Computer Engineering Commons^™

Training Machine Learning Agents In A 3d Game Engine, Diego Calderon

Computer Science and Computer Engineering Undergraduate Honors Theses

Artificial intelligence (AI) and video games benefit from each other. Games provide a challenging domain for testing learning algorithms, and AI provides a framework to designing and implementing intelligent behavior, which reinforces meaningful play. Medium and small studios, and independent game developers, have limited resources to design, implement, and maintain agents with reactive behavior. In this research, we trained agents using machine learning (ML), aiming to find an alternative to expensive traditional algorithms for intelligent behavior used in video games. We use Unity as a game engine to implement the environments and TensorFlow for the neural network training.

Enginews, May 2018, School Of Computer Science & Engineering

News, Magazines and Reports

Trial and Error: Adjusting to the MakerSpace --Looking Forward: Rube Goldberg Machine.

Building Data Visualization Applications To Facilitate Vehicular Networking Research, Noah Carter

Undergraduate Honors Theses

A web app was developed which allows any internet-connected device to remotely monitor a roadway intersection’s state over HTTP. A mapping simulation was enhanced to allow researchers to retroactively track the location and the ad-hoc connectivity of vehicle clusters. A performance analysis was conducted on the utilized network partitioning algorithm. This work was completed under and for the utility of ETSU’s Vehicular Networking Lab. It can serve as a basis for further development in the field of wireless automobile connectivity.

Wifi Gate Guard: A Captive Portal Implementation For Home Networks, Ben Blumenberg

Computer Science and Software Engineering

WiFi Gate Guard aims to improve the user experience for authentication on home wireless networks, by alleviating some of the hardships causes by passwords and by offering a platform on which further security enhancements could be built. It accomplishes this by using captive portal technology, making it extremely easy for guests to authenticate without needing to ask for a password. Home network administrators can approve or deny access using a simple iOS app. WiFi Gate Guard is built to run on basic home routers, with minimal other hardware requirements. Once it’s up and running, passwords never need to be used …

Assessing The Quality And Stability Of Recommender Systems, David Shriver

School of Computing: Dissertations, Theses, and Student Research

Recommender systems help users to find products they may like when lacking personal experience or facing an overwhelmingly large set of items. However, assessing the quality and stability of recommender systems can present challenges for developers. First, traditional accuracy metrics, such as precision and recall, for validating the quality of recommendations, offer only a coarse, one-dimensional view of the system performance. Second, assessing the stability of a recommender systems requires generating new data and retraining a system, which is expensive. In this work, we present two new approaches for assessing the quality and stability of recommender systems to address these …

Performance Evaluation Of V-Enodeb Using Virtualized Radio Resource Management, Sai Keerti Teja Boddepalli

School of Computing: Dissertations, Theses, and Student Research

With the demand upsurge for high bandwidth services, continuous increase in the number of cellular subscriptions, adoption of Internet of Things (IoT), and marked growth in Machine-to-Machine (M2M) traffic, there is great stress exerted on cellular network infrastructure. The present wireline and wireless networking technologies are rigid in nature and heavily hardware-dependent, as a result of which the process of infrastructure upgrade to keep up with future demand is cumbersome and expensive.

Software-defined networks (SDN) hold the promise to decrease network rigidity by providing central control and flow abstraction, which in current network setups are hardware-based. The embrace of SDN …

Digital Automatic Speech Recognition Using Kaldi, Sarah Habeeb Alyousefi

Theses and Dissertations

The Automatic speech recognition (ASR) system is one of most important technologies that used for human-machine interaction. The main goal of the ASR system is to recognize different natural languages that are spoken by humans. The difficulties of these recognition systems depend on many factors, such as noises, variability of the speakers, and problems of continuous speech. For that reason, many researchers and foundations have designed different kinds of licensed toolkits and software that are specialized in building speech recognition systems, including , Julius, Sphinx-4, RWTH ASR, and HTK toolkits. In this thesis, Kaldi toolkit, which is one of the …

A Proposed Approach To Hybrid Software-Hardware Application Design For Enhanced Application Performance, Alex Shipman

Graduate Theses and Dissertations

One important aspect of many commercial computer systems is their performance; therefore, system designers seek to improve the performance next-generation systems with respect to previous generations. This could mean improved computational performance, reduced power consumption leading to better battery life in mobile devices, smaller form factors, or improvements in many areas. In terms of increased system speed and computation performance, processor manufacturers have been able to increase the clock frequency of processors up to a point, but now it is more common to seek performance gains through increased parallelism (such as a processor having more processor cores on a single …

A Survey Of Three-Dimensional Sound And Its Applications, Andrew Topping

Capstone Projects and Master's Theses

This research project seeks to develop a foundation of knowledge about three-dimensional sound (3-D sound) and its utilization across various media. Topics covered include the techniques by which 3-D sound is accomplished, its departures from the standard paradigm of stereophonic audio, the range of creative and engineering considerations within 3-D contexts and examinations of existing 3-D audio applications.

