Digital Commons Network^™

A Deep Learning Approach For Airport Runway Identification From Satellite Imagery, Mahmut Gemici

Theses and Dissertations

The United States lacks a comprehensive national database of private Prior Permission Required (PPR) airports. The primary reason such a database does not exist is that there are no federal regulatory obligations for these facilities to have their information re-evaluated or updated by the Federal Aviation Administration (FAA) or the local state Department of Transportation (DOT) once the data has been entered into the system. The often outdated and incorrect information about landing sites presents a serious risk factor in aviation safety. In this thesis, we present a machine learning approach for detecting airport landing sites from Google Earth satellite …

Evaluation Of Material Request Order To Support Sustainable Construction, Fajar Susilowati, Nur Nahdiah Anggraeni

Makara Journal of Technology

This study was conducted on one of Indonesia’s apartment projects, in which reinforced concrete is the main structure. Based on existing project data, this project experienced a decline in the construction work’s progress, thus reducing the project’s overall progress. This decline occurred because the delivery of concrete reinforcement material was delayed. This study aimed to determine the process of material request order and its relationship with the work implementation, as well as the factors that influenced the delayed arrival of concrete reinforcement material at the project site. The method used in this study was observation and interview. Data were analyzed …

A Dual-Stack Coaxial Magnetic Gear For A Wave Energy Conversion Generator, Hossein Baninajar, Sina Modaresahmadi, Ho Yin Wong, Jonathan Z. Bird, Wesley B. Williams, Bertrand Dechant, Parker Southwick

Electrical and Computer Engineering Faculty Publications and Presentations

This paper presents the electromagnetic and mechanical design and analyses of a 7.67:1 gear ratio magnetic gear for a wave energy converter demonstrator. A 2-D and 3-D magnetostatic finite element analysis (FEA) was conducted to maximize the mass torque density. To increase torque without increasing the diameter a unique dual-stack rotor topology was used along with a twelve-segment per pole-pair inner rotor Halbach array and a four-segment per pole-pair outer rotor Halbach topology. The eddy current loss within the magnetic gear was mitigated by using laminated magnets and a low-loss electrical steel. The experimentally tested magnetic gear had a peak …

Model-Based Deep Learning For Computational Imaging, Xiaojian Xu

McKelvey School of Engineering Graduate Student Theses & Dissertations

This dissertation addresses model-based deep learning for computational imaging. The motivation of our work is driven by the increasing interests in the combination of imaging model, which provides data-consistency guarantees to the observed measurements, and deep learning, which provides advanced prior modeling driven by data. Following this idea, we develop multiple algorithms by integrating the classical model-based optimization and modern deep learning to enable efficient and reliable imaging. We demonstrate the performance of our algorithms by validating their performance on various imaging applications and providing rigorous theoretical analysis.

The dissertation evaluates and extends three general frameworks, plug-and-play priors (PnP), regularized …

Soft Electronics And Sensors For Wearable Healthcare Applications, Li-Wei Lo

McKelvey School of Engineering Graduate Student Theses & Dissertations

Wearable electronics are becoming increasingly essential to personalized medicine by collecting and analyzing massive amounts of biological signals from internal organs, muscles, and blood vessels. Conventional rigid electronics may lead to motion artifacts and errors in collected data due to the mismatches in mechanical properties between human skin. Instead, soft wearable electronics provide a better platform and interface that can form intimate contact and conformably adapt to human skin. In this respect, this thesis focuses on new materials formulation, fabrication, characterization of low-cost, high sensitivity and reliable sensors for wearable health monitoring applications.

More specifically, we have studied the silver …

Development Of The Subwave Rov And Neural-Inertial Positioning System, Jason Farmer

Theses and Dissertations

This report documents the development of the Subwave, a remotely-operated underwater vehicle (ROV), and an artificial neural network based inertial positioning system. The Subwave uses the open-source ArduSub software framework, commercial-off-the-shelf hardware components, and several custom systems. It is designed as a platform for researching autonomous underwater vehicles (AUVs). The first step for an AUV is navigating waypoints, which requires the AUV to know its global position. Since global navigation satellite systems (GNSSs) are denied underwater, the available underwater positioning systems were surveyed and determined that all the available systems were too large and expensive for the Subwave. It was …

Nbt (No-Boundary Thinking): Needed To Attend To Ethical Implications Of Data And Ai, Joan Peckham, Andy Perkins, Tayo Obafemi-Ajayi, Xiuzhen Huang

