={Mouallem, P. and Crawl, D. and Altintas, I. and Vouk, M. and Yildiz, U.}, year={2010}, pages={452–460} }
 @inbook{boyer_phillips_ingram_ha_wallis_vouk_lester_2010, title={Characterizing the Effectiveness of Tutorial Dialogue with Hidden Markov Models}, ISBN={9783642133879 9783642133886}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-642-13388-6_10}, DOI={10.1007/978-3-642-13388-6_10}, abstractNote={Identifying effective tutorial dialogue strategies is a key issue for intelligent tutoring systems research. Human-human tutoring offers a valuable model for identifying effective tutorial strategies, but extracting them is a challenge because of the richness of human dialogue. This paper addresses that challenge through a machine learning approach that 1) learns tutorial strategies from a corpus of human tutoring, and 2) identifies the statistical relationships between student outcomes and the learned strategies. We have applied hidden Markov modeling to a corpus of annotated task-oriented tutorial dialogue to learn one model for each of two effective human tutors. We have identified significant correlations between the automatically extracted tutoring modes and student learning outcomes. This work has direct applications in authoring data-driven tutorial dialogue system behavior and in investigating the effectiveness of human tutoring.}, booktitle={Intelligent Tutoring Systems}, publisher={Springer Berlin Heidelberg}, author={Boyer, Kristy Elizabeth and Phillips, Robert and Ingram, Amy and Ha, Eun Young and Wallis, Michael and Vouk, Mladen and Lester, James}, year={2010}, pages={55–64} }
 @inproceedings{anbalagan_vouk_2009, title={An empirical study of security problem reports in Linux distributions}, booktitle={International symposium on empirical software engineering and}, author={Anbalagan, P. and Vouk, M.}, year={2009}, pages={482–485} }
 @article{xing_bitzer_alexander_vouk_stomp_2009, title={Identification of protein-coding sequences using the hybridization of 18S rRNA and mRNA during translation}, volume={37}, ISSN={["1362-4962"]}, DOI={10.1093/nar/gkn917}, abstractNote={We introduce a new approach in this article to distinguish protein-coding sequences from non-coding sequences utilizing a period-3, free energy signal that arises from the interactions of the 3′-terminal nucleotides of the 18S rRNA with mRNA. We extracted the special features of the amplitude and the phase of the period-3 signal in protein-coding regions, which is not found in non-coding regions, and used them to distinguish protein-coding sequences from non-coding sequences. We tested on all the experimental genes from Saccharomyces cerevisiae and Schizosaccharomyces pombe. The identification was consistent with the corresponding information from GenBank, and produced better performance compared to existing methods that use a period-3 signal. The primary tests on some fly, mouse and human genes suggests that our method is applicable to higher eukaryotic genes. The tests on pseudogenes indicated that most pseudogenes have no period-3 signal. Some exploration of the 3′-tail of 18S rRNA and pattern analysis of protein-coding sequences supported further our assumption that the 3′-tail of 18S rRNA has a role of synchronization throughout translation elongation process. This, in turn, can be utilized for the identification of protein-coding sequences.}, number={2}, journal={NUCLEIC ACIDS RESEARCH}, author={Xing, Chuanhua and Bitzer, Donald L. and Alexander, Winser E. and Vouk, Mladen A. and Stomp, Anne-Marie}, year={2009}, month={Feb}, pages={591–601} }
 @article{boyer_phillips_wallis_vouk_lester_2009, title={Investigating the role of student motivation in computer science education through one-on-one tutoring}, volume={19}, ISSN={0899-3408 1744-5175}, url={http://dx.doi.org/10.1080/08993400902937584}, DOI={10.1080/08993400902937584}, abstractNote={The majority of computer science education research to date has focused on purely cognitive student outcomes. Understanding the motivational states experienced by students may enhance our understanding of the computer science learning process, and may reveal important instructional interventions that could benefit student engagement and retention. This article investigates issues of student motivation as they arise during one-on-one human tutoring in introductory computer science. The findings suggest that the choices made during instructional discourse are associated with cognitive and motivational outcomes, and that particular strategies can be leveraged based on an understanding of the student motivational state.}, number={2}, journal={Computer Science Education}, publisher={Informa UK Limited}, author={Boyer, Kristy Elizabeth and Phillips, Robert and Wallis, Michael D. and Vouk, Mladen A. and Lester, James C.}, year={2009}, month={Jun}, pages={111–135} }
