Computer Science
Permanent URI for this collectionhttp://hdl.handle.net/10342/42
Browse
Recent Submissions
Item Open Access Warfarin Sensitivity is Associated with Increased Hospital Mortality in Critically Ill Patients(2022-05-05) Wang, Ping; et alItem Open Access A FRAMEWORK FOR AUTOMATICALLY GENERATING QUESTIONS FOR TOPICS IN DISCRETE MATHEMATICS(East Carolina University, 2020-11-17) Houshvand, SalarAutomated question generation is critical for realizing personalized learning. Also, learning research shows that answering questions is a more effective method than rereading the textbook multiple times. However, creating different types of questions is intellectually challenging and time-intensive. Therefore, it emphasizes a necessity for an automated way to generate questions and evaluate them. In this research after analyzing the existing approaches to automated question generation, we conclude that most of the current systems use natural language process techniques to extract questions from the text, therefore, other topics such as mathematics are lacking an automated question generation system that could help learners to assess their knowledge.In this research we present a novel framework that automatically generates unlimited numbers of questions for different topics in discrete mathematics. We created multiple algorithms for various questions in four main topics using Python. Our final product is presented as an application programming interface (API) using Flask library, which makes it easy to gain access and use this system in any future developments. Finally, we discuss the potential extensions that can be added to our framework as future contributions. The repository for this framework is freely available at https://github.com/SalarHoushvand/discrete-math-restfulAPI.Item Open Access Studies on Gopala-Hemachandra Codes and their Applications(East Carolina University, 2020-11-16) Childers, LoganGopala-Hemachandra codes are a variation of the Fibonacci universal code and have applications in data compression and cryptography. We study a specific parameterization of Gopala-Hemachandra codes and present several results pertaining to these codes. We show that GH_{a}(n) always exists for any n >= 1, when -2 >= a >= -4, meaning that these are universal codes. We develop two new algorithms to determine whether a GH code exists for a given a and n, and to construct them if they exist. We also prove that when a = -(4+k), where k >= 1, that there are at most k consecutive integers for which GH codes do not exist. In 2014, Nalli and Ozyilmaz proposed a stream cipher based on GH codes. We show that this cipher is insecure and provide experimental results on the performance of our program that cracks this cipher.Item Open Access ENVIRONMENTAL MODEL ACCURACY IMPROVEMENT FRAMEWORK USING STATISTICAL TECHNIQUES AND A NOVEL TRAINING APPROACH(East Carolina University, 2020-06-22) Matta, RekeshIt is challenging to predict environmental behaviors because of extreme events, such as heatwaves, typhoons, droughts, tsunamis, torrential downpour, wind ramps, or hurricanes. In this thesis, we proposed a novel framework to improve environmental model accuracy with a novel training approach. Extreme event detection algorithms are surveyed, selected, and applied in our proposed framework. The application of statistics in extreme events detection is quite diverse and leads to diverse formulations, which need to be designed for a specific problem. Each formula needs to be tailored specially to work with the available data in the given situation. This diversity is one of the driving forces of this research towards identifying the most common mixture of components utilized in the analysis of extreme events detection. Besides the extreme event detection algorithm, we also integrated the sliding window approach to see how well our models predict future events. To test the proposed framework, we collected coastal data from various sources and obtained the results; we improved the predictive accuracy of various machine learning models by 20% to 25% increase in R2 value using our approach. Apart from that, we organized the discussion along with different extreme event detection types, presented a few outlier definitions, and briefly introduced their techniques. We also summarized the statistical methods involved in the detection of environmental extremes, such as wind ramps and climatic events.Item Open Access MVC EDUCATION 3D : A FRAMEWORK FOR DISTANCE EDUCATION VIRTUAL REALITY APPLICATIONS(East Carolina University, 2020-06-22) Chegireddy, Yashwanth ReddyRecent advancements in the online course delivery for Distance Education(DE) pro- gram is evolving from day-to-day. Though DE programs cost less and also provide exibility to students depending on their pace of learning, delivering lab experiments to them is always a challenging task for the instructors. Few hands-on experiments need students to visit campus in order to perform them. But amateurs who never had training experience, frequent on-campus visits can be more cost-effective. We propose Model-View-Controller-Education-3D (MVC-E3D), a framework to develop virtual reality applications. This