Electrical and Computer Engineering Faculty Research & Creative Works

In this era of Big Data and AI, expertise in multiple aspects of data, computing, and the domains of application is needed. This calls for teams of experts with different training and perspectives. Because data analysis can have serious ethical implications, it is important that these teams are well and deeply integrated. No-Boundary Thinking (NBT) teams can provide support for team formation and maintenance, thereby attending to the many dimensions of the ethics of data and analysis. In this NBT workshop session, we discuss the ethical concerns that arise from the use of data and AI, and the implications for …

Golightly : A Gpu Implementation Of The Finite-Difference Time-Domain Method, S. David Lively

Electrical Engineering Theses and Dissertations

Traditionally, optical circuit design is tested and validated using software which implement numerical modeling techniques such as Beam Propagation, Finite Element Analysis and the Finite-Difference Time-Domain (FDTD) method. FDTD simulations require significant computational power. Existing installations may distribute the computational requirements across large clusters of high-powered servers. This approach entails significant expense in terms of hardware, staffing and software support which may be prohibitive for some research facilities and private-sector engineering firms. The application of modern programmable GPUs to problems in scientific visualization and computation has facilitated faster development cycles for a variety of industry segments including large dataset visualization, …

Charger Robotic Air Hockey-Modified Air Hockey Table Featuring Automated Play Against A Human Opponent, Robert Geren

Honors Capstone Projects and Theses

No abstract provided.

System Identification Of Linear And Non-Linear Dynamical Systems Using Semi-Definite Programming Via Penalized Parabolic Relaxation Method, Adnan Nasir

Electrical Engineering Dissertations - Archive

This document is prepared to highlight the difference between two very important fields in the realm of Convex Optimization, Machine Learning, Artificial Intelligence and many such sprouting advance fields currently impacting the whole world. The main aim of the recent SDP algorithms is to relax the NP-Hard Convex optimization problems and transform them into amenable jobs without strong theoretical guarantees, but these algorithms tends to approximate the practical in demand applications in many of the aforementioned fields. Moreover, The lack of theoretical guarantee makes the SDP relaxation in-exact and unoptimizable in finite duration. The actual world applications most of the …

Embedding A Grid Of Load Cells Into A Dining Table For Automatic Monitoring And Detection Of Eating Events, Mohammad Mayyan

All Dissertations

This dissertation describes a “smart dining table” that can detect and measure consumption events. This work is motivated by the growing problem of obesity, which is a global problem and an epidemic in the United States and Europe. Chapter 1 gives a background on the economic burden of obesity and its comorbidities. For the assessment of obesity, we briefly describe the classic dietary assessment tools and discuss their drawback and the necessity of using more objective, accurate, low-cost, and in-situ automatic dietary assessment tools. We explain in short various technologies used for automatic dietary assessment such as acoustic-, motion-, or …

Advanced Topologies Of High Step-Up Dc-Dc Converters For Renewable Energy Applications, Ramin Rahimi

Doctoral Dissertations

"This research is focused on developing several advanced topologies of high step-up DC-DC converters to connect low-voltage renewable energy (RE) sources, such as photovoltaic (PV) panels and fuel cells (FCs), into a high-voltage DC bus in renewable energy applications. The proposed converters are based on the combinations of various voltage-boosting (VB) techniques, including interleaved and quadratic structures, switched-capacitor (SC)-based voltage multiplier (VM) cells, and magnetically coupled inductor (CI) and built-in-transformer (BIT). The proposed converters offer outstanding features, including high voltage gain with low or medium duty cycle, a small number of components, low current and voltage stresses on the components, …

Glaciernet2: A Hybrid Multi-Model Learning Architecture For Alpine Glacier Mapping, Zhiyuan Xie, Umesh K. Haritashya, Vijayan K. Asari, Michael P. Bishop, Jeffrey S. Kargel, Theus Aspiras

Electrical and Computer Engineering Faculty Publications

In recent decades, climate change has significantly affected glacier dynamics, resulting in mass loss and an increased risk of glacier-related hazards including supraglacial and proglacial lake development, as well as catastrophic outburst flooding. Rapidly changing conditions dictate the need for continuous and detailed ob-servations and analysis of climate-glacier dynamics. Thematic and quantitative information regarding glacier geometry is fundamental for understanding climate forcing and the sensitivity of glaciers to climate change, however, accurately mapping debris-cover glaciers (DCGs) is notoriously difficult based upon the use of spectral information and conventional machine-learning techniques. The objective of this research is to improve upon an …