Development Of The Codebase For Ece Design: Smartwatch Device And App For Continuous Glucose Monitoring, Keelin J. Becker-Wheeler

Honors Scholar Theses

This honors thesis describes the development of the codebase for the 2018 University of Connecticut ECE Senior Design project titled "Smartwatch Device and App for Continuous Glucose Monitoring''. The goal for the senior design project is to remove the dependencies imposed by a previously-designed prototype of a glucose-monitoring smartwatch, by creating a new custom device without those dependencies. Development of the new codebase involves splitting the tasks of an Arduino codebase into a number of logical components that are then implemented in C. This new codebase makes substantial improvements to the overall program structure and organization, as well as numerous …

Security Analysis Of The Uconn Husky One Card, Trevor Phillips

Honors Scholar Theses

The “Husky One Card” is the name given to student IDs at the University of Connecticut. It can identify students, faculty, and staff in a variety of situations. The One Card is used for meal plans, Husky Bucks (an equivalent of money, but valid only in the Storrs area), residence hall/ university facility access, and student health services. The current Husky One Card consists of a picture identification on the front and a standard 1-dimensional barcode and 3-track magnetic strip on the back.

The goal of this thesis is to investigate the feasibility of cloning Husky One Cards, the ease …

Handwritten Digit Recognition By Multi-Class Support Vector Machines, Yu Wang

Graduate Theses/Dissertations

Support Vector Machine(SVM) is a widely-used tool for pattern classification problems. The main idea behind SVM is to separate two different groups with a hyperplane which makes the margin of these two groups maximized. It doesn't require any knowledge about the object we are focused on, since it can catch the features automatically. The idea of SVM can be easily generalized to nonlinear model by a mapping from the original space to a high-dimensional feature space, and they construct a max-margin linear classifier in the high dimensional feature space.

This thesis will investigate the basic idea of SVM and apply …

Securing Soft Ips Against Hardware Trojan Insertion, Thao Phuong Le

Graduate Theses and Dissertations

Due to the increasing complexity of hardware designs, third-party hardware Intellectual Property (IP) blocks are often incorporated in order to alleviate the burden on hardware designers. However, the prevalence use of third-party IPs has raised security concerns such as Trojans inserted by attackers. Hardware Trojans in these soft IPs are extremely difficult to detect through functional testing and no single detection methodology has been able to completely address this issue. Based on a Register-Transfer Level (RTL) and gate-level soft IP analysis method named Structural Checking, this dissertation presents a hardware Trojan detection methodology and tool by detailing the implementation of …

Automatic Speech Recognition Adaptation For Various Noise Levels, Azhar Sabah Abdulaziz

Theses and Dissertations

The automatic speech recognition (ASR) is a set of complicated algorithms that convert the intended spoken utterance into a textual form. Acoustic features, which are extracted from the speech signal, are matched against a trained network of linguistic and acoustic models. The ASR performance is degraded significantly when the ambient noise is different than that of the training data. Many approaches have been introduced to address this problem with various degrees of complexity and improvement rates. The general pattern of solving this issue lies in three categories: empowering features, train a general acoustic model and transform models to match noisy …

An Empirical Study On The Recovery Speed Of Usb Flash Drives Utilizing Raid-5 Compared To Hdds And Ssds, Joshua Manuel Martins

Honors Theses

Since their creation and implementation, storage drives have undergone and continue to undergo drastic changes in speed, size, and reliability. The original storage drives, known as hard disk drives (HDDs), are constructed using moving parts. The second modern type of storage drives, known as solid state drives (SSDs), are constructed using a series of silicon chips that utilize no moving parts. The third and most recent innovation in storage drives, known as USB flash drives (USBs), use only a single silicon chip to provide storage which grants them the smallest form factor of the three drive types.