framework is similar to MVC architecture, but an additional component - Education (E) module, which has instructional content like lab manual, demo videos, quiz section and User Feedback System(UFS) required for training purposes, are added to the Model (M) component. Besides this, the framework illustrates how to broadcast course contents to students' machines remotely using Photon Unity Networking (PUN) plugin.To show how the proposed framework works, we have implemented a pre-hands-on experiment for ladder safety virtual reality training class, where an instructor hosts a 3D environment based construction lab experiment on a server allowing Distance Education (DE) students to access and finish the training. Hosting a server can reduce computational requirements for student computers. Each system component can be reused for other hands-on experiments. Students can gain experience in lab equipment and familiarize themselves with the preliminary steps before visiting on-campus lab training.Item Restricted Archival Document Processing using Cognitive Computing(East Carolina University, 2019-07-22) Patel, Himaniben PThe world, as we know it, is constructed in the form of knowledge. Our ancestors have passed their experiences to the next generation over time using handwritten documents. Although these old manuscripts are still available however, to disseminate that information to everyone, they must be converted into digital form. In the 21st century, the computers are becoming faster than ever before, thanks to the advancement of the fields of machine learning, deep learning, big data, cognitive computing and etc. A relationship between data may be found, which may, in turn, solves most of the problems. Cognitive computing can be used to deal with a vast amount of data to discovers hidden patterns or insights. Although research has explored many diverse, specific fields of application for cognitive computing, a comprehensive overview of the concept and its use is severely lacking. By leveraging the abilities of cognitive computing, text may be extracted from the handwritten documents in the form of images. The first part of the thesis focuses on the literature review of research papers related to applications of cognitive computing, collected from IEEE, ACM, and Springer databases. Currently, two companies provide cognitive computing services related to handwritten text recognition, Microsoft Azure's Computer Vision and Google Cloud's Vision AI. The second part focuses on conducting a performance analysis between these services based on some pre-defined criteria, where Microsoft Azure's Computer Vision service performed better overall for cursive English. Transkribus is a platform for automated recognition and transcription of archival documents, which uses a deep learning model to recognize text from an image. The third part focuses on analyzing the effectiveness of Microsoft Azure's Computer Vision service, by conducting performance analysis with Transkribus where images (collected from the Library of Congress with their transcribed text) were submitted. The results showed that Microsoft Azure's Computer vision service performed better compared to Transkribus. The last part focuses on increasing the accuracy of the Microsoft Azure's Computer Vision service by improving the quality of images. Various image pre-processing techniques were analyzed and applied to the dataset. Both improved and un-improved images were given as input to Microsoft Azure's Computer Vision service, and their results were evaluated, which showed that Microsoft Azure's Computer Vision's accuracy could increase for some images by improving the quality of the image.Item Open Access DYNAMIC DEFENSES AND THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES(East Carolina University, 2019-05-02) Thomas, SamAdversarial machine learning has been an important area of study for the securing of machine learning systems. However, for every defense that is made to protect these artificial learners, a more sophisticated attack emerges to defeat it. This has created an arms race, with the problem of adversarial attacks never being fully mitigated. This thesis examines the field of adversarial machine learning; specifically, the property of transferability, and the use of dynamic defenses as a solution to attacks which leverage it. We show that this is an emerging field of research, which may be the solution to one of the most intractable problems in adversarial machine learning. We go on to implement a minimal experiment, demonstrating that research within this area is easily accessible. Finally, we address some of the hurdles to overcome in order to unify the disparate aspects of current related research.Item Open Access Modeling and Prediction of Cryptocurrency Prices Using Machine Learning Techniques(East Carolina University, 2019-05-01) Ashayer, AlirezaWith the introduction of Bitcoin in the year 2008 as the first practical decentralized cryptocurrency, the interest in cryptocurrencies and their underlying technology, Blockchain, has skyrocketed. Their promise of security, anonymity, and lack of a central controlling authority make them ideal for users who