Computer Sciences Commons^™

Using Structural And Semantic Methodologies To Enhance Biomedical Terminologies, Zhe He

Dissertations

Biomedical terminologies and ontologies underlie various Health Information Systems (HISs), Electronic Health Record (EHR) Systems, Health Information Exchanges (HIEs) and health administrative systems. Moreover, the proliferation of interdisciplinary research efforts in the biomedical field is fueling the need to overcome terminological barriers when integrating knowledge from different fields into a unified research project. Therefore well-developed and well-maintained terminologies are in high demand. Most of the biomedical terminologies are large and complex, which makes it impossible for human experts to manually detect and correct all errors and inconsistencies. Automated and semi-automated Quality Assurance methodologies that focus on areas that are more …

Vehicle Re-Routing Strategies For Congestion Avoidance, Juan Pan

Dissertations

Traffic congestion causes driver frustration and costs billions of dollars annually in lost time and fuel consumption. This dissertation introduces a cost-effective and easily deployable vehicular re-routing system that reduces the effects of traffic congestion. The system collects real-time traffic data from vehicles and road-side sensors, and computes proactive, individually tailored re-routing guidance, which is pushed to vehicles when signs of congestion are observed on their routes. Subsequently, this dissertation proposes and evaluates two classes of re-routing strategies designed to be incorporated into this system, namely, Single Shortest Path strategies and Multiple Shortest Paths Strategies.

These strategies are firstly implemented …

Svmaud: Using Textual Information To Predict The Audience Level Of Written Works Using Support Vector Machines, Todd Will

Dissertations

Information retrieval systems should seek to match resources with the reading ability of the individual user; similarly, an author must choose vocabulary and sentence structures appropriate for his or her audience. Traditional readability formulas, including the popular Flesch-Kincaid Reading Age and the Dale-Chall Reading Ease Score, rely on numerical representations of text characteristics, including syllable counts and sentence lengths, to suggest audience level of resources. However, the author’s chosen vocabulary, sentence structure, and even the page formatting can alter the predicted audience level by several levels, especially in the case of digital library resources. For these reasons, the performance of …

Automatic Image Correspondence For Video Clips, Adam Helps, Dr. Thomas Sederberg

Journal of Undergraduate Research

Image correspondence is a powerful method for matching features in two images. It has a wide variety of applications, and can be used to automatically perform complex image manipulation tasks that have previously been done by hand. In this research, image correspondence has been used to manipulate video clips, including morphing and slow motion techniques.

Interactive, Three-Dimensional Web Presentation Of Object-Oriented Java Concepts, Robert Franklin, Dr. Robert Burton

Journal of Undergraduate Research

The advent and subsequent widespread use of the Internet have facilitated and motivated hypermedia distance learning.

Memory-Guided Exploration In Reinforcement Learning, James L. Carroll, Todd Peterson

Journal of Undergraduate Research

Traditional reinforcement learning techniques learn a single task by giving the agent positive and negative rewards. In one type of reinforcement learning, called Q-learning, the agent stores Qvalues, which are the expected reward for performing an action in a given state. Task transfer is a method of transferring information learned in one task to another related task. Most work in transfer has focused on classification techniques. The purpose of our research has been to extend classification techniques to reinforcement learning.

Image Tile Compression For Interactive Terrain Visualization With A Slow Network Connection, Brandon Lloyd, Dr. Parris K. Egbert

Journal of Undergraduate Research

In the 3D graphics lab at BYU we have developed a terrain visualization program called DVIEW capable of handling extremely large datasets. Our largest model is a piece of the Wasatch front nearly 100 miles long and 50 miles wide. The original vision for DVIEW was to provide users with fast internet connections with the opportunity to navigate the model on their home PCs. We have developed methods in the lab that make it possible to render the model at interactive frame rates with commodity hardware. Unfortunately, only a fast network connection can handle the enormous amount of data that …

Extraction Of Genealogical Information From The Internet, Troy Walker, Dr. David Embley

Journal of Undergraduate Research

Data extraction is a rapidly growing area of computer science. It focuses on the extraction of pertinent data from large stores of knowledge such as databases or the internet. Data extraction allows us to use existing stores of data in new ways. One application for data extraction is genealogical research. Various commercial and non-profit groups make genealogical data available on line. In addition to these, hundreds of personal web pages contain personal family trees. I wanted to enable the extraction of information from these sources by computer. BYU’s Data Extraction Group (DEG) has developed tools for extracting data from web …

Image Compression Using Triangular Meshes, G. Thomas Finnigan, Dr. Thomas W. Sederberg

Journal of Undergraduate Research

Image Compression is a way of decreasing the amount of space needed to store or transmit an image by removing redundant information. In many ways, compression it like folding clothing – the result takes up less space, but it not immediately usable. Compressing an image means that it is cheaper to store, and faster to transmit, but may take more time to compress and decompress. The best compression methods compress and decompress quickly, but offer a significant savings in the size of the file.