 @article{schaffer_averitt_hoit_peeler_sills_vouk_2009, title={NCSU's Virtual Computing Lab: A Cloud Computing Solution}, volume={42}, ISSN={["1558-0814"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-68349092594&partnerID=MN8TOARS}, DOI={10.1109/mc.2009.230}, abstractNote={The delivery of many diverse computing services over the Internet, with flexible provisioning, has led to much greater efficiency, substantial cost savings, and many ways to enable and empower end users. NCSU's own experience with cloud computing, through its Virtual Computing Lab, indicates that this approach would be beneficial to a much wider audience.ays to enable and empower end users. NCSU's own experience with cloud computing, through its Virtual Computing Lab, indicates that this approach would be beneficial to a much wider audience.}, number={7}, journal={COMPUTER}, author={Schaffer, Henry E. and Averitt, Samuel F. and Hoit, Marc I. and Peeler, Aaron and Sills, Eric D. and Vouk, Mladen A.}, year={2009}, month={Jul}, pages={94–97} }
 @inbook{mouallem_barreto_klasky_podhorszki_vouk_2009, title={Tracking Files in the Kepler Provenance Framework}, ISBN={9783642022784 9783642022791}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-642-02279-1_21}, DOI={10.1007/978-3-642-02279-1_21}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Berlin Heidelberg}, author={Mouallem, Pierre and Barreto, Roselyne and Klasky, Scott and Podhorszki, Norbert and Vouk, Mladen}, year={2009}, pages={273–282} }
 @inbook{nagappan_vouk_2008, title={A Model for Sharing of Confidential Provenance Information in a Query Based System}, ISBN={9783540899648 9783540899655}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-540-89965-5_8}, DOI={10.1007/978-3-540-89965-5_8}, abstractNote={Workflow management systems are increasingly being used to automate scientific discovery. Provenance meta-data is collected about scientific workflows, processes, simulations and data to add value. There is a variety of workflow management tools that cater to this. The provenance information may have as much value as the raw data. Typically, sensitive information produced by a computational processes or experiments is well guarded. However, this may not necessarily be true when it comes to provenance information. The issue is how to share confidential provenance information. We present a model for sharing provenance information when the confidentiality level is decided by the user dynamically. The key feature of this model is the Query Sharing concept. We illustrate the model for workflows implemented using provenance enabled Kepler system.}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Berlin Heidelberg}, author={Nagappan, Meiyappan and Vouk, Mladen A.}, year={2008}, pages={62–69} }
 @article{layman_williams_slaten_berenson_vouk_2008, title={Addressing diverse needs through a balance of agile and plan-driven software development methodologies in the core software engineering course}, volume={24}, number={4}, journal={International Journal of Engineering Education}, author={Layman, L. and Williams, L. and Slaten, K. and Berenson, S. and Vouk, M.}, year={2008}, pages={659–670} }
 @inbook{boyer_phillips_wallis_vouk_lester_2008, title={Balancing Cognitive and Motivational Scaffolding in Tutorial Dialogue}, ISBN={9783540691303 9783540691327}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-540-69132-7_28}, DOI={10.1007/978-3-540-69132-7_28}, abstractNote={A key challenge in the design of tutorial dialogue systems is identifying tutorial strategies that can effectively balance the tradeoffs between cognitive and affective student outcomes. This balance is problematic because the precise nature of the interdependence between cognitive and affective strategies is not well understood. Furthermore, previous studies suggest that some cognitive and motivational goals are at odds with one another because a tutorial strategy designed to maximize one may negatively impact the other. This paper reports on a tutorial dialogue study that investigates motivational strategies and cognitive feedback. It was found that the choice of corrective tutorial strategy makes a significant difference in the outcomes of both student learning gains and self-efficacy gains.}, booktitle={Intelligent Tutoring Systems}, publisher={Springer Berlin Heidelberg}, author={Boyer, Kristy Elizabeth and Phillips, Robert and Wallis, Michael and Vouk, Mladen and Lester, James}, year={2008}, month={Aug}, pages={239–249} }
