Engineering Commons^™

Visual Speech Recognition Using A 3d Convolutional Neural Network, Matthew Rochford

Master's Theses

Main stream automatic speech recognition (ASR) makes use of audio data to identify spoken words, however visual speech recognition (VSR) has recently been of increased interest to researchers. VSR is used when audio data is corrupted or missing entirely and also to further enhance the accuracy of audio-based ASR systems. In this research, we present both a framework for building 3D feature cubes of lip data from videos and a 3D convolutional neural network (CNN) architecture for performing classification on a dataset of 100 spoken words, recorded in an uncontrolled envi- ronment. Our 3D-CNN architecture achieves a testing accuracy of …

Evaluating Urban Downtown One-Way To Two-Way Street Conversion Using Microscopic Traffic Simulation, Bernice Liu

Master's Theses

Located in the heart of Silicon Valley, Downtown San Jose is attracting new residents, visitors, and businesses. Clearly, the mobility of these residents, visitors, and businesses cannot be accommodated by streets that focus on the single-occupancy automobile mode. To increase the potential for individuals to use non-single-occupancy modes of travel, the downtown area must have a cohesive plan to integrate multimodal use and public life. Complete streets are an integral component of the multi-modal transport system and more livable communities. Complete streets refer to roads designed to accommodate multiple modes, users, and activities including walking, cycling, transit, automobile, and nearby …

Dynamic Pressure Sensing For The Flight Test Data System, Marc Y. Goupil

Master's Theses

This thesis describes the design, assembly, and test of the FTDS-K, a new device in the Boundary Layer Data System (BLDS) family of flight data acquisition systems. The FTDS-K provides high-frequency, high-gain data acquisition capability for up to two pressure sensors and an additional three low-frequency pressure sensors. Development of the FTDS-K was separated into a core module, specialized analog subsystem, and practical testing of the FTDS-K in a flow measurement mission. The core module combines an nRF52840-based microcontroller module, switching regulator, microSD card, real-time clock, temperature sensor, and trio of pressure sensors to provide the same capabilities as previous-generation …

Flight Test Data System For Strain Measurement, Zachary David Wilson

Master's Theses

This thesis describes the design and evaluation of two devices to be included in the next generation of the family of devices called the Boundary Layer Data System (BLDS). The first device, called the Quasi-Static Strain Data Acquisition System, is a continuation of the BLDS-M series of devices to be known as the Flight Test Data System (FTDS) that uses a modular approach to acquire non-flow, quasi-static mechanical strain measurements. Various breakout boards and development boards were used to synthesize the device, which were housed by a custom PCB board. The system is controlled by the Simblee^TM System on …

Android And Web Application For Tracking Employees, Kaival Dholakia

Electronic Theses, Projects, and Dissertations

The purpose that this tracking system serves is to keep track of the employees of the company who have the nature of their job which involves a lot of traveling to various locations on a day to day basis. It is an amalgamation of Android as well as a Web application. The employee is supposed to pass the location and image as per the terms and conditions specified to use the Android application. The web application is used by the admin department to access the information which would help them monitor the location of the employee in a timely manner. …

Method For Spatial Overlap Estimation Of Electroencephalography And Functional Magnetic Resonance Imaging Responses, N. Heugel, E. Liebenthal, Scott A. Beardsley

Biomedical Engineering Faculty Research and Publications

Background

Simultaneous functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) measurements may represent activity from partially divergent neural sources, but this factor is seldom modeled in fMRI-EEG data integration.

New method

This paper proposes an approach to estimate the spatial overlap between sources of activity measured simultaneously with fMRI and EEG. Following the extraction of task-related activity, the key steps include, 1) distributed source reconstruction of the task-related ERP activity (ERP source model), 2) transformation of fMRI activity to the ERP spatial scale by forward modelling of the scalp potential field distribution and backward source reconstruction (fMRI source simulation) …

Second-Order Fault Tolerant Extended Kalman Filter For Discrete Time Nonlinear Systems, Xin Wang, Edwin E. Yaz