value their privacy. Academic research on machine learning, Blockchain technology, and their intersection have increased significantly in recent years. Specifically, one of the interest areas for researchers is the possibility of predicting the future prices of these cryptocurrencies using supervised machine learning techniques. In this thesis, we investigate their ability to make one day ahead price prediction of several popular cryptocurrencies using five widely used time-series prediction models. These models are designed by optimizing model parameters, such as activation functions, before settling on the final models presented in this thesis. Finally, we report the performance of each time-series prediction model measured by its mean squared error and accuracy in price movement direction prediction.Item Open Access The Relationship Between Categorical Expenditures and Graduation Rates at North Carolina Community Colleges(East Carolina University, 2018-12-10) Smith, Davis BThe public perception of higher education, the culture of that institution, and its value to American citizens is changing. Taxpayer demands to downsize costly government expenditures, including government subsidizing of state supported educational institutions, have resulted in increased scrutiny of colleges and universities. Special programs have been reduced and in the case of post-secondary schools, there is increased pressure to find alternative funding sources and to increase tuition requirements. As a result, educational stakeholders have been forced to examine all aspects of institutional performance, especially numbers of graduating students. Though numerous theories suggest innovative ways to increase student success, college presidents face the reality of limited money to implement every success effort. More informed spending decisions might be possible by exploring an economic production function model to see what expenditures might produce better student success results at post-secondary institutions. This study examined four expenditure inputs - instructional support, academic support, institutional support, and student services support -, to determine whether there were any relationships between expenditure categories and graduation rates. My population included the 58 North Carolina Community College System (NCCCS) schools between the years of 2004-2014 using ordinary least squares regression to test my research question. The data for this study were collected from The Integrated Postsecondary Education Data System (IPEDS). The results of my study revealed there was no statistically significant relationship between individual expenditure category and graduation rates of those institutions for that time period.Item Restricted A Scalable Solution for Extreme Multi-class Product Classification: An E-commerce Case Study(East Carolina University, 2018-04-27) Fathi, EhsanImage classification is the main task in image processing. Although, there were a lot of advances in recent years, it is still quite a challenge. On the other hand, due to the progress in technology, e-commerce has emerged as the fastest-growing sector of the U.S. marketplace. Product classification is an extremely important issue in e-commerce. In this work, we propose a scalable, flexible, practical, modular and efficient architecture to use image classification techniques for product classification just using product images. Considering the diversity of products offering in retail online retail stores it is not surprising that we confront an excessive number of classes. Case study is Cdiscount which is the biggest non-food e-commerce company in France which has made about 3 billion euros. As the trend of growing rate of this e-commerce shows they will have about 30 million products up for sale while they just had 10 million products until 2 years ago. As the next step to toward business expansion, they decided to employ image processing techniques. The structure of the dataset, diversity of the products and volume of it makes it unique between all the available public data sets. We focused on developing a CNN architecture to tackle this challenge and provide a more general, flexible, scalable and efficient solution for Cdiscount image classification business problem. Results of applying the proposed architecture shows a reasonable accuracy which shows the efficiency of the architecture. A comparison between proposed model and previous models is also provided.Item Open Access MC/DC COVERAGE FOR REQUIREMENTS SPECIFICATIONS(East Carolina University, 2018-05-02) Das, GouravIn the early 1990s, the Modi ed Condition/Decision Coverage (MC/DC) criterion was suggested as a structural white-box testing approach, but it can also be used for blackbox speci cation-based testing. Practical application of MC/DC for speci cationbased testing has its own unique features and is sometimes quite di erent from codebased applications. However, MC/DC as a black-box approach has not been studied su ciently, and thus, the application of MC/DC for speci cation coverage was the main research problem considered in this thesis. The goal of this study was to analyze MC/DC as a black-box