Engineering Commons^™

Nonuniform Sampling-Based Breast Cancer Classification, Santiago Posso

Theses and Dissertations--Electrical and Computer Engineering

The emergence of deep learning models and their success in visual object recognition have fueled the medical imaging community's interest in integrating these algorithms to improve medical diagnosis. However, natural images, which have been the main focus of deep learning models and mammograms, exhibit fundamental differences. First, breast tissue abnormalities are often smaller than salient objects in natural images. Second, breast images have significantly higher resolutions but are generally heavily downsampled to fit these images to deep learning models. Models that handle high-resolution mammograms require many exams and complex architectures. Additionally, spatially resizing mammograms leads to losing discriminative details essential …

Reinventing Integrated Photonic Devices And Circuits For High Performance Communication And Computing Applications, Venkata Sai Praneeth Karempudi

Theses and Dissertations--Electrical and Computer Engineering

The long-standing technological pillars for computing systems evolution, namely Moore's law and Von Neumann architecture, are breaking down under the pressure of meeting the capacity and energy efficiency demands of computing and communication architectures that are designed to process modern data-centric applications related to Artificial Intelligence (AI), Big Data, and Internet-of-Things (IoT). In response, both industry and academia have turned to 'more-than-Moore' technologies for realizing hardware architectures for communication and computing. Fortunately, Silicon Photonics (SiPh) has emerged as one highly promising ‘more-than-Moore’ technology. Recent progress has enabled SiPh-based interconnects to outperform traditional electrical interconnects, offering advantages like high bandwidth density, …

A Flexible Photonic Reduction Network Architecture For Spatial Gemm Accelerators For Deep Learning, Bobby Bose

Theses and Dissertations--Electrical and Computer Engineering

As deep neural network (DNN) models increase significantly in complexity and size, it has become important to increase the computing capability of specialized hardware architectures typically used for DNN processing. The major linear operations of DNNs, which comprise the fully connected and convolution layers, are commonly converted into general matrix-matrix multiplication (GEMM) operations for acceleration. Specialized GEMM accelerators are typically employed to implement these GEMM operations, where a GEMM operation is decomposed into multiple vector-dot-product operations that run in parallel. A common challenge that arises in modern DNNs is the mismatch between the matrices used for GEMM operations and the …

A Phase Change Memory And Dram Based Framework For Energy-Efficient And High-Speed In-Memory Stochastic Computing, Supreeth Mysore

Theses and Dissertations--Electrical and Computer Engineering

Convolutional Neural Networks (CNNs) have proven to be highly effective in various fields related to Artificial Intelligence (AI) and Machine Learning (ML). However, the significant computational and memory requirements of CNNs make their processing highly compute and memory-intensive. In particular, the multiply-accumulate (MAC) operation, which is a fundamental building block of CNNs, requires enormous arithmetic operations. As the input dataset size increases, the traditional processor-centric von-Neumann computing architecture becomes ill-suited for CNN-based applications. This results in exponentially higher latency and energy costs, making the processing of CNNs highly challenging.

To overcome these challenges, researchers have explored the Processing-In Memory (PIM) …

Modeling The Early Visual System, Nicholas Lanning

Theses and Dissertations--Electrical and Computer Engineering

There are two encoding schema present in simple cells in the early visual system of vertebrates: the retinal simple cells activate highly when the receptive field contains a center surround stimulus, while the primary visual cortex’s (V1) simple cells activate highly when the receptive field contains visual edges. Work has been done in the past to enforce constraints on visual machine learning such that the retinal or V1 encoding is learned, but this work is often done to emulate retinal and V1 encoding in a vacuum. Recent work using convolutional neural networks focuses on anatomical constraints along with a supervised …

Building Energy Modeling And Studies Of Electric Power Distribution Systems With Distributed Energy Resources, Evan S. Jones

Theses and Dissertations--Electrical and Computer Engineering

There is significant opportunity for savings in energy and investment from improved performance of electric Power Distribution Systems (PDSs) through optimal planning and operation of conventional voltage-controlling devices. Novel multi-step model conversion and optimal capacitor planning (OCP) procedures are proposed for large-scale utility PDSs and are exemplified with an existing utility circuit of approximately 4,000 buses. Simulated optimal control and operation is achieved with a cluster-based approach that utilizes load-forecasting to minimize equipment degradation by intelligently dispersing device setting adjustments over time such that they remain most applicable. Improved performance may also be achieved through smart building technologies and Virtual …