Design And Implementation Of A Novel Eit/Ecg System With An Adaptive Current Source Act-5 / Narrative Competence And Cognitive Mapping As A Culturally Sustaining Pedagogy In The Education Of Emergent Bilinguals, Ahmed Abdelwahab

Legacy Theses & Dissertations (2009 - 2024)

Electrical Impedance Tomography (EIT) is a promising medical imaging technique used to detect the body's internal electrical characteristics based on electrical measurements made on its surface. EIT systems, particularly those that use parallel, multiple source architectures, require current sources with very high output impedance. This is a usual challenge for EIT as the practical current sources come with finite output impedance, which is highly degraded as the operation frequency gets wider. To overcome this challenge and maintain the high output impedance requirement, sources often use complex analog circuits which require manual or electronically-controlled adjustments.

An Evaluation Of Wi-Fi 802.11b Backscatter, Anthony Chen

All Theses

Internet of Things (IoT) devices are in need of low-power communications systems with longevity and reliability. With the use of backscatter technology, IoT devices can communicate at the cost of almost no power and can last for up to a decade. Furthermore, backscatter technology is compatible with everyday wireless signals such as Wi-Fi and Bluetooth, allowing for easy communication without specific hardware constraints. This thesis aims to evaluate a Wi-Fi backscatter system and analyze its ease in triggering off of such ambient signals and sources. The system will utilize Wi-Fi 802.11b as a backscatter source to trigger the backscatter system …

Distributed Learning With Automated Stepsizes, Benjamin Liggett

All Theses

Stepsizes for optimization problems play a crucial role in algorithm convergence, where the stepsize must undergo tedious manual tuning to obtain near-optimal convergence. Recently, an adaptive method for automating stepsizes was proposed for centralized optimization. However, this method is not directly applicable to decentralized optimization because it allows for heterogeneous agent stepsizes. Furthermore, directly using consensus between agent stepsizes to mitigate stepsize heterogeneity can decrease performance and even lead to divergence.

This thesis proposes an algorithm to remedy the tedious manual tuning of stepsizes in decentralized optimization. Our proposed algorithm automates the stepsize and uses dynamic consensus between agents’ stepsizes …

Experimental Evaluation Of A 63.3:1 Dual-Stage Coaxial Magnetic Gear, Hossein Baninajar, Sina Modaresahmadi, H. Y. Wong, Jonathan Bird, W. Williams, B. Dechant

Electrical and Computer Engineering Faculty Publications and Presentations

This paper presents the construction and testing results for a 63.3:1 dual-stage coaxial magnetic gear for use in a marine hydrokinetic generator demonstrator application. The dual-stage magnetic gear is composed of series-connected coaxial magnetic gear. The stage-2 magnetic gear utilizes Halbach magnet arrays on both rotors and has a 9.5:1 gear ratio. The stage-1 magnetic gear utilizes a Halbach rotor on the outer rotor and a flux concentration inner rotor. The stage-1 magnetic gear has a 6.67:1 gear ratio and at the peak torque of 1220Nm the stage-1 MG was shown to be capable of operating with a 268 N·m/L …

Ternary Logic Design In Topological Quantum Computing, Muhammad Ilyas, Shawn Cui, Marek Perkowski

Electrical and Computer Engineering Faculty Publications and Presentations

A quantum computer can perform exponentially faster than its classical counterpart. It works on the principle of superposition. But due to the decoherence effect, the superposition of a quantum state gets destroyed by the interaction with the environment. It is a real challenge to completely isolate a quantum system to make it free of decoherence. This problem can be circumvented by the use of topological quantum phases of matter. These phases have quasiparticles excitations called anyons. The anyons are charge-flux composites and show exotic fractional statistics. When the order of exchange matters, then the anyons are called non-Abelian anyons. Majorana …

Enhanced Supervised Descent Learning Technique For Electromagnetic Inverse Scattering Problems By The Deep Convolutional Neural Networks, He Ming Yao, Rui Guo, Maokun Li, Lijun Jiang, Michael Kwok Po Ng