technique, investigate factors that distinguish black- and white-box applications of this approach, and provide proper de nitions and rules with a prototype implementation to evaluate the MC/DC level during black-box testing.Item Open Access Exploring the Usability Issues Encountered by Individuals with Visual Impairments on Social Networking Sites: Problem Description, System Evaluation and Semantic Web Solution(East Carolina University, 2014-08-28) Brinkley, JulianWhile social networking sites (SNSs) like Facebook are widely used and have been broadly studied, investigations of their use by individuals with visual impairments are scarce within the academic literature. Anecdotal complaints regarding their usability however can be found in abundance online; an extension of the well documented difficulty that users with visual impairments have in interacting with the web generally relative to the sighted. The investigation of this issue began with a pilot study of the online behavioral habits of 46 internet users; 26 of whom self-identified as having a visual impairment (either blind or low vision). This was followed by an ethnographic usability study of the Facebook mobile interface, involving six blind participants, using JAWS screen reading software on desktop computers. Of the features evaluated participants were most severely challenged by the process of creating a user profile and identifying other users with whom to establish relationships. A portable profile architecture based on semantic web technologies is presented as a potential solution that may improve usability by decoupling the profile and relationship maintenance activity from any single system.Item Open Access GestDefLS : A Gesture Definition Language in Swift(East Carolina University, 2015) Writtenberry, Robert WilliamThe application programming interfaces supplied by Apple for developing applications in the Swift programming language on iOS devices provide limited support when it comes to declaring gesture recognizers outside of those simple ones currently provided. GestDefLS seeks to provide the service of allowing the developer to define custom, single- or multi-touch gesture recognizers. The language has the benefits of providing a concise, easy-to-understand language for declaring gestures, in addition to being readily compatible within Apple's Swift programming language. Furthermore, the language provides a higher level of modularity in terms of separating gesture recognition code from code pertaining to what the application should actually accomplish.Item Open Access USING HYBRID SCRUM TO MEET WATERFALL PROCESS DELIVERABLES(East Carolina University, 2013) Moster, EmilSystem Development Life Cycles (SDLCs) for organizations are often based upon traditional software development models such as the waterfall model. These processes are complex, heavy in documentation deliverables, and are rigid and less flexible than other methods being used in modern software development. Consider by contrast, agile methods for software development. In essence, agile methods recommend lightweight documentation and simplified process. The focus shifts to completed software as the "measure of success" for delivery of product in software projects, versus accurate and comprehensive documentation, and the accomplishment of static milestones in a work breakdown structure. This thesis implements, explores, and recommends a hybrid agile approach to Scrum in order to satisfy the rigid, document-laden deliverables of a waterfall-based SDLC process. This hybrid Scrum is a balance of having enough documentation and process - but not too much - to meet SDLC deliverables, while at the same time focusing on timely product delivery and customer interactions that come from an agile approach to software development.Item Open Access Cloud Platform for Research Crowdsourcing in Mobile Testing(East Carolina University, 2013) Starov, OleksiiMobile application testing and testing over a cloud are two highly topical fields nowadays. Mobile testing presents specific test activities, including verification of an application against a variety of heterogeneous smartphone models and versions of operating systems (OS), build distribution and test team management, monitoring and user experience analytics of an application in production, etc. Cloud benefits are widely used to support all these activities. This study conducts in-depth analyses of existing cloud services for mobile testing and addresses their weaknesses regarding research purposes and testing needs of the critical and business-critical mobile applications. During this study, a Cloud Testing of Mobile Systems (CTOMS) framework for effective research crowdsourcing in mobile testing was developed. The framework is presented as a lightweight and easily scalable distributed system that provides a cloud service to run tests on a variety of remote mobile devices. CTOMS provides implementation of two novel functionalities that are demanded by advanced investigations in mobile testing. First, it allows full multidirectional testing, which provides the opportunities to test an application on different devices and/or OS versions, and new device models or