Application Of Conventional Feedforward And Deep Neural Networks To Power Distribution System State Estimation And State Forecasting, James Paul Carmichael

Theses and Dissertations--Electrical and Computer Engineering

Classical neural networks such as feedforward multilayer perceptron models (MLPs) are well established as universal approximators and as such, show promise in applications such as static state estimation in power transmission systems. This research investigates the application of conventional neural networks (MLPs) and deep learning based models such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) to mitigate challenges in power distribution system state estimation and forecasting based upon conventional analytic methods. The ability of MLPs to perform regression to perform power system state estimation will be investigated. MLPs are considered based upon their promise to learn …

Establishing The Foundation To Robotize Complex Welding Processes Through Learning From Human Welders Based On Deep Learning Techniques, Rui Yu

Theses and Dissertations--Electrical and Computer Engineering

As the demand for customized, efficient, and high-quality production increases, traditional manufacturing processes are transforming into smart manufacturing with the aid of advancements in information technology, such as cyber-physical systems (CPS), the Internet of Things (IoT), big data, and artificial intelligence (AI). The key requirement for integration with these advanced information technologies is to digitize manufacturing processes to enable analysis, control, and interaction with other digitized components. The integration of deep learning algorithm and massive industrial data will be critical components in realizing this process, leading to enhanced manufacturing in the Future of Work at the Human-Technology Frontier (FW-HTF).

This …

Optimal Design Of Special High Torque Density Electric Machines Based On Electromagnetic Fea, Murat G. Kesgin

Theses and Dissertations--Electrical and Computer Engineering

Electric machines with high torque density are essential for many low-speed direct-drive systems, such as wind turbines, electric vehicles, and industrial automation. Permanent magnet (PM) machines that incorporate a magnetic gearing effect are particularly useful for these applications due to their potential for achieving extremely high torque density. However, when the number of rotor polarities is increased, there is a corresponding need to increase the number of stator slots and coils proportionally. This can result in manufacturing challenges. A new topology of an axial-flux vernier-type machine of MAGNUS type has been presented to address the mentioned limitation. These machines can …

Determining Power System Fault Location Using Neural Network Approach, Edward O. Ojini

Theses and Dissertations--Electrical and Computer Engineering

Fault location remains an extremely pivotal feature of the electric power grid as it ensures efficient operation of the grid and prevents large downtimes during fault occurrences. This will ultimately enhance and increase the reliability of the system. Since the invention of the electric grid, many approaches to fault location have been studied and documented. These approaches are still effective and are implemented in present times, and as the power grid becomes even more broadened with new forms of energy generation, transmission, and distribution technologies, continued study on these methods is necessary. This thesis will focus on adopting the artificial …

Synthesizing Dysarthric Speech Using Multi-Speaker Tts For Dsyarthric Speech Recognition, Mohammad Soleymanpour

Theses and Dissertations--Electrical and Computer Engineering

Dysarthria is a motor speech disorder often characterized by reduced speech intelligibility through slow, uncoordinated control of speech production muscles. Automatic Speech recognition (ASR) systems may help dysarthric talkers communicate more effectively. However, robust dysarthria-specific ASR requires a significant amount of training speech is required, which is not readily available for dysarthric talkers.

In this dissertation, we investigate dysarthric speech augmentation and synthesis methods. To better understand differences in prosodic and acoustic characteristics of dysarthric spontaneous speech at varying severity levels, a comparative study between typical and dysarthric speech was conducted. These characteristics are important components for dysarthric speech modeling, …

Parametric Average-Value Modeling, Simulation, And Characterization Of Machine-Rectifier Systems, Isuje Ojo

Theses and Dissertations--Electrical and Computer Engineering

There are many techniques for modeling and simulation of synchronous machine-rectifier systems. The more common approaches are the detailed and average-value modeling techniques. The detailed simulation technique takes into account the details of the diode switching and is both very accurate and very expensive in terms of computational resources. To alleviate this disadvantage, the average-value modeling technique is often utilized. In this approach, the details of diode switching are neglected or averaged. In that light, the work presented herein proposes a unique saliency-sensitive parametric average-value model (SSPAVM) of the synchronous machine-rectifier system. This model extends existing parametric average-value models to …