This study compared …

Consensus Ensemble Approaches Improve De Novo Transcriptome Assemblies, Adam Voshall

School of Computing: Dissertations, Theses, and Student Research

Accurate and comprehensive transcriptome assemblies lay the foundation for a range of analyses, such as differential gene expression analysis, metabolic pathway reconstruction, novel gene discovery, or metabolic flux analysis. With the arrival of next-generation sequencing technologies it has become possible to acquire the whole transcriptome data rapidly even from non-model organisms. However, the problem of accurately assembling the transcriptome for any given sample remains extremely challenging, especially in species with a high prevalence of recent gene or genome duplications, those with alternative splicing of transcripts, or those whose genomes are not well studied. This thesis provides a detailed overview of …

Application Of Cosine Similarity In Bioinformatics, Srikanth Maturu

School of Computing: Dissertations, Theses, and Student Research

Finding similar sequences to an input query sequence (DNA or proteins) from a sequence data set is an important problem in bioinformatics. It provides researchers an intuition of what could be related or how the search space can be reduced for further tasks. An exact brute-force nearest-neighbor algorithm used for this task has complexity O(m * n) where n is the database size and m is the query size. Such an algorithm faces time-complexity issues as the database and query sizes increase. Furthermore, the use of alignment-based similarity measures such as minimum edit distance adds an additional complexity to the …

Horse Racing Prediction Using Graph-Based Features., Mehmet Akif Gulum

Electronic Theses and Dissertations

This thesis presents an applied horse racing prediction using graph based features on a set of horse races data. We used artificial neural network and logistic regression models to train then test to prediction without graph based features and with graph based features. This thesis can be explained in 4 main parts. Collect data from a horse racing website held from 2015 to 2017. Train data to using predictive models and make a prediction. Create a global directed graph of horses and extract graph-based features (Core Part) . Add graph based features to basic features and train to using same …

Skill Builder: Assistive Technology For Developing Skill And Habits, Aaron Kay

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

The Skill Builder application is assistive technology for helping individuals build skills through reminders and self-reporting feedback. The application has been built to support Android and iOS devices and followed a user-centric design methodology. Skill Builder’s architecture and development processes are set forth using cross-platform development environments and a native software development kit for the three different versions of the application that were built. The strengths and weaknesses of each of the platforms are explored.

Several studies have been proposed for helping individuals with different needs learn the skills to cope with their challenges. Applications of Skill Builder include students …

Authentication Via Openathens: Implementing A Single Sign-On Solution For Primo, Alma, And Ezproxy, Travis Clamon

ETSU Faculty Works

OpenAthens is a hosted identity and access management service that provides a streamlined solution for implementing single sign-on authentication. This presentation will outline the steps East Tennessee State University took to configure OpenAthens authentication across the Alma, Primo, and EZproxy platforms. We will give a brief overview of the internal configurations related to LDAP integration, allocating electronic resources, and selectively assigning permissions. Finally, we will share our experiences with OpenAthens including support, vendor adoption, and end user benefits.

Machine Learning For Omics Data Analysis., Ameni Trabelsi

Electronic Theses and Dissertations

In proteomics and metabolomics, to quantify the changes of abundance levels of biomolecules in a biological system, multiple sample analysis steps are involved. The steps include mass spectrum deconvolution and peak list alignment. Each analysis step introduces a certain degree of technical variation in the abundance levels (i.e. peak areas) of those molecules. Some analysis steps introduce technical variations that affect the peak areas of all molecules equally while others affect the peak areas of a subset of molecules with varying degrees. To correct these technical variations, some existing normalization methods simply scale the peak areas of all molecules detected …

Maintainability Analysis Of Mining Trucks With Data Analytics., Abdulgani Kahraman

Electronic Theses and Dissertations

The mining industry is one of the biggest industries in need of a large budget, and current changes in global economic challenges force the industry to reduce its production expenses. One of the biggest expenditures is maintenance. Thanks to the data mining techniques, available historical records of machines’ alarms and signals might be used to predict machine failures. This is crucial because repairing machines after failures is not as efficient as utilizing predictive maintenance. In this case study, the reasons for failures seem to be related to the order of signals or alarms, called events, which come from trucks. The …

End-To-End Learning Framework For Circular Rna Classification From Other Long Non-Coding Rnas Using Multi-Modal Deep Learning., Mohamed Chaabane

Electronic Theses and Dissertations

Over the past two decades, a circular form of RNA (circular RNA) produced from splicing mechanism has become the focus of scientific studies due to its major role as a microRNA (miR) ac tivity modulator and its association with various diseases including cancer. Therefore, the detection of circular RNAs is a vital operation for continued comprehension of their biogenesis and purpose. Prediction of circular RNA can be achieved by first distinguishing non-coding RNAs from protein coding gene transcripts, separating short and long non-coding RNAs (lncRNAs), and finally pre dicting circular RNAs from other lncRNAs. However, available tools to distinguish circular …

Robust Fuzzy Clustering For Multiple Instance Regression., Mohamed Trabelsi

Electronic Theses and Dissertations

Multiple instance regression (MIR) operates on a collection of bags, where each bag contains multiple instances sharing an identical real-valued label. Only few instances, called primary instances, contribute to the bag labels. The remaining instances are noise and outliers observations. The goal in MIR is to identify the primary instances within each bag and learn a regression model that can predict the label of a previously unseen bag. In this thesis, we introduce an algorithm that uses robust fuzzy clustering with an appropriate distance to learn multiple linear models from a noisy feature space simultaneously. We show that fuzzy memberships …

