Engineering Commons^™

Evaluation Of Robust Deep Learning Pipelines Targeting Low Swap Edge Deployment, David Carter Cornett

Masters Theses

The deep learning technique of convolutional neural networks (CNNs) has greatly advanced the state-of-the-art for computer vision tasks such as image classification and object detection. These solutions rely on large systems leveraging wattage-hungry GPUs to provide the computational power to achieve such performance. However, the size, weight and power (SWaP) requirements of these conventional GPU-based deep learning systems are not suitable when a solution requires deployment to so called "Edge" environments such as autonomous vehicles, unmanned aerial vehicles (UAVs) and smart security cameras.

The objective of this work is to benchmark FPGA-based alternatives to conventional GPU systems that have the …

Modeling And Characterization Of Optical Metasurfaces, Mahsa Torfeh

Masters Theses

Metasurfaces are arrays of subwavelength meta-atoms that shape waves in a compact and planar form factor. During recent years, metasurfaces have gained a lot of attention due to their compact form factor, easy integration with other devices, multi functionality and straightforward fabrication using conventional CMOS techniques. To provide and evaluate an efficient metasurface, an optimized design, high resolution fabrication and accurate measurement is required. Analysis and design of metasurfaces require accurate methods for modeling their interactions with waves. Conventional modeling techniques assume that metasurfaces are locally periodic structures excited by plane waves, restricting their applicability to gradually varying metasurfaces that …

Dissolved Organic Carbon And The Potential Role To Stream Acidity In The Great Smoky Mountains National Park, Jason R. Brown

Masters Theses

A substantial societal shift towards environmental awareness has focused research efforts on the impacts of pollution on natural landscapes. Improvements to pollutant regulations and technology have resulted in sizeable reductions of atmospheric deposition of anthropogenic acids, especially nitrates and sulfates, which has altered the role of these ions in the environment. As such, understandings of environmental chemistry dynamics have required regular updating.

Through the National Park Service Vital Signs monitoring program, increases in precipitation pH observed in Great Smoky Mountains National Park (GRSM) has been attributed to the reduction of inorganic acid concentrations. Unfortunately, these improvements have not been uniformly …

Power System Stability Assessment With Supervised Machine Learning, Mirka Mandich

Masters Theses

Power system stability assessment has become an important area of research due to the increased penetration of photovoltaics (PV) in modern power systems. This work explores how supervised machine learning can be used to assess power system stability for the Western Electricity Coordinating Council (WECC) service region as part of the Data-driven Security Assessment for the Multi-Timescale Integrated Dynamics and Scheduling for Solar (MIDAS) project. Data-driven methods offer to improve power flow scheduling through machine learning prediction, enabling better energy resource management and reducing demand on real-time time-domain simulations. Frequency, transient, and small signal stability datasets were created using the …

Neural Network Supervised And Reinforcement Learning For Neurological, Diagnostic, And Modeling Problems, Donald Wunsch Iii

Masters Theses

“As the medical world becomes increasingly intertwined with the tech sphere, machine learning on medical datasets and mathematical models becomes an attractive application. This research looks at the predictive capabilities of neural networks and other machine learning algorithms, and assesses the validity of several feature selection strategies to reduce the negative effects of high dataset dimensionality. Our results indicate that several feature selection methods can maintain high validation and test accuracy on classification tasks, with neural networks performing best, for both single class and multi-class classification applications. This research also evaluates a proof-of-concept application of a deep-Q-learning network (DQN) to …

A Simple Background Elimination Method For Miniaturized Fiber-Optic Raman Probe, Bohong Zhang

Masters Theses

"Raman scattering is called a photonic - molecular interaction based on the kinetic model of the analytic. Due to the uniqueness of the Raman scattering technique, it can provide a unique fingerprint signal for molecular recognition. However, a serious challenge often encountered in Raman measurement comes from the requirements of fast, real-time remote sensing, background fluorescence suppression, and micro-environmental detection.

A new Miniaturized Fiber-Optic Raman Probe (MFORP) for Raman spectroscopy, used especially for eliminating background fluorescence and enhancing sampling, is presented. Its main purpose is to provide an overview of excellent research on the detection of very small substances and …

A Compact Wavelength Meter Using A Multimode Fiber, Ogbole Collins Inalegwu

Masters Theses

“Wavelength meters are very important for precision measurements of both pulses and continuous-wave optical sources. Conventional wavelength meters employ gratings, prisms, interferometers, and other wavelength-sensitive materials in their design. Here, we report a simple and compact wavelength meter based on a section of multimode fiber and a camera. The concept is to correlate the multimodal interference pattern (i.e., speckle pattern) at the end-face of a multimode fiber with the wavelength of the input lightsource. Through a series of experiments, specklegrams from the end face of a multimode fiber as captured by a charge-coupled device (CCD) camera were recorded; the images …

Relationships Among Mineralogy, Geochemistry, And Oil And Gas Production In The Tuscaloosa Marine Shale, Hayley Roxana Beitel

Masters Theses

"The Tuscaloosa Marine Shale (TMS) is an unconventional shale reservoir located in southeast Louisiana and southwest Mississippi. Limited mineralogical and geochemical data for the TMS have been published. The data that do exist indicate that the formation is heterogeneous. Consequently, previous investigators and oil and gas companies have not managed to effectively link mineralogical and chemical changes to oil and gas production in the TMS. These linkages are critical to establish for future exploration efforts. In this study, we attempt to establish these relationships by gathering all existing mineralogical and chemical data in the TMS, including newly acquired data from …