Three Dimensional Photonics Structures: Design And Applications, Mansoor Sultan

Theses and Dissertations--Electrical and Computer Engineering

Photonics is an emerging technology for light control, emission, and detection. Photonic devices control photons the same way electronic circuits control electrons in active or passive mode depending on the energy requirement of the device. This dissertation will discuss the design, fabrication, testing of photonic structures with applications including imaging and renewable energy. First, we developed a novel lithography method for fluoropolymer resist based on variable pressure electron beam lithography (VP-EBL). VP-EBL proves to be an efficient method for patterning a widely used, but challenging to process, fluoropolymer, Teflon AF. However, rather than solely mitigating charging, the ambient gas is …

Explainable Data-Driven Motor Condition Monitoring And Fault Disgnosis, Yuming Wang

Theses and Dissertations--Electrical and Computer Engineering

Industrial motors are widely used in various fields such as power generation, mining, and manufacturing. Motor faults and time-consuming maintenance process will lead to serious economic losses in this context. To monitor motor faults and detect motor conditions, different types of sensors that can test vibration and current signals are mounted on motors. However, the main challenge was how to use information gained by sensors to analyze or diagnose motor conditions.

Machine learning is a popular technology in recent years, and it's very suitable for crunching and analyzing data. As an important subset of machine learning, deep learning is suitable …

Developing Reactive Distributed Aerial Robotics Platforms For Real-Time Contaminant Mapping, Joshua Ashley

Theses and Dissertations--Electrical and Computer Engineering

The focus of this research is to design a sensor data aggregation system and centralized sensor-driven trajectory planning algorithm for fixed-wing aircraft to optimally assist atmospheric simulators in mapping the local environment in real-time. The proposed application of this work is to be used in the event of a hazardous contaminant leak into the atmosphere as a fleet of sensing unmanned aerial vehicles (UAVs) could provide valuable information for evacuation measures. The data aggregation system was designed using a state-of-the-art networking protocol and radio with DigiMesh and a process/data management system in the ROS2 DDS. This system was tested to …

Models And Optimal Controls For Smart Homes And Their Integration Into The Electric Power Grid, Huangjie Gong

Theses and Dissertations--Electrical and Computer Engineering

Smart homes can operate as a distributed energy resource (DER), when equipped with controllable high-efficiency appliances, solar photovoltaic (PV) generators, electric vehicles (EV) and energy storage systems (ESS). The high penetration of such buildings changes the typical electric power load profile, which without appropriate controls, may become a “duck curve” when the surplus PV generation is high, or a “dragon curve” when the EV charging load is high. A smart home may contribute to an optimal solution of such problems through the energy storage capacity, provided by its by battery energy storage system (BESS), heating, ventilation, and air conditioning (HVAC) …

Hourly Dispatching Wind-Solar Hybrid Power System With Battery-Supercapacitor Hybrid Energy Storage, Pranoy Kumar Singha Roy

Theses and Dissertations--Electrical and Computer Engineering

This dissertation demonstrates a dispatching scheme of wind-solar hybrid power system (WSHPS) for a specific dispatching horizon for an entire day utilizing a hybrid energy storage system (HESS) configured by batteries and supercapacitors. Here, wind speed and solar irradiance are predicted one hour ahead of time using a multilayer perceptron Artificial Neural Network (ANN), which exhibits satisfactory performance with good convergence mapping between input and target output data. Furthermore, multiple state of charge (SOC) controllers as a function of energy storage system (ESS) SOC are developed to accurately estimate the grid reference power (P_Grid,ref) for each dispatching period. …

Energy-Efficient And Secure Hardware Using Adiabatic Logic And Non-Volatile Mtj Devices, Zachary Kahleifeh