A Framework For Cardio-Pulmonary Resuscitation (Cpr) Scene Retrieval From Medical Simulation Videos Based On Object And Activity Detection., Anju Panicker Madhusoodhanan Sathik

Electronic Theses and Dissertations

In this thesis, we propose a framework to detect and retrieve CPR activity scenes from medical simulation videos. Medical simulation is a modern training method for medical students, where an emergency patient condition is simulated on human-like mannequins and the students act upon. These simulation sessions are recorded by the physician, for later debriefing. With the increasing number of simulation videos, automatic detection and retrieval of specific scenes became necessary. The proposed framework for CPR scene retrieval, would eliminate the conventional approach of using shot detection and frame segmentation techniques. Firstly, our work explores the application of Histogram of Oriented …

Network Science Algorithms For Mobile Networks., Heba Mohamed Elgazzar

Electronic Theses and Dissertations

Network Science is one of the important and emerging fields in computer science and engineering that focuses on the study and analysis of different types of networks. The goal of this dissertation is to design and develop network science algorithms that can be used to study and analyze mobile networks. This can provide essential information and knowledge that can help mobile networks service providers to enhance the quality of the mobile services. We focus in this dissertation on the design and analysis of different network science techniques that can be used to analyze the dynamics of mobile networks. These techniques …

Wisdom Of Artificial Crowds Feature Selection In Untargeted Metabolomics: An Application To The Development Of A Blood-Based Diagnostic Test For Thrombotic Myocardial Infarction, Patrick J. Trainor, Roman V. Yampolskiy, Andrew P. Defilippis

Faculty and Staff Scholarship

Introduction: Heart disease remains a leading cause of global mortality. While acute myocardial infarction (colloquially: heart attack), has multiple proximate causes, proximate etiology cannot be determined by a blood-based diagnostic test. We enrolled a suitable patient cohort and conducted a non-targeted quantification of plasma metabolites by mass spectrometry for developing a test that can differentiate between thrombotic MI, non-thrombotic MI, and stable disease. A significant challenge in developing such a diagnostic test is solving the NP-hard problem of feature selection for constructing an optimal statistical classifier. Objective: We employed a Wisdom of Artificial Crowds (WoAC) strategy for solving the feature …

Asynchronous Circuit Stacking For Simplified Power Management, Andrew Lloyd Suchanek

Graduate Theses and Dissertations

As digital integrated circuits (ICs) continue to increase in complexity, new challenges arise for designers. Complex ICs are often designed by incorporating multiple power domains therefore requiring multiple voltage converters to produce the corresponding supply voltages. These converters not only take substantial on-chip layout area and/or off-chip space, but also aggregate the power loss during the voltage conversions that must occur fast enough to maintain the necessary power supplies. This dissertation work presents an asynchronous Multi-Threshold NULL Convention Logic (MTNCL) “stacked” circuit architecture that alleviates this problem by reducing the number of voltage converters needed to supply the voltage the …

Service Quality Assessment For Cloud-Based Distributed Data Services, Arun Adiththan

Dissertations, Theses, and Capstone Projects

The issue of less-than-100% reliability and trust-worthiness of third-party controlled cloud components (e.g., IaaS and SaaS components from different vendors) may lead to laxity in the QoS guarantees offered by a service-support system S to various applications. An example of S is a replicated data service to handle customer queries with fault-tolerance and performance goals. QoS laxity (i.e., SLA violations) may be inadvertent: say, due to the inability of system designers to model the impact of sub-system behaviors onto a deliverable QoS. Sometimes, QoS laxity may even be intentional: say, to reap revenue-oriented benefits by cheating on resource allocations and/or …

Critical-Point Model Dielectric Function Analysis Of Wo3 Thin Films Deposited By Atomic Layer Deposition Techniques, Ufuk Kılıç, Derek Sekora, Alyssa Mock, Rafał Korlacki, Elena M. Echeverría, Natale J. Ianno, Eva Schubert, Mathias Schubert

Department of Electrical and Computer Engineering: Faculty Publications

WO₃ thin films were grown by atomic layer deposition and spectroscopic ellipsometry data gathered in the photon energy range of 0.72-8.5 eV and from multiple samples was utilized to determine the frequency dependent complex-valued isotropic dielectric function for WO₃. We employ a critical-point model dielectric function analysis and determine a parameterized set of oscillators and compare the observed critical-point contributions with the vertical transition energy distribution found within the band structure of WO₃ calculated by density functional theory. We investigate surface roughness with atomic force microscopy and compare to ellipsometric determined effective roughness layer thickness.