Electrical and Computer Engineering Faculty Research & Creative Works

This work proposes a novel deep learning (DL) framework to solve the electromagnetic inverse scattering (EMIS) problems. The proposed framework integrates the complex-valued deep convolutional neural network (DConvNet) into the supervised descent method (SDM) to realize both off-line training and on-line 'imaging' prediction for EMIS. The offline training consists of two parts: 1) DConvNet training: the training dataset is created, and the proposed DConvNet is trained to realize the EM forward process and 2) SDM training: the trained DConvNet is integrated into the SDM framework, and the average descent directions between the initial prediction and the true label of SDM …

A Millimeter-Wave Frequency-Reconfigurable Fabry-Pérot Cavity Antenna, Min Li, Muhammad Yasir Jamal, Xiaoqiang Li, Kwan Lawrence Yeung, Lijun Jiang, Tatsuo Itoh, Ross Murch

Electrical and Computer Engineering Faculty Research & Creative Works

This letter introduces a method for implementing a frequency-reconfigurable Fabry-Pérot cavity (FPC) antenna utilizing polarization standing waves (PSWs). The PSW is supported by two metasurfaces (MSs) at cavity ends. The resonant condition allows the antenna to have frequency-reconfigurable characteristic by mechanically rotating the top MS around the center and relative to the bottom MS, without adjusting the physical dimension. The antenna is prototyped at 60 GHz for millimeter-wave applications. Simulated and measured results demonstrate that a tunable frequency range of 60.8-66.2 GHz with a maximum boresight gain of around 22.2 dBi can be attained, verifying the antenna concept.

Optimization Of High-Speed Channel For Signal Integrity With Deep Genetic Algorithm, Huan Huan Zhang, Zhao Sheng Xue, Xin Yi Liu, Ping Li, Lijun Jiang, Guang Ming Shi

Electrical and Computer Engineering Faculty Research & Creative Works

A deep genetic algorithm (GA) is proposed to optimize the high-speed channel for signal integrity. In the traditional genetic algorithm-based high-speed channel optimization method, the eye height and eye width of the eye diagram are obtained by eye diagram simulation based on the full-wave algorithm, which is computationally expensive. In this letter, a deep neural network (DNN) is trained to predict the eye diagram information corresponding to a set of given design parameters of the high-speed channel. This DNN is embedded into the genetic algorithm to carry out the evaluation operation, which can greatly accelerate the evaluation process. A high-speed …

Huber Kalman Filter For Wi-Fi Based Vehicle Driver's Respiration Detection, Yang Yang, Yunlong Luo, Alex Qi, Ge Shi, Miao Miao, Jun Fan, Jianhua Ma, Yihong Qi

Electrical and Computer Engineering Faculty Research & Creative Works

The use of breath detection in vehicles can reduce the number of vehicular accidents caused by drivers in poor physical condition. Prior studies of contactless respiration detection mainly targeted a static person. However, there are emerging applications to sense a driver, with emphasis on contactless methods. For example, being able to detect a driver's respiration while driving by using a vehicular Wi-Fi system can significantly enhance driving safety. The sensing system can be mounted on the back of the driver's seat, and it can sense the tiny chest displacement of the driver via Wi-Fi signals. The body displacement and car …

Z-Source-Based High Step-Up Dc-Dc Converters For Photovoltaic Applications, Ramin Rahimi, Saeed Habibi, Mehdi Ferdowsi, Pourya Shamsi

Electrical and Computer Engineering Faculty Research & Creative Works

This article proposes three high step-up Z-source (ZS)-based dc-dc converters by integrating the conventional ZS network with switched-capacitor (SC) cells. The proposed converters offer a simple structure with a smooth input current, a high-voltage gain, and low voltage stress on the semiconductor devices. In addition, the proposed converters, unlike some existing ZS-based topologies in the literature, do not impose any limitation on the duty cycle of the power switch. These characteristics make the proposed converters excellent candidates to interface a low-voltage solar photovoltaic (PV) panel with a high-voltage dc bus in PV applications. Among the proposed three converters, the operating …

Hybrid Smart Transformer For Enhanced Power System Protection Against Dc With Advanced Grid Support, Moazzam Nazir

All Dissertations

The traditional grid is rapidly transforming into smart substations and grid assets incorporating advanced control equipment with enhanced functionalities and rapid self-healing features. The most important and strategic equipment in the substation is the transformer and is expected to perform a variety of functions beyond mere voltage conversion and isolation. While the concept of smart solid-state transformers (SSTs) is being widely recognized, their respective lifetime and reliability raise concerns, thus hampering the complete replacement of traditional transformers with SSTs. Under this scenario, introducing smart features in conventional transformers utilizing simple, cost-effective, and easy to install modules is a highly desired …

