Recent Submissions

  • EVALUATING SHORT-WAVE INFRARED IMAGES ON A CONVOLUTIONAL NEURAL NETWORK 

    Contributor:Bihn, Michael Joseph;
    Date Submitted:2017-12
    Machine learning algorithms, both neural networks and non neural networks, have been tested against RGB facial images for years. Their success is dependent on clearly distinguishable cropped faces. Poor lighting and distance ...
  • Enhancing the Bootstrapping Network in Cloud-based Onion Routing (COR) 

    Contributor:Snider, Kevin;
    Date Submitted:2017-12
    The maintenance of privacy and anonymity on the Internet has become a large concern for many users worldwide. The online service known as Tor (The Onion Router) is one of the most popular tools available to users seeking ...
  • Travel Plan Generator 

    Contributor:Shao, Likun;
    Date Submitted:2017-12
    Travelers usually have their customized travel plans before starting their trips. A good travel plan can make them convenient to arrange their trips and make trips well organized. In order to customize personal travel ...
  • FULLY HOMOMORPHIC ENCRYPTION OVER EXTERIOR PRODUCT SPACES 

    Contributor:Honorio Araujo da Silva, David William;
    Date Submitted:2017-12
    In this work I propose a new symmetric fully homomorphic encryption powered by Exterior Algebra and Product Spaces, more specifically by Geometric Algebra as a mathematical language for creating cryptographic solutions, ...
  • Autoregressive Density Estimation in Latent Spaces 

    Contributor:Olmo Hernández, Alberto;
    Date Submitted:2017-12
    We propose an extension of recent autoregressive density estimation approaches such as PixelCNN and WaveNet that models the density of a latent variable space rather than the output space. In other words, we propose a ...
  • NEURAL NETWORKS FOR HUMAN CELL DETECTION AND COUNTING 

    Contributor:Valdivieso Tamayo, Natalia;
    Date Submitted:2017-12
    In this work, we present a method to count and detect the position of breast cancer cells and bone marrow human cells using a Convolutional Neural Network (CNN). We compare our F1-results against state-of-the-art results ...
  • Improving Techniques for SQL Injection Defenses 

    Contributor:Kilaru, Divya;
    Date Submitted:2017-12
    In this thesis, we investigate how SQL injection attacks occur and how to patch a web app with the SQL injection vulnerability. Various SQL injection tools are evaluated for their functionalities and capabilities. A python ...
  • Dual Marching Squares: Implementation and Analysis Using VTK 

    Contributor:Garg, Manu;
    Date Submitted:2017-12
    ABSTRACT In the past few decades’ volume rendering is perhaps one of the most visited research topics in the field of scientific visualization. Since volume datasets are large and require considerable computing power to ...
  • Detection And Analysis Of Software Clones 

    Contributor:Sheneamer, Abdullah Mohammad;
    Date Submitted:2017-08
    Effective detection of code clones is important for software maintenance. Code clones introduce difficulty in software maintenance and lead to bug propagation. Detection of duplicated bugs within a piece of software is ...
  • CONTINUOUS AUTHENTICATION OF SMARTPHONE OWNERS BASED ON APP ACCESS BEHAVIOR 

    Contributor:Alzubaidi, Abdulaziz Ali;
    Date Submitted:2017-08
    In recent years, smartphone use has become ubiquitous. The number of the applications on these devices has increased tremendously, leading to an increase in potential threats to the personal accounts of smartphone owners. ...
  • Cloud based Web Resilience using Node.js 

    Contributor:Gunnam, Pragati;
    Date Submitted:2017-08
    Web services are used almost everyday and for everything. Combining these with cloud based services would allow the web applications to become more available for the users. Delivering such cloud based web applications to ...
  • Optimizing Pedestrian Flow In Airports 

    Contributor:Jordan, Gabriel;
    Date Submitted:2017-05
    Denver International Airport has expressed interest in discovering innovative techniques to optimize pedestrian flow in its massive airport which contains upwards of 53 million passengers each year that travel through the ...
  • ENSEMBLE LEARNING FOR MULTIPLE DATA MINING PROBLEMS 

    Contributor:Doan, Tri Si;
    Date Submitted:2017-05
    Data mining practitioners often face problems of the unavailability of all training data at the same time and the inability to process a large amount of data due to constraints such as lack of adequate system memory. ...
  • Enhancing and Evaluating Global Pairwise Alignment of Protein-Protein Interaction Networks 

    Contributor:Elmsallati, Ahed Ashur;
    Date Submitted:2017-05
    Network Alignment over graph-structured data has recently received considerable attention in many application domains. Global network alignment tries to uniquely find the best mapping for a node in one network to only one ...
  • BETTER LEARNING THROUGH IMPROVED DISTRIBUTIONAL MODELING 

    Contributor:Rudd, Ethan McAvoy;
    Date Submitted:2017-05
    With the 21st century well underway, machine learning algorithms have advanced considerably in the ability to tackle difficult recognition problems. However, machine recognition is still rife with challenges, some of which ...
  • Advancing Fingerprint-Enhanced Authentication: Consistent, Discerning, and Durable Representation and Matching 

    Contributor:Alsaadi, Fawaz;
    Date Submitted:2017-05
    Throughout human history, the achievement of security through authentication has been filled with challenges. Technological evolution has created an unprecedented conjunction of scale and artifice that have turned our ...
  • Deep Learning For Brain Tumor Segmentation 

    Contributor:Moreno Lopez, Marc;
    Date Submitted:2017-05
    In this work, we present a novel method to segment brain tumors using deep learning. An accurate brain tumor segmentation is key for a patient to get the right treatment and for the doctor who must perform surgery. Due to ...
  • The Network Certification Description Language 

    Contributor:Hanson, Cody Lawrence;
    Date Submitted:2017-05
    Modern IP networks are complex entities that require constant maintenance and care. Similarly, constructing a new network comes with a high amount of upfront cost, planning, and risk. Unlike the disciplines of software ...
  • LexBank: A Multilingual Lexical Resource for Low-Resource Languages 

    Contributor:AL Tarouti, FERAS ALI;
    Date Submitted:2016-08
    In this dissertation, we present new methods to create essential lexical resources for low-resource languages. Specifically, we develop methods for enhancing automatically created wordnets. As a baseline, we start by ...
  • Towards Community Cloud Trustworthiness 

    Contributor:Alotaibi, Ahad;
    Date Submitted:2016-08
    Alotaibi, Ahad Saad (M.S, Computer science) Towards Community Cloud Trustworthiness Thesis directed by Associate Professor Edward Chow. In this thesis we presented an authorization system for community cloud. We ...

View more