Comparison Of Different Differential Expression Analysis Tools For Rna-Seq Data, Junfei Zhu

Theses

In molecular biology research, RNA-seq is a relatively new method for transcriptome profiling. It utilizes the next generation sequencing technology to provide huge amount information about the variety and abundance of RNA present in an organism of interest at a specific state and a given time. One of the most important tasks of RNA-seq analysis is finding genes that are expressed differently in different subject groups. A lot of differential expression analysis tools for RNA-seq have been developed, but there is no golden standard in this field. In this research, four commonly used tools (DESeq, edgeR, limma, and cuffdiff) are …

Providing Flexible File-Level Data Filtering For Big Data Analytics, Lei Xu, Ziling Huang, Hong Jiang, Lei Tian, David Swanson

School of Computing: Technical Reports

The enormous amount of big data datasets impose the needs for effective data filtering technique to accelerate the analytics process. We propose a Versatile Searchable File System, VSFS, which provides a transparent, flexible and near real-time file-level data filtering service by searching files directly through the file system. Therefore, big data analytics applications can transparently utilize this filtering service without application modifications. A versatile index scheme is designed to adapt to the exploratory and ad-hoc nature of the big data analytics activities. Moreover, VSFS uses a RAM-based distributed architecture to perform file indexing. The evaluations driven by three real-world analytics …

Human-Robot Interface Design, Jacob W. Crandall, Dr. Michael A. Goodrich

Journal of Undergraduate Research

Over the last few years, there have been vast advancements in robot technology. These advancements have made robots more powerful. However, because of robot limitations, many interesting tasks will probably include humans and robots cooperating to achieve a shared goal. Lessons from process automation indicate that, in many instances, increased machine automation can actually decreased the effectiveness of human operators. This lesson tells robot designers that robots must be designed with human factors in mind. Situations arise where “artificial intelligence” isn’t sufficient and human reasoning can significantly improve performance.

Hybrid Radial Basis Functions For Image Representation, Samuel Payne, Dr. Bryan Morse

Journal of Undergraduate Research

My ORCA research topic was 3D shape representation. I proposed research to develop a new method for representing surfaces that combined two current methods. The oldest method (thinplate spline model) was developed by Turk and O’Brien in 1998. The second method (compactly supported RBF) was developed by my mentor, Bryan Morse in May 2001. These methods have complimenting strengths and weaknesses. Therefore I planned to hybridize these two methods to preserve the strengths in both, and thus overcome their respective weakness.

Agent Decompositions In Reinforcement Learning Architectures, Nancy Owens Fulda, Todd Peterson

Journal of Undergraduate Research

Reinforcement learning is a sub-discipline of machine learning in which an autonomous program, called an agent, learns to behave appropriately in its environment. Appropriate behavior is described in terms of numerical reinforcements which the agent receives for appropriate or inappropriate actions. By storing a running average of the reinforcements received for given actions in given situations, the agent learns which behaviors are most desirable.

Reinforcement Learning Task Clustering, James Carroll, Todd Peterson

Journal of Undergraduate Research

Reinforcement Learning is a process whereby actions are acquired using reinforcement signals. A signal is given to an autonomous agent indicating how well that agent is performing an action. The agent then attempts to maximize this reinforcement signal. One common method in reinforcement learning is Q-learning where the agent attempts to learn the expected temporally discounted value function for performing an action a in a state s Q(s,a). This function is updated according to:

Ivus Validation Of Patient Coronary Artery Lumen Area Obtained From Ct Images, Tong Luo, Thomas Wischgoll, Bon Kwon Koo, Yunlong Huo, Ghassan S. Kassab

Computer Science and Engineering Faculty Publications

Aims

Accurate computed tomography (CT)-based reconstruction of coronary morphometry (diameters, length, bifurcation angles) is important for construction of patient-specific models to aid diagnosis and therapy. The objective of this study is to validate the accuracy of patient coronary artery lumen area obtained from CT images based on intravascular ultrasound (IVUS).