 @inbook{vouk_altintas_barreto_blondin_cheng_critchlow_khan_klasky_ligon_ludaescher_et al._2007, title={Automation of Network-Based Scientific Workflows}, ISBN={9780387736587}, url={http://dx.doi.org/10.1007/978-0-387-73659-4_3}, DOI={10.1007/978-0-387-73659-4_3}, abstractNote={Comprehensive, end-to-end, data and workflow management solutions are needed to handle the increasing complexity of processes and data volumes associated with modern distributed scientific problem solving, such as ultrascale simulations and high-throughput experiments. The key to the solution is an integrated network-based framework that is functional, dependable, faulttolerant, and supports data and process provenance. Such a framework needs to make development and use of application workflows dramatically easier so that scientists’ efforts can shift away from data management and utility software development to scientific research and discovery. An integrated view of these activities is provided by the notion of scientific workflows - a series of structured activities and computations that arise in scientific problem-solving. An information technology framework that supports scientific workflows is the Ptolemy II based environment called Kepler. This paper discusses the issues associated with practical automation of scientific processes and workflows and illustrates this with workflows developed using the Kepler framework and tools.}, booktitle={IFIP The International Federation for Information Processing}, publisher={Springer US}, author={Vouk, M. A. and Altintas, I. and Barreto, R. and Blondin, J. and Cheng, Z. and Critchlow, T. and Khan, A. and Klasky, S. and Ligon, J. and Ludaescher, B. and et al.}, year={2007}, month={Nov}, pages={35–61} }
 @article{batchelor_beck_becoulet_budny_chang_diamond_dong_fu_fukuyama_hahm_et al._2007, title={Simulation of Fusion Plasmas: Current Status and Future Direction}, volume={9}, ISSN={1009-0630}, url={http://dx.doi.org/10.1088/1009-0630/9/3/13}, DOI={10.1088/1009-0630/9/3/13}, abstractNote={I. Introduction (Z. Lin, G. Y. Fu, J. Q. Dong) II. Role of theory and simulation in fusion sciences 1. The Impact of theory and simulation on tokomak experiments (H. R. Wilson, T.S. Hahm and F. Zonca) 2. Tokomak Transport Physics for the Era of ITER: Issues for Simulations (P.H. Diamond and T.S. Hahm) III. Status of fusion simulation and modeling 1. Nonlinear Governing Equations for Plasma Simulations (T. S. Hahm) 2. Equilibrium and stability (L.L. Lao, J. Manickam) 3. Transport modeling (R.E. Waltz) 4. Nonlinear MHD (G.Y. Fu) 5. Turbulence (Z. Lin and R.E. Waltz) 6. RF heating and current drive (D.A. Batchelor) 7. Edge physics Simulations (X.Q. Xu and C.S. Chang) 8. Energetic particle physics (F. Zonca, G.Y. Fu and S.J. Wang) 9. Time-dependent Integrated Modeling (R.V. Budny) 10. Validation and verification (J. Manickam) IV. Major initiatives on fusion simulation 1. US Scientific Discovery through Advanced Computing (SciDAC) Program & Fusion Energy Science (W. Tang) 2. EU Integrated Tokamak Modelling (ITM) Task Force (A. Becoulet) 3. Fusion Simulations Activities in Japan (A. Fukuyama, N. Nakajima, Y. Kishimoto, T. Ozeki, and M. Yagi) V. Cross-disciplinary research in fusion simulation 1. Applied mathematics: Models, Discretizations, and Solvers (D.E. Keyes) 2. Computational Science (K. Li) 3. Scientific Data and Workflow Management (S. Klasky, M. Beck, B. Ludaescher, N. Podhorszki, M.A. Vouk) 4. Collaborative tools (J. Manickam)}, number={3}, journal={Plasma Science and Technology}, publisher={IOP Publishing}, author={Batchelor, D A and Beck, M and Becoulet, A and Budny, R V and Chang, C S and Diamond, P H and Dong, J Q and Fu, G Y and Fukuyama, A and Hahm, T S and et al.}, year={2007}, month={Jun}, pages={312–387} }
 @misc{batchelor_beck_becoulet_budny_chang_diamond_dong_fu_fukuyama_hahm_et al._2007, title={Simulation of fusion plasmas: Current status and future direction}, volume={9}, number={3}, journal={Plasma Science & Technology}, author={Batchelor, D. A. and Beck, M. and Becoulet, A. and Budny, R. V. and Chang, C. S. and Diamond, P. H. and Dong, J. Q. and Fu, G. Y. and Fukuyama, A. and Hahm, T. S. and et al.}, year={2007}, pages={312–387} }
 @article{may_vouk_bitzer_2006, title={Classification of Escherichia coli K-12 ribosome binding sites}, volume={25}, ISSN={["0739-5175"]}, DOI={10.1109/memb.2006.1578668}, abstractNote={Drawing on parallels between genetic information processing in living organisms and the processing of communications data, we develop an error-control coding-based translation initiation classification system that uses an eleven base classification window. An overview of channel codes and a summary of the translation initiation process are presented. Parallels between the two are drawn and a brief review of a channel code model for translation initiation is shown. A block-code Bayesian classifier is presented and the results of applying the system to the translation start site location problem for Escherichia coli K-12 is discussed.}, number={1}, journal={IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE}, author={May, EE and Vouk, MA and Bitzer, DL}, year={2006}, pages={90–97} }