Theses and Dissertations--Electrical and Computer Engineering

Internet of Things (IoT) is a collection of devices that exchange data through a network to implement complex applications. IoT devices increase the quality of life of their user base which has a wide variety such as the medical field, consumer electronics, and the manufacturing sector. However, IoT devices have several challenges that need to be overcome namely, security and energy consumption. The threat vector that IoT devices face is growing and includes the following threats, the leakage of information through a side-channel attack known as the Correlation Power Analysis (CPA), authentication, piracy, etc. A side-channel attack is an attack …

Development Of Dc Circuit Breakers For Medium-Voltage Electrified Transportation, Trevor Morgan Arvin

Theses and Dissertations--Electrical and Computer Engineering

Medium-voltage DC (MVDC) distribution is an enabling technology for the electrification of transportation such as aircraft and shipboard. One main obstacle for DC distribution is the lack of adequate circuit fault protection. The challenges are due to the rapidly rising fault currents and absence of zero crossings in DC systems compared to AC counterparts. Existing DC breaker solutions lack comprehensive consideration of energy efficiency, power density, fault interruption speed, reliability, and implementation cost.

In this thesis, two circuit topologies of improved DC circuit breakers are developed: the resonant current source based hybrid DC breaker (RCS-HDCB) and the high temperature superconductor …

Energy Harvesting And Sensor Based Hardware Security Primitives For Cyber-Physical Systems, Carson Labrado

Theses and Dissertations--Electrical and Computer Engineering

The last few decades have seen a large proliferation in the prevalence of cyber-physical systems. Although cyber-physical systems can offer numerous advantages to society, their large scale adoption does not come without risks. Internet of Things (IoT) devices can be considered a significant component within cyber-physical systems. They can provide network communication in addition to controlling the various sensors and actuators that exist within the larger cyber-physical system. The adoption of IoT features can also provide attackers with new potential avenues to access and exploit a system's vulnerabilities. Previously, existing systems could more or less be considered a closed system …

Accelerometer-Based Vigilance State Classification In Dairy Cows, Evan King

Theses and Dissertations--Electrical and Computer Engineering

Globally, dairy farming is a $700 billion industry, with more than 9 million dairy cows in the United States alone. Depriving cows of required activities such as sleep has been shown to negatively impact reproductive efficiency, decrease the volume of milk produced, and increase the risk of culling. Overcrowded herds can decrease individual animal health, demanding the need for automatic behavior detection that would provide insight into their state of health.

Using electroencephalography (EEG), electrooculography (EOG), and electromyography (EMG) to characterize the phases of sleep is a technique which has been used for decades. While these techniques are considered the …

Transmission-Level Impact Analysis Of Utility-Scale Solar Photovoltaic Systems And Battery Energy Storage Grid Support, Gerald W. Bankes Ii

Theses and Dissertations--Electrical and Computer Engineering

Solar photovoltaic energy generation is expected to grow dramatically in coming years in order to take advantage of renewable and clean sources of electricity. This thesis presents research on the impact of increasing solar PV penetration, specifically of large, utility-scale PV facilities, on transmission network performance. The development of Python programming tools for automation of power flow analysis is presented. A modified version of the IEEE 118-Bus test system is developed and modified to simulate increasing PV generation on the transmission system. The impacts on performance are analyzed trends are reported. Battery energy storage systems are studied in this thesis …

Designing Novel Hardware Security Primitives For Smart Computing Devices, Amitkumar Degada

Theses and Dissertations--Electrical and Computer Engineering

Smart computing devices are miniaturized electronics devices that can sense their surroundings, communicate, and share information autonomously with other devices to work cohesively. Smart devices have played a major role in improving quality of the life and boosting the global economy. They are ubiquitously present, smart home, smart city, smart girds, industry, healthcare, controlling the hazardous environment, and military, etc. However, we have witnessed an exponential rise in potential threat vectors and physical attacks in recent years. The conventional software-based security approaches are not suitable in the smart computing device, therefore, hardware-enabled security solutions have emerged as an attractive choice. …

Special Power Electronics Converters And Machine Drives With Wide Band-Gap Devices, Yibin Zhang

Theses and Dissertations--Electrical and Computer Engineering

Power electronic converters play a key role in power generation, storage, and consumption. The major portion of power losses in the converters is dissipated in the semiconductor switching devices. In recent years, new power semiconductors based on wide band-gap (WBG) devices have been increasingly developed and employed in terms of promising merits including the lower on-state resistance, lower turn-on/off energy, higher capable switching frequency, higher temperature tolerance than conventional Si devices. However, WBG devices also brought new challenges including lower fault tolerance, higher system cost, gate driver challenges, and high dv/dt and resulting increased bearing current in electric machines.