OS versions for their compatibility with the most popular applications in the market, or just legacy critical apps, etc. Second, CTOMS demonstrates the effective integration of the appropriate testing techniques for mobile development within such a service. In particular, it provides a user with suggestions about coverage of configurations to test on using combinatorial approaches like a base choice, pair-wise, and t-way. The current CTOMS version supports automated functional testing of Android applications and detection of defects in the user interface (UI). This has a great value because requirements for UI and user experience are high for any modern mobile application. The fundamental analysis of possible test types and techniques using a system like CTOMS was conducted, and ways of possible enhancements and extensions of functionality for possible research are listed. The first case studies prove the work of implemented novel concepts, their usefulness, and their convenience for experiments in mobile testing. The overall work proves that a study of cloud mobile testing is feasible even with small research resources.Item Open Access Overhauling Legacy Enterprise Software Applications with a Concept Refinement Process Model(East Carolina University, 2013) Knight, Daniel P.Currently, there are many legacy enterprise software applications in active deployment that are outdated. These large legacy applications are rapidly becoming less practical for both the organizations they service, and for the organizations responsible for servicing them. Due to this problem, organizations utilizing legacy enterprise software applications are looking for feasible methods for overhauling them. This thesis establishes a process model for refining the initial concept associated with overhauling legacy enterprise software applications, and examines a case study of that process as applied to a real-world legacy software system.Item Open Access Improving Access to Information through Conceptual Classification(East Carolina University, 2011) Bazargani, SaharOverwhelming the users with large amount of information on the Web has resulted in users' inability to find the information and their dissatisfaction with available information searching and filtering systems. On the other hand, the information is distributed over many websites and a large part of it (for example news) is updated frequently. Keeping track of the changes in huge amount of information is a real problem for users. Due to the great impact the information has on people's lives and business decision-making, much research has been done on the efficient ways of accessing and analyzing the information. This thesis will propose a conceptual classification method and ranking of the information in order to provide better user access to a wider range of information, it also provides the information that may help in analyzing the global trends in various fields. In order to demonstrate the effectiveness of this method, a feed aggregator system has been developed and evaluated through this thesis. To improve the flexibility and adaptability of the system, we have adopted the agent-oriented software engineering architecture that has also helped facilitating the development process. In addition, since the system deals with storing and processing large amounts of information, that requires a large number of resources the cloud platform service has been used as a platform for deploying the application. The result was a cloud based software service that benefited from the unlimited on-demand resources. To take advantage of the available features of public cloud computing platforms, those supporting the agent-oriented design, the multi-agent system was implemented by mapping the agents to the cloud computing services. In addition, the cloud queue service that is provided by some cloud providers such as Microsoft and Amazon was used to implement indirect communication among the agents in the multi-agent system.Item Open Access Security Analysis and Framework of Cloud Computing with Parity-Based Partially Distributed File System(East Carolina University, 2011) Asghary Karahroudy, AliCloud computing offers massive scalability, immediate availability, and low cost services as major benefits, but as with most new technologies, it introduces new risks and vulnerabilities too. Despite the fact that different cloud structures and services are expanding, the cloud computing penetration has not been as envisioned. Some specific concerns have stopped enterprises from completely joining the cloud. One of the major disadvantages of using cloud computing is its increased security risks. In this study I conduct an in depth analyses of the different aspects of security issues in cloud computing and propose a file distribution model as a possible solution to alleviate those security risks. It also shows the effectiveness of the new security model as compared with those currently being used. I present, a new file storage system with variable size chunks, distributed chunk addressing, decentralized file allocation tables, spread deciphering key, randomly selected file servers, and fault tolerant chunk system.