Methods and Results

Morphometric data of 5 patient CT scans with 11 arteries from IVUS were reconstructed including the lumen cross sectional area (CSA), diameter and length. The volumetric data from CT images were analyzed at sub-pixel accuracy to obtain accurate vessel center lines and CSA. A new center line …

Information Technology Benchmarking Survey Of Institutions Of Higher Education, Alan P. Hyatt, Dr. Eric L. Denna

Journal of Undergraduate Research

In the realm of higher education, learning is continually facilitated, enhanced, and improved through technology. At Brigham Young University, the summary mission of the Office of Information Technology is to support the mission and objectives of the Church Educational System and its operating units by acquiring, creating, organizing, and making available tools that (1) enhance student learning, faculty teaching, and scholarship, and (2) improve the key decision and administrative processes of the BYU entities.

Improved Hyperweb Search Efficiency Through Index Replication, Jared Holcomb, Dr. Scott Woodfield

Journal of Undergraduate Research

The hyperweb is a network based on a modified hypercube1 topology. It is used to create a peerto- peer network for a distributed database (such as a genealogical database.) Two major drawbacks that a peer-to-peer network suffers are a low reliability rate for individual nodes and a slower search speed as the system grows. Both of these problems can be addressed by replicating data across several nodes. First, any particular node has a relatively high probability of being down so a copy of the information a node contains is stored on several other nodes, thereby decreasing the total probability of …

Using Haptics To Assist Automobile Drivers, Kevin Alejandro Roundy, Dr. Michael A. Goodrich

Journal of Undergraduate Research

The purpose of this research project was to further Nissan Motor Company’s research in technologies designed to improve driver comfort and safety.

Wireless Network Signal Analysis, Nathan P. Sharp, Dr. Mark E. Clement

Journal of Undergraduate Research

The process of measuring wireless signal strength for networks can be complex and subjective. There is no “tried and true” way of determining the best layout for a network, but with some fairly simple analysis, much can be done to improve the performance of the network. Empirical data shows how much different materials inhibit the signal (see Fig. 1-3 below). For example, in an office setting, determining if brick walls or cubical walls are more penetrable will be very useful when laying out a wireless network.

Learning General Features From Images And Audio With Stacked Denoising Autoencoders, Nathaniel H. Nifong

Dissertations and Theses

One of the most impressive qualities of the brain is its neuro-plasticity. The neocortex has roughly the same structure throughout its whole surface, yet it is involved in a variety of different tasks from vision to motor control, and regions which once performed one task can learn to perform another. Machine learning algorithms which aim to be plausible models of the neocortex should also display this plasticity. One such candidate is the stacked denoising autoencoder (SDA). SDA's have shown promising results in the field of machine perception where they have been used to learn abstract features from unlabeled data. In …

Optimizing Ad-Hoc On-Demand Distance Vector (Aodv) Routing Protocol Using Geographical Location Data, Remo Cocco

Theses and Dissertations

This thesis summarizes the body of research regarding location-aided routing protocols for mobile ad-hoc networks (MANET). This study focuses on the use of geographical location information to reduce the control traffic overhead caused by the route discovery process in the ad-hoc on-demand distance vector (AODV) routing protocol. During this process, AODV will flood the entire network with route request packets. This introduces significant packet-handling overhead into the network. This thesis introduces Geographical AODV (GeoAODV), which uses geographical location information to limit the search area during the route discovery process to include only promising search paths. Also, this thesis benchmarks GeoAODV's …

Scene-Dependent Human Intention Recognition For An Assistive Robotic System, Kester Duncan

USF Tampa Graduate Theses and Dissertations

In order for assistive robots to collaborate effectively with humans for completing everyday tasks, they must be endowed with the ability to effectively perceive scenes and more importantly, recognize human intentions. As a result, we present in this dissertation a novel scene-dependent human-robot collaborative system capable of recognizing and learning human intentions based on scene objects, the actions that can be performed on them, and human interaction history. The aim of this system is to reduce the amount of human interactions necessary for communicating tasks to a robot. Accordingly, the system is partitioned into scene understanding and intention recognition modules. …

Parallel Programming With Migratable Objects: Charm++ In Practice, Bilge Acun, Abhishek Gupta, Nikhil Jain, Akhil Langer, Harshitha Menon, Eric Mikida, Xiang Ni, Michael Robson, Yanhua Sun, Ehsan Totoni, Lukasz Wesolowski, Laxmikant Kale

