Engineering Commons^™

Investigating Semantic Properties Of Images Generated From Natural Language Using Neural Networks, Samuel Ward Schrader

Boise State University Theses and Dissertations

This work explores the attributes, properties, and potential uses of generative neural networks within the realm of encoding semantics. It works toward answering the questions of: If one uses generative neural networks to create a picture based on natural language, does the resultant picture encode the text's semantics in a way a computer system can process? Could such a system be more precise than current solutions at detecting, measuring, or comparing semantic properties of generated images, and thus their source text, or their source semantics?

This work is undertaken in the hope that detecting previously unknown properties, or better understanding …

Incremental Processing For Improving Conversational Grounding In A Chatbot, Aprajita Shukla

Boise State University Theses and Dissertations

Current Digital Personal Assistants can be quite efficient while performing routine tasks like setting up reminders and looking up information. However, they do not attempt to establish common ground–the process of establishing and building mutual understanding–and require a significant amount of initial data to learn how to understand user intent. In this thesis, an incremental processing framework is leveraged through a chatbot interface which updates its understanding state at each inputted word, asks the user to clarify input when the system is unsure and prompts user to give feedback several times during an interaction, all of which are instrumental in …

Minos: Unsupervised Netflow-Based Detection Of Infected And Attacked Hosts, And Attack Time In Large Networks, Mousume Bhowmick

Boise State University Theses and Dissertations

Monitoring large-scale networks for malicious activities is increasingly challenging: the amount and heterogeneity of traffic hinder the manual definition of IDS signatures and deep packet inspection. In this thesis, we propose MINOS, a novel fully unsupervised approach that generates an anomaly score for each host allowing us to classify with high accuracy each host as either infected (generating malicious activities), attacked (under attack), or clean (without any infection). The generated score of each hour is able to detect the time frame of being attacked for an infected or attacked host without any prior knowledge. MINOS automatically creates a personalized traffic …

Cognitive Satellite Communications And Representation Learning For Streaming And Complex Graphs., Wenqi Liu

Electronic Theses and Dissertations

This dissertation includes two topics. The first topic studies a promising dynamic spectrum access algorithm (DSA) that improves the throughput of satellite communication (SATCOM) under the uncertainty. The other topic investigates distributed representation learning for streaming and complex networks. DSA allows a secondary user to access the spectrum that are not occupied by primary users. However, uncertainty in SATCOM causes more spectrum sensing errors. In this dissertation, the uncertainty has been addressed by formulating a DSA decision-making process as a Partially Observable Markov Decision Process (POMDP) model to optimally determine which channels to sense and access. Large-scale networks have attracted …

An Explainable Recommender System Based On Semantically-Aware Matrix Factorization., Mohammed Sanad Alshammari

Electronic Theses and Dissertations

Collaborative Filtering techniques provide the ability to handle big and sparse data to predict the ratings for unseen items with high accuracy. Matrix factorization is an accurate collaborative filtering method used to predict user preferences. However, it is a black box system that recommends items to users without being able to explain why. This is due to the type of information these systems use to build models. Although rich in information, user ratings do not adequately satisfy the need for explanation in certain domains. White box systems, in contrast, can, by nature, easily generate explanations. However, their predictions are less …

Formally Designing And Implementing Cyber Security Mechanisms In Industrial Control Networks., Mehdi Sabraoui

Electronic Theses and Dissertations

This dissertation describes progress in the state-of-the-art for developing and deploying formally verified cyber security devices in industrial control networks. It begins by detailing the unique struggles that are faced in industrial control networks and why concepts and technologies developed for securing traditional networks might not be appropriate. It uses these unique struggles and examples of contemporary cyber-attacks targeting control systems to argue that progress in securing control systems is best met with formal verification of systems, their specifications, and their security properties. This dissertation then presents a development process and identifies two technologies, TLA+ and seL4, that can be …

Predicting Critical Warps In Near-Threshold Gpgpu Applications Using A Dynamic Choke Point Analysis, Sourav Sanyal

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

General purpose graphics processing units (GP-GPU), owing to their enormous thread-level parallelism, can significantly improve the power consumption at the near-threshold (NTC) operating region, while offering close to a super-threshold performance. However, process variation (PV) can drastically reduce the GPU performance at NTC. In this work, choke points—a unique device-level characteristic of PV at NTC—that can exacerbate the warp criticality problem in GPUs have been explored. It is shown that the modern warp schedulers cannot tackle the choke point induced critical warps in an NTC GPU. Additionally, Choke Point Aware Warp Speculator, a circuit-architectural solution is proposed to dynamically …

Stamina: Stochastic Approximate Model-Checker For Infinite-State Analysis, Thakur Neupane

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Reliable operation of every day use computing system, from simple coffee machines to complex flight controller system in an aircraft, is necessary to save time, money, and in some cases lives. System testing can check for the presence of unwanted execution but cannot guarantee the absence of such. Probabilistic model checking techniques have demonstrated significant potential in verifying performance and reliability of various systems whose execution are defined with likelihood. However, its inability to scale limits its applicability in practice.