 @inbook{lobo_bitzer_vouk_2006, title={Locally Invertible Multivariate Polynomial Matrices}, ISBN={9783540354819 9783540354826}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/11779360_33}, DOI={10.1007/11779360_33}, abstractNote={A new class of rectangular zero prime multivariate polynomial matrices are introduced and their inverses are computed. These matrices are ideal for use in multidimensional systems involving input-output transformations. We show that certain multivariate polynomial matrices, when transformed to the sequence space domain, have an invertible subsequence map between their input and output sequences. This invertible subsequence map can be used to derive the polynomial inverse matrix together with a set of pseudo-inverses. All computations are performed using elementary operations on the ground field without using any polynomial operations.}, booktitle={Coding and Cryptography}, publisher={Springer Berlin Heidelberg}, author={Lobo, Ruben G. and Bitzer, Donald L. and Vouk, Mladen A.}, year={2006}, pages={427–441} }
 @article{lobo_bitzer_vouk_2006, title={Locally invertible multivariate polynomial matrices}, number={3969}, journal={Lecture Notes in Computer Science}, author={Lobo, R. G. and Bitzer, D. L. and Vouk, M. A.}, year={2006}, pages={427–441} }
 @article{zheng_williams_nagappan_snipes_hudepohl_vouk_2006, title={On the value of static analysis for fault detection in software}, volume={32}, ISSN={["1939-3520"]}, DOI={10.1109/TSE.2006.38}, abstractNote={No single software fault-detection technique is capable of addressing all fault-detection concerns. Similarly to software reviews and testing, static analysis tools (or automated static analysis) can be used to remove defects prior to release of a software product. To determine to what extent automated static analysis can help in the economic production of a high-quality product, we have analyzed static analysis faults and test and customer-reported failures for three large-scale industrial software systems developed at Nortel Networks. The data indicate that automated static analysis is an affordable means of software fault detection. Using the orthogonal defect classification scheme, we found that automated static analysis is effective at identifying assignment and checking faults, allowing the later software production phases to focus on more complex, functional, and algorithmic faults. A majority of the defects found by automated static analysis appear to be produced by a few key types of programmer errors and some of these types have the potential to cause security vulnerabilities. Statistical analysis results indicate the number of automated static analysis faults can be effective for identifying problem modules. Our results indicate static analysis tools are complementary to other fault-detection techniques for the economic production of a high-quality software product.}, number={4}, journal={IEEE TRANSACTIONS ON SOFTWARE ENGINEERING}, author={Zheng, J and Williams, L and Nagappan, N and Snipes, W and Hudepohl, JP and Vouk, MA}, year={2006}, month={Apr}, pages={240–253} }
 @article{starmer_stomp_vouk_bitzer_2006, title={Predicting Shine-Dalgarno sequence locations exposes genome annotation errors}, volume={2}, ISSN={["1553-7358"]}, DOI={10.1371/journal.pcbi.0020057}, abstractNote={In prokaryotes, Shine–Dalgarno (SD) sequences, nucleotides upstream from start codons on messenger RNAs (mRNAs) that are complementary to ribosomal RNA (rRNA), facilitate the initiation of protein synthesis. The location of SD sequences relative to start codons and the stability of the hybridization between the mRNA and the rRNA correlate with the rate of synthesis. Thus, accurate characterization of SD sequences enhances our understanding of how an organism's transcriptome relates to its cellular proteome. We implemented the Individual Nearest Neighbor Hydrogen Bond model for oligo–oligo hybridization and created a new metric, relative spacing (RS), to identify both the location and the hybridization potential of SD sequences by simulating the binding between mRNAs and single-stranded 16S rRNA 3′ tails. In 18 prokaryote genomes, we identified 2,420 genes out of 58,550 where the strongest binding in the translation initiation region