Computer Science: Faculty Publications

The advent of petascale computing has introduced new challenges (e.g. Heterogeneity, system failure) for programming scalable parallel applications. Increased complexity and dynamism in science and engineering applications of today have further exacerbated the situation. Addressing these challenges requires more emphasis on concepts that were previously of secondary importance, including migratability, adaptivity, and runtime system introspection. In this paper, we leverage our experience with these concepts to demonstrate their applicability and efficacy for real world applications. Using the CHARM++ parallel programming framework, we present details on how these concepts can lead to development of applications that scale irrespective of the rough …

Model-Free Q-Learning Over Finite Horizon For Uncertain Linear Continuous-Time Systems, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, a novel optimal control over finite horizon has been introduced for linear continuous-time systems by using adaptive dynamic programming (ADP). First, a new time-varying Q-function parameterization and its estimator are introduced. Subsequently, Q-function estimator is tuned online by using both Bellman equation in integral form and terminal cost. Eventually, near optimal control gain is obtained by using the Q-function estimator. All the closed-loop signals are shown to be bounded by using Lyapunov stability analysis where bounds are functions of initial conditions and final time while the estimated control signal converges close to the optimal value. The simulation …

Event-Based Optimal Regulator Design For Nonlinear Networked Control Systems, Avimanyu Sahoo, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a novel stochastic event-based near optimal control strategy to regulate a networked control system (NCS) represented as an uncertain nonlinear continuous time system. An online stochastic actor-critic neural network (NN) based approach is utilized to achieve the near optimal regulation in the presence of network constraints, such as, network induced time-varying delays and random packet losses under event-based transmission of the feedback signals. The transformed nonlinear NCS in discrete-time after the incorporation the delays and packet losses are utilized for the actor-critic NN based controller design. To relax the knowledge of the control coefficient matrix, a NN …

Neural Network-Based Adaptive Optimal Consensus Control Of Leaderless Networked Mobile Robots, Haci Mehmet Guzey, Hao Xu, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

A novel neural network (NN)-based optimal adaptive consensus control scheme is introduced in this paper for networked mobile robots in the presence of unknown robot dynamics. Throughout the paper, two NNs are used. The unknown formation dynamics of each robot is identified by using the first NN. The second NN is utilized to approximate a novel value function derived in this paper as a function of augmented error vector, which is comprised of the regulation and consensus-based formation errors of each robot. A novel near optimal controller is developed by using approximated value function and identified formation dynamics. The Lyapunov …

Rethinking Fs-Isac: An It Security Information Sharing Network Model For The Financial Services Sector, Charles Zhechao Liu, Humayun Zafar, Yoris A. Au

Faculty Articles

This study examines a critical incentive alignment issue facing FS-ISAC (the information sharing alliance in the financial services industry). Failure to encourage members to share their IT security-related information has seriously undermined the founding rationale of FS-ISAC. Our analysis shows that many information sharing alliances’ membership policies are plagued with the incentive misalignment issue and may result in a “free-riding” or “no information sharing” equilibrium. To address this issue, we propose a new information sharing membership policy that incorporates an insurance option and show that the proposed policy can align members’ incentives and lead to a socially optimal outcome. Moreover, …

Hardware Components In Cybersecurity Education, Dan Chia-Tien Lo, Max North, Sarah North

Faculty Articles

Hardware components have been designated as required academic content for colleges to be recognized as a center of academic excellence in cyber operations by the National Security Agency (NSA). To meet the hardware requirement, computer science and information technology programs must cover hardware concepts and design skills, topics which are less emphasized in existing programs. This paper describes a new pedagogical model for hardware based on network intrusion detection taught at college and graduate levels in a National Center of Academic Excellence in Information Assurance Education Program (CAE/IAE). The curriculum focuses on the fundamental concepts of network intrusion detection mechanisms, …

Parameter Synthesis For Hierarchical Concurrent Real-Time Systems, Étienne André, Yang Liu, Jun Sun, Jin Song Dong

Research Collection School Of Computing and Information Systems

Modeling and verifying complex real-time systems, involving timing delays, are notoriously difficult problems. Checking the correctness of a system for one particular value for each delay does not give any information for other values. It is thus interesting to reason parametrically, by considering that the delays are parameters (unknown constants) and synthesizing a constraint guaranteeing a correct behavior. We present here Parametric Stateful Timed Communicating Sequential Processes, a language capable of specifying and verifying parametric hierarchical real-time systems with complex data structures. Although we prove that the synthesis is undecidable in general, we present several semi-algorithms for efficient parameter synthesis, …