This …

Boundary Integral Equation Method For Electrostatic Field Prediction In Piecewise-Homogeneous Electrolytes, Christopher Keith Pratt

Theses and Dissertations--Electrical and Computer Engineering

This thesis presents a method to predict electrostatic fields, potentials, and currents in regions containing piecewise-homogeneous electrolytes. Additionally, an efficient electric field calculation is presented. A boundary integral equation is formulated for the boundary potentials and currents and is discretized using the Locally Corrected Nyström method. Solution convergence with respect to the mesh discretization and basis order is investigated. The techniques are validated through analysis of problems with either analytic solutions, with published data, or with other solution methods.

Fabrication And Simulation Of Perovskite Solar Cells, Maniell Workman

Theses and Dissertations--Electrical and Computer Engineering

Since the dawning of the industrial revolution, the world has had a need for mass energy production. In the 1950s silicon solar panels were invented. Silicon solar panels have been the main source of solar energy production. They have set the standard for power conversion efficiency for subsequent generations of photovoltaic technology. Solar panels utilize light’s ability to generate an electron hole pair. By creating a PN Junction in the photovoltaic semiconductor, the electron and hole are directed in opposing layers of the solar panel generating the electric current. Second generation solar panels utilized different thin film materials to fabricate …

Traveling Wave Fault Location Method For Distribution Systems With Distributed Generation, Oluwafeyisayo Afolabi

Theses and Dissertations--Electrical and Computer Engineering

Fault location is an important topic within electric power systems, as accurate fault location techniques will improve the reliability of the system and reduce downtime caused by outages. This paper explores fault location in distribution systems with distributed generation using the traveling wave fault location method. The single-ended and double-ended traveling wave methods are evaluated using a single-circuit distribution system which is modeled using MATLAB SIMULINK. The results are compared using a basis of signals and bus pairs across fault types, sampling rates and fault resistances.

Vibro-Acoustic Codling Moth Larvae Infestation Detection In Apples, Chadwick A. Parrish

Theses and Dissertations--Electrical and Computer Engineering

Within recent years, the demand for organic produce has greatly increased due to many factors, including increasing knowledge about such things as dietary fiber and balanced gastrointestinal bacterial ecosystems. This increase in demand, coupled with the financial penalties for sending invasive species and pests across borders, presents a need for a scalable and accurate system to non-destructively detect infestation. The proposed work addresses this problem by testing the performance of a non-destructive vibro-acoustic method for detecting lava activity in apples. This involved 3 steps; design a mechanical data collection prototype for testing apples, a evaluate a set of features, and …

Machine Learning Approach For Vigilance State Classification In Mice, Anik Muhury

Theses and Dissertations--Electrical and Computer Engineering

Sleep has a significant impact on cognitive abilities such as memory, reaction time, productivity, and creative thinking; however, there are many aspects of this important activity that are not clearly understood. Over the last century, researchers have developed technology and animal models to assist in the study of sleep. Manual sleep scoring is time consuming, reduces productivity, and is impacted by human scorer subjectivity. On the other hand, automatic sleep stage categorization can enhance consistency and reliability, aiding professionals in identifying sleep related health problems.

In recent times various studies reported significant achievements for automatic vigilance detection and overcome the …

Toward Intelligent Welding By Building Its Digital Twin, Qiyue Wang

Theses and Dissertations--Electrical and Computer Engineering

To meet the increasing requirements for production on individualization, efficiency and quality, traditional manufacturing processes are evolving to smart manufacturing with the support from the information technology advancements including cyber-physical systems (CPS), Internet of Things (IoT), big industrial data, and artificial intelligence (AI). The pre-requirement for integrating with these advanced information technologies is to digitalize manufacturing processes such that they can be analyzed, controlled, and interacted with other digitalized components. Digital twin is developed as a general framework to do that by building the digital replicas for the physical entities. This work takes welding manufacturing as the case study to …