This thesis presents a new model checker, STAMINA, with efficient and scalable model truncation for probabilistic verification. STAMINA uses a …

A Simulation Tool For Evaluating The Environmental Impacts Of Management Scenarios For Modern Broiler Production Systems, Martin Andrew Christie

Graduate Theses and Dissertations

The purpose of this work is to provide a simulation tool that allows broiler production practitioners and researchers to simulate the effects of farm design and management practices on resource consumption and environmental impacts. This tool allows the user to design unique farms and simulates on farm processes required to raise broiler chicks to a marketable age. The use can input data such as farm location, broiler breed, flock size, ration type, barn dimensions, and climate control equipment specifications. The algorithms used to simulate broiler breed specific feed intake, broiler weight gain, and other on farm processes such as heating, …

Adaptation Of A Deep Learning Algorithm For Traffic Sign Detection, Jose Luis Masache Narvaez

Electronic Thesis and Dissertation Repository

Traffic signs detection is becoming increasingly important as various approaches for automation using computer vision are becoming widely used in the industry. Typical applications include autonomous driving systems, mapping and cataloging traffic signs by municipalities. Convolutional neural networks (CNNs) have shown state of the art performances in classification tasks, and as a result, object detection algorithms based on CNNs have become popular in computer vision tasks. Two-stage detection algorithms like region proposal methods (R-CNN and Faster R-CNN) have better performance in terms of localization and recognition accuracy. However, these methods require high computational power for training and inference that make …

An Efficient Multiple-Place Foraging Algorithm For Scalable Robot Swarms, Qi Lu

Computer Science ETDs

Searching and collecting multiple resources from large unmapped environments is an important challenge. It is particularly difficult given limited time, a large search area and incomplete data about the environment. This search task is an abstraction of many real-world applications such as search and rescue, hazardous material clean-up, and space exploration. The collective foraging behavior of robot swarms is an effective approach for this task. In our work, individual robots have limited sensing and communication range (like ants), but they are organized and work together to complete foraging tasks collectively. An efficient foraging algorithm coordinates robots to search and collect …

Design Of A Canine Inspired Quadruped Robot As A Platform For Synthetic Neural Network Control, Cody Warren Scharzenberger

Dissertations and Theses

Legged locomotion is a feat ubiquitous throughout the animal kingdom, but modern robots still fall far short of similar achievements. This paper presents the design of a canine-inspired quadruped robot named DoggyDeux as a platform for synthetic neural network (SNN) research that may be one avenue for robots to attain animal-like agility and adaptability. DoggyDeux features a fully 3D printed frame, 24 braided pneumatic actuators (BPAs) that drive four 3-DOF limbs in antagonistic extensor-flexor pairs, and an electrical system that allows it to respond to commands from a SNN comprised of central pattern generators (CPGs). Compared to the previous version …

Large Scale Electronic Health Record Data And Echocardiography Video Analysis For Mortality Risk Prediction, Alvaro Emilio Ulloa Cerna

Electrical and Computer Engineering ETDs

Electronic health records contain the clinical history of patients. The enormous potential for discovery in such a rich dataset is hampered by their complexity. We hypothesize that machine learning models trained on EHR data can predict future clinical events significantly better than current models. We analyze an EHR database of 594,862 Echocardiography studies from 272,280 unique patients with both unsupervised and supervised machine learning techniques.

In the unsupervised approach, we first develop a simulation framework to evaluate a family of different clustering pipelines. We apply the optimized approach to 41,645 patients with heart failure without providing any survival information to …

Nonlinear Attitude And Pose Filters With Superior Convergence Properties, Hashim Abdellah Hashim Mohamed

Electronic Thesis and Dissertation Repository

In this thesis, several deterministic and stochastic attitude filtering solutions on the special orthogonal group SO(3) are proposed. Firstly, the attitude estimation problem is approached on the basis of nonlinear deterministic filters on SO(3) with guaranteed transient and steady-state measures. The second solution to the attitude estimation problem considers nonlinear stochastic filters on SO(3) with superior convergence properties with two filters being developed in the sense of Ito, and one in the sense of Stratonovich.