included the start codon, deviating from the expected location for the SD sequence of five to ten bases upstream. We designated these as RS+1 genes. Additional analysis uncovered an unusual bias of the start codon in that the majority of the RS+1 genes used GUG, not AUG. Furthermore, of the 624 RS+1 genes whose SD sequence was associated with a free energy release of less than −8.4 kcal/mol (strong RS+1 genes), 384 were within 12 nucleotides upstream of in-frame initiation codons. The most likely explanation for the unexpected location of the SD sequence for these 384 genes is mis-annotation of the start codon. In this way, the new RS metric provides an improved method for gene sequence annotation. The remaining strong RS+1 genes appear to have their SD sequences in an unexpected location that includes the start codon. Thus, our RS metric provides a new way to explore the role of rRNA–mRNA nucleotide hybridization in translation initiation.}, number={5}, journal={PLOS COMPUTATIONAL BIOLOGY}, author={Starmer, J. and Stomp, A. and Vouk, M. and Bitzer, D.}, year={2006}, month={May}, pages={454–466} }
 @inproceedings{berenson_michael_vouk_2006, title={The relationship between high school mathematics and career choices among high achieving young women}, booktitle={Pme 30: proceedings of the 30th conference of the international group for the psychology of mathematics education, vol 1,}, author={Berenson, S. B. and Michael, J. J. and Vouk, M.}, year={2006}, pages={220–220} }
 @article{oothongsap_viniotis_vouk_2006, title={Theoretical analysis of the SABUL congestion control algorithm}, volume={31}, ISSN={["1572-9451"]}, DOI={10.1007/s11235-006-6516-8}, number={2-3}, journal={TELECOMMUNICATION SYSTEMS}, author={Oothongsap, P and Viniotis, Y and Vouk, M}, year={2006}, month={Mar}, pages={115–139} }
 @inbook{barnes_bitzer_vouk_2005, title={Experimental Analysis of the Q-Matrix Method in Knowledge Discovery}, volume={3488}, ISBN={9783540258780 9783540319498}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/11425274_62}, DOI={10.1007/11425274_62}, abstractNote={The q-matrix method, a new method for data mining and knowledge discovery, is compared with factor analysis and cluster analysis in analyzing fourteen experimental data sets. This method creates a matrix-based model that extracts latent relationships among observed binary variables. Results show that the q-matrix method offers several advantages over factor analysis and cluster analysis for knowledge discovery. The q-matrix method can perform fully unsupervised clustering, where the number of clusters is not known in advance. It also yields better error rates than factor analysis, and is comparable in error to cluster analysis. The q-matrix method also allows for automatic interpretation of the data sets. These results suggest that the q-matrix method can be an important tool in automated knowledge discovery.}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Berlin Heidelberg}, author={Barnes, Tiffany and Bitzer, Donald and Vouk, Mladen}, year={2005}, pages={603–611} }
 @article{may_vouk_bitzer_rosnick_2004, title={An error-correcting code framework for genetic sequence analysis}, volume={341}, ISSN={["1879-2693"]}, DOI={10.1016/j.jfranklin.2003.12.009}, abstractNote={A fundamental challenge for engineering communication systems is the problem of transmitting information from the source to the receiver over a noisy channel. This same problem exists in a biological system. How can information required for the proper functioning of a cell, an organism, or a species be transmitted in an error introducing environment? Source codes (compression codes) and channel codes (error-correcting codes) address this problem in engineering communication systems. The ability to extend these information theory concepts to study information transmission in biological systems can contribute to the general understanding of biological communication mechanisms and extend the field of coding theory into the biological domain. In this work, we review and compare existing coding theoretic methods for modeling genetic systems. We introduce a new error-correcting code framework for understanding translation initiation, at the cellular level and present research results for Escherichia coli K-12. By studying translation initiation, we hope to gain insight into potential error-correcting aspects of genomic sequences and systems.}, number={1-2}, journal={JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS}, author={May, EE and Vouk, MA and Bitzer, DL and Rosnick, DI}, year={2004}, pages={89–109} }