Warp-Aware Adaptive Energy Efficiency Calibration For Multi-Gpu Systems, Zhuowei Wang, Xiaoyu Song, Lianglun Cheng, Hai Wan, Wuqing Zhao, Tao Wang

Electrical and Computer Engineering Faculty Publications and Presentations

Massive GPU acceleration processors have been used in high-performance computing systems. The Dennard-scaling has led to power and thermal constraints limiting the performance of such systems. The demand for both increased performance and energy-efficiency is highly desired. This paper presents a multi-layer low-power optimisation method for warps and tasks parallelisms. We present a dynamic frequency regulation scheme for performance parameters in terms of load balance and load imbalance. The method monitors the energy parameters in runtime and adjusts adaptively the voltage level to ensure the performance efficiency with energy reduction. The experimental results show that the multi-layer low-power optimisation with …

Collaborative Robotics Strategies For Handling Non-Repetitive Micro-Drilling Tasks Characterized By Low Structural Mechanical Impedance, Xiangyu Wang

Mechanical & Aerospace Engineering Theses & Dissertations

Mechanical micro-drilling finds widespread use in diverse applications ranging from advanced manufacturing to medical surgery. This dissertation aims to develop techniques that allow programming of robots to perform effective micro-drilling tasks. Accomplishing this goal is faced with several challenges. Micro-drills suffer from frequent breakage caused from variations in drill process parameters. Micro-drilling tasks afford extremely low feed rates and almost zero tolerance for any feed rate variations. The accompanying robot programming task is made difficult as mathematical models that capture the micro-drilling process complexities and sensitive variations in micro-drill parameters are highly difficult to obtain. Therefore, an experimental approach is …

Gp-K: A Probabilistic Method For Hourly Day-Ahead Power Load Forecasting, Miguel A. Hombrados-Herrera

Electrical and Computer Engineering ETDs

The elevated costs that incur power grid stakeholders due to forecasting errors in power load demand have created the need for forecasting methods that provide accurate predictions and allow for assessing the reliability of their predictions. This thesis proposes a probabilistic forecasting method for multi-step ahead forecasting.

In particular, it presents a probabilistic method to perform a 24-hours-ahead power load forecasting that arises as the combination of Gaussian Process regressors with NMF (nonnegative matrix factorization) and integrates the advantages of both methods. Instead of training 24 independent processes for each hour of the predicted day, this work proposes to factorize …

Protection Of Microgrids: A Scalable And Topology Agnostic Scheme With Self-Healing Dynamic Reconfiguration, Phani Harsha Gadde

All Dissertations

Momentum towards realizing the smart grid will continue to result in high penetration of renewable fed Distributed Energy Resources (DERs) in the Electric Power System (EPS). These DERs will most likely be Inverter Based Resources(IBRs) and will be an integral part of the distribution system in the near future. The drive towards resiliency with these IBRs will enable a modular topology where several microgrids are tied together, operating synchronously to form the future EPS at the distribution level.

Since the microgrids can evolve from existing distribution feeders, they will be unbalanced in load, phases, and feeder impedances. A typical control …

Subwavelength Engineering Of Silicon Photonic Waveguides, Farhan Bin Tarik

All Dissertations

The dissertation demonstrates subwavelength engineering of silicon photonic waveguides in the form of two different structures or avenues: (i) a novel ultra-low mode area v-groove waveguide to enhance light-matter interaction; and (ii) a nanoscale sidewall crystalline grating performed as physical unclonable function to achieve hardware and information security. With the advancement of modern technology and modern supply chain throughout the globe, silicon photonics is set to lead the global semiconductor foundries, thanks to its abundance in nature and a mature and well-established industry. Since, the silicon waveguide is the heart of silicon photonics, it can be considered as the core …

Algorithm Optimization And Hardware Acceleration For Machine Learning Applications On Low-Energy Systems, Jianchi Sun

All Dissertations

Machine learning (ML) has been extensively employed for strategy optimization, decision making, data classification, etc. While ML shows great triumph in its application field, the increasing complexity of the learning models introduces neoteric challenges to the ML system designs. On the one hand, the applications of ML on resource-restricted terminals, like mobile computing and IoT devices, are prevented by the high computational complexity and memory requirement. On the other hand, the massive parameter quantity for the modern ML models appends extra demands on the system's I/O speed and memory size. This dissertation investigates feasible solutions for those challenges with software-hardware …