This thesis also presents several deterministic and stochastic pose filtering solutions developed on the special Euclidean group SE(3). The first solution includes two nonlinear deterministic …

Developing 5gl Concepts From User Interactions, David Stuckless Meyer

Masters Theses

In the fulfilling of the contracts generated in Test Driven Development, a developer could be said to act as a constraint solver, similar to those used by a 5th Generation Language(5GL). This thesis presents the hypothesis that 5GL linguistic mechanics, such as facts, rules and goals, will be emergent in the communications of developer pairs performing Test Driven Development, validating that 5GL syntax is congruent with the ways that practitioners communicate. Along the way, nomenclatures and linguistic patterns may be observed that could inform the design of future 5GL languages.

Survival Theory Modelling For Information Diffusion, Akshay Aravamudan

Theses and Dissertations

Information diffusion is the spread of information within a network. In this thesis, we model information diffusion as a survival process. We have adopted an existing algorithm called NetRate for modelling information diffusion. This model involves finding the distribution of trasmission time between two nodes in the network. We modify NetRate’s concave-down log-likelihood expression by adding partial parentage information and formulate an Expectation-Minimization (EM) algorithm to learn the parameters. We also describe a simulation scheme for NetRate inspired by point process simulation strategies. Using the assumptions of the NetRate model, we derive a a method to model popularity as a …

Large-Scale Data Analysis And Deep Learning Using Distributed Cyberinfrastructures And High Performance Computing, Richard Dodge Platania

LSU Doctoral Dissertations

Data in many research fields continues to grow in both size and complexity. For instance, recent technological advances have caused an increased throughput in data in various biological-related endeavors, such as DNA sequencing, molecular simulations, and medical imaging. In addition, the variance in the types of data (textual, signal, image, etc.) adds an additional complexity in analyzing the data. As such, there is a need for uniquely developed applications that cater towards the type of data. Several considerations must be made when attempting to create a tool for a particular dataset. First, we must consider the type of algorithm required …

Enhanced Multimedia Exchanges Over The Internet, Fuad Shamieh

Electronic Thesis and Dissertation Repository

Although the Internet was not originally designed for exchanging multimedia streams, consumers heavily depend on it for audiovisual data delivery. The intermittent nature of multimedia traffic, the unguaranteed underlying communication infrastructure, and dynamic user behavior collectively result in the degradation of Quality-of-Service (QoS) and Quality-of-Experience (QoE) perceived by end-users. Consequently, the volume of signalling messages is inevitably increased to compensate for the degradation of the desired service qualities. Improved multimedia services could leverage adaptive streaming as well as blockchain-based solutions to enhance media-rich experiences over the Internet at the cost of increased signalling volume. Many recent studies in the literature …

Towards Efficient Intrusion Detection Using Hybrid Data Mining Techniques, Fadi Salo

Electronic Thesis and Dissertation Repository

The enormous development in the connectivity among different type of networks poses significant concerns in terms of privacy and security. As such, the exponential expansion in the deployment of cloud technology has produced a massive amount of data from a variety of applications, resources and platforms. In turn, the rapid rate and volume of data creation in high-dimension has begun to pose significant challenges for data management and security. Handling redundant and irrelevant features in high-dimensional space has caused a long-term challenge for network anomaly detection. Eliminating such features with spectral information not only speeds up the classification process, but …

Authentication And Sql-Injection Prevention Techniques In Web Applications, Cagri Cetin

USF Tampa Graduate Theses and Dissertations

This dissertation addresses the top two “most critical web-application security risks” by combining two high-level contributions.

The first high-level contribution introduces and evaluates collaborative authentication, or coauthentication, a single-factor technique in which multiple registered devices work together to authenticate a user. Coauthentication provides security benefits similar to those of multi-factor techniques, such as mitigating theft of any one authentication secret, without some of the inconveniences of multi-factor techniques, such as having to enter passwords or biometrics. Coauthentication provides additional security benefits, including: preventing phishing, replay, and man-in-the-middle attacks; basing authentications on high-entropy secrets that can be generated and updated automatically; …

Homebook, Stephen Poth, Simon Stauber, Jake Vargas

Computer Science and Engineering Senior Theses

Having a reliable address system is something that is often taken for granted, but simply having one comes with immense benefits. People can easily find locations of friends and family, services like taxis know exactly where to pick customers up, and emergency response units can accurately find the scene of emergencies quickly. However, in many developing countries, these are luxuries only afforded by the wealthy and privileged neighborhoods. Locations are given haphazardly through description, often leading to late arrivals. In some cases this can be a dire possibility. Our solution aims to change this by developing a mobile application that …

Trippit: An Optimal Itinerary Generator, Andrew Nguyen, Osama Shoubber

Computer Science and Engineering Senior Theses

Travelers often lose interest and joy when traveling in tourist-packed areas around the world. As more restaurants and attractions open up in popular cities, the wait and travel time from one location to another inevitably increases. Each attraction has certain hours throughout the day where visitors surge and the wait times increase. In addition, traffic and travel time is an important factor to consider when looking to optimize ones trip. However, with large amounts of attractions, it is difficult to calculate and consider the most optimal routes and times an individual should use to visit each possible attraction. Travelers ultimately …