 @article{may_vouk_bitzer_rosnick_2004, title={Coding theory based models for protein translation initiation in prokaryotic organisms}, volume={76}, ISSN={["0303-2647"]}, DOI={10.1016/j.biosystems.2004.05.017}, abstractNote={Our research explores the feasibility of using communication theory, error control (EC) coding theory specifically, for quantitatively modeling the protein translation initiation mechanism. The messenger RNA (mRNA) of Escherichia coli K-12 is modeled as a noisy (errored), encoded signal and the ribosome as a minimum Hamming distance decoder, where the 16S ribosomal RNA (rRNA) serves as a template for generating a set of valid codewords (the codebook). We tested the E. coli based coding models on 5′ untranslated leader sequences of prokaryotic organisms of varying taxonomical relation to E. coli including: Salmonella typhimurium LT2, Bacillus subtilis, and Staphylococcus aureus Mu50. The model identified regions on the 5′ untranslated leader where the minimum Hamming distance values of translated mRNA sub-sequences and non-translated genomic sequences differ the most. These regions correspond to the Shine–Dalgarno domain and the non-random domain. Applying the EC coding-based models to B. subtilis, and S. aureus Mu50 yielded results similar to those for E. coli K-12. Contrary to our expectations, the behavior of S. typhimurium LT2, the more taxonomically related to E. coli, resembled that of the non-translated sequence group.}, number={1-3}, journal={BIOSYSTEMS}, author={May, EE and Vouk, MA and Bitzer, DL and Rosnick, DI}, year={2004}, pages={249–260} }
 @inbook{oothongsap_viniotis_vouk_2004, title={Experimental analysis of the SABUL congestion control algorithm}, volume={3042}, ISBN={3540219595}, DOI={10.1007/978-3-540-24693-0_131}, abstractNote={Several new protocols such as RBUDP, User-Level UDP, Tsunami, and SABUL, have been proposed as alternatives to TCP for high-speed data transfer. The purpose of this paper is to analyze experimentally the effects of SABUL congeston control algorithm on SABUL and performance metrics such as bandwidth utilization, self-fairness, and aggressiveness. Our results confirm some expected behavior of SABUL and reveal some less expected one. Our experiments also indicate that SABUL implementation and design can result in an even more erratic behavior and degraded performance under high-congestion conditions.}, booktitle={Networking 2004: Networking technologies, services, and protocols: Performance of computer and communication networks, mobile and wireless commuication: Third International IFIP-TC6 Networking Conference, Athens, Greece, May 9-14, 2004 ; Proceedings}, publisher={Berlin; New York: Springer}, author={Oothongsap, P. and Viniotis, Y. and Vouk, M.}, year={2004}, pages={1433–1439} }
 @inbook{vouk_rivers_2003, title={Construction of reliable software in resource-constrained environments}, ISBN={0471413739}, DOI={10.1002/0471393002.ch9}, abstractNote={Current software development practices are often “business-driven” and therefore tend to encourage testing approaches that reduce verification and validation activities to shorten schedules. In this paper, we focus on efficiency of testing and resulting software quality (reliability) in such an environment. We use a resource constrained testing model to analyze data from several projects. Our results indicate that in a practical resource constrained environment there is little room for improving testing during the actual process. Furthermore, there is likely to be considerable variability in the quality of testing, within a testing phase, that may stem from a variety of sources such as the human element, software development practices and the structure of the software itself. However, it is interesting to note that there are experimental results showing that testing efficiency can be improved over longer periods of time through process improvement, and that software quality does appear to be positively correlated with an increase in the average testing efficiency that stems from process improvements.}, booktitle={Case studies in reliability and maintenance (Wiley series in probability and statistics)}, publisher={Hoboken, N.J.: Wiley-Interscience}, author={Vouk, M. A. and Rivers, A. T.}, editor={W. R. Blischke and Murthy, D. N. P.Editors}, year={2003} }
 @article{labbe_mohammed_streck_vouk_2001, title={Alcatel - North Carolina State University Virtual Laboratory for End-to-End Quality of Service Engineering}, number={3}, journal={Alcatel Telecommunications Review}, author={Labbe, T. and Mohammed, A. and Streck, J. P. and Vouk, M. A.}, year={2001}, pages={227–231} }