Electrical and Computer Engineering Faculty Research and Publications

As missing sensor data may severely degrade the overall system performance and stability, reliable state estimation is of great importance in modern data-intensive control, computing, and power systems applications. Aiming at providing a more robust and resilient state estimation technique, this paper presents a novel second-order fault-tolerant extended Kalman filter estimation framework for discrete-time stochastic nonlinear systems under sensor failures, bounded observer-gain perturbation, extraneous noise, and external disturbances condition. The failure mechanism of multiple sensors is assumed to be independent of each other with various malfunction rates. The proposed approach is a locally unbiased, minimum estimation error covariance based nonlinear …

Comparison And Design Optimization Of A Five-Phase Flux-Switching Pm Machine For In-Wheel Traction Applications, Hao Chen, Xiangdong Liu, Nabeel Demerdash, Ayman M. El-Refaie, Jing Zhao, Jiangbiao He

Electrical and Computer Engineering Faculty Research and Publications

A comparative study of five-phase outer-rotor flux-switching permanent magnet (FSPM) machines with different topologies for in-wheel traction applications is presented in this paper. Those topologies include double-layer winding, single-layer winding, C-core, and E-core configurations. The electromagnetic performance in the low-speed region, the flux-weakening capability in the high-speed region, and the fault-tolerance capability are all investigated in detail. The results indicate that the E-core FSPM machine has performance advantages. Furthermore, two kinds of E-core FSPM machines with different stator and rotor pole combinations are optimized, respectively. In order to reduce the computational burden during the large-scale optimization process, a mathematical technique …

Comparative Study Of Winding Configurations Of A Five-Phase Flux-Switching Pm Machine, Hao Chen, Xiangdong Liu, Ayman M. El-Refaie, Jing Zhao, Nabeel Demerdash, Jiangbiao He

Electrical and Computer Engineering Faculty Research and Publications

This paper introduces a general method for determination of the most suitable winding configurations for five-phase flux-switching permanent magnet (FSPM) machines, associated with feasible stator/rotor-pole combinations. Consequently, the effect of winding configurations on the performance of a five-phase outer-rotor FSPM machine is thoroughly investigated, including non-overlapping concentrated windings (single-layer, double-layer, and multi-layer) as well as distributed winding. The electromagnetic characteristics in the low-speed region, the flux-weakening capability in the high-speed region, and the fault-tolerant capability under faulty situations are evaluated and compared in detail. This work shows that compared with the conventional single-layer or double-layer concentrated windings, the FSPM machine …

Analysis Of A Celestial Icosahedron Shaped Vacuum Lighter Than Air Vehicle, Dustin P. Graves, Kyle D. Moore, Anthony N. Palazotto

Faculty Publications

Excerpt: The celestial icosahedron geometry is considered as a potential design for a vacuum lighter than air vehicle. The goal of this research is ultimately to determine the feasibility of the design and to understand the initial fluid-structure interaction of the vacuum lighter than air vehicle and the surrounding airflow.

An Agent Based Model Of Passenger Boarding For Examining Commercial Aircraft Boarding Strategies, Frank W. Ciarallo, Raymond R. Hill, Kerry K. Ward

Faculty Publications

We use an agent-based simulation methodology to study airline passenger boarding using measures that reflect both the customer experience and airline efficiency perspective. This approach supports exploration of models of actual aircraft used in practice and detailed modeling of passenger dynamics. This paper discusses the modeling approach and a set of experiments comparing several boarding strategies from practical settings as well as the literature.

Analyzing Impacts Of Transportation And Non-Transportation Activities On Human Health With An Advanced Platform For Collecting Travel And Physical Activity Data, Raed Abdullah Hasan

Dissertations

Recently much attention is paid to the lack of physical activities that may cause the health problems in many counties. Travel activities provide a certain amount of physical activities, and the active transportation, such as walking and cycling, becomes more important as an essential element of transportation. The active transportation is expected to contribute to improving human health by reducing cardiovascular disease, obesity, and premature death. However, detailed relationship between the transportation choices and human health has not been well understood. Therefore, there is a need for investigating traveler behaviors and how their choices affect physical activities and public health. …

A Reinforcement Learning Approach To Spacecraft Trajectory Optimization, Daniel S. Kolosa