Deaddropbox: A Time-Locked Safe For Data, Robert Herriott, Peter Paulson, Nathaniel Kragas

Computer Science and Engineering Senior Theses

This project is a proof-of-concept for software which would allow users to securely store sensitive data in such a way that it is difficult or impossible for third parties to compromise the data, even when the user is compelled to assist them. It will operate by storing data across multiple devices in a unreadable form so that it is inaccessible until the data is reunified. The user may specify the circumstances under which different pieces of the data may be accessed, so that it is impossible to access under circumstances of duress.

A Questioning Agent For Literary Discussion, Robbie Culkin, Tim Shur

Computer Science and Engineering Senior Theses

Developing a compelling and cohesive thesis for analytical writing can be a daunting task, even for those who have produced many written works, and finding others to engage with in literary discussion can be equally challenging. In this paper, we describe our solution: Questioner, a discussion tool that engages users in conversation about an academic topic of their choosing for the purpose of collecting thoughts on a subject and constructing an argument. This system will ask informed questions that prompt further discussion about the topic and provide a discussion report after the conversation has ended. We found that our system …

Doorbell For The Hearing Impaired, Shannen Edwin, Dominic Magdaluyo

Computer Science and Engineering Senior Theses

Doorbell options for hearing impaired individuals is seriously limited. Affordable solutions are not scalable while other solutions are expensive. With this in mind, we designed a scalable and affordable system that will be beneficial to hearing impaired individuals in a small aspect of their life. Our solution takes advantage of affordable IoT devices and software to build a proof of concept. Due to the scope of the project, we only designed a proof of concept, in the hope that a company can design a viable product that will not only benefit hearing impaired individuals but bring a powerful IoT system …

Keyboard Hero, Connor Lucier

Computer Science and Engineering Senior Theses

Learning the piano is a complicated process that involves a lifetime of practice. For many new musicians, however, this task is overwhelming and discouraging because of the many skills involved in playing the piano. To solve this problem, I aim to create a computer game compatible with MIDI keyboards that gives novice pianists an alternative to the typical learning process and gives experienced pianists a new and useful practice tool. The game I created is inspired by two popular video games, Guitar Hero and Rock Band, featuring instant accuracy feedback against imported MIDI tracks, high score tracking, and the ability …

The Labyrinth, Derek Nakamura, Marko Trapani, Liam Walker

Computer Science and Engineering Senior Theses

The Labyrinth is a puzzle video game meant to be experienced with a virtual reality headset. It aims to differ from typical puzzle games by being simultaneously fun, immersive, and mentally stimulating. The game consists of three unique level types, with room for further development to create more complex versions of said levels. In this document, we discuss how we developed the game environment to effectively engage the player in enjoyable and engaging problem-solving challenges. The game has been rigidly tested and play-testers were surveyed on their experiences, in order to improve the game.

The Original Beat: An Electronic Music Production System And Its Design, Eli Yale, Christian Quintero, Matt Kordonsky

Computer Science and Engineering Senior Theses

The barrier to entry in electronic music production is high. It requires expensive, complicated software, extensive knowledge of music theory and experience with sound generation. Digital Audio Workstations (DAWs) are the main tools used to piece together digital sounds and produce a complete song. While these DAWs are great for music professionals, they have a steep learning curve for beginners and they must run native on a user’s computer. For a novice to begin creating music takes much more time, eort, and money than it should. We believe anyone who is interested in creating electronic music deserves a simple way …

Justrun - Social Gps Running Game, Riley Bergin, Maggie Cai, Simran Judge, Grace Ling

Interdisciplinary Design Senior Theses

With advances in technology allowing people to live more sedentary lives, more and more people are struggling to live a healthy active lifestyle. In the efforts to combat unhealthy styles of living, we wish to introduce a mobile app that takes advantage of motivational game mechanics to motivate players will make go on runs regularly.

Galápago!, Jeffrey Nguyen, Sally Park, Manuel Sanchez

Computer Science and Engineering Senior Theses

The Galápagos Islands are the tourism hub in Ecuador. The islands greatly benefit economically from the tourism industry, but tourism also affects the conservation of the islands and the local businesses. Locals are suffering due to the impact of tourism. Tourists from around the world go to the archipelago seeking the beauty of the islands. People come on cruise ships to ports, but many aren’t aware of the local businesses and etiquette on the islands, preferring to stay on the ship or near the ports. GalápaGo! is the solution for locals and tourists on the Galapagos Islands. The goal of …