 @article{potok_vouk_rindos_1999, title={Productivity analysis of object-oriented software developed in a commercial environment}, volume={29}, ISSN={["0038-0644"]}, DOI={10.1002/(SICI)1097-024X(199908)29:10<833::AID-SPE258>3.0.CO;2-P}, abstractNote={The introduction of object‐oriented technology does not appear to hinder overall productivity on new large commercial projects, but nor does it seem to improve it in the first two product generations. In practice, the governing influence may be the business workflow, and not the methodology. Copyright © 1999 John Wiley & Sons, Ltd.}, number={10}, journal={SOFTWARE-PRACTICE & EXPERIENCE}, author={Potok, TE and Vouk, M and Rindos, A}, year={1999}, month={Aug}, pages={833–847} }
 @article{vouk_bitzer_klevans_1999, title={Workflow and end-user quality of service issues in Web-based education}, volume={11}, ISSN={["1558-2191"]}, DOI={10.1109/69.790839}, abstractNote={The option of obtaining education over networks is quickly becoming a reality for all those who have access to the Internet and the World Wide Web (WWW). However, at present, network-based education (NBE) over the WWW and the Internet in general faces a number of pitfalls. The problems range from inadequate end-user quality of service (QoS), to inadequate materials, to shortcomings in learning paradigms, and to missing or inappropriate student assessment and feedback mechanisms. In this paper, we discuss some major issues that, although mostly solved for NBE, still face Web-based education (WEE). These include the required workflow-oriented technological and quality of service support. In discussing the issues, we use examples from a wide-area NBE/WBE system called NovaNET and a WEE system called Web Lecture System (WLS). We recommend that WEE system developers construct operational user (workflow) profiles before building their content and interfaces. Our experience is that, especially for synchronous WEE systems, user-level round-trip keystroke delays should not exceed about 250 ms and the overall availability of the system (including network-related service failures) should be at least 0.95. We also suggest that a successful WEE system will have a sound auto-adaptive knowledge assessment component, a "virtual" laboratory capability, and a set of strong collaborative functions.}, number={4}, journal={IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING}, author={Vouk, MA and Bitzer, DL and Klevans, RL}, year={1999}, pages={673–687} }
 @misc{bitzer_dholakia_koorapaty_vouk_1998, title={On locally invertible rate-1/n convolutional encoders}, volume={44}, ISSN={["1557-9654"]}, DOI={10.1109/18.651074}, abstractNote={A locally invertible convolutional encoder has a local inverse defined as a full rank w/spl times/w matrix that specifies a one-to-one mapping between equal-length blocks of information and encoded bits. In this correspondence, it is shown that a rate-1/n convolutional encoder is nondegenerate and noncatastrophic if and only if it is locally invertible. Local invertibility is used to obtain upper and lower bounds on the number of consecutive zero-weight branches in a convolutional codeword. Further, existence of a local inverse can be used as an alternate test for noncatastrophicity instead of the usual approach involving computation of the greatest common divisor of n polynomials.}, number={1}, journal={IEEE TRANSACTIONS ON INFORMATION THEORY}, author={Bitzer, DL and Dholakia, A and Koorapaty, H and Vouk, MA}, year={1998}, month={Jan}, pages={420–422} }
 @article{rajala_vouk_nilsson_miller_schrag_burke_brawner_viniotis_perros_1997, title={Technology for support of network-based education workflows in North Carolina: NC State-Fujitsu education partnership final report for the period June 1, 1996-December 31, 1996}, number={3}, journal={TR (Center for Advanced Computing and Communication)}, author={Rajala, S. A. and Vouk, M. A. and Nilsson, A. A. and Miller, T. K. and Schrag, R. L. and Burke, J. R. and Brawner, C. E. and Viniotis, I. and Perros, H. G.}, year={1997} }
 @misc{bitzer_vouk_srinivasan_lo_dholakia_gonzalez_lee_wang_koorapaty_1995, title={System for encoding and decoding of convolutionally encoded data}, volume={5381425}, publisher={Washington, DC: U.S. Patent and Trademark Office}, author={Bitzer, D. L. and Vouk, M. A. and Srinivasan, V. and Lo, S. K. and Dholakia, A. and Gonzalez, E. M. and Lee, T. M. and Wang, L. and Koorapaty, H.}, year={1995} }
 @inproceedings{boyer_ha_wallis_phillips_vouk_lester, title={Discovering tutorial dialogue strategies with hidden Markov models}, volume={200}, booktitle={Artificial intelligence in education - building learnning systems that care: from knowledge representation to affective modelling }, author={Boyer, K. E. and Ha, E. Y. and Wallis, M. D. and Phillips, R. and Vouk, M. A. and Lester, J. C.}, pages={141–148} }