Dissertations

This dissertation explores a novel method of solving low-thrust spacecraft targeting problems using reinforcement learning. A reinforcement learning algorithm based on Deep Deterministic Policy Gradients was developed to solve low-thrust trajectory optimization problems. The algorithm consists of two neural networks, an actor network and a critic network. The actor approximates a thrust magnitude given the current spacecraft state expressed as a set of orbital elements. The critic network evaluates the action taken by the actor based on the state and action taken. Three different types of trajectory problems were solved, a generalized orbit change maneuver, a semimajor axis change maneuver, …

Mdt Geolocation Through Machine Learning: Evaluation Of Supervised Regression Ml Algorithms, Aria Canadell Solana

Theses and Dissertations

Minimizing Drive Test is a statistical protocol used to evaluate the network performance. It provides several benefits with respect to traditional drive test analysis; however, multiple inconveniences exist that prevent cell companies from precisely retrieving most of the locations of these reports. . MATLAB and Jupyter Notebook were used to prepare the data and create the models. Multiple supervised regression algorithms were tested and evaluated. The best predictions were obtained from the K-Nearest Neighbor algorithm with one ‘k’ and distance-weighted predictions. The UE geolocation was predicted with a median accuracy of 5.42 meters, a mean error of 61.62 meters, and …

Mathematical Model, Simulated Design And Experimental Results For Parabolic Mirror Based Multiplexer For Spatially Multiplexed Fiber Optic Communication Systems, Ce Su

Theses and Dissertations

Spatial Domain Multiplexing (SDM) is a multi-input multi-output (MIMO) architecture. It adds an innovative dimension to optical fiber communication systems by enabling spatial reuse of the optical frequencies. SDM utilizes radially distributed spatial locations for different input signals based on their input launch angles. These input channels propagate in a helical path inside the carrier fiber. These SDM input channels do not encounter any perceptible cross-talk or inter-symbol interference. The SDM system is similar to other optical communication systems. However, they require two added parts. These parts are the spatial multiplexer, also known as the Beam Combiner Module (BCM) and …

Air Quality Monitoring Wireless Sensor Network With Electrochemical Sensing Elements, Saeed Faisal Malky

Theses and Dissertations

Harmful atmospheric pollutants have been attributed to causing adverse weather conditions and health problems, which are particularly prevalent in more populated global regions, such as megacities. Nongovernmental and international agencies throughout the world have likewise called for increased awareness and action to effectively counter the increased rates of air pollution, as the consequences seem ominous. Meanwhile, in several major urban landscapes such as Saudi Arabia, no modern apparatus or efficient systematic mechanisms exist for the qualitative detection of dangerous pollutants and gases. The current counterparts for hazardous gas measurements are expensive, bulky and cumbersome to set up. Thus, sensor devices …

Remote Sensing, Modeling, And Spectroscopic Studies Of Gigantic Jets And Lightning Leaders, Levi Boggs

Theses and Dissertations

This dissertation focuses on four interrelated investigations with the ultimate goal of better understanding electrical phenomena in the lower and upper atmosphere. The four investigations utilized observations and data analysis for electrical discharges occurring in the troposphere, such as cloud-to-ground and intracloud discharges, and discharges occurring in the stratosphere/lower ionosphere, known as gigantic jets. The observations are from ground-based high-speed cameras and lightning locating systems, space-borne lightning imagers, and remote and in-situ meteorological instrumentation. Numerical modeling was also performed to study the lightning associated with gigantic jets by using a stochastic lighting propagation model. Finally, this dissertation focuses on the …

Socialization Of Veterans Using Virtual Reality, Joan M. Savage

Theses and Dissertations

Virtual reality, augmented reality, mixed reality, and video games are growing in popularity and fulfilling genuine human needs that the real world is currently unable to satisfy. Games are providing rewards that reality is not. They are teaching and inspiring and engaging us in ways that reality is not (McGonigal, 2011). The purpose of this study was to capture the essence of socialization in virtual reality as a Ph.D. dissertation topic at Florida Institute of Technology - Human-Centered Design. This study used a phenomenology methodology to capture the experiences of beneficial features of players who use virtual reality. The study …

Machine Learning In The State Design Pattern, Timothy Matthew Von Friesen

Theses and Dissertations

As the Internet of Things revolution continues to become more prevalent in humanity's daily routine, securing these devices is paramount. Society has seen a substantial increase in activity in the cyber-warfare battle space, resulting in an increasing amount of security breaches every year. The responsibility of securing our devices can no longer rely solely on cyber-security engineers keeping systems hardened through Security Technical Implementation Guides and vulnerability scans; it must shift towards the developer. Previous research has been done in this area of securing our devices. However, these solutions rely heavily on cloud computing resources to perform computationally expensive algorithms. …

Improving Grapheme-To-Phoneme Translation With The Use Of Nalu Attention Mechanisms, Brian Sheldon Smith

Theses and Dissertations

In recent years, Natural Language Processing in the field of machine learning has seen some major improvements. Data scientists have shown that neural networks are capable of breaking down semantics of sentences, translating languages, and answering complex questions with fast recall. While impressive, these feats all hinge on having access to a massive amount of clean text, or data sets with almost perfect grammar and spelling. Without this, neural networks will usually fail to converge on a meaningful result. To partially this dependency, Grapheme-to-Phoneme conversion can be employed. This is the conversion of words from their spellings to a form …

Multiple Ssid Framework For Rss-Fingerprint Based Indoor Positioning Systems, Ahmed Kareem Abed

Dissertations

Location-Based Indoor positioning systems significance stems from the bloom of recent applications in various fields such as in tracking services for an elder or a patient within large living communities, mobile robot localization, and several other security applications. Currently, Global Positioning Systems (GPS) are the most widely used location-sensing technique. However, satellite-based GPS signals require line of sight (LOS) to work correctly, which is something cannot be achieved inside buildings. Fortunately, wireless LAN can be employed in indoor positioning systems (IPS), and since all large buildings such as malls, hospitals, airports, schools, and museums have hundreds of Wi-Fi access points, …

Semantic And Qualitative Physics-Based Formal Reasoning For Functional Decomposition In Mechanical Design, Xiaoyang Mao

Theses and Dissertations

Function modeling plays an essential role in academy design studies, yet a lack of acceptance in industry. A possible reason is that the designer must have well understand of the controlled vocabularies and grammars to utilize this method. The research presented in this dissertation is to fill this gap so that designers can use function-based design method without relevant knowledge. In graph-based function models, the function verbs and flow nouns are usually chosen from predefined vocabularies. The vocabulary class definitions, combined with function modeling grammars defined at various levels of formalism, enable function-based reasoning. However, the text written in plain …

Multi-Facet Retrofit Approach To Improve Energy Efficiency Of Existing Class Of Single-Family Residential Buildings In Florida, Kwame Baffour Ohene Amoah

Theses and Dissertations

There are many approaches to incorporate energy efficiency measures (EEMs) into building through retrofit projects. Single-family buildings are an essential target for energy improvements because of their energy-saving potential and considerable market share. This study evaluates energy savings and cost-effectiveness of individual retrofit options. It proposes energy efficiency measures for an existing class of single-family homes constructed between the years of 1950 and 1970. The study uses a baseline building located in Melbourne, FL, as a case study. A survey via clustering data mining was conducted on Florida Single-Family Residential (SFR) buildings (1950 – 1970) to establish patterns of construction, …

An Optimal Allocation And Sizing Strategy Of Distributed Energy Storage Systems To Improve Performance Of Distribution Networks, Choton K. Das, Octavian Bass, Thair S. Mahmoud, Ganesh Kothapalli, Mohammad A. S. Masoum, Navid Mousavi

Research outputs 2014 to 2021

The allocation of grid-scale energy storage systems (ESSs) can play a significant role in solving distribution network issues and improving overall network performance. This paper presents a strategy for optimal allocation and sizing of distributed ESSs through P and Q injection by the ESSs to a distribution network. The investigation is carried out in a renewable-penetrated (wind and solar) medium voltage IEEE-33 bus distribution network for two different scenarios: (1) using a uniform ESS size and (2) using non-uniform ESS sizes. DIgSILENT PowerFactory is used for system modeling and testing, and simulation events are automated using Python scripting. A hybrid …

Deep Donors And Acceptors In Β-Ga2O3 Crystals: Determination Of The Fe2+/3+ Level By A Noncontact Method, Christopher A. Lenyk, Timothy D. Gustafson, Larry E. Halliburton, Nancy C. Giles

Faculty Publications

Electron paramagnetic resonance (EPR), infrared absorption, and thermoluminescence (TL) are used to determine the Fe^2+/3+ level in Fe-doped β-Ga₂O₃ crystals. With these noncontact spectroscopy methods, a value of 0.84 ± 0.05 eV below the conduction band is obtained for this level. Our results clearly establish that the E2 level observed in deep level transient spectroscopy (DLTS) experiments is due to the thermal release of electrons from Fe²⁺ ions. The crystals used in this investigation were grown by the Czochralski method and contained large concentrations of Fe acceptors and Ir donors, and trace amounts of Cr …

Hvac System Energy Audit For Leverett Elementary School, Connor Smalling

Biological and Agricultural Engineering Undergraduate Honors Theses

Leverett Elementary School is located in Fayetteville, AR. The school needs significant upgrades to its infrastructure. The Fayetteville Public School District has voted to pursue an Energy Services Performance Contract (ESPC) in order to finance the desired upgrades to Leverett Elementary, among other schools in the district.

The scope of this thesis was to perform an energy audit on the existing heating, ventilation, and air conditioning (HVAC) system. By using an energy modeling software, eQuest, the building and the existing base system were modeled to determine utility consumption. Three different HVAC system alternatives were analyzed against the base system by …

Drivers Of On-Farm Performance Of Irrigation Water Management Practices: Empirical Evidence From Eastern Arkansas, Jacob Askey

Biological and Agricultural Engineering Undergraduate Honors Theses

Unsustainable agricultural practices are putting a strain on freshwater supplies in many parts of the world. More efficient irrigation techniques are going to be critical to feed a growing population. Data from the 2016 Arkansas Irrigation Survey was used to assess the adoption of three Irrigation Water Management (IWM) practices: multiple inlet rice irrigation, tailwater recovery, and storage reservoirs. Results indicate that these practices do not always lead to reported pumping time reductions, a proxy for water use savings. Large variations in pumping time reduction are observed across producers for all three practices. A Tobit model was used to examine …

Transmission-Scale Battery Energy Storage Systems: A Systematic Literature Review, Kevin Marnell, Manasseh Obi, Robert B. Bass

Electrical and Computer Engineering Faculty Publications and Presentations

When the transmission capacity of an electrical system is insufficient to adequately serve customer demand, the transmission system is said to be experiencing congestion. More transmission lines can be built to increase capacity. However, transmission congestion typically only occurs during periods of peak demand, which occur just a few times per year; capitol-intensive investments in new transmission capacity address problems that occur infrequently. Alternative solutions to alleviated transmission congestion have been devised, including generation curtailment, demand response programs, and various remedial action schema. Though not currently a common solution, battery energy storage systems can also provide transmission congestion relief. Technological …

Secure Two-Party Protocol For Privacy-Preserving Classification Via Differential Privacy, Manish Kumar

Boise State University Theses and Dissertations

Privacy-preserving distributed data mining is the study of mining on distributed data—owned by multiple data owners—in a non-secure environment, where the mining protocol does not reveal any sensitive information to the data owners, the individual privacy is preserved, and the output mining model is practically useful. In this thesis, we propose a secure two-party protocol for building a privacy-preserving decision tree classifier over distributed data using differential privacy. We utilize secure multiparty computation to ensure that the protocol is privacy-preserving. Our algorithm also utilizes parallel and sequential compositions, and applies distributed exponential mechanism to ensure that the output is differentially-private. …

Controlling Strain Energy Density In 3d Cellular Collagen Constructs During Complex Loads, Katherine Hollar

Boise State University Theses and Dissertations

Mechanical stimulation applied to damaged soft tissues, such as ligament, can promote tissue remodeling to accelerate healing. To help identify treatments that encourage ligament healing, bioreactors have been designed to subject 3D cellularized constructs to various loading conditions in order to determine the mechanical mechanisms that trigger cell-mediated repair. An innovative approach is to use a bioreactor to apply controlled states of biaxial stress to study the effects of strain energy density and distortion energy on cell activity. Tissue distortion has been linked to changes in the structure and function of ligament, yet the